qg2021.bib

@article{BrowningBrowning2009,
abstract = {We present methods for imputing data for ungenotyped markers and for inferring haplotype phase in large data sets of unrelated individuals and parent-offspring trios. Our methods make use of known haplotype phase when it is available, and our methods are computationally efficient so that the full information in large reference panels with thousands of individuals is utilized. We demonstrate that substantial gains in imputation accuracy accrue with increasingly large reference panel sizes, particularly when imputing low-frequency variants, and that unphased reference panels can provide highly accurate genotype imputation. We place our methodology in a unified framework that enables the simultaneous use of unphased and phased data from trios and unrelated individuals in a single analysis. For unrelated individuals, our imputation methods produce well-calibrated posterior genotype probabilities and highly accurate allele-frequency estimates. For trios, our haplotype-inference method is four orders of magnitude faster than the gold-standard PHASE program and has excellent accuracy. Our methods enable genotype imputation to be performed with unphased trio or unrelated reference panels, thus accounting for haplotype-phase uncertainty in the reference panel. We present a useful measure of imputation accuracy, allelic R(2), and show that this measure can be estimated accurately from posterior genotype probabilities. Our methods are implemented in version 3.0 of the BEAGLE software package.},
author = {Browning, Brian L. and Browning, Sharon R.},
doi = {10.1016/j.ajhg.2009.01.005},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/American Journal of Human Genetics/Browning, Browning - 2009 - A unified approach to genotype imputation and haplotype-phase inference for large data sets of trios and unr.pdf:pdf},
issn = {1537-6605},
journal = {Am. J. Hum. Genet.},
keywords = {Beagle,Computer Simulation,Female,Gene Frequency,Gene Frequency: genetics,Genetic,Genotype,Haplotypes,Haplotypes: genetics,Humans,Male,Markov Chains,Models,Nuclear Family,Reproducibility of Results},
mendeley-tags = {Beagle},
month = feb,
number = {2},
pages = {210--23},
pmid = {19200528},
title = {{A unified approach to genotype imputation and haplotype-phase inference for large data sets of trios and unrelated individuals.}},
url = {http://www.sciencedirect.com/science/article/pii/S0002929709000123},
volume = {84},
year = {2009}
}
@article{BrowningYu2009,
abstract = {We present a novel method for simultaneous genotype calling and haplotype-phase inference. Our method employs the computationally efficient BEAGLE haplotype-frequency model, which can be applied to large-scale studies with millions of markers and thousands of samples. We compare genotype calls made with our method to genotype calls made with the BIRDSEED, CHIAMO, GenCall, and ILLUMINUS genotype-calling methods, using genotype data from the Illumina 550K and Affymetrix 500K arrays. We show that our method has higher genotype-call accuracy and yields fewer uncalled genotypes than competing methods. We perform single-marker analysis of data from the Wellcome Trust Case Control Consortium bipolar disorder and type 2 diabetes studies. For bipolar disorder, the genotype calls in the original study yield 25 markers with apparent false-positive association with bipolar disorder at a p < 10(-7) significance level, whereas genotype calls made with our method yield no associated markers at this significance threshold. Conversely, for markers with replicated association with type 2 diabetes, there is good concordance between genotype calls used in the original study and calls made by our method. Results from single-marker and haplotypic analysis of our method's genotype calls for the bipolar disorder study indicate that our method is highly effective at eliminating genotyping artifacts that cause false-positive associations in genome-wide association studies. Our new genotype-calling methods are implemented in the BEAGLE and BEAGLECALL software packages.},
author = {Browning, Brian L. and Yu, Zhaoxia},
doi = {10.1016/j.ajhg.2009.11.004},
file = {::},
issn = {1537-6605},
journal = {Am. J. Hum. Genet.},
keywords = {Algorithms,Alleles,Beagle,Data Interpretation,False Positive Reactions,Genetic Markers,Genome-Wide Association Study,Genotype,Haplotypes,Humans,Models,Oligonucleotide Array Sequence Analysis,Probability,Reproducibility of Results,Software,Statistical},
mendeley-groups = {Software,DGRP genomic features},
mendeley-tags = {Beagle},
month = dec,
number = {6},
pages = {847--61},
pmid = {19931040},
title = {{Simultaneous genotype calling and haplotype phasing improves genotype accuracy and reduces false-positive associations for genome-wide association studies.}},
url = {http://www.sciencedirect.com/science/article/pii/S0002929709005199},
volume = {85},
year = {2009}
}
@article{DelosCampos2010,
abstract = {Although genome-wide association studies have identified markers that are associated with various human traits and diseases, our ability to predict such phenotypes remains limited. A perhaps overlooked explanation lies in the limitations of the genetic models and statistical techniques commonly used in association studies. We propose that alternative approaches, which are largely borrowed from animal breeding, provide potential for advances. We review selected methods and discuss the challenges and opportunities ahead.},
author = {de los Campos, Gustavo and Gianola, Daniel and Allison, David B.},
doi = {10.1038/nrg2898},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/Nature Reviews Genetics/de los Campos, Gianola, Allison - 2010 - Predicting genetic predisposition in humans the promise of whole-genome markers.pdf:pdf;:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/Nature Reviews Genetics/de los Campos, Gianola, Allison - 2010 - Predicting genetic predisposition in humans the promise of whole-genome markers.pdf:pdf},
issn = {1471-0064},
journal = {Nat. Rev. Genet.},
keywords = {Disease,Disease: genetics,Genetic Markers,Genetic Predisposition to Disease,Genome-Wide Association Study,Humans},
month = dec,
number = {12},
pages = {880--6},
pmid = {21045869},
publisher = {Nature Publishing Group},
title = {{Predicting genetic predisposition in humans: the promise of whole-genome markers.}},
url = {http://www.ncbi.nlm.nih.gov/pubmed/21045869},
volume = {11},
year = {2010}
}
@article{Johnson1995,
author = {Johnson, D.L. and Thompson, Robin},
doi = {10.3168/jds.S0022-0302(95)76654-1},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/Journal of Dairy Science/Johnson, Thompson - 1995 - Restricted Maximum Likelihood Estimation of Variance Components for Univariate Animal Models Using Sparse Mat.pdf:pdf},
issn = {00220302},
journal = {J. Dairy Sci.},
keywords = {AI-REML,Per's references.},
mendeley-tags = {Per's references.},
month = feb,
number = {2},
pages = {449--456},
publisher = {Elsevier},
title = {{Restricted Maximum Likelihood Estimation of Variance Components for Univariate Animal Models Using Sparse Matrix Techniques and Average Information}},
url = {http://www.journalofdairyscience.org/article/S0022-0302(95)76654-1/abstract},
volume = {78},
year = {1995}
}

@article{langoallen2010,
abstract = {Most common human traits and diseases have a polygenic pattern of inheritance: DNA sequence variants at many genetic loci influence the phenotype. Genome-wide association (GWA) studies have identified more than 600 variants associated with human traits, but these typically explain small fractions of phenotypic variation, raising questions about the use of further studies. Here, using 183,727 individuals, we show that hundreds of genetic variants, in at least 180 loci, influence adult height, a highly heritable and classic polygenic trait. The large number of loci reveals patterns with important implications for genetic studies of common human diseases and traits. First, the 180 loci are not random, but instead are enriched for genes that are connected in biological pathways (P = 0.016) and that underlie skeletal growth defects (P < 0.001). Second, the likely causal gene is often located near the most strongly associated variant: in 13 of 21 loci containing a known skeletal growth gene, that gene was closest to the associated variant. Third, at least 19 loci have multiple independently associated variants, suggesting that allelic heterogeneity is a frequent feature of polygenic traits, that comprehensive explorations of already-discovered loci should discover additional variants and that an appreciable fraction of associated loci may have been identified. Fourth, associated variants are enriched for likely functional effects on genes, being over-represented among variants that alter amino-acid structure of proteins and expression levels of nearby genes. Our data explain approximately 10\% of the phenotypic variation in height, and we estimate that unidentified common variants of similar effect sizes would increase this figure to approximately 16\% of phenotypic variation (approximately 20\% of heritable variation). Although additional approaches are needed to dissect the genetic architecture of polygenic human traits fully, our findings indicate that GWA studies can identify large numbers of loci that implicate biologically relevant genes and pathways.},
author = {{Lango Allen}, Hana and Estrada, Karol and Lettre, Guillaume and Berndt, Sonja I. and Weedon, Michael N. and Rivadeneira, Fernando and Willer, Cristen J. and Jackson, Anne U. and Vedantam, Sailaja and Raychaudhuri, Soumya and Ferreira, Teresa and Wood, Andrew R. and Weyant, Robert J. and Segr\`{e}, Ayellet V. and Speliotes, Elizabeth K. and Wheeler, Eleanor and Soranzo, Nicole and Park, Ju-Hyun and Yang, Jian and Gudbjartsson, Daniel and Heard-Costa, Nancy L. and Randall, Joshua C. and Qi, Lu and {Vernon Smith}, Albert and M\"{a}gi, Reedik and Pastinen, Tomi and Liang, Liming and Heid, Iris M. and Luan, Jian'an and Thorleifsson, Gudmar and et al.},
doi = {10.1038/nature09410},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/Nature/Lango Allen et al. - 2010 - Hundreds of variants clustered in genomic loci and biological pathways affect human height.pdf:pdf},
issn = {1476-4687},
journal = {Nature},
keywords = {Body Height,Body Height: genetics,Chromosomes,Genetic Loci,Genetic Loci: genetics,Genetic Predisposition to Disease,Genetic Predisposition to Disease: genetics,Genome,Genome-Wide Association Study,Human,Human: genetics,Humans,Metabolic Networks and Pathways,Metabolic Networks and Pathways: genetics,Multifactorial Inheritance,Multifactorial Inheritance: genetics,Pair 3,Pair 3: genetics,Pathways,Phenotype,Polymorphism,Single Nucleotide,Single Nucleotide: genetics},
mendeley-tags = {Pathways},
month = oct,
number = {7317},
pages = {832--8},
pmid = {20881960},
publisher = {Nature Publishing Group, a division of Macmillan Publishers Limited. All Rights Reserved.},
shorttitle = {Nature},
title = {{Hundreds of variants clustered in genomic loci and biological pathways affect human height}},
url = {http://dx.doi.org/10.1038/nature09410 http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=2955183\&tool=pmcentrez\&rendertype=abstract},
volume = {467},
year = {2010}
}
@article{Mackay2012,
abstract = {A major challenge of biology is understanding the relationship between molecular genetic variation and variation in quantitative traits, including fitness. This relationship determines our ability to predict phenotypes from genotypes and to understand how evolutionary forces shape variation within and between species. Previous efforts to dissect the genotype-phenotype map were based on incomplete genotypic information. Here, we describe the Drosophila melanogaster Genetic Reference Panel (DGRP), a community resource for analysis of population genomics and quantitative traits. The DGRP consists of fully sequenced inbred lines derived from a natural population. Population genomic analyses reveal reduced polymorphism in centromeric autosomal regions and the X chromosome, evidence for positive and negative selection, and rapid evolution of the X chromosome. Many variants in novel genes, most at low frequency, are associated with quantitative traits and explain a large fraction of the phenotypic variance. The DGRP facilitates genotype-phenotype mapping using the power of Drosophila genetics.},
author = {Mackay, Trudy F. C. and Richards, Stephen and Stone, Eric A. and Barbadilla, Antonio and Ayroles, Julien F. and Zhu, Dianhui and Casillas, S\`{o}nia and Han, Yi and Magwire, Michael M. and Cridland, Julie M. and Richardson, Mark F. and Anholt, Robert R. H. and Barr\'{o}n, Maite and Bess, Crystal and Blankenburg, Kerstin Petra and Carbone, Mary Anna and Castellano, David and Chaboub, Lesley and Duncan, Laura and Harris, Zeke and Javaid, Mehwish and Jayaseelan, Joy Christina and Jhangiani, Shalini N. and Jordan, Katherine W. and Lara, Fremiet and Lawrence, Faye and Lee, Sandra L. and Librado, Pablo and Linheiro, Raquel S. and Lyman, Richard F. and Mackey, Aaron J and Munidasa, Mala and Muzny, Donna Marie and Nazareth, Lynne and Newsham, Irene and Perales, Lora and Pu, Ling-Ling and Qu, Carson and R\`{a}mia, Miquel and Reid, Jeffrey G. and Rollmann, Stephanie M. and Rozas, Julio and Saada, Nehad and Turlapati, Lavanya and Worley, Kim C. and Wu, Yuan-Qing and Yamamoto, Akihiko and Zhu, Yiming and Bergman, Casey M. and Thornton, Kevin R. and Mittelman, David and Gibbs, Richard A.},
doi = {10.1038/nature10811},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/Nature/Mackay et al. - 2012 - The Drosophila melanogaster Genetic Reference Panel.pdf:pdf},
issn = {1476-4687},
journal = {Nature},
keywords = {Alleles,Animals,Centromere,Centromere: genetics,Chromosomes,DGRP,Drosophila melanogaster,Drosophila melanogaster: genetics,Genetic,Genetic: genetics,Genome-Wide Association Study,Genomics,Genotype,Insect,Insect: genetics,Phenotype,Polymorphism,Quantitative Trait Loci,Quantitative Trait Loci: genetics,Selection,Single Nucleotide,Single Nucleotide: genetics,Starvation,Starvation: genetics,Telomere,Telomere: genetics,X Chromosome,X Chromosome: genetics},
mendeley-tags = {DGRP},
month = feb,
number = {7384},
pages = {173--8},
pmid = {22318601},
publisher = {Nature Publishing Group, a division of Macmillan Publishers Limited. All Rights Reserved.},
shorttitle = {Nature},
title = {{The \textit{Drosophila melanogaster} Genetic Reference Panel}},
url = {http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3683990\&tool=pmcentrez\&rendertype=abstract http://dx.doi.org/10.1038/nature10811},
volume = {482},
year = {2012}
}
@inproceedings{Madsen1994,
address = {Guelph, Canada},
author = {Madsen, Per and Jensen, Just and Thompson, Robin},
booktitle = {5th WCGALP},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/5th WCGALP/Madsen, Jensen, Thompson - 1994 - Estimation of (co)variance components by REML in multivariate mixed linear models using average of obs.pdf:pdf},
keywords = {Per's references,REML},
mendeley-tags = {Per's references},
pages = {455--462},
title = {{Estimation of (co)variance components by REML in multivariate mixed linear models using average of observed and expected information}},
year = {1994}
}
@article{Makowsky2011,
abstract = {Despite rapid advances in genomic technology, our ability to account for phenotypic variation using genetic information remains limited for many traits. This has unfortunately resulted in limited application of genetic data towards preventive and personalized medicine, one of the primary impetuses of genome-wide association studies. Recently, a large proportion of the "missing heritability" for human height was statistically explained by modeling thousands of single nucleotide polymorphisms concurrently. However, it is currently unclear how gains in explained genetic variance will translate to the prediction of yet-to-be observed phenotypes. Using data from the Framingham Heart Study, we explore the genomic prediction of human height in training and validation samples while varying the statistical approach used, the number of SNPs included in the model, the validation scheme, and the number of subjects used to train the model. In our training datasets, we are able to explain a large proportion of the variation in height (h(2) up to 0.83, R(2) up to 0.96). However, the proportion of variance accounted for in validation samples is much smaller (ranging from 0.15 to 0.36 depending on the degree of familial information used in the training dataset). While such R(2) values vastly exceed what has been previously reported using a reduced number of pre-selected markers (<0.10), given the heritability of the trait (∼ 0.80), substantial room for improvement remains.},
author = {Makowsky, Robert and Pajewski, Nicholas M. and Klimentidis, Yann C. and Vazquez, Ana I. and Duarte, Christine W. and Allison, David B. and de los Campos, Gustavo},
doi = {10.1371/journal.pgen.1002051},
editor = {Gibson, Greg},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/PLoS Genetics/Makowsky et al. - 2011 - Beyond missing heritability prediction of complex traits.pdf:pdf;:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/PLoS Genetics/Makowsky et al. - 2011 - Beyond missing heritability prediction of complex traits(2).pdf:pdf},
issn = {1553-7404},
journal = {PLoS Genet.},
keywords = {Bayes Theorem,Body Height,Body Height: genetics,Genome,Genome-Wide Association Study,Genotype,Heritable,Human,Humans,Peters intro refs,Phenotype,Polymorphism,Quantitative Trait,Single Nucleotide},
mendeley-tags = {Peters intro refs},
month = apr,
number = {4},
pages = {e1002051},
pmid = {21552331},
publisher = {Public Library of Science},
title = {{Beyond missing heritability: prediction of complex traits.}},
url = {http://dx.plos.org/10.1371/journal.pgen.1002051 http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3084207\&tool=pmcentrez\&rendertype=abstract},
volume = {7},
year = {2011}
}
@article{Manolio2009,
abstract = {Genome-wide association studies have identified hundreds of genetic variants associated with complex human diseases and traits, and have provided valuable insights into their genetic architecture. Most variants identified so far confer relatively small increments in risk, and explain only a small proportion of familial clustering, leading many to question how the remaining, 'missing' heritability can be explained. Here we examine potential sources of missing heritability and propose research strategies, including and extending beyond current genome-wide association approaches, to illuminate the genetics of complex diseases and enhance its potential to enable effective disease prevention or treatment.},
author = {Manolio, Teri A. and Collins, Francis S. and Cox, Nancy J. and Goldstein, David B. and Hindorff, Lucia A. and Hunter, David J. and McCarthy, Mark I. and Ramos, Erin M. and Cardon, Lon R. and Chakravarti, Aravinda and Cho, Judy H. and Guttmacher, Alan E. and Kong, Augustine and Kruglyak, Leonid and Mardis, Elaine and Rotimi, Charles N. and Slatkin, Montgomery and Valle, David and Whittemore, Alice S. and Boehnke, Michael and Clark, Andrew G. and Eichler, Evan E. and Gibson, Greg and Haines, Jonathan L. and Mackay, Trudy F. C. and McCarroll, Steven A. and Visscher, Peter M.},
doi = {10.1038/nature08494},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/Nature/Manolio et al. - 2009 - Finding the missing heritability of complex diseases.pdf:pdf},
issn = {1476-4687},
journal = {Nature},
keywords = {Genetic Diseases,Genetic Predisposition to Disease,Genetic Predisposition to Disease: genetics,Genetics,Genome-Wide Association Study,Genome-Wide Association Study: methods,Genome-Wide Association Study: trends,Humans,Inborn,Inborn: genetics,Inheritance Patterns,Inheritance Patterns: genetics,Medical,Medical: methods,Medical: trends,Pedigree,Peters intro refs},
mendeley-tags = {Peters intro refs},
month = oct,
number = {7265},
pages = {747--53},
pmid = {19812666},
publisher = {Macmillan Publishers Limited. All rights reserved},
shorttitle = {Nature},
title = {{Finding the missing heritability of complex diseases.}},
url = {http://dx.doi.org/10.1038/nature08494},
volume = {461},
year = {2009}
}
@article{Penagaricano2012,
abstract = {Whole-genome association studies typically focus on genetic markers with the strongest evidence of association. However, single markers often explain only a small component of the genetic variance and hence offer a limited understanding of the trait under study. As such, the objective of this study was to perform a pathway-based association analysis in Holstein dairy cattle in order to identify relevant pathways involved in bull fertility. The results of a single-marker association analysis, using 1,755 bulls with sire conception rate data and genotypes for 38,650 single nucleotide polymorphisms (SNPs), were used in this study. A total of 16,819 annotated genes, including 2,767 significantly associated with bull fertility, were used to interrogate a total of 662 Gene Ontology (GO) terms and 248 InterPro (IP) entries using a test of proportions based on the cumulative hypergeometric distribution. After multiple-testing correction, 20 GO categories and one IP entry showed significant overrepresentation of genes statistically associated with bull fertility. Several of these functional categories such as small GTPases mediated signal transduction, neurogenesis, calcium ion binding, and cytoskeleton are known to be involved in biological processes closely related to male fertility. These results could provide insight into the genetic architecture of this complex trait in dairy cattle. In addition, this study shows that quantitative trait pathways inferred from single-marker analyses could enhance our interpretations of the results of genome-wide association studies.},
author = {Pe\~{n}agaricano, Francisco and Weigel, Kent A and Rosa, Guilherme J M and Khatib, Hasan},
doi = {10.3389/fgene.2012.00307},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/Frontiers in Genetics/Pe\~{n}agaricano et al. - 2012 - Inferring quantitative trait pathways associated with bull fertility from a genome-wide association study.pdf:pdf},
issn = {1664-8021},
journal = {Front. Genet.},
keywords = {Peters ref},
mendeley-tags = {Peters ref},
month = jan,
pages = {307},
pmid = {23335935},
title = {{Inferring quantitative trait pathways associated with bull fertility from a genome-wide association study.}},
url = {http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3542705\&tool=pmcentrez\&rendertype=abstract},
volume = {3},
year = {2012}
}
@article{Su2012,
abstract = {This study investigated genomic prediction using medium-density ($\sim$54,000; 54K) and high-density marker panels ($\sim$777,000; 777K), based on data from Nordic Holstein and Red Dairy Cattle (RDC). The Holstein data comprised 4,539 progeny-tested bulls, and the RDC data 4,403 progeny-tested bulls. The data were divided into reference data and test data using October 1, 2001, as a cut-off date (birth date of the bulls). This resulted in about 25\% genotyped bulls in the Holstein test data and 20\% in the RDC test data. For each breed, 3 data sets of markers were used to predict breeding values: (1) 54K data set with missing genotypes, (2) 54K data set where missing genotypes were imputed, and (3) imputed high-density (HD) marker data set created by imputing the 54K data to the HD data based on 557 bulls genotyped using a 777K single nucleotide polymorphism chip in Holstein, and 706 bulls in RDC. Based on the 3 marker data sets, direct genomic breeding values (DGV) for protein, fertility, and udder health were predicted using a genomic BLUP model (GBLUP) and a Bayesian mixture model with 2 normal distributions. Reliability of DGV was measured as squared correlations between deregressed proofs (DRP) and DGV corrected for reliability of DRP. Unbiasedness was assessed by regression of DRP on DGV, based on the bulls in the test data sets. Averaged over the 3 traits, reliability of DGV based on the HD markers was 0.5\% higher than that based on the 54K data in Holstein, and 1.0\% higher than that in RDC. In addition, the HD markers led to an improvement of unbiasedness of DGV. The Bayesian mixture model led to 0.5\% higher reliability than the GBLUP model in Holstein, but not in RDC. Imputing missing genotypes in the 54K marker data did not improve genomic predictions for most of the traits.},
annote = {Replace tildes with \$\backslash sim 54,000\$.},
author = {Su, G. and Br{\o}ndum, Rasmus F and Ma, Peipei and Guldbrandtsen, Bernt and Aamand, G.P. and Lund, Mogens Sand{\o}},
doi = {10.3168/jds.2012-5379},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/Journal of Dairy Science/Su et al. - 2012 - Comparison of genomic predictions using medium-density (∼54,000) and high-density (∼777,000) single nucleotide polymo.pdf:pdf},
issn = {1525-3198},
journal = {J. Dairy Sci.},
keywords = {777k,Animals,Bayes Theorem,Cattle,Cattle: genetics,Female,Genetic,Genetic Markers,Genome,Genotype,Heritable,Holstein,Imputation,Male,Models,Polymorphism,Quantitative Trait,Reproducibility of Results,SNP50,Selection,Single Nucleotide},
mendeley-tags = {777k,Holstein,Imputation,SNP50},
month = aug,
number = {8},
pages = {4657--65},
pmid = {22818480},
publisher = {Elsevier},
title = {{Comparison of genomic predictions using medium-density ($\sim 54,000$) and high-density ($\sim 777,000$) single nucleotide polymorphism marker panels in Nordic Holstein and Red Dairy Cattle populations.}},
url = {http://www.journalofdairyscience.org/article/S0022-0302(12)00455-9/abstract},
volume = {95},
year = {2012}
}
@article{Zimin2009,
abstract = {The genome of the domestic cow, Bos taurus, was sequenced using a mixture of hierarchical and whole-genome shotgun sequencing methods.},
author = {Zimin, Aleksey V. and Delcher, Arthur L. and Florea, Liliana and Kelley, David R. and Schatz, Michael C. and Puiu, Daniela and Hanrahan, Finnian and Pertea, Geo and {Van Tassell}, Curtis P. and Sonstegard, Tad S. and Mar\c{c}ais, Guillaume and Roberts, Michael and Subramanian, Poorani and Yorke, James A. and Salzberg, Steven L},
doi = {10.1186/gb-2009-10-4-r42},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/Genome Biology/Zimin et al. - 2009 - A whole-genome assembly of the domestic cow, Bos taurus.pdf:pdf},
issn = {1465-6914},
journal = {Genome Biol.},
keywords = {Animals,Cattle,Cattle: genetics,Chromosome Mapping,DNA,DNA: methods,DNA: statistics \& numerical data,Female,Genome,Genome: genetics,Genomics,Human,Human: genetics,Humans,Male,Sequence Analysis,Synteny,Y Chromosome,Y Chromosome: genetics},
month = jan,
number = {4},
pages = {R42},
pmid = {19393038},
title = {{A whole-genome assembly of the domestic cow, \textit{Bos taurus}.}},
url = {http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=2688933\&tool=pmcentrez\&rendertype=abstract},
volume = {10},
year = {2009}
}
@article{Zuk2012,
abstract = {Human genetics has been haunted by the mystery of "missing heritability" of common traits. Although studies have discovered >1,200 variants associated with common diseases and traits, these variants typically appear to explain only a minority of the heritability. The proportion of heritability explained by a set of variants is the ratio of (i) the heritability due to these variants (numerator), estimated directly from their observed effects, to (ii) the total heritability (denominator), inferred indirectly from population data. The prevailing view has been that the explanation for missing heritability lies in the numerator-that is, in as-yet undiscovered variants. While many variants surely remain to be found, we show here that a substantial portion of missing heritability could arise from overestimation of the denominator, creating "phantom heritability." Specifically, (i) estimates of total heritability implicitly assume the trait involves no genetic interactions (epistasis) among loci; (ii) this assumption is not justified, because models with interactions are also consistent with observable data; and (iii) under such models, the total heritability may be much smaller and thus the proportion of heritability explained much larger. For example, 80\% of the currently missing heritability for Crohn's disease could be due to genetic interactions, if the disease involves interaction among three pathways. In short, missing heritability need not directly correspond to missing variants, because current estimates of total heritability may be significantly inflated by genetic interactions. Finally, we describe a method for estimating heritability from isolated populations that is not inflated by genetic interactions.},
author = {Zuk, Or and Hechter, Eliana and Sunyaev, Shamil R and Lander, Eric S},
doi = {10.1073/pnas.1119675109},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/Proceedings of the National Academy of Sciences of the United States of America/Zuk et al. - 2012 - The mystery of missing heritability Genetic interactions create phantom heritability.pdf:pdf},
issn = {1091-6490},
journal = {Proc. Natl. Acad. Sci. U. S. A.},
keywords = {Peters intro refs},
mendeley-tags = {Peters intro refs},
month = jan,
number = {4},
pages = {1193--8},
pmid = {22223662},
title = {{The mystery of missing heritability: Genetic interactions create phantom heritability.}},
url = {http://www.pnas.org/cgi/content/abstract/109/4/1193},
volume = {109},
year = {2012}
}
@article{Hu2013,
abstract = {The Animal QTL database (QTLdb; http://www.animalgenome.org/QTLdb) is designed to house all publicly available QTL and single-nucleotide polymorphism/gene association data on livestock animal species. An earlier version was published in the Nucleic Acids Research Database issue in 2007. Since then, we have continued our efforts to develop new and improved database tools to allow more data types, parameters and functions. Our efforts have transformed the Animal QTLdb into a tool that actively serves the research community as a quality data repository and more importantly, a provider of easily accessible tools and functions to disseminate QTL and gene association information. The QTLdb has been heavily used by the livestock genomics community since its first public release in 2004. To date, there are 5920 cattle, 3442 chicken, 7451 pigs, 753 sheep and 88 rainbow trout data points in the database, and at least 290 publications that cite use of the database. The rapid advancement in genomic studies of cattle, chicken, pigs, sheep and other livestock animals has presented us with challenges, as well as opportunities for the QTLdb to meet the evolving needs of the research community. Here, we report our progress over the recent years and highlight new functions and services available to the general public.},
author = {Hu, Zhi-Liang and Park, Carissa A. and Wu, Xiao-Lin and Reecy, James M.},
doi = {10.1093/nar/gks1150},
file = {::},
issn = {1362-4962},
journal = {Nucleic Acids Res.},
keywords = {Animals,Cattle,Chromosome Banding,Chromosome Mapping,Databases,Genome-Wide Association Study,Genomics,Internet,Livestock,Livestock: genetics,Nucleic Acid,Peters references,Quantitative Trait Loci,Software},
mendeley-tags = {Peters references},
month = jan,
number = {Database issue},
pages = {D871--9},
pmid = {23180796},
title = {{Animal QTLdb: an improved database tool for livestock animal QTL/association data dissemination in the post-genome era.}},
url = {http://nar.oxfordjournals.org/content/41/D1/D871.abstract},
volume = {41},
year = {2013}
}
@article{Lage2012,
abstract = {Congenital heart disease (CHD) occurs in ∼1\% of newborns. CHD arises from many distinct etiologies, ranging from genetic or genomic variation to exposure to teratogens, which elicit diverse cell and molecular responses during cardiac development. To systematically explore the relationships between CHD risk factors and responses, we compiled and integrated comprehensive datasets from studies of CHD in humans and model organisms. We examined two alternative models of potential functional relationships between genes in these datasets: direct convergence, in which CHD risk factors significantly and directly impact the same genes and molecules and functional convergence, in which risk factors significantly impact different molecules that participate in a discrete heart development network. We observed no evidence for direct convergence. In contrast, we show that CHD risk factors functionally converge in protein networks driving the development of specific anatomical structures (e.g., outflow tract, ventricular septum, and atrial septum) that are malformed by CHD. This integrative analysis of CHD risk factors and responses suggests a complex pattern of functional interactions between genomic variation and environmental exposures that modulate critical biological systems during heart development.},
author = {Lage, Kasper and Greenway, Steven C. and Rosenfeld, Jill A. and Wakimoto, Hiroko and Gorham, Joshua M. and Segr\`{e}, Ayellet V. and Roberts, Amy E. and Smoot, Leslie B. and Pu, William T. and Pereira, Alexandre C. and Mesquita, Sonia M. and Tommerup, Niels and Brunak, S\o ren and Ballif, Blake C. and Shaffer, Lisa G. and Donahoe, Patricia K. and Daly, Mark J. and Seidman, Jonathan G. and Seidman, Christine E. and Larsen, Lars A.},
doi = {10.1073/pnas.1210730109},
issn = {1091-6490},
journal = {Proc. Natl. Acad. Sci. U. S. A.},
keywords = {Congenital,Congenital: epidemiology,Congenital: genetics,Databases,Environment,Genetic,Genetic Predisposition to Disease,Genetic Predisposition to Disease: epidemiology,Hand Deformities,Heart,Heart: embryology,Humans,Infant,Newborn,Nonparametric,Peters references,Protein Interaction Maps,Protein Interaction Maps: genetics,Risk Factors,Statistics,Transcriptome},
mendeley-tags = {Peters references},
month = aug,
number = {35},
pages = {14035--40},
pmid = {22904188},
title = {{Genetic and environmental risk factors in congenital heart disease functionally converge in protein networks driving heart development.}},
url = {http://www.pnas.org/content/109/35/14035},
volume = {109},
year = {2012}
}
@article{Maurano2012,
abstract = {Genome-wide association studies have identified many noncoding variants associated with common diseases and traits. We show that these variants are concentrated in regulatory DNA marked by deoxyribonuclease I (DNase I) hypersensitive sites (DHSs). Eighty-eight percent of such DHSs are active during fetal development and are enriched in variants associated with gestational exposure–related phenotypes. We identified distant gene targets for hundreds of variant-containing DHSs that may explain phenotype associations. Disease-associated variants systematically perturb transcription factor recognition sequences, frequently alter allelic chromatin states, and form regulatory networks. We also demonstrated tissue-selective enrichment of more weakly disease-associated variants within DHSs and the de novo identification of pathogenic cell types for Crohn’s disease, multiple sclerosis, and an electrocardiogram trait, without prior knowledge of physiological mechanisms. Our results suggest pervasive involvement of regulatory DNA variation in common human disease and provide pathogenic insights into diverse disorders.},
annote = {10.1126/science.1222794 },
author = {Maurano, Matthew T. and Humbert, Richard and Rynes, Eric and Thurman, Robert E. and Haugen, Eric and Wang, Hao and Reynolds, Alex P. and Sandstrom, Richard and Qu, Hongzhu and Brody, Jennifer and Shafer, Anthony and Neri, Fidencio and Lee, Kristen and Kutyavin, Tanya and Stehling-Sun, Sandra and Johnson, Audra K. and Canfield, Theresa K. and Giste, Erika and Diegel, Morgan and Bates, Daniel and Hansen, R. Scott and Neph, Shane and Sabo, Peter J. and Heimfeld, Shelly and Raubitschek, Antony and Ziegler, Steven and Cotsapas, Chris and Sotoodehnia, Nona and Glass, Ian and Sunyaev, Shamil R. and Kaul, Rajinder and Stamatoyannopoulos, John A.},
doi = {10.1126/science.1222794},
journal = {Science},
keywords = {Peters references},
mendeley-tags = {Peters references},
month = sep,
number = {6099},
pages = {1190--1195},
title = {{Systematic Localization of Common Disease-Associated Variation in Regulatory DNA}},
url = {http://www.sciencemag.org/content/337/6099/1190.abstract},
volume = {337},
year = {2012}
}
@article{ORoak2012,
annote = {10.1038/nature10989},
author = {O'Roak, Brian J. and Vives, Laura and Girirajan, Santhosh and Karakoc, Emre and Krumm, Niklas and Coe, Bradley P. and Levy, Roie and Ko, Arthur and Lee, Choli and Smith, Joshua D. and Turner, Emily H. and Stanaway, Ian B. and Vernot, Benjamin and Malig, Maika and Baker, Carl and Reilly, Beau and Akey, Joshua M. and Borenstein, Elhanan and Rieder, Mark J. and Nickerson, Deborah A. and Bernier, Raphael and Shendure, Jay and Eichler, Evan E.},
issn = {0028-0836},
journal = {Nature},
keywords = {Peters references},
mendeley-tags = {Peters references},
month = may,
number = {7397},
pages = {246--250},
publisher = {Nature Publishing Group, a division of Macmillan Publishers Limited. All Rights Reserved.},
title = {{Sporadic autism exomes reveal a highly interconnected protein network of de novo mutations}},
url = {http://dx.doi.org/10.1038/nature10989 http://www.nature.com/nature/journal/v485/n7397/abs/nature10989.html\#supplementary-information},
volume = {485},
year = {2012}
}
@article{Yang2011,
abstract = {We estimate and partition genetic variation for height, body mass index (BMI), von Willebrand factor and QT interval (QTi) using 586,898 SNPs genotyped on 11,586 unrelated individuals. We estimate that \~{}45\%, \~{}17\%, \~{}25\% and \~{}21\% of the variance in height, BMI, von Willebrand factor and QTi, respectively, can be explained by all autosomal SNPs and a further \~{}0.5–1\% can be explained by X chromosome SNPs. We show that the variance explained by each chromosome is proportional to its length, and that SNPs in or near genes explain more variation than SNPs between genes. We propose a new approach to estimate variation due to cryptic relatedness and population stratification. Our results provide further evidence that a substantial proportion of heritability is captured by common SNPs, that height, BMI and QTi are highly polygenic traits, and that the additive variation explained by a part of the genome is approximately proportional to the total length of DNA contained within genes therein.},
author = {Yang, Jian and Manolio, Teri A. and Pasquale, Louis R. and Boerwinkle, Eric and Caporaso, Neil and Cunningham, Julie M. and de Andrade, Mariza and Feenstra, Bjarke and Feingold, Eleanor and Hayes, M Geoffrey and Hill, William G. and Landi, Maria Teresa and Alonso, Alvaro and Lettre, Guillaume and Lin, Peng and Ling, Hua and Lowe, William and Mathias, Rasika A. and Melbye, Mads and Pugh, Elizabeth and Cornelis, Marilyn C. and Weir, Bruce S. and Goddard, Michael E. and Visscher, Peter M.},
doi = {10.1038/ng.823},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/Nature Genetics/Yang et al. - 2011 - Genome partitioning of genetic variation for complex traits using common SNPs.pdf:pdf},
issn = {1061-4036},
journal = {Nat. Genet.},
keywords = {Peters intro refs},
mendeley-groups = {Manuscript1,DGRP genomic features},
mendeley-tags = {Peters intro refs},
month = may,
number = {6},
pages = {519--525},
title = {{Genome partitioning of genetic variation for complex traits using common SNPs}},
url = {http://www.nature.com/doifinder/10.1038/ng.823},
volume = {43},
year = {2011}
}

@manual{RCoreTeam,
address = {Vienna, Austria},
annote = {\{ISBN\} 3-900051-07-0},
author = {{R Core Team}},
isbn = {3-900051-07-0},
mendeley-groups = {Manuscript1,DGRP genomic features},
organization = {R Foundation for Statistical Computing},
publisher = {R Foundation for Statistical Computing},
title = {{R: A Language and Environment for Statistical Computing}},
url = {http://www.r-project.org/},
year = {2012}
}
@article{Wood2011,
author = {Wood, Simon N.},
doi = {10.1111/j.1467-9868.2010.00749.x},
issn = {13697412},
journal = {J. R. Stat. Soc. B.},
keywords = {GAM,R-package,mgcv},
mendeley-groups = {DGRP genomic features},
mendeley-tags = {GAM,mgcv,R-package},
month = jan,
number = {1},
pages = {3--36},
title = {{Fast stable restricted maximum likelihood and marginal likelihood estimation of semiparametric generalized linear models}},
url = {http://doi.wiley.com/10.1111/j.1467-9868.2010.00749.x},
volume = {73},
year = {2011}
}
@article{Wood2004,
abstract = {Representation of generalized additive models (GAM's) using penalized regression splines allows GAM's to be employed in a straightforward manner using penalized regression methods. Not only is inference facilitated by this approach, but it is also possible to integrate model selection in the form of smoothing parameter selection into model fitting in a computationally efficient manner using well founded criteria such as generalized cross-validation. The current fitting and smoothing parameter selection methods for such models are usually effective, but do not provide the level of numerical stability to which users of linear regression packages, for example, are accustomed. In particular the existing methods cannot deal adequately with numerical rank deficiency of the GAM fitting problem, and it is not straightforward to produce methods that can do so, given that the degree of rank deficiency can be smoothing parameter dependent. In addition, models with the potential flexibility of GAM's can also present practical fitting difficulties as a result of indeterminacy in the model likelihood: Data with many zeros fitted by a model with a log link are a good example. In this article it is proposed that GAM's with a ridge penalty provide a practical solution in such circumstances, and a multiple smoothing parameter selection method suitable for use in the presence of such a penalty is developed. The method is based on the pivoted QR decomposition and the singular value decomposition, so that with or without a ridge penalty it has good error propagation properties and is capable of detecting and coping elegantly with numerical rank deficiency. The method also allows mixtures of user specified and estimated smoothing parameters and the setting of lower bounds on smoothing parameters. In terms of computational efficiency, the method compares well with existing methods. A simulation study compares the method to existing methods, including treating GAM's as mixed models},
author = {Wood, Simon N.},
doi = {http://dx.doi.org/10.1198/016214504000000980},
journal = {J. Am. Stat. Assoc.},
keywords = {GAM,R-package,mgcv},
mendeley-groups = {DGRP genomic features},
mendeley-tags = {GAM,mgcv,R-package},
month = sep,
number = {467},
pages = {673--686},
publisher = {University of Bath},
title = {{Stable and efficient multiple smoothing parameter estimation for generalized additive models}},
url = {http://opus.bath.ac.uk/7196/1/magic.pdf},
volume = {99},
year = {2004}
}
 @Manual{org.Dm.eg.db,
    title = {org.Dm.eg.db: Genome wide annotation for Fly},
    author = {Marc Carlson},
    note = {R package version 2.10.1},
  }

@article{Aguilar2011,
	abstract = "Genomic evaluations can be calculated using a unified procedure that combines phenotypic, pedigree and genomic information. Implementation of such a procedure requires the inverse of the relationship matrix based on pedigree and genomic relationships. The objective of this study was to investigate efficient computing options to create relationship matrices based on genomic markers and pedigree information as well as their inverses. SNP maker information was simulated for a panel of 40 K SNPs, with the number of genotyped animals up to 30 000. Matrix multiplication in the computation of the genomic relationship was by a simple 'do' loop, by two optimized versions of the loop, and by a specific matrix multiplication subroutine. Inversion was by a generalized inverse algorithm and by a LAPACK subroutine. With the most efficient choices and parallel processing, creation of matrices for 30 000 animals would take a few hours. Matrices required to implement a unified approach can be computed 
efficiently. Optimizations can be either by modifications of existing code or by the use of efficient automatic optimizations provided by open source or third-party libraries.",
	author = "Aguilar, I. and Misztal, I. and Legarra, A. and Tsuruta, S.",
	doi = "10.1111/j.1439-0388.2010.00912.x",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Aguilar et al. - 2011 - Efficient computation of the genomic relationship matrix and other matrices used in single-step evaluation.pdf:pdf",
	issn = "1439-0388",
	journal = "Journal of animal breeding and genetics = Zeitschrift f{\"u}r Tierz{\"u}chtung und Z{\"u}chtungsbiologie",
	keywords = "computing methods; genomic selection; relationship matrix",
	month = dec,
	number = "6",
	pages = "422--428",
	pmid = "22059575",
	title = "{Efficient computation of the genomic relationship matrix and other matrices used in single-step evaluation.}",
	url = "http://doi.wiley.com/10.1111/j.1439-0388.2010.00912.x; http://www.ncbi.nlm.nih.gov/pubmed/22059575",
	volume = "128",
	year = "2011"
}

@article{Allison1999,
	abstract = "Detection of linkage to genes for quantitative traits remains a challenging task. Recently, variance components (VC) techniques have emerged as among the more powerful of available methods. As often implemented, such techniques require assumptions about the phenotypic distribution. Usually, multivariate normality is assumed. However, several factors may lead to markedly nonnormal phenotypic data, including (a) the presence of a major gene (not necessarily linked to the markers under study), (b) some types of gene x environment interaction, (c) use of a dichotomous phenotype (i.e., affected vs. unaffected), (d) nonnormality of the population within-genotype (residual) distribution, and (e) selective (extreme) sampling. Using simulation, we have investigated, for sib-pair studies, the robustness of the likelihood-ratio test for a VC quantitative-trait locus-detection procedure to violations of normality that are due to these factors. Results showed (a) that some types of nonnormality, such as 
leptokurtosis, produced type I error rates in excess of the nominal, or alpha, levels whereas others did not; and (b) that the degree of type I error-rate inflation appears to be directly related to the residual sibling correlation. Potential solutions to this problem are discussed. Investigators contemplating use of this VC procedure are encouraged to provide evidence that their trait data are normally distributed, to employ a procedure that allows for nonnormal data, or to consider implementation of permutation tests.",
	author = "Allison, D B and Neale, M C and Zannolli, R and Schork, N J and Amos, C I and Blangero, J",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Allison et al. - 1999 - Testing the robustness of the likelihood-ratio test in a variance-component quantitative-trait loci-mapping procedure.pdf:pdf",
	issn = "0002-9297",
	journal = "Am. J. Hum. Genet.",
	keywords = "Analysis of Variance; Chromosome Mapping; Computer Simulation; Genetic Linkage; Humans; Likelihood Functions; Likelihood tests; Matched-Pair Analysis; Nuclear Family; Phenotype; Quantitative Trait; Heritable; Reproducibility of Results; Sample Size; Software; Statistical Distributions",
	mendeley-tags = "Likelihood tests",
	month = aug,
	number = "2",
	pages = "531--44",
	title = "{Testing the robustness of the likelihood-ratio test in a variance-component quantitative-trait loci-mapping procedure.}",
	url = "http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=1377951&tool=pmcentrez&rendertype=abstract",
	volume = "65",
	year = "1999"
}

@article{Balding2006,
	author = "Balding, David J.",
	doi = "10.1038/nrg1916",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Balding - 2006 - A tutorial on statistical methods for population association studies.pdf:pdf",
	issn = "1471-0056",
	journal = "Nat Rev Genet",
	keywords = "GWAS; Microarray; Peters intro refs",
	mendeley-tags = "GWAS,Microarray,Peters intro refs",
	month = oct,
	number = "10",
	pages = "781--791",
	title = "{A tutorial on statistical methods for population association studies}",
	url = "http://dx.doi.org/10.1038/nrg1916",
	volume = "7",
	year = "2006"
}

@article{Ballantyne2012,
	author = "Ballantyne, A. P. and Alden, C. B. and Miller, J. B. and Tans, P. P. and White, J. W. C.",
	issn = "0028-0836",
	journal = "Nature",
	month = aug,
	number = "7409",
	pages = "70--72",
	publisher = "Nature Publishing Group, a division of Macmillan Publishers Limited. All Rights Reserved.",
	shorttitle = "Nature",
	title = "{Increase in observed net carbon dioxide uptake by land and oceans during the past 50 years}",
	url = "http://dx.doi.org/10.1038/nature11299",
	volume = "488",
	year = "2012"
}

@article{Bar2007,
abstract = {Our objective was to estimate the milk losses associated with multiple occurrences of generic bovine clinical mastitis (CM) within and across lactations. We studied 10,380 lactations from 5 large, high-producing dairy herds that used automatic recording of daily milk yields. Mixed models, with a random herd effect and an autoregressive covariance structure to account for repeated measurements, were used to quantify the effect of CM and other control variables (parity, week of lactation, other diseases) on milk yield. Many cows that developed CM were higher producers than their non-mastitic herdmates before CM occurred. Milk yield began to drop after diagnosis; the greatest loss occurred in the first weeks (up to 126 kg) and then gradually tapered to a constant value approximately 2 mo after CM. Mastitic cows often never recovered their potential yield. First-lactation cows lost 164 kg of milk for the first episode and 198 kg for the second in the 2 mo after CM diagnosis, compared with their potential yield. Among older cows, this estimate was 253 kg for the first, 238 kg for the second, and 216 kg for the third CM case. A cow that had 1 or more CM episodes in her previous lactation produced 1.2 kg/d less milk over the whole current lactation (95\% confidence interval: 0.6, 1.7) than a cow without CM in her previous lactation. These findings provide dairy producers with information on the average milk loss associated with CM cases without considering the causative agent, and can be used for economic analysis.},
author = {Bar, D and Gr\"{o}hn, Y T and Bennett, G and Gonz\'{a}lez, R N and Hertl, J A and Schulte, H F and Tauer, L W and Welcome, F L and Schukken, Y H},
doi = {10.3168/jds.2007-0145},
file = {:C$\backslash$:/Users/STME/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Bar et al. - 2007 - Effect of repeated episodes of generic clinical mastitis on milk yield in dairy cows.pdf:pdf},
issn = {1525-3198},
journal = {J. Dairy Sci.},
keywords = {Animals,Bacteria,Bacteria: isolation \& purification,Bo's reference.,Bovine,Bovine: microbiology,Bovine: physiopathology,Cattle,Cattle Diseases,Cattle Diseases: microbiology,Cattle Diseases: physiopathology,Dairying,Female,Lactation,Lactation: physiology,Mastitis,Milk,Milk: secretion,Time Factors},
mendeley-tags = {Bo's reference.},
month = oct,
number = {10},
pages = {4643--53},
pmid = {17881685},
publisher = {Elsevier},
title = {{Effect of repeated episodes of generic clinical mastitis on milk yield in dairy cows.}},
url = {http://www.journalofdairyscience.org/article/S0022-0302(07)71928-8/abstract},
volume = {90},
year = {2007}
}

@article{Browning2009,
	abstract = "We present methods for imputing data for ungenotyped markers and for inferring haplotype phase in large data sets of unrelated individuals and parent-offspring trios. Our methods make use of known haplotype phase when it is available, and our methods are computationally efficient so that the full information in large reference panels with thousands of individuals is utilized. We demonstrate that substantial gains in imputation accuracy accrue with increasingly large reference panel sizes, particularly when imputing low-frequency variants, and that unphased reference panels can provide highly accurate genotype imputation. We place our methodology in a unified framework that enables the simultaneous use of unphased and phased data from trios and unrelated individuals in a single analysis. For unrelated individuals, our imputation methods produce well-calibrated posterior genotype probabilities and highly accurate allele-frequency estimates. For trios, our haplotype-inference method is four orders 
of magnitude faster than the gold-standard PHASE program and has excellent accuracy. Our methods enable genotype imputation to be performed with unphased trio or unrelated reference panels, thus accounting for haplotype-phase uncertainty in the reference panel. We present a useful measure of imputation accuracy, allelic R(2), and show that this measure can be estimated accurately from posterior genotype probabilities. Our methods are implemented in version 3.0 of the BEAGLE software package.",
	author = "Browning, Brian L and Browning, Sharon R",
	doi = "10.1016/j.ajhg.2009.01.005",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Browning, Browning - 2009 - A unified approach to genotype imputation and haplotype-phase inference for large data sets of trios and unrelated individuals.pdf:pdf",
	issn = "1537-6605",
	journal = "American journal of human genetics",
	keywords = "Computer Simulation; Female; Gene Frequency; Gene Frequency: genetics; Genotype; Haplotypes; Haplotypes: genetics; Humans; Male; Markov Chains; Models; Genetic; Nuclear Family; Reproducibility of Results",
	month = feb,
	number = "2",
	pages = "210--23",
	pmid = "19200528",
	title = "{A unified approach to genotype imputation and haplotype-phase inference for large data sets of trios and unrelated individuals.}",
	url = "http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=2668004&tool=pmcentrez&rendertype=abstract",
	volume = "84",
	year = "2009"
}

@article{Buitenhuis2011,
	abstract = "Bovine mastitis is one of the most costly and prevalent diseases affecting dairy cows worldwide. In order to develop new strategies to prevent Escherichia coli-induced mastitis, a detailed understanding of the molecular mechanisms underlying the host immune response to an E. coli infection is necessary. To this end, we performed a global gene-expression analysis of mammary gland tissue collected from dairy cows that had been exposed to a controlled E. coli infection. Biopsy samples of healthy and infected utter tissue were collected at T = 24 h post-infection (p.i.) and at T = 192 h p.i. to represent the acute phase response (APR) and chronic stage, respectively. Differentially expressed (DE) genes for each stage were analyzed and the DE genes detected at T = 24 h were also compared to data collected from two previous E. coli mastitis studies that were carried out on post mortem tissue.",
	author = "Buitenhuis, Bart and {R{\o}ntved}, Christine M. and Edwards, Stefan McKinnon and Ingvartsen, Klaus L. and {S{\o}rensen}, Peter",
	doi = "10.1186/1471-2164-12-130",
	file = "::",
	issn = "1471-2164",
	journal = "BMC Genomics",
	keywords = "Animal; Animal: metabolism; Animal: microbiology; Animals; Bovine; Bovine: genetics; Bovine: immunology; Bovine: microbiology; Cattle; Escherichia coli; Escherichia coli Infections; Escherichia coli Infections: genetics; Escherichia coli Infections: immunology; Escherichia coli Infections: veterinary; Female; Gene Expression Profiling; Lipid Metabolism; Lipid Metabolism: genetics; Mammary Glands; Mastitis; Milk; Milk: microbiology; Oligonucleotide Array Sequence Analysis",
	month = jan,
	number = "1",
	pages = "130",
	pmid = "21352611",
	title = "{In depth analysis of genes and pathways of the mammary gland involved in the pathogenesis of bovine \textit{Escherichia coli}-mastitis.}",
	url = "http://www.biomedcentral.com/1471-2164/12/130",
	volume = "12",
	year = "2011"
}

@misc{orgBtdb2011,
	author = "Carlson, Marc and Falcon, Seth and Pages, Herve and Li, Nianhua",
	title = "{org.Bt.eg.db: Genome wide annotation for Bovine. R package version 2.5.0.}",
	year = "2011"
}

@article{CorbeilSearle1976,
	author = "Corbeil, RR",
	journal = "Technometrics",
	keywords = "Mixed Model; Restricted Maximum Likelihood; Variance Components; W-transformation",
	month = feb,
	number = "1",
	pages = "31--38",
	series = "{Technometrics}",
	title = "{Restricted maximum likelihood (REML) estimation of variance components in the mixed model}",
	url = "http://www.jstor.org/stable/1267913; http://www.jstor.org/stable/10.2307/1267913",
	volume = "18",
	year = "1976"
}


@misc{AnnotationFuncs2011,
	author = "Edwards, Stefan McKinnon",
	month = feb,
	title = "{Annotation translation functions for Bioconductors annotation packages}",
	url = "http://www.iysik.com/index.php?page=annotation-functions",
	year = "2011"
}

@misc{txtPhenomeWWW,
	author = "Edwards, Stefan McKinnon and Jiang, Li",
	title = "{txtPhenome - using textual descriptions as phenotypes}",
	url = "https://djfextranet.agrsci.dk/sites/txtphenome/public/Pages/front.aspx",
	urldate = "01-11-2011",
	year = "2011"
}

@article{Fridley2011,
	abstract = "The last decade of human genetic research witnessed the completion of hundreds of genome-wide association studies (GWASs). However, the genetic variants discovered through these efforts account for only a small proportion of the heritability of complex traits. One explanation for the missing heritability is that the common analysis approach, assessing the effect of each single-nucleotide polymorphism (SNP) individually, is not well suited to the detection of small effects of multiple SNPs. Gene set analysis (GSA) is one of several approaches that may contribute to the discovery of additional genetic risk factors for complex traits. Complex phenotypes are thought to be controlled by networks of interacting biochemical and physiological pathways influenced by the products of sets of genes. By assessing the overall evidence of association of a phenotype with all measured variation in a set of genes, GSA may identify functionally relevant sets of genes corresponding to relevant biomolecular pathways,
 which will enable more focused studies of genetic risk factors. This approach may thus contribute to the discovery of genetic variants responsible for some of the missing heritability. With the increased use of these approaches for the secondary analysis of data from GWAS, it is important to understand the different GSA methods and their strengths and weaknesses, and consider challenges inherent in these types of analyses. This paper provides an overview of GSA, highlighting the key challenges, potential solutions, and directions for ongoing research.",
	author = "Fridley, Brooke L and Biernacka, Joanna M",
	doi = "10.1038/ejhg.2011.57",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Fridley, Biernacka - 2011 - Gene set analysis of SNP data benefits, challenges, and future directions.pdf:pdf",
	issn = "1476-5438",
	journal = "Eur. J. Hum. Genet.",
	keywords = "Disease; Disease: genetics; Genetic Predisposition to Disease; Genome-Wide Association Study; Genome-Wide Association Study: methods; Humans; Linkage Disequilibrium; Metabolic Networks and Pathways; Models; Polymorphism; Recommended by Peter; Single Nucleotide; Statistical",
	mendeley-tags = "Recommended by Peter",
	month = aug,
	number = "8",
	pages = "837--43",
	pmid = "21487444",
	title = "{Gene set analysis of SNP data: benefits, challenges, and future directions.}",
	url = "http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3172936&tool=pmcentrez&rendertype=abstract",
	volume = "19",
	year = "2011"
}

@article{biobase2004,
	abstract = "The Bioconductor project is an initiative for the collaborative creation of extensible software for computational biology and bioinformatics. The goals of the project include: fostering collaborative development and widespread use of innovative software, reducing barriers to entry into interdisciplinary scientific research, and promoting the achievement of remote reproducibility of research results. We describe details of our aims and methods, identify current challenges, compare Bioconductor to other open bioinformatics projects, and provide working examples",
	author = "Gentleman, Robert and Carey, Vincent and Bates, Douglas and Bolstad, Ben and Dettling, Marcel and Dudoit, Sandrine and Ellis, Byron and Gautier, Laurent and Ge, Yongchao and Gentry, Jeff and Hornik, Kurt and Hothorn, Torsten and Huber, Wolfgang and Iacus, Stefano and Irizarry, Rafael and Leisch, Friedrich and Li, Cheng and Maechler, Martin and Rossini, Anthony and Sawitzki, Gunther and Smith, Colin and Smyth, Gordon K. and Tierney, Luke and Yang, Jean and Zhang, Jianhua",
	doi = "10.1186/gb-2004-5-10-r80",
	issn = "1465-6906",
	journal = "Genome Biol.",
	number = "10",
	pages = "R80",
	title = "{Bioconductor: open software development for computational biology and bioinformatics}",
	url = "http://genomebiology.com/2004/5/10/R80",
	volume = "5",
	year = "2004"
}

@article{Gilmour1995,
	abstract = "A strategy of using an average information matrix is shown to be computationally convenient and efficient for estimating variance components by restricted maximum likelihood (REML) in the mixed linear model. Three applications are described. The motivation for the algorithm was the estimation of variance components in the analysis of wheat variety means from 1,071 experiments representing 10 years and 60 locations in New South Wales. We also apply the algorithm to the analysis of designed experiments by incomplete block analysis and spatial analysis of field experiments.",
	author = "Gilmour, Arthur R and Thompson, Robin and Cullis, Brian R",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Gilmour, Thompson, Cullis - 1995 - Average Information REML An Efficient Algorithm for Variance Parameter Estimation in Linear Mixed Models.pdf:pdf",
	issn = "0006341X",
	journal = "Biometrics",
	number = "4",
	pages = "1440--1450",
	publisher = "International Biometric Society",
	title = "{Average Information REML: An Efficient Algorithm for Variance Parameter Estimation in Linear Mixed Models}",
	url = "http://www.jstor.org/stable/2533274",
	volume = "51",
	year = "1995"
}

@article{Goddard2008,
	author = "Goddard, Mike",
	doi = "10.1007/s10709-008-9308-0",
	issn = "0016-6707",
	journal = "Genetica",
	keywords = "NOVA course",
	mendeley-tags = "NOVA course",
	month = aug,
	number = "2",
	pages = "245--257",
	shorttitle = "Genomic selection",
	title = "{Genomic selection: prediction of accuracy and maximisation of long term response}",
	url = "http://www.springerlink.com/index/10.1007/s10709-008-9308-0",
	volume = "136",
	year = "2008"
}

@article{Goeman2004,
	abstract = "Motivation: This paper presents a global test to be used for the analysis of microarray data. Using this test it can be determined whether the global expression pattern of a group of genes is significantly related to some clinical outcome of interest. Groups of genes may be any size from a single gene to all genes on the chip (e.g. known pathways, specific areas of the genome or clusters from a cluster analysis). Result: The test allows groups of genes of different size to be compared, because the test gives one p-value for the group, not a p-value for each gene. Researchers can use the test to investigate hypotheses based on theory or past research or to mine gene ontology databases for interesting pathways. Multiple testing problems do not occur unless many groups are tested. Special attention is given to visualizations of the test result, focussing on the associations between samples and showing the impact of individual genes on the test result.",
	author = "Goeman, J. J. and van de Geer, S. a. and de Kort, F. and van Houwelingen, H. C.",
	doi = "10.1093/bioinformatics/btg382",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Goeman et al. - 2003 - A global test for groups of genes testing association with a clinical outcome.pdf:pdf",
	issn = "1367-4803",
	journal = "Bioinformatics",
	month = dec,
	number = "1",
	pages = "93--99",
	title = "{A global test for groups of genes: testing association with a clinical outcome}",
	url = "http://bioinformatics.oxfordjournals.org/cgi/doi/10.1093/bioinformatics/btg382",
	volume = "20",
	year = "2004"
}

@article{Goeman2006,
author = {Goeman, Jelle J. and van de Geer, Sara a. and van Houwelingen, Hans C.},
doi = {10.1111/j.1467-9868.2006.00551.x},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/Journal of the Royal Statistical Society Series B (Statistical Methodology)/Goeman, van de Geer, van Houwelingen - 2006 - Testing against a high dimensional alternative.pdf:pdf},
issn = {1369-7412},
journal = {J. R. Stat. Soc. Ser. B (Statistical Methodol.},
keywords = {Gene set test,empirical bayes modelling,f -test,high dimensional data,hypothesis testing,locally most powerful test,power,score test},
mendeley-tags = {Gene set test},
month = jun,
number = {3},
pages = {477--493},
title = {{Testing against a high dimensional alternative}},
url = {http://doi.wiley.com/10.1111/j.1467-9868.2006.00551.x},
volume = {68},
year = {2006}
}


@article{Grisart2004,
	abstract = "We recently used a positional cloning approach to identify a nonconservative lysine to alanine substitution (K232A) in the bovine DGAT1 gene that was proposed to be the causative quantitative trait nucleotide underlying a quantitative trait locus (QTL) affecting milk fat composition, previously mapped to the centromeric end of bovine chromosome 14. We herein generate genetic and functional data that confirm the causality of the DGAT1 K232A mutation. We have constructed a high-density single-nucleotide polymorphism map of the 3.8-centimorgan BULGE30-BULGE9 interval containing the QTL and show that the association with milk fat percentage maximizes at the DGAT1 gene. We provide evidence that the K allele has undergone a selective sweep. By using a baculovirus expression system, we have expressed both DGAT1 alleles in Sf9 cells and show that the K allele, causing an increase in milk fat percentage in the live animal, is characterized by a higher Vmax in producing triglycerides than the A allele.",
	author = "Grisart, Bernard and Farnir, Fr{\'e}d{\'e}ric and Karim, Latifa and Cambisano, Nadine and Kim, Jong-Joo and Kvasz, Alex and Mni, Myriam and Simon, Patricia and Fr{\`e}re, Jean-Marie and Coppieters, Wouter and Georges, Michel",
  doi = "10.1073/pnas.0308518100",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Grisart et al. - 2004 - Genetic and functional confirmation of the causality of the DGAT1 K232A quantitative trait nucleotide in affecting milk yield and composition(2).pdf:pdf",
	issn = "0027-8424",
	journal = "P. Natl. Acad. Sci. USA",
	keywords = "Acyltransferases; Acyltransferases: genetics; Acyltransferases: metabolism; Amino Acid Substitution; Animal; Animals; Base Sequence; Cattle; Cattle: genetics; Cell Line; Chromosome Mapping; DGAT1; DNA Primers; Diacylglycerol O-Acyltransferase; Female; Genetic Markers; Linkage Disequilibrium; Male; Mammary Glands; Milk; Milk: secretion; Mutagenesis; Quantitative Trait Loci; Recombinant Proteins; Recombinant Proteins: metabolism; Reverse Transcriptase Polymerase Chain Reaction; Site-Directed; Spodoptera",
	mendeley-tags = "DGAT1",
	month = feb,
	number = "8",
	pages = "2398--403",
	pmid = "14983021",
	title = "{Genetic and functional confirmation of the causality of the DGAT1 K232A quantitative trait nucleotide in affecting milk yield and composition}",
	url = "http://www.pnas.org/cgi/content/abstract/101/8/2398",
	volume = "101",
	year = {2004}
}

@article{Jensen1997,
	abstract = "An algorithm for the REML estimation of (co) variance components in general multivariate mixed linear models is described. The algorithm is based on the use of Average Information (AI) as second differentials of the likelihood function. The AI is obtained by averaging the information matrices based on observed and expected information. It is manipulated to a form that is much easier to calculate than either of the two. This involves the setting up of dummy variables as functions of residuals and calculating sums of squares and cross-products associated with these. Procedures that are based on second differentials can lead to estimates outside the parameter space. By contrast, the EM-algorithm always ensures that estimates are in the parameter space. An alternative fonnulation of the EM-algorithm allows the possibility of constructing algorithms that are intermediate between AI and EM and can ensure estimates within the parameter space without the problem of slow convergence of the EM algorithm.
The new algorithm was compared to derivative-free (DF) and EM algorithms by analysing two sets of field data under several models. The AI algorithm converged in much fewer rounds than the other algorithms and was in general able to locate a higher maximum of the likelihood function.",
	author = "Jensen, Just and Mantysaari, Esa A. and Madsen, Per and Thompson, Robin",
	journal = "J. Indian Soc. Agr. Stat.",
	pages = "215--236",
	title = "{Residual Maximum likelihood Estimation of (Co) Variance Components in Multivariate Mixed Linear Models Using Average Information}",
	url = "http://isas.org.in/jisas/jsp/abstract.jsp?title=Residual",
	volume = "49",
	year = "1997"
}

@article{Jiang2008,
	abstract = "Liver plays a profound role in the acute phase response (APR) observed in the early phase of acute bovine mastitis caused by Escherichia coli (E. coli). To gain an insight into the genes and pathways involved in hepatic APR of dairy cows we performed a global gene expression analysis of liver tissue sampled at different time points before and after intra-mammary (IM) exposure to E. coli lipopolysaccharide (LPS) treatment.",
	author = "Jiang, Li and {S{\o}rensen}, Peter and {R{\o}ntved}, Christine and Vels, Lotte and Ingvartsen, Klaus L",
	doi = "10.1186/1471-2164-9-443",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Jiang et al. - 2008 - Gene expression profiling of liver from dairy cows treated intra-mammary with lipopolysaccharide.pdf:pdf",
	issn = "1471-2164",
	journal = "BMC genomics",
	keywords = "Acute-Phase Proteins; Acute-Phase Proteins: genetics; Acute-Phase Proteins: metabolism; Acute-Phase Reaction; Acute-Phase Reaction: genetics; Acute-Phase Reaction: veterinary; Animals; Cattle; Dairying; Escherichia coli Infections; Escherichia coli Infections: genetics; Escherichia coli Infections: veterinary; Female; Gene Expression Profiling; Lipopolysaccharides; Lipopolysaccharides: metabolism; Lipopolysaccharides: pharmacology; Liver; Liver: metabolism; Mammary Glands; Animal; Mammary Glands; Animal: immunology; Mammary Glands; Animal: metabolism; Mastitis; Bovine; Mastitis; Bovine: genetics; Mastitis; Bovine: metabolism; txtPhenome",
	mendeley-tags = "txtPhenome",
	month = jan,
	number = "1",
	pages = "443",
	pmid = "18816405",
	title = "{Gene expression profiling of liver from dairy cows treated intra-mammary with lipopolysaccharide.}",
	url = "http://www.biomedcentral.com/1471-2164/9/443",
	volume = "9",
	year = "2008"
}

@article{Jiang2012,
	abstract = "Identifying causal genes that underlie complex traits such as susceptibility to disease is a primary aim of genetic and biomedical studies. Genetic mapping of quantitative trait loci (QTL) and gene expression profiling based on high-throughput technologies are common first approaches toward identifying associations between genes and traits; however, it is often difficult to assess whether the biological function of a putative candidate gene is consistent with a particular phenotype. Here, we have implemented a network-based disease gene prioritization approach for ranking genes associated with quantitative traits and diseases in livestock species. The approach uses ortholog mapping and integrates information on disease or trait phenotypes, gene-associated phenotypes, and protein-protein interactions. It was used for ranking all known genes present in the cattle genome for their potential roles in bovine mastitis. Gene-associated phenome profile and transcriptome profile in response to 
Escherichia coli infection in the mammary gland were integrated to make a global inference of bovine genes involved in mastitis. The top ranked genes were highly enriched for pathways and biological processes underlying inflammation and immune responses, which supports the validity of our approach for identifying genes that are relevant to animal health and disease. These gene-associated phenotypes were used for a local prioritization of candidate genes located in a QTL affecting the susceptibility to mastitis. Our study provides a general framework for prioritizing genes associated with various complex traits in different species. To our knowledge this is the first time that gene expression, ortholog mapping, protein interactions, and biomedical text data have been integrated systematically for ranking candidate genes in any livestock species.",
	author = "Jiang, Li and {S{\o}rensen}, Peter and Thomsen, Bo and Edwards, Stefan McKinnon and Skarman, Axel and {R{\o}ntved}, Christine M. and Lund, Mogens Sand{\o} and Workman, Christopher T.",
	doi = "10.1152/physiolgenomics.00047.2011",
	file = "::",
	issn = "1531-2267",
	journal = "Physiological genomics",
	month = mar,
	number = "5",
	pages = "305--17",
	pmid = "22234994",
	title = "{Gene prioritization for livestock diseases by data integration.}",
	url = "http://physiolgenomics.physiology.org/cgi/content/abstract/44/5/305",
	volume = "44",
	year = "2012"
}



@article{Kanamori2004,
	abstract = "Here we describe the development of a genome-wide and nonredundant mouse transcription factor database and its viewer (http://genome.gsc.riken.gp/TFdb/). We systematically selected transcription factors with DNA-binding properties and their regulators on the basis of their LocusLink and Gene Ontology annotations. We also incorporated into our database information regarding the corresponding available cDNA clones and their structural properties. Because of these features, our database is unique and may provide useful information for systematic genome-wide studies of transcriptional regulation.",
	author = "Kanamori, Mutsumi and Konno, Hideaki and Osato, Naoki and Kawai, Jun and Hayashizaki, Yoshihide and Suzuki, Harukazu",
	doi = "10.1016/j.bbrc.2004.07.179",
	issn = "0006-291X",
	journal = "Biochemical and biophysical research communications",
	keywords = "Animals; DNA-Binding Proteins; DNA-Binding Proteins: genetics; Databases; Nucleic Acid; Gene Expression Regulation; Gene Expression Regulation: genetics; Mice; Mice: genetics; TF; Transcription Factors; Transcription Factors: genetics; Transcription; Genetic; Transcription; Genetic: genetics",
	mendeley-tags = "TF",
	month = sep,
	number = "3",
	pages = "787--93",
	pmid = "15336533",
	title = "{A genome-wide and nonredundant mouse transcription factor database.}",
	url = "http://dx.doi.org/10.1016/j.bbrc.2004.07.179",
	volume = "322",
	year = "2004"
}

@article{Kanehisa1997,
	author = "Kanehisa, M",
	doi = "10.1016/S0168-9525(97)01223-7",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Kanehisa - 1997 - A database for post-genome analysis.pdf:pdf",
	journal = "Trends in Genetics",
	keywords = "KEGG",
	mendeley-tags = "KEGG",
	number = "9",
	pages = "375--376",
	title = "{A database for post-genome analysis}",
	volume = "13",
	year = "1997"
}

@article{Kanehisa1996,
	author = "Kanehisa, M",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Kanehisa - 1996 - Toward pathway engineering a new database of genetic and molecular pathways.pdf:pdf",
	journal = "Science \& Technology Japan",
	keywords = "KEGG",
	mendeley-tags = "KEGG",
	pages = "34--38",
	title = "{Toward pathway engineering: a new database of genetic and molecular pathways}",
	url = "http://www.genome.jp/kegg/docs/stj.pdf",
	volume = "59",
	year = "1996"
}

@article{Kanehisa2008,
	abstract = "KEGG (http://www.genome.jp/kegg/) is a database of biological systems that integrates genomic, chemical and systemic functional information. KEGG provides a reference knowledge base for linking genomes to life through the process of PATHWAY mapping, which is to map, for example, a genomic or transcriptomic content of genes to KEGG reference pathways to infer systemic behaviors of the cell or the organism. In addition, KEGG provides a reference knowledge base for linking genomes to the environment, such as for the analysis of drug-target relationships, through the process of BRITE mapping. KEGG BRITE is an ontology database representing functional hierarchies of various biological objects, including molecules, cells, organisms, diseases and drugs, as well as relationships among them. KEGG PATHWAY is now supplemented with a new global map of metabolic pathways, which is essentially a combined map of about 120 existing pathway maps. In addition, smaller pathway modules are defined and stored in 
KEGG MODULE that also contains other functional units and complexes. The KEGG resource is being expanded to suit the needs for practical applications. KEGG DRUG contains all approved drugs in the US and Japan, and KEGG DISEASE is a new database linking disease genes, pathways, drugs and diagnostic markers.",
	author = "Kanehisa, Minoru and Araki, Michihiro and Goto, Susumu and Hattori, Masahiro and Hirakawa, Mika and Itoh, Masumi and Katayama, Toshiaki and Kawashima, Shuichi and Okuda, Shujiro and Tokimatsu, Toshiaki and Yamanishi, Yoshihiro",
	doi = "10.1093/nar",
	issn = "1362-4962",
	journal = "Nucleic Acids Res.",
	keywords = "Databases- Factual; Disease; Genomics; Humans; Internet; Metabolic Networks and Pathways; Molecular Structure; Pharmaceutical Preparations; Systems Biology; Systems Integration; User-Computer Interface",
	mendeley-tags = "Databases- Factual,Disease,Genomics,Humans,Internet,Metabolic Networks and Pathways,Molecular Structure,Pharmaceutical Preparations,Systems Biology,Systems Integration,User-Computer Interface",
	month = jan,
	number = "Database issue",
	pages = "D480--484",
	title = "{KEGG for linking genomes to life and the environment}",
	url = "http://www.ncbi.nlm.nih.gov/pubmed/18077471",
	volume = "36",
	year = "2008"
}

@article{Kanehisa2000,
	abstract = "KEGG (Kyoto Encyclopedia of Genes and Genomes) is a knowledge base for systematic analysis of gene functions, linking genomic information with higher order functional information. The genomic information is stored in the GENES database, which is a collection of gene catalogs for all the completely sequenced genomes and some partial genomes with up-to-date annotation of gene functions. The higher order functional information is stored in the PATHWAY database, which contains graphical representations of cellular processes, such as metabolism, membrane transport, signal transduction and cell cycle. The PATHWAY database is supplemented by a set of ortholog group tables for the information about conserved subpathways (pathway motifs), which are often encoded by positionally coupled genes on the chromosome and which are especially useful in predicting gene functions. A third database in KEGG is LIGAND for the information about chemical compounds, enzyme molecules and enzymatic reactions. KEGG provides 
Java graphics tools for browsing genome maps, comparing two genome maps and manipulating expression maps, as well as computational tools for sequence comparison, graph comparison and path computation. The KEGG databases are daily updated and made freely available (http://www.genome.ad.jp/kegg/ )",
	author = "Kanehisa, Minoru and Goto, Susumu",
	doi = "10.1093/nar",
	journal = "Nucleic Acids Research",
	keywords = "KEGG",
	mendeley-tags = "KEGG",
	number = "1",
	pages = "27--30",
	title = "{KEGG: Kyoto Encyclopedia of Genes and Genomes}",
	url = "http://nar.oxfordjournals.org/content/28/1/27.abstract",
	volume = "28",
	year = "2000"
}

@article{Kanehisa2006,
	abstract = "The increasing amount of genomic and molecular information is the basis for understanding higher-order biological systems, such as the cell and the organism, and their interactions with the environment, as well as for medical, industrial and other practical applications. The KEGG resource (http://www.genome.jp/kegg/) provides a reference knowledge base for linking genomes to biological systems, categorized as building blocks in the genomic space (KEGG GENES) and the chemical space (KEGG LIGAND), and wiring diagrams of interaction networks and reaction networks (KEGG PATHWAY). A fourth component, KEGG BRITE, has been formally added to the KEGG suite of databases. This reflects our attempt to computerize functional interpretations as part of the pathway reconstruction process based on the hierarchically structured knowledge about the genomic, chemical and network spaces. In accordance with the new chemical genomics initiatives, the scope of KEGG LIGAND has been significantly expanded to cover both 
endogenous and exogenous molecules. Specifically, RPAIR contains curated chemical structure transformation patterns extracted from known enzymatic reactions, which would enable analysis of genome-environment interactions, such as the prediction of new reactions and new enzyme genes that would degrade new environmental compounds. Additionally, drug information is now stored separately and linked to new KEGG DRUG structure maps",
	author = "Kanehisa, Minoru and Goto, Susumu and Hattori, Masahiro and Aoki-Kinoshita, Kiyoko F. and Itoh, Masumi and Kawashima, Shuichi and Katayama, Toshiaki and Araki, Michihiro and Hirakawa, Mika",
	doi = "10.1093/nar",
	issn = "1362-4962",
	journal = "Nucleic Acids Research",
	keywords = "Biotransformation; Chemical Phenomena; Chemistry; Databases- Factual; Databases- Genetic; Environment; Enzymes; Genomics; Humans; Internet; KEGG; Ligands; Pharmaceutical Preparations; Signal Transduction; Systems Integration; User-Computer Interface",
	mendeley-tags = "Biotransformation,Chemical Phenomena,Chemistry,Databases- Factual,Databases- Genetic,Environment,Enzymes,Genomics,Humans,Internet,KEGG,Ligands,Pharmaceutical Preparations,Signal Transduction,Systems Integration,User-Computer Interface",
	month = jan,
	number = "Database issue",
	pages = "D354--D357",
	shorttitle = "From genomics to chemical genomics",
	title = "{From genomics to chemical genomics: new developments in KEGG}",
	url = "http://nar.oxfordjournals.org/content/34/suppl\_1/D354.abstract; http://www.ncbi.nlm.nih.gov/pubmed/16381885",
	volume = "34",
	year = "2006"
}

@article{Kanehisa2002,
	abstract = "The Kyoto Encyclopedia of Genes and Genomes (KEGG) is the primary database resource of the Japanese GenomeNet service (http://www.genome.ad.jp/) for understanding higher order functional meanings and utilities of the cell or the organism from its genome information. KEGG consists of the PATHWAY database for the computerized knowledge on molecular interaction networks such as pathways and complexes, the GENES database for the information about genes and proteins generated by genome sequencing projects, and the LIGAND database for the information about chemical compounds and chemical reactions that are relevant to cellular processes. In addition to these three main databases, limited amounts of experimental data for microarray gene expression profiles and yeast two-hybrid systems are stored in the EXPRESSION and BRITE databases, respectively. Furthermore, a new database, named SSDB, is available for exploring the universe of all protein coding genes in the complete genomes and for identifying 
functional links and ortholog groups. The data objects in the KEGG databases are all represented as graphs and various computational methods are developed to detect graph features that can be related to biological functions. For example, the correlated clusters are graph similarities which can be used to predict a set of genes coding for a pathway or a complex, as summarized in the ortholog group tables, and the cliques in the SSDB graph are used to annotate genes. The KEGG databases are updated daily and made freely available (http://www.genome.ad.jp/kegg/).",
	author = "Kanehisa, Minoru and Goto, Susumu and Kawashima, Shuichi and Nakaya, Akihiro",
	issn = "1362-4962",
	journal = "Nucleic Acids Research",
	keywords = "Animals; Computational Biology; Computer Graphics; Databases- Genetic; Databases- Protein; Gene Expression Profiling; Genome; Humans; Information Storage and Retrieval; Internet; Japan; Macromolecular Substances; Metabolism; Multigene Family; Protein Conformation; Proteins; Sequence Homology",
	month = jan,
	number = "1",
	pages = "42--46",
	title = "{The KEGG databases at GenomeNet}",
	url = "http://www.ncbi.nlm.nih.gov/pubmed/11752249",
	volume = "30",
	year = "2002"
}

@article{Kanehisa2012,
	abstract = "Kyoto Encyclopedia of Genes and Genomes (KEGG, http://www.genome.jp/kegg/ or http://www.kegg.jp/) is a database resource that integrates genomic, chemical and systemic functional information. In particular, gene catalogs from completely sequenced genomes are linked to higher-level systemic functions of the cell, the organism and the ecosystem. Major efforts have been undertaken to manually create a knowledge base for such systemic functions by capturing and organizing experimental knowledge in computable forms; namely, in the forms of KEGG pathway maps, BRITE functional hierarchies and KEGG modules. Continuous efforts have also been made to develop and improve the cross-species annotation procedure for linking genomes to the molecular networks through the KEGG Orthology system. Here we report KEGG Mapper, a collection of tools for KEGG PATHWAY, BRITE and MODULE mapping, enabling integration and interpretation of large-scale data sets. We also report a variant of the KEGG mapping procedure to 
extend the knowledge base, where different types of data and knowledge, such as disease genes and drug targets, are integrated as part of the KEGG molecular networks. Finally, we describe recent enhancements to the KEGG content, especially the incorporation of disease and drug information used in practice and in society, to support translational bioinformatics.",
	author = "Kanehisa, Minoru and Goto, Susumu and Sato, Yoko and Furumichi, Miho and Tanabe, Mao",
	doi = "10.1093/nar",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Kanehisa et al. - 2012 - KEGG for integration and interpretation of large-scale molecular data sets.pdf:pdf",
	issn = "1362-4962",
	journal = "Nucleic Acids Research",
	keywords = "Computational Biology; Databases; Disease; Factual; Genomics; Humans; KEGG; Knowledge Bases; Molecular Sequence Annotation; Pharmacological Phenomena; Software; Systems Integration",
	mendeley-tags = "KEGG",
	month = jan,
	number = "Database issue",
	pages = "D109--14",
	pmid = "22080510",
	title = "{KEGG for integration and interpretation of large-scale molecular data sets.}",
	url = "http://nar.oxfordjournals.org/content/40/D1/D109.long",
	volume = "40",
	year = "2012"
}

@article{Kemper2012,
	abstract = "Much of the heritability for human stature is caused by mutations of small-to-medium effect. This is because detrimental pleiotropy restricts large-effect mutations to very low frequency.",
	author = "Kemper, Kathryn E. and Visscher, Peter M. and Goddard, Michael E.",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Kemper, Visscher, Goddard - 2012 - Genetic architecture of body size in mammals.pdf:pdf",
	journal = "Genome Biol.",
	keywords = "Human height; Recommended by Peter; mutation-selection balance; mutations effects",
	mendeley-tags = "Recommended by Peter",
	number = "4",
	pages = "244",
	title = "{Genetic architecture of body size in mammals}",
	url = "http://genomebiology.com/2012/13/4/244; http://w14.biomedcentral.com/content/pdf/gb-2012-13-4-244.pdf",
	volume = "13",
	year = "2012"
}

@misc{quantreg,
	abstract = "R package version 4.81",
	author = "Koenker, Roger",
	keywords = "R-package",
	mendeley-tags = "R-package",
	title = "{quantreg: Quantile Regression}",
	url = "http://cran.r-project.org/package=quantreg",
	year = "2012"
}

@article{Koenker1978,
	abstract = {A simple minimization problem yielding the ordinary sample quantiles in the location model is shown to generalize naturally to the linear model generating a new class of statistics we term "regression quantiles." The estimator which minimizes the sum of absolute residuals is an important special case. Some equivariance properties and the joint asymptotic distribution of regression quantiles are established. These results permit a natural generalization to the linear model of certain well-known robust estimators of location. Estimators are suggested, which have comparable efficiency to least squares for Gaussian linear models while substantially out-performing the least-squares estimator over a wide class of non-Gaussian error distributions.},
	author = "Koenker, Roger and Basset, Gilbert",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Koenker, Basset - 1978 - Regression Quantiles.pdf:pdf",
	journal = "Econometrica",
	keywords = "Regression Quantiles",
	number = "1",
	pages = "33--50",
	title = "{Regression Quantiles}",
	url = "http://www.jstor.org/stable/1913643",
	volume = "46",
	year = "1978"
}

@article{Koenker1994,
	author = "Koenker, Roger and Ng, Pin and Portnoy, Stephen",
	doi = "10.2307/2337070",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Koenker, Ng, Portnoy - 1994 - Quantile Smoothing Splines.pdf:pdf",
	issn = "00063444",
	journal = "Biometrika",
	keywords = "Regression Quantiles",
	month = dec,
	number = "4",
	pages = "673",
	title = "{Quantile Smoothing Splines}",
	url = "http://www.jstor.org/stable/2337070?origin=crossref",
	volume = "81",
	year = "1994"
}

@article{Ku2010,
	author = "Ku, Chee Seng and Loy, En Yun and Pawitan, Yudi and Chia, Kee Seng",
	doi = "10.1038/jhg.2010.19",
	issn = "1434-5161, 1435-232X",
	journal = "Journal of Human Genetics",
	month = mar,
	pages = "195--206",
	shorttitle = "The pursuit of genome-wide association studies",
	title = "{The pursuit of genome-wide association studies: where are we now?}",
	url = "http://www.nature.com/doifinder/10.1038/jhg.2010.19",
	volume = "55",
	year = "2010"
}


@article{Lee2006,
	author = "Lee, Sang Hong and van der Werf, Julius H.J.",
	doi = "10.1051/gse\AE2005025",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Lee, Werf - 2006 - An efficient variance component approach implementing an average information REML suitable for combined LD and linkage mapping with a general complex pedigree.pdf:pdf",
	journal = "Genet Sel Evol",
	pages = "25--43",
	title = "{An efficient variance component approach implementing an average information REML suitable for combined LD and linkage mapping with a general complex pedigree}",
	volume = "38",
	year = "2006"
}



@article{Lehne2009,
	abstract = "Over the past few years, the number of known protein-protein interactions has increased substantially. To make this information more readily available, a number of publicly available databases have set out to collect and store protein-protein interaction data. Protein-protein interactions have been retrieved from six major databases, integrated and the results compared. The six databases (the Biological General Repository for Interaction Datasets [BioGRID], the Molecular INTeraction database [MINT], the Biomolecular Interaction Network Database [BIND], the Database of Interacting Proteins [DIP], the IntAct molecular interaction database [IntAct] and the Human Protein Reference Database [HPRD]) differ in scope and content; integration of all datasets is non-trivial owing to differences in data annotation. With respect to human protein-protein interaction data, HPRD seems to be the most comprehensive. To obtain a complete dataset, however, interactions from all six databases have to be combined. 
To overcome this limitation, meta-databases such as the Agile Protein Interaction Database (APID) offer access to integrated protein-protein interaction datasets, although these also currently have certain restrictions.",
	author = "Lehne, Benjamin and Schlitt, Thomas",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Lehne, Schlitt - 2009 - Protein-protein interaction databases keeping up with growing interactomes.pdf:pdf",
	issn = "1479-7364",
	journal = "Human genomics",
	keywords = "Animals; Databases; Humans; Protein; Protein Interaction Mapping; STRING; Software",
	mendeley-tags = "STRING",
	month = apr,
	number = "3",
	pages = "291--7",
	pmid = "19403463",
	title = "{Protein-protein interaction databases: keeping up with growing interactomes.}",
	url = "http://www.ncbi.nlm.nih.gov/pubmed/19403463",
	volume = "3",
	year = "2009"
}

@inproceedings{LidauerStranden1999,
	address = "Tuusula, Finland",
	author = "Lidauer, M. and Strand{\'e}n, Ismo",
	booktitle = "International workshop on high performance computing and new statistical methods in dairy cattle breeding",
	pages = "20--25",
	publisher = "INTERBULL Bulletin, No. 20",
	title = "{Fast and flexible program for genetic evaluation in dairy cattle.}",
	year = "1999"
}

@article{Lippert2011,
	abstract = "We describe factored spectrally transformed linear mixed models (FaST-LMM), an algorithm for genome-wide association studies (GWAS) that scales linearly with cohort size in both run time and memory use. On Wellcome Trust data for 15,000 individuals, FaST-LMM ran an order of magnitude faster than current efficient algorithms. Our algorithm can analyze data for 120,000 individuals in just a few hours, whereas current algorithms fail on data for even 20,000 individuals (http://mscompbio.codeplex.com/).",
	author = "Lippert, Christoph and Listgarten, Jennifer and Liu, Ying and Kadie, Carl M and Davidson, Robert I and Heckerman, David",
	doi = "10.1038/nmeth.1681",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Lippert et al. - 2011 - FaST linear mixed models for genome-wide association studies.pdf:pdf",
	issn = "1548-7105",
	journal = "Nature methods",
	keywords = "Algorithms; Computer Simulation; Genetic; Genome-Wide Association Study; Models; Software",
	month = jan,
	number = "10",
	pages = "833--5",
	pmid = "21892150",
	title = "{FaST linear mixed models for genome-wide association studies.}",
	url = "http://www.ncbi.nlm.nih.gov/pubmed/21892150",
	volume = "8",
	year = "2011"
}

@article{Lund2011,
	abstract = "Size of the reference population and reliability of phenotypes are crucial factors influencing the reliability of genomic predictions. It is therefore useful to combine closely related populations. Increased accuracies of genomic predictions depend on the number of individuals added to the reference population, the reliability of their phenotypes, and the relatedness of the populations that are combined.",
	author = "Lund, Mogens Sand{\o} and de Roos, Adrianus P W and de Vries, Alfred G and Druet, Tom and Ducrocq, Vincent and Fritz, S{\'e}bastien and Guillaume, Fran\c{c}ois and Guldbrandtsen, Bernt and Liu, Zenting and Reents, Reinhard and Schrooten, Chris and Seefried, Franz and Su, Guosheng",
	doi = "10.1186/1297-9686-43-43",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Lund et al. - 2011 - A common reference population from four European Holstein populations increases reliability of genomic predictions.pdf:pdf",
	issn = "1297-9686",
	journal = "Genet. Sel. Evol.",
	month = jan,
	number = "1",
	pages = "43",
	pmid = "22152008",
	title = "{A common reference population from four European Holstein populations increases reliability of genomic predictions.}",
	url = "http://www.gsejournal.org/content/43/1/43",
	volume = "43",
	year = "2011"
}

@book{LynchWalsh1998,
	address = "Sunderland, USA",
	author = "Lynch, Michael and Walsh, Bruce",
	isbn = "0-87893-481-2",
	publisher = "Sinauer Associates, Inc.",
	title = "{Genetics and Analysis of Quantitative Traits}",
	year = "1998"
}

@misc{DMU5.1,
	address = "Tjele, Denmark",
	author = "Madsen, Per and Jensen, Just",
	pages = "32",
	title = "{A User's Guide to DMU. A Package for Analysing Multivariate Mixed Models. Version 6, release 5.1}",
	url = "http://dmu.agrsci.dk/dmuv6\_guide.5.1.pdf",
	year = "2012"
}



@article{Meuwissen2009,
	author = "Meuwissen, Theo H. E.",
	doi = "10.1186/1297-9686-41-35",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Meuwissen - 2009 - Accuracy of breeding values of'unrelated'individuals predicted by dense SNP genotyping.pdf:pdf",
	issn = "1297-9686",
	journal = "Genet Sel Evol",
	keywords = "BayesB; G-BLUP; MIXTURE; SNP genotyping; Scaling markers; Statistical model",
	mendeley-tags = "BayesB,G-BLUP,MIXTURE,SNP genotyping,Scaling markers,Statistical model",
	number = "1",
	pages = "35",
	title = "{Accuracy of breeding values of 'unrelated' individuals predicted by dense SNP genotyping}",
	url = "http://www.gsejournal.org/content/41/1/35; http://www.biomedcentral.com/content/pdf/1297-9686-41-35.pdf",
	volume = "41",
	year = "2009"
}

@article{Meuwissen2001,
	abstract = "Recent advances in molecular genetic techniques will make dense marker maps available and genotyping many individuals for these markers feasible. Here we attempted to estimate the effects of [\~{}]50,000 marker haplotypes simultaneously from a limited number of phenotypic records. A genome of 1000 cM was simulated with a marker spacing of 1 cM. The markers surrounding every 1-cM region were combined into marker haplotypes. Due to finite population size (Ne = 100), the marker haplotypes were in linkage disequilibrium with the QTL located between the markers. Using least squares, all haplotype effects could not be estimated simultaneously. When only the biggest effects were included, they were overestimated and the accuracy of predicting genetic values of the offspring of the recorded animals was only 0.32. Best linear unbiased prediction of haplotype effects assumed equal variances associated to each 1-cM chromosomal segment, which yielded an accuracy of 0.73, although this assumption was far 
from true. Bayesian methods that assumed a prior distribution of the variance associated with each chromosome segment increased this accuracy to 0.85, even when the prior was not correct. It was concluded that selection on genetic values predicted from markers could substantially increase the rate of genetic gain in animals and plants, especially if combined with reproductive techniques to shorten the generation interval",
	author = "Meuwissen, Theo H. E. and Hayes, B. J. and Goddard, Michael E.",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Meuwissen, Hayes, Goddard - 2001 - Prediction of total genetic value using genome-wide dense marker maps.pdf:pdf",
	journal = "Genetics",
	month = apr,
	number = "4",
	pages = "1819--1829",
	title = "{Prediction of total genetic value using genome-wide dense marker maps}",
	url = "http://www.genetics.org/cgi/content/abstract/157/4/1819; http://www.genetics.org/content/157/4/1819.short",
	volume = "157",
	year = "2001"
}

@article{Newton2007,
	author = "Newton, Michael A. and Quintana, Fernando A. and den Boon, Johan A. and Sengupta, Srikumar and Ahlquist, Paul",
	doi = "10.1214/07-AOAS104",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Newton et al. - 2007 - Random-set methods identify distinct aspects of the enrichment signal in gene-set analysis.pdf:pdf",
	issn = "1932-6157",
	journal = "Ann. Appl. Stat.",
	month = jun,
	number = "1",
	pages = "85--106",
	title = "{Random-set methods identify distinct aspects of the enrichment signal in gene-set analysis}",
	url = "http://projecteuclid.org/euclid.aoas/1183143730",
	volume = "1",
	year = "2007"
}

@incollection{mmtx2007,
	annote = "10.1007/978-1-59745-547-3\_9",
	author = "Osborne, John D and Lin, Simon and Zhu, Lihua Julie and Kibbe, Warren A",
	booktitle = "{Gene Function Analysis}",
	editor = "Ochs, Michael F and Walker, John M",
	isbn = "978-1-59745-547-3",
	pages = "153--169",
	publisher = "Humana Press",
	series = "{Methods in Molecular Biology}",
	title = "{Mining Biomedical Data Using MetaMap Transfer (MMTx) and the Unified Medical Language System (UMLS)}",
	url = "http://dx.doi.org/10.1007/978-1-59745-547-3\_9",
	volume = "408",
	year = "2007"
}

@article{Reml1971,
	abstract = "A method is proposed for estimating intra-block and inter-blook weights in the analysis of incomplete block designs with block sizes not necessarily equal. The method consists of maximizing the likelihood, not of all the data, but of a set of selected error contrasts. When block sizes are equal results are identical with those obtained by the method of Nelder (1968) for generally balanced designs. Although mainly concerned with incomplete block designs the paper also gives in outline an extension of the modified maximum likelihood procedure to designs with a more complicated block structure.",
	author = "Patterson, H.D. and Thompson, R.",
	doi = "10.1093/biomet",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Patterson, Thompson - 1971 - Recovery of inter-block information when block sizes are unequal.pdf:pdf",
	issn = "0006-3444",
	journal = "Biometrika",
	keywords = "REML",
	mendeley-tags = "REML",
	month = dec,
	number = "3",
	pages = "545--554",
	title = "{Recovery of inter-block information when block sizes are unequal}",
	url = "http://biomet.oxfordjournals.org/cgi/content/abstract/58/3/545",
	volume = "58",
	year = "1971"
}


@misc{PersNote,
address = {Tjele, Denmark},
author = {Jensen, Just and Madsen, Per},
keywords = {DMU},
pages = {6},
publisher = {Danish Institute of Agricultural Sciences},
title = {{Calculation of Standard Errors of estimates of genetic and phenotypic parameters in DMU}},
year = {2005}
}


@article{Pomp2008,
	abstract = "Traits related to energy balance and obesity are exceptionally complex, with varying contributions of genetic susceptibility and interacting environmental factors. The use of mouse models has been a powerful driving force in understanding the genetic architecture of polygenic traits such as obesity. However, the use of mouse models for analysis of complex traits is at an important crossroad. Genome-wide association studies in humans are now leading to direct identification of obesity genes. In this review, we focus on three areas representing the current and future roles of mouse models regarding genetics of complex obesity. First, we summarize increasingly powerful ways to harness the strength of mouse models for discovery of genes affecting polygenic obesity. Second, we examine the status of using a systems biology approach to dissect the genetic architecture of obesity. And third, we explore the effects of recent findings indicating increasing levels of complexity in the nature of variation 
underlying, and the heritability of, complex traits such as obesity.",
	author = "Pomp, Daniel and Nehrenberg, Derrick and Estrada-Smith, Daria",
	doi = "10.1146/annurev.nutr.27.061406.093552",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Pomp, Nehrenberg, Estrada-Smith - 2008 - Complex genetics of obesity in mouse models.pdf:pdf",
	issn = "0199-9885",
	journal = "Annual review of nutrition",
	keywords = "Animals; Animals; Genetically Modified; Disease Models; Animal; Energy Metabolism; Energy Metabolism: genetics; Genetic Variation; Humans; Mice; Models; Genetic; Multigene Family; Multigene Family: genetics; Obesity; Obesity: genetics; Peters intro refs; Quantitative Trait Loci; Quantitative Trait; Heritable",
	language = "en",
	mendeley-tags = "Peters intro refs",
	month = jan,
	pages = "331--45",
	pmid = "18435591",
	publisher = "Annual Reviews",
	title = "{Complex genetics of obesity in mouse models.}",
	url = "http://www.annualreviews.org/doi/abs/10.1146/annurev.nutr.27.061406.093552",
	volume = "28",
	year = "2008"
}

@article{Portnoy1997,
	abstract = "Since the time of Gauss, it has been generally accepted that \$\backslash ell\_2\$-methods of combining observations by minimizing sums of squared errors have significant computational advantages over earlier \$\backslash ell\_1\$-methods based on minimization of absolute errors advocated by Boscovich, Laplace and others. However, \$\backslash ell\_1\$-methods are known to have significant robustness advantages over \$\backslash ell\_2\$-methods in many applications, and related quantile regression methods provide a useful, complementary approach to classical least-squares estimation of statistical models. Combining recent advances in interior point methods for solving linear programs with a new statistical preprocessing approach for \$\backslash ell\_1\$-type problems, we obtain a 10- to 100-fold improvement in computational speeds over current (simplex-based) \$\backslash ell\_1\$-algorithms in large problems, demonstrating that \$\backslash ell\_1\$-methods can be made competitive with \$\
backslash ell\_2\$-methods in terms of computational speed throughout the entire range of problem sizes. Formal complexity results suggest that \$\backslash ell\_1\$-regression can be made faster than least-squares regression for \$n\$ sufficiently large and \$p\$ modest.",
	author = "Portnoy, Stephen and Koenker, Roger",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Portnoy, Koenker - 1997 - The Gaussian Hare and the Laplacian Tortoise Computability of Squared- Error versus Absolute-Error Estimators.pdf:pdf",
	issn = "0883-4237",
	journal = "Statistical Science",
	keywords = "and phrases; gression quantiles; interior",
	month = nov,
	number = "4",
	pages = "279--296",
	shorttitle = "The Gaussian Hare and the Laplacian Tortoise",
	title = "{The Gaussian Hare and the Laplacian Tortoise: Computability of Squared- Error versus Absolute-Error Estimators}",
	url = "http://www.jstor.org/stable/2246216; http://www.jstor.org/stable/pdfplus/2246216.pdf?acceptTC=true",
	volume = "12",
	year = "1997"
}


@article{Schaeffer2006,
	abstract = "Animals can be genotyped for thousands of single nucleotide polymorphisms (SNPs) at one time, where the SNPs are located at roughly 1-cM intervals throughout the genome. For each contiguous pair of SNPs there are four possible haplotypes that could be inherited from the sire. The effects of each interval on a trait can be estimated for all intervals simultaneously in a model where interval effects are random factors. Given the estimated effects of each haplotype for every interval in the genome, and given an animal's genotype, a 'genomic' estimated breeding value is obtained by summing the estimated effects for that genotype. The accuracy of that estimator of breeding values is around 80\%. Because the genomic estimated breeding values can be calculated at birth, and because it has a high accuracy, a strategy that utilizes these advantages was compared with a traditional progeny testing strategy under a typical Canadian-like dairy cattle situation. Costs of proving bulls were reduced by 92\% and 
genetic change was increased by a factor of 2. Genome-wide selection may become a popular tool for genetic improvement in livestock.",
	author = "Schaeffer, L R",
	doi = "10.1111/j.1439-0388.2006.00595.x",
	file = ":home/stefan/PhD/Articles/Schaeffer (2006).pdf:pdf",
	institution = "Department of Animal and Poultry Science, Centre for Genetic Improvement of Livestock, University of Guelph, Guelph, ON, Canada. lrs@uoguelph.ca",
	issn = "0931-2668",
	journal = "Journal of Animal Breeding and Genetics",
	keywords = "Breeding: economics; Breeding: methods; Cattle: genetics; Dairying: methods; Genome: genetics; animals; breeding; breeding economics; breeding methods; cattle; cattle genetics; dairying; dairying methods; female; genetic; genetic markers; genome; genome genetics; haplotypes; male; models; selection",
	month = aug,
	number = "4",
	pages = "218--23",
	pmid = "16882088",
	publisher = "Wiley Online Library",
	title = "{Strategy for applying genome-wide selection in dairy cattle}",
	url = "http://www.ncbi.nlm.nih.gov/pubmed/16882088",
	volume = "123",
	year = "2006"
}

@article{Schukken2011,
abstract = {Many different bacterial species have the ability to cause an infection of the bovine mammary gland and the host response to these infections is what we recognize as mastitis. In this review we evaluate the pathogen specific response to the three main bacterial species causing bovine mastitis: Escherichia coli, Streptococcus uberis and Staphylococcus aureus. In this paper we will review the bacterial growth patterns, host immune response and clinical response that results from the intramammary infections. Clear differences in bacterial growth pattern are shown between bacterial species. The dominant pattern in E. coli infections is a short duration high bacteria count infection, in S. aureus this is more commonly a persistent infection with relative low bacteria counts and in S. uberis a long duration high bacteria count infection is often observed. The host immune response differs significantly depending on the invading bacterial species. The underlying reasons for the differences and the resulting host response are described. Finally we discuss the clinical response pattern for each of the three bacterial species. The largest contrast is between E. coli and S. aureus where a larger proportion of E. coli infections cause potentially severe clinical symptoms, whereas the majority of S. aureus infections go clinically unnoticed. The relevance of fully understanding the bovine host response to intramammary infection is discussed, some major gaps in our knowledge are highlighted and directions for future research are indicated.},
author = {Schukken, Ynte H and G\"{u}nther, J and Fitzpatrick, J and Fontaine, M C and Goetze, L and Holst, O and Leigh, J and Petzl, W and Schuberth, H-J and Sipka, A and Smith, D G E and Quesnell, R and Watts, J and Yancey, R and Zerbe, H and Gurjar, A and Zadoks, R N and Seyfert, H-M},
doi = {10.1016/j.vetimm.2011.08.022},
file = {:C$\backslash$:/Users/STME/Documents/Artikler/Schukken et al (2011).pdf:pdf},
issn = {1873-2534},
journal = {Vet. Immunol. Immunop.},
keywords = {Adaptive Immunity,Adaptive Immunity: immunology,Animal,Animal: immunology,Animal: microbiology,Animals,Bo's reference.,Bovine,Bovine: immunology,Bovine: microbiology,Cattle,Cellular,Cellular: immunology,Cytokines,Cytokines: immunology,Escherichia coli,Escherichia coli Infections,Escherichia coli Infections: immunology,Escherichia coli Infections: microbiology,Escherichia coli Infections: veterinary,Escherichia coli: immunology,Female,Immunity,Innate,Innate: immunology,Lactation,Lactation: immunology,Mammary Glands,Mastitis,Staphylococcal Infections,Staphylococcal Infections: immunology,Staphylococcal Infections: microbiology,Staphylococcal Infections: veterinary,Staphylococcus aureus,Staphylococcus aureus: immunology,Streptococcal Infections,Streptococcal Infections: immunology,Streptococcal Infections: microbiology,Streptococcal Infections: veterinary,Streptococcus,Streptococcus: immunology,Toll-Like Receptors,Toll-Like Receptors: immunology},
mendeley-tags = {Bo's reference.},
month = dec,
number = {3-4},
pages = {270--89},
pmid = {21955443},
publisher = {Elsevier B.V.},
title = {{Host-response patterns of intramammary infections in dairy cows.}},
url = {http://dx.doi.org/10.1016/j.vetimm.2011.08.022},
volume = {144},
year = {2011}
}

@article{Silver2012,
	abstract = {Where causal SNPs (single nucleotide polymorphisms) tend to accumulate within biological pathways, the incorporation of prior pathways information into a statistical model is expected to increase the power to detect true associations in a genetic association study. Most existing pathways-based methods rely on marginal SNP statistics and do not fully exploit the dependence patterns among SNPs within pathways.We use a sparse regression model, with SNPs grouped into pathways, to identify causal pathways associated with a quantitative trait. Notable features of our "pathways group lasso with adaptive weights" (P-GLAW) algorithm include the incorporation of all pathways in a single regression model, an adaptive pathway weighting procedure that accounts for factors biasing pathway selection, and the use of a bootstrap sampling procedure for the ranking of important pathways. P-GLAW takes account of the presence of overlapping pathways and uses a novel combination of techniques to optimise model 
estimation, making it fast to run, even on whole genome datasets.In a comparison study with an alternative pathways method based on univariate SNP statistics, our method demonstrates high sensitivity and specificity for the detection of important pathways, showing the greatest relative gains in performance where marginal SNP effect sizes are small.},
	author = "Silver, Matt and Montana, Giovanni",
	doi = "10.2202/1544-6115.1755",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Silver, Montana - 2012 - Fast identification of biological pathways associated with a quantitative trait using group lasso with overlaps.pdf:pdf",
	issn = "1544-6115",
	journal = "Stat. Appl. Genet. Molec. Biol.",
	keywords = "Alzheimer Disease; Alzheimer Disease: genetics; Genetic; Humans; Models; Polymorphism; Quantitative Trait Loci; Recommended by Peter; Regression Analysis; Single Nucleotide",
	mendeley-tags = "Recommended by Peter",
	month = jan,
	number = "1",
	pages = "Article 7",
	pmid = "22499682",
	title = "{Fast identification of biological pathways associated with a quantitative trait using group lasso with overlaps.}",
	url = "http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3491888&tool=pmcentrez&rendertype=abstract",
	volume = "11",
	year = "2012"
}

@unpublished{Axel2011progress,
	address = "Tjele, Denmark",
	author = "Skarman, Axel and Jiang, Li and Madsen, Per and {S{\o}rensen}, Peter",
	institution = "Department of Molecular Biology and Genetics, Aarhus University",
	title = "{Genome partitioning of udder health trait in dairy cattle}",
	year = "2011"
}

@misc{Sorensen2012Note,
	author = "Sorensen, Daniel",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Sorensen - 2012 - Note A genomic model.pdf:pdf",
	pages = "1--2",
	title = "{Note: A genomic model}",
	year = "2012"
}

@techreport{Sorensen1996,
	address = "Tjele, Denmark",
	author = "Sorensen, Daniel",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Sorensen - 1996 - Gibbs sampling in Quantitative Genetics.pdf:pdf",
	institution = "Danish Institute of Animal Science",
	pages = "18--20,74--79,103--109",
	title = "{Gibbs sampling in Quantitative Genetics}",
	year = "1996"
}

@book{SorensenGianola2002,
	author = "Sorensen, Daniel and Gianola, Daniel",
	isbn = "0-387-95440-6",
	publisher = "Springer",
	title = "{Likelihood, Bayesian, and MCMC Methods in Quantitative Genetics}",
	year = "2002"
}


@article{StrandenGarrick2009,
	abstract = "Conventional prediction of dairy cattle merit involves setting up and solving linear equations with the number of unknowns being the number of animals, typically millions, multiplied by the number of traits being simultaneously assessed. The coefficient matrix has been large and sparse and iteration on data has been the method of choice, whereby the coefficient matrix is not stored but recreated as needed. In contrast, genomic prediction involves assessment of the merit of genome fragments characterized by single nucleotide polymorphism genotypes, currently some 50,000, which can then be used to predict the merit of individual animals according to the fragments they have inherited. The prediction equations for chromosome fragments typically have fewer than 100,000 unknowns, but the number of observations used to predict the fragment effects can be one-tenth the number of fragments. The coefficient matrix tends to be dense and the resulting system of equations can be ill behaved. Equivalent 
computing algorithms for genomic prediction were derived. The number of unknowns in the equivalent system grows with number of genotyped animals, usually bulls, rather than the number of chromosome fragment effects. In circumstances with fewer genotyped animals than single nucleotide polymorphism genotypes, these equivalent computations allow the solving of a smaller system of equations that behaves numerically better. There were 3 solving strategies compared: 1 method that formed and stored the coefficient matrix in memory and 2 methods that iterate on data. Finally, formulas for reliabilities of genomic predictions of merit were developed.",
	author = "Strand{\'e}n, Ismo and Garrick, D.J.",
	doi = "10.3168/jds.2008-1929",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Strand{\'e}n, Garrick - 2009 - Technical note Derivation of equivalent computing algorithms for genomic predictions and reliabilities of animal merit.pdf:pdf",
	issn = "1525-3198",
	journal = "Journal of dairy science",
	keywords = "Algorithms; Animals; Cattle; Cattle: genetics; Dairying; Dairying: methods; Genome; Genome: genetics; Reproducibility of Results",
	month = jun,
	number = "6",
	pages = "2971--5",
	pmid = "19448030",
	publisher = "Elsevier",
	title = "{Technical note: Derivation of equivalent computing algorithms for genomic predictions and reliabilities of animal merit.}",
	url = "http://www.ncbi.nlm.nih.gov/pubmed/19448030",
	volume = "92",
	year = "2009"
}

@article{StrandenMantysaari2010,
	author = "Stranden, Ismo and Mantysaari, Esa A.",
	journal = "INTERBULL Bulletin",
	title = "{A Recipe for Multiple Trait Deregression.}",
	volume = "42",
	year = "2010"
}

@article{VanRaden2007,
	abstract = "Models that include genomic relationships can predict genetic effects more accurately than those that use expected relationships from pedigrees. Relationship matrices can estimate the expected fraction of genes identical by descent, the actual fraction of DNA shared, or the fraction of alleles shared for loci that affect a particular trait. Each may be a valid answer to the question ``Are two individuals related?'' Several options are available for including genomic relationships in genetic evaluations.",
	author = "VanRaden, P.M.",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/VanRaden - 2007 - Genomic Measures og Relationship and Inbreeding.pdf:pdf",
	journal = "Interbull Annual Meeting Proc.",
	pages = "33--36",
	title = "{Genomic Measures of Relationship and Inbreeding}",
	volume = "37",
	year = "2007"
}

@article{VanRaden2008,
	abstract = "Efficient methods for processing genomic data were developed to increase reliability of estimated breeding values and to estimate thousands of marker effects simultaneously. Algorithms were derived and computer programs tested with simulated data for 2,967 bulls and 50,000 markers distributed randomly across 30 chromosomes. Estimation of genomic inbreeding coefficients required accurate estimates of allele frequencies in the base population. Linear model predictions of breeding values were computed by 3 equivalent methods: 1) iteration for individual allele effects followed by summation across loci to obtain estimated breeding values, 2) selection index including a genomic relationship matrix, and 3) mixed model equations including the inverse of genomic relationships. A blend of first- and second-order Jacobi iteration using 2 separate relaxation factors converged well for allele frequencies and effects. Reliability of predicted net merit for young bulls was 63\% compared with 32\% using the 
traditional relationship matrix. Nonlinear predictions were also computed using iteration on data and nonlinear regression on marker deviations; an additional (about 3\%) gain in reliability for young bulls increased average reliability to 66\%. Computing times increased linearly with number of genotypes. Estimation of allele frequencies required 2 processor days, and genomic predictions required <1 d per trait, and traits were processed in parallel. Information from genotyping was equivalent to about 20 daughters with phenotypic records. Actual gains may differ because the simulation did not account for linkage disequilibrium in the base population or selection in subsequent generations.",
	author = "VanRaden, P.M.",
	doi = "10.3168/jds.2007-0980",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/VanRaden - 2008 - Efficient methods to compute genomic predictions(3).pdf:pdf",
	issn = "1525-3198",
	journal = "J. Dairy Sci.",
	keywords = "Animals; Cattle; Cattle: genetics; Computer Simulation; Female; Gene Frequency; Genetic; Genome; Genome: genetics; Genomic prediction; Inbreeding; Male; Models; Pedigree; Reproducibility of Results",
	mendeley-tags = "Genomic prediction",
	month = nov,
	number = "11",
	pages = "4414--23",
	pmid = "18946147",
	publisher = "Elsevier",
	title = "{Efficient methods to compute genomic predictions.}",
	url = "http://www.ncbi.nlm.nih.gov/pubmed/18946147; http://www.journalofdairyscience.org/article/S0022-0302(08)70990-1/abstract",
	volume = "91",
	year = "2008"
}



@article{Visscher2007,
	author = "Visscher, Peter M. and Macgregor, Stuart and Benyamin, Beben and Zhu, Gu and Gordon, Scott and Medland, Sarah and Hill, William G. and Hottenga, Jouke-Jan and Willemsen, Gonneke and Boomsma, Dorret I. and Liu, Yao-Zhong and Deng, Hong-Wen and Montgomery, Grant W. and Martin, Nicholas G.",
	doi = "10.1086/522934",
	issn = "00029297",
	journal = "The American Journal of Human Genetics",
	month = nov,
	pages = "1104--1110",
	title = "{Genome Partitioning of Genetic Variation for Height from 11,214 Sibling Pairs}",
	url = "http://linkinghub.elsevier.com/retrieve/pii/S0002929707638841",
	volume = "81",
	year = "2007"
}

@inproceedings{Vuori2006,
	address = "Belo Horizonte, MG, Brazil",
	author = "Vuori, K. and Strand{\'e}n, Ismo and Lidauer, M. and Mantysaari, Esa A.",
	booktitle = "Proc. 8th World Congr. Genet. Appl. Livest. Prod., August 13-18",
	pages = "Proceedings CD",
	title = "{MiX99 - Effective solver for large and complex linear mixed models.}",
	year = "2006"
}

@article{Wang2010,
	abstract = "Genome-wide association (GWA) studies have typically focused on the analysis of single markers, which often lacks the power to uncover the relatively small effect sizes conferred by most genetic variants. Recently, pathway-based approaches have been developed, which use prior biological knowledge on gene function to facilitate more powerful analysis of GWA study data sets. These approaches typically examine whether a group of related genes in the same functional pathway are jointly associated with a trait of interest. Here we review the development of pathway-based approaches for GWA studies, discuss their practical use and caveats, and suggest that pathway-based approaches may also be useful for future GWA studies with sequencing data.",
	author = "Wang, Kai and Li, Mingyao and Hakonarson, Hakon",
	doi = "10.1038/nrg2884",
	file = ":home/stefan/PhD/Articles/Wang et al (2010) Analysing biological pathways in GWAS.pdf:pdf",
	institution = "Center for Applied Genomics, The Childrens Hospital of Philadelphia, Pennsylvania 19104, USA.",
	issn = "1471-0056",
	journal = "Nat. Rev. Genet.",
	keywords = "GWAS; Joint analysis; Multi-marker association tests; Pathway analysis; review",
	mendeley-tags = "GWAS,Joint analysis,Multi-marker association tests,Pathway analysis,review",
	month = dec,
	number = "12",
	pages = "843--854",
	pmid = "21085203",
	publisher = "Nature Publishing Group",
	title = "{Analysing biological pathways in genome-wide association studies}",
	url = "http://dx.doi.org/10.1038/nrg2884; http://www.nature.com/doifinder/10.1038/nrg2884",
	volume = "11",
	year = "2010"
}

@article{Wu2011,
	abstract = "Sequencing studies are increasingly being conducted to identify rare variants associated with complex traits. The limited power of classical single-marker association analysis for rare variants poses a central challenge in such studies. We propose the sequence kernel association test (SKAT), a supervised, flexible, computationally efficient regression method to test for association between genetic variants (common and rare) in a region and a continuous or dichotomous trait while easily adjusting for covariates. As a score-based variance-component test, SKAT can quickly calculate p values analytically by fitting the null model containing only the covariates, and so can easily be applied to genome-wide data. Using SKAT to analyze a genome-wide sequencing study of 1000 individuals, by segmenting the whole genome into 30 kb regions, requires only 7 hr on a laptop. Through analysis of simulated data across a wide range of practical scenarios and triglyceride data from the Dallas Heart Study, we show 
that SKAT can substantially outperform several alternative rare-variant association tests. We also provide analytic power and sample-size calculations to help design candidate-gene, whole-exome, and whole-genome sequence association studies.",
	author = "Wu, Michael C and Lee, Seunggeun and Cai, Tianxi and Li, Yun and Boehnke, Michael and Lin, Xihong",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Wu et al. - 2011 - Rare-variant association testing for sequencing data with the sequence kernel association test.pdf:pdf",
	issn = "1537-6605",
	journal = "American Journal of Human Genetics",
	keywords = "Computer Simulation; Databases; Gene Frequency; Genetic; Genetic Association Studies; Genetic Association Studies: methods; Genetic Loci; Genetic Variation; Humans; Models; Recommended by Peter; SKAT; Sequence Analysis; Sequence Analysis: methods; Software",
	mendeley-tags = "Recommended by Peter,SKAT",
	month = jul,
	number = "1",
	pages = "82--93",
	title = "{Rare-variant association testing for sequencing data with the sequence kernel association test.}",
	url = "http://www.cell.com/AJHG/fulltext/S0002-9297(11)00222-9",
	volume = "89",
	year = "2011"
}

@article{Yang2010,
	abstract = "SNPs discovered by genome-wide association studies (GWASs) account for only a small fraction of the genetic variation of complex traits in human populations. Where is the remaining heritability? We estimated the proportion of variance for human height explained by 294,831 SNPs genotyped on 3,925 unrelated individuals using a linear model analysis, and validated the estimation method with simulations based on the observed genotype data. We show that 45\% of variance can be explained by considering all SNPs simultaneously. Thus, most of the heritability is not missing but has not previously been detected because the individual effects are too small to pass stringent significance tests. We provide evidence that the remaining heritability is due to incomplete linkage disequilibrium between causal variants and genotyped SNPs, exacerbated by causal variants having lower minor allele frequency than the SNPs explored to date.",
	author = "Yang, Jian and Benyamin, Beben and McEvoy, Brian P. and Gordon, Scott and Henders, Anjali K. and Nyholt, Dale R. and Madden, Pamela A. and Heath, Andrew C. and Martin, Nicholas G. and Montgomery, Grant W. and Goddard, Michael E. and Visscher, Peter M.",
	doi = "10.1038/ng.608",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Yang et al. - 2010 - Common SNPs explain a large proportion of the heritability for human height.pdf:pdf",
	issn = "1546-1718",
	journal = "Nat. Genet.",
	keywords = "80 and over; Adolescent; Adult; Aged; Algorithms; Body Height; Body Height: genetics; Female; Gene Frequency; Genetic; Genetic Predisposition to Disease; Genetic Predisposition to Disease: genetics; Genome; Genome-Wide Association Study; Genome-Wide Association Study: methods; Genotype; Human; Humans; Linkage Disequilibrium; Logistic Models; Male; Middle Aged; Models; Polymorphism; Single Nucleotide; Young Adult",
	month = jul,
	number = "7",
	pages = "565--9",
	pmid = "20562875",
	title = "{Common SNPs explain a large proportion of the heritability for human height.}",
	url = "http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3232052&tool=pmcentrez&rendertype=abstract",
	volume = "42",
	year = "2010"
}

@article{Zuk2012,
	abstract = {Human genetics has been haunted by the mystery of "missing heritability" of common traits. Although studies have discovered >1,200 variants associated with common diseases and traits, these variants typically appear to explain only a minority of the heritability. The proportion of heritability explained by a set of variants is the ratio of (i) the heritability due to these variants (numerator), estimated directly from their observed effects, to (ii) the total heritability (denominator), inferred indirectly from population data. The prevailing view has been that the explanation for missing heritability lies in the numerator-that is, in as-yet undiscovered variants. While many variants surely remain to be found, we show here that a substantial portion of missing heritability could arise from overestimation of the denominator, creating "phantom heritability." Specifically, (i) estimates of total heritability implicitly assume the trait involves no genetic interactions (epistasis) among loci; (ii) 
this assumption is not justified, because models with interactions are also consistent with observable data; and (iii) under such models, the total heritability may be much smaller and thus the proportion of heritability explained much larger. For example, 80\% of the currently missing heritability for Crohn's disease could be due to genetic interactions, if the disease involves interaction among three pathways. In short, missing heritability need not directly correspond to missing variants, because current estimates of total heritability may be significantly inflated by genetic interactions. Finally, we describe a method for estimating heritability from isolated populations that is not inflated by genetic interactions.},
	author = "Zuk, Or and Hechter, Eliana and Sunyaev, Shamil R and Lander, Eric S",
	doi = "10.1073/pnas.1119675109",
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Zuk et al. - 2012 - The mystery of missing heritability Genetic interactions create phantom heritability.pdf:pdf",
	issn = "1091-6490",
	journal = "Proceedings of the National Academy of Sciences of the United States of America",
	keywords = "Peters intro refs",
	mendeley-tags = "Peters intro refs",
	month = jan,
	number = "4",
	pages = "1193--8",
	pmid = "22223662",
	title = "{The mystery of missing heritability: Genetic interactions create phantom heritability.}",
	url = "http://www.pnas.org/cgi/content/abstract/109/4/1193",
	volume = "109",
	year = "2012"
}

@misc{wwwkegg,
	file = ":home/stefan/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Unknown - Unknown - KEGG Kyoto Encyclopedia of Genes and Genomes.html:html",
	keywords = "Brite database; KEGG; Kanehisa Laboratories; Kyoto Encyclopedia of Genes and Genomes; Ligand database; Pathway database",
	title = "{KEGG: Kyoto Encyclopedia of Genes and Genomes}",
	url = "http://www.genome.jp/kegg",
	urldate = "21/03/13"
}

@article{Casanova-Acebes2013,
abstract = {Unique among leukocytes, neutrophils follow daily cycles of release from and migration back into the bone marrow, where they are eliminated. Because removal of dying cells generates homeostatic signals, we explored whether neutrophil elimination triggers circadian events in the steady state. Here, we report that the homeostatic clearance of neutrophils provides cues that modulate the physiology of the bone marrow. We identify a population of CD62L(LO) CXCR4(HI) neutrophils that have "aged" in the circulation and are eliminated at the end of the resting period in mice. Aged neutrophils infiltrate the bone marrow and promote reductions in the size and function of the hematopoietic niche. Modulation of the niche depends on macrophages and activation of cholesterol-sensing nuclear receptors and is essential for the rhythmic egress of hematopoietic progenitors into the circulation. Our results unveil a process that synchronizes immune and hematopoietic rhythms and expand the ascribed functions of neutrophils beyond inflammation. PAPERFLICK:},
author = {Casanova-Acebes, Mar\'{\i}a and Pitaval, Christophe and Weiss, Linnea A and Nombela-Arrieta, C\'{e}sar and Ch\`{e}vre, Rapha\"{e}l and A-Gonz\'{a}lez, Noelia and Kunisaki, Yuya and Zhang, Dachuan and van Rooijen, Nico and Silberstein, Leslie E and Weber, Christian and Nagasawa, Takashi and Frenette, Paul S and Castrillo, Antonio and Hidalgo, Andr\'{e}s},
doi = {10.1016/j.cell.2013.04.040},
issn = {1097-4172},
journal = {Cell},
keywords = {Animals,Bo's manuscript,Bone Marrow,Bone Marrow: physiology,Cell Aging,Cell Movement,Circadian Rhythm,Female,Hematopoietic Stem Cells,Hematopoietic Stem Cells: metabolism,Homeostasis,Male,Mice,Mice, Inbred C57BL,Neutrophils,Neutrophils: cytology,Neutrophils: immunology,Neutrophils: physiology,Orphan Nuclear Receptors,Orphan Nuclear Receptors: metabolism},
mendeley-tags = {Bo's manuscript},
month = may,
number = {5},
pages = {1025--35},
pmid = {23706740},
publisher = {Elsevier},
title = {{Rhythmic modulation of the hematopoietic niche through neutrophil clearance.}},
url = {http://www.cell.com/fulltext/S0092-8674(13)00516-3},
volume = {153},
year = {2013}
}

@article{Dibner2010,
abstract = {Most physiology and behavior of mammalian organisms follow daily oscillations. These rhythmic processes are governed by environmental cues (e.g., fluctuations in light intensity and temperature), an internal circadian timing system, and the interaction between this timekeeping system and environmental signals. In mammals, the circadian timekeeping system has a complex architecture, composed of a central pacemaker in the brain's suprachiasmatic nuclei (SCN) and subsidiary clocks in nearly every body cell. The central clock is synchronized to geophysical time mainly via photic cues perceived by the retina and transmitted by electrical signals to SCN neurons. In turn, the SCN influences circadian physiology and behavior via neuronal and humoral cues and via the synchronization of local oscillators that are operative in the cells of most organs and tissues. Thus, some of the SCN output pathways serve as input pathways for peripheral tissues. Here we discuss knowledge acquired during the past few years on the complex structure and function of the mammalian circadian timing system.},
author = {Dibner, Charna and Schibler, Ueli and Albrecht, Urs},
doi = {10.1146/annurev-physiol-021909-135821},
file = {:C$\backslash$:/Users/STME/Documents/Artikler/Dibner et al (2010) Mammalian circadian timing system.pdf:pdf},
issn = {1545-1585},
journal = {Annual review of physiology},
keywords = {Animals,Biological Clocks,Biological Clocks: drug effects,Biological Clocks: physiology,Bo's reference,Brain,Brain: physiology,Central Nervous System,Central Nervous System: drug effects,Central Nervous System: physiology,Circadian Rhythm,Circadian Rhythm: drug effects,Circadian Rhythm: physiology,Food,Humans,Peripheral Nervous System,Peripheral Nervous System: drug effects,Peripheral Nervous System: physiology,Reinforcement (Psychology),Reward,Suprachiasmatic Nucleus,Suprachiasmatic Nucleus: physiology},
language = {en},
mendeley-tags = {Bo's reference},
month = jan,
pages = {517--49},
pmid = {20148687},
publisher = {Annual Reviews},
title = {{The mammalian circadian timing system: organization and coordination of central and peripheral clocks.}},
url = {http://www.annualreviews.org/doi/full/10.1146/annurev-physiol-021909-135821?url\_ver=Z39.88-2003\&rfr\_id=ori:rid:crossref.org\&rfr\_dat=cr\_pub\%3dpubmed},
volume = {72},
year = {2010}
}
@article{Kollet2006,
abstract = {Here we investigated the potential role of bone-resorbing osteoclasts in homeostasis and stress-induced mobilization of hematopoietic progenitors. Different stress situations induced activity of osteoclasts (OCLs) along the stem cell-rich endosteum region of bone, secretion of proteolytic enzymes and mobilization of progenitors. Specific stimulation of OCLs with RANKL recruited mainly immature progenitors to the circulation in a CXCR4- and MMP-9-dependent manner; however, RANKL did not induce mobilization in young female PTPepsilon-knockout mice with defective OCL bone adhesion and resorption. Inhibition of OCLs with calcitonin reduced progenitor egress in homeostasis, G-CSF mobilization and stress situations. RANKL-stimulated bone-resorbing OCLs also reduced the stem cell niche components SDF-1, stem cell factor (SCF) and osteopontin along the endosteum, which was associated with progenitor mobilization. Finally, the major bone-resorbing proteinase, cathepsin K, also cleaved SDF-1 and SCF. Our findings indicate involvement of OCLs in selective progenitor recruitment as part of homeostasis and host defense, linking bone remodeling with regulation of hematopoiesis.},
author = {Kollet, Orit and Dar, Ayelet and Shivtiel, Shoham and Kalinkovich, Alexander and Lapid, Kfir and Sztainberg, Yejezkel and Tesio, Melania and Samstein, Robert M and Goichberg, Polina and Spiegel, Asaf and Elson, Ari and Lapidot, Tsvee},
doi = {10.1038/nm1417},
issn = {1078-8956},
journal = {Nature Medicine},
keywords = {Animals,Bo's reference,Bone Resorption,Bone and Bones,Bone and Bones: anatomy \& histology,Carrier Proteins,Carrier Proteins: metabolism,Cathepsin K,Cathepsins,Cathepsins: genetics,Cathepsins: metabolism,Cell Line,Cell Movement,Cell Movement: physiology,Chemokine CXCL12,Chemokines, CXC,Chemokines, CXC: metabolism,Female,Hematopoietic Stem Cells,Hematopoietic Stem Cells: cytology,Hematopoietic Stem Cells: physiology,Homeostasis,Humans,Matrix Metalloproteinase 9,Matrix Metalloproteinase 9: metabolism,Membrane Glycoproteins,Membrane Glycoproteins: metabolism,Mice,Mice, Inbred Strains,Mice, Knockout,Osteoclasts,Osteoclasts: cytology,Osteoclasts: metabolism,Protein Tyrosine Phosphatases,Protein Tyrosine Phosphatases: genetics,Protein Tyrosine Phosphatases: metabolism,RANK Ligand,Receptor Activator of Nuclear Factor-kappa B,Receptor-Like Protein Tyrosine Phosphatases, Class,Receptors, CXCR4,Receptors, CXCR4: metabolism,Stem Cell Factor,Stem Cell Factor: metabolism},
mendeley-tags = {Bo's reference},
month = jun,
number = {6},
pages = {657--64},
pmid = {16715089},
publisher = {Nature Publishing Group},
shorttitle = {Nat Med},
title = {{Osteoclasts degrade endosteal components and promote mobilization of hematopoietic progenitor cells.}},
url = {http://dx.doi.org/10.1038/nm1417},
volume = {12},
year = {2006}
}
@article{Perretti2009,
abstract = {Glucocorticoids are widely used for the management of inflammatory diseases. Their clinical application stems from our understanding of the inhibitory effect of the corticosteroid hormone cortisol on several components of the immune system. Endogenous and exogenous glucocorticoids mediate their multiple anti-inflammatory effects through many effector molecules. In this Opinion article, we focus on the role of one such effector molecule, annexin A1, and summarize the recent studies that provide insight into its molecular and pharmacological functions in immune responses. In addition, we propose a model in which glucocorticoids regulate the expression and function of annexin A1 in opposing ways in innate and adaptive immune cells to mediate the resolution of inflammation.},
author = {Perretti, Mauro and D'Acquisto, Fulvio},
doi = {10.1038/nri2470},
issn = {1474-1741},
journal = {Nat. Rev. Immunol.},
keywords = {Animals,Annexin A1,Annexin A1: deficiency,Annexin A1: genetics,Annexin A1: physiology,Anti-Inflammatory Agents,Anti-Inflammatory Agents: therapeutic use,Bo's reference,Circadian Rhythm,Gene Expression Regulation,Gene Expression Regulation: drug effects,Glucocorticoids,Glucocorticoids: pharmacology,Glucocorticoids: physiology,Humans,Hydrocortisone,Hydrocortisone: physiology,Immune System,Immune System: drug effects,Immune System: physiology,Immunity, Innate,Immunity, Innate: drug effects,Inflammation,Inflammation: physiopathology,Lipoxins,Lipoxins: physiology,Macrophages,Macrophages: immunology,Macrophages: metabolism,Mice,Mice, Knockout,Models, Immunological,Monocytes,Monocytes: immunology,Monocytes: metabolism,Neutrophils,Neutrophils: immunology,Neutrophils: metabolism,Receptors, Formyl Peptide,Receptors, Formyl Peptide: deficiency,Receptors, Formyl Peptide: genetics,Receptors, Formyl Peptide: physiology,Receptors, Lipoxin,Receptors, Lipoxin: physiology,T-Lymphocyte Subsets,T-Lymphocyte Subsets: immunology},
mendeley-tags = {Bo's reference},
month = jan,
number = {1},
pages = {62--70},
pmid = {19104500},
publisher = {Nature Publishing Group},
shorttitle = {Nat Rev Immunol},
title = {{Annexin A1 and glucocorticoids as effectors of the resolution of inflammation.}},
url = {http://dx.doi.org/10.1038/nri2470},
volume = {9},
year = {2009}
}
@article{Scheiermann2013,
abstract = {Circadian rhythms, which have long been known to play crucial roles in physiology, are emerging as important regulators of specific immune functions. Circadian oscillations of immune mediators coincide with the activity of the immune system, possibly allowing the host to anticipate and handle microbial threats more efficiently. These oscillations may also help to promote tissue recovery and the clearance of potentially harmful cellular elements from the circulation. This Review summarizes the current knowledge of circadian rhythms in the immune system and provides an outlook on potential future implications.},
author = {Scheiermann, Christoph and Kunisaki, Yuya and Frenette, Paul S},
doi = {10.1038/nri3386},
file = {:C$\backslash$:/Users/STME/Documents/Artikler/Scheiermann et al (2013) Circadian control of immune system.pdf:pdf},
issn = {1474-1741},
journal = {Nature Reviews Immunology},
keywords = {Adaptive Immunity,Adaptive Immunity: physiology,Animals,Blood Cell Count,Bo's reference,Chronobiology Disorders,Chronobiology Disorders: immunology,Circadian Rhythm,Circadian Rhythm Signaling Peptides and Proteins,Circadian Rhythm Signaling Peptides and Proteins:,Circadian Rhythm: immunology,Disease Susceptibility,Drug Chronotherapy,Feedback,Gene Expression Regulation,Gene Expression Regulation: physiology,Genetic,Genetic: physiology,Hormones,Hormones: physiology,Humans,Humoral,Humoral: physiology,Immune System,Immune System: physiology,Immunity,Immunological,Inflammation,Inflammation: immunology,Inflammation: physiopathology,Mammals,Mammals: immunology,Mammals: physiology,Mice,Models,Physiological,Physiological: physiology,Transcription},
mendeley-tags = {Bo's reference},
month = mar,
number = {3},
pages = {190--8},
pmid = {23391992},
publisher = {Nature Publishing Group},
shorttitle = {Nat Rev Immunol},
title = {{Circadian control of the immune system.}},
url = {http://www.ncbi.nlm.nih.gov/pubmed/23391992 http://dx.doi.org/10.1038/nri3386},
volume = {13},
year = {2013}
}

@article{Sharma2011,
abstract = {Mastitis is characterized by physical, chemical and bacteriological changes in the milk and pathological changes in the glandular tissue of the udder and affects the quality and quantity of milk. The bacterial contamination of milk from the affected cows render it unfit for human consumption and provides a mechanism of spread of diseases like tuberculosis, sore-throat, Q-fever, brucellosis, leptospirosis etc. and has zoonotic importance. Somatic cell count (SCC) is a useful predictor of intramammary infection (IMI) that includes leucocytes (75\%) i.e. neutrophils, macrophages, lymphocytes, erythrocytes and epithelial cells (25\%). Leucocytes increase in response to bacterial infection, tissue injury and stress. Somatic cells are protective for the animal body and fight infectious organisms. An elevated SCC in milk has a negative influence on the quality of raw milk. Subclinical mastitis is always related to low milk production, changes to milk consistency (density), reduced possibility of adequate milk processing, low protein and high risk for milk hygiene since it may even contain pathogenic organisms. This review collects and collates relevant publications on the subject.},
author = {Sharma, N. and Singh, N.K. and Bhadwal, M.S.},
doi = {10.5713/ajas.2011.10233},
file = {:C$\backslash$:/Users/STME/Documents/Artikler/Sharma et al (2011) Relationship of Somatic Cell Count and Mastitis - An Overview.pdf:pdf},
issn = {1011-2367},
journal = {Asian-Australasian Journal of Animal Sciences},
keywords = {Bo,factors,management,mastitis,scc},
mendeley-tags = {Bo},
month = mar,
number = {3},
pages = {429--438},
title = {{Relationship of Somatic Cell Count and Mastitis: An Overview}},
volume = {24},
year = {2011}
}
@article{Singh2004,
author = {Singh, Nikhil and Rieder, Michael J and Tucker, M Jane},
file = {:C$\backslash$:/Users/STME/Documents/Artikler/Singh et al (2004).pdf:pdf},
journal = {Paediatr. Perinat. Ep.},
keywords = {Bo's reference,anti-inflammatory,cytokine,glucocorticoids,immunosuppression,t-lymphocyte},
mendeley-tags = {Bo's reference},
number = {2},
pages = {107--115},
title = {{Mechanisms of glucocorticoid-mediated anti- inflammatory and immunosuppressive action}},
volume = {6},
year = {2004}
}
@article{Yacoubian2007,
abstract = {Prostaglandins and leukotrienes are lipid mediators that carry out pivotal roles in host defense and acute inflammation. Failure to completely resolve an acute inflammatory response can lead to chronic inflammation, scarring, and eventual loss of tissue function. Until recently, it was thought that tissue resolution of acute inflammation was a passive event. However, it is now known than lipoxins, which--like prostaglandins and leukotrienes--are also derived from arachidonic acid, are active anti-inflammatory and proresolution mediators, acting in part by reducing neutrophil entry to the inflammation site and stimulating the uptake of apoptotic polymorphonuclear leukocytes by macrophages. Novel families of locally acting and locally generated mediators derived from omega-3 polyunsaturated fatty acids have also been identified as biosynthetically active components in the resolution phase of inflammation. The new families of chemical mediators are termed 'resolvins' and 'protectins' because individual members of each family are stereospecific in controlling the duration and magnitude of inflammation in animal models. Possible deficiencies in the biosynthesis of lipoxins, resolvins, and protectins, and/or their signal transduction, might underlie some aspects of pathogenesis in chronic inflammatory diseases.},
author = {Yacoubian, Stephanie and Serhan, Charles N},
doi = {10.1038/ncprheum0616},
issn = {1745-8390},
journal = {Nat. Rev. Rheumatol.},
keywords = {Animals,Anti-Inflammatory Agents,Anti-Inflammatory Agents: pharmacology,Anti-Inflammatory Agents: therapeutic use,Aspirin,Aspirin: pharmacology,Aspirin: therapeutic use,Bo's reference,Fatty Acids, Omega-3,Fatty Acids, Omega-3: physiology,Humans,Inflammation,Inflammation Mediators,Inflammation Mediators: immunology,Inflammation Mediators: physiology,Inflammation: immunology,Inflammation: physiopathology,Leukocytes,Leukocytes: physiology,Leukotrienes,Leukotrienes: physiology,Lipoxins,Lipoxins: immunology,Lipoxins: physiology,Prostaglandins,Prostaglandins: physiology,Rheumatic Diseases,Rheumatic Diseases: drug therapy},
mendeley-tags = {Bo's reference},
month = oct,
number = {10},
pages = {570--9; quiz 1 p following 589},
pmid = {17906612},
publisher = {Nature Publishing Group},
shorttitle = {Nat Clin Pract Rheum},
title = {{New endogenous anti-inflammatory and proresolving lipid mediators: implications for rheumatic diseases.}},
url = {http://dx.doi.org/10.1038/ncprheum0616},
volume = {3},
year = {2007}
}
@article{Zmrzljak2012,
abstract = {Metabolic processes have to be regulated tightly to prevent waste of energy and to ensure sufficient detoxification. Most anabolic processes operate in a timely manner when energy intake is the highest, while catabolism takes place in energy spending periods. Endobiotic and xenobiotic metabolism are therefore under circadian control. Circadian regulation is mediated through the suprachiasmatic nucleus (SCN), a master autonomous oscillator of the brain. Although many peripheral organs have their own oscillators, the SCN is important in orchestrating and entraining organs according to the environmental light cues. However, light is not the only signal for entrainment of internal clocks. For endobiotic and xenobitoic detoxification pathways, the food composition and intake regime are equally important. The rhythm of the liver as an organ where the major metabolic pathways intersect depends on SCN signals, signals from endocrine tissues, and, importantly, the type and time of feeding or xenobiotics ingestion. Several enzymes are involved in detoxification processes. Phase I is composed mainly of cytochromes P450, which are regulated by nuclear receptors. Phase II enzymes modify the phase I metabolites, while phase III includes membrane transporters responsible for the elimination of modified xenobiotics. Phases I-III of drug metabolism are under strong circadian regulation, starting with the drug-sensing nuclear receptors and ending with drug transporters. Disturbed circadian regualtion (jet-lag, shift work, and dysfunction of core clock genes) leads to changed periods of activity, sleep disorders, disturbed glucose homeostasis, breast or colon cancer, and metabolic syndrome. As many xenobiotics influence the circadian rhythm of the liver, bad drug administration timing can worsen the above listed effects. This review will cover the major hepatic circadian regulation of endogenous and xenobiotic metabolic pathways and will provide examples of how good timing of drug administration can change drug failure to treatment success.},
author = {Zmrzljak, Ursula Prosenc and Rozman, Damjana},
doi = {10.1021/tx200538r},
issn = {1520-5010},
journal = {Chemical research in toxicology},
keywords = {Bo's reference,Circadian Rhythm,Circadian Rhythm: physiology,Cytochrome P-450 Enzyme System,Cytochrome P-450 Enzyme System: metabolism,Humans,Liver,Liver: metabolism,Metabolic Detoxication, Drug,Peroxisome Proliferator-Activated Receptors,Peroxisome Proliferator-Activated Receptors: metab,Receptors, Cytoplasmic and Nuclear,Receptors, Cytoplasmic and Nuclear: metabolism,Sleep,Sleep: physiology,Xenobiotics,Xenobiotics: metabolism},
mendeley-tags = {Bo's reference},
month = apr,
number = {4},
pages = {811--24},
pmid = {22303888},
publisher = {American Chemical Society},
title = {{Circadian regulation of the hepatic endobiotic and xenobitoic detoxification pathways: the time matters.}},
url = {http://dx.doi.org/10.1021/tx200538r},
volume = {25},
year = {2012}
}


@article{Bionaz2012,
    author = {Bionaz, , Massimo AND Periasamy, , Kathiravan AND Rodriguez-Zas, , Sandra L. AND Everts, , Robin E. AND Lewin, , Harris A. AND Hurley, , Walter L. AND Loor, , Juan J.},
    journal = {PLoS ONE},
    publisher = {Public Library of Science},
    title = {Old and New Stories: Revelations from Functional Analysis of the Bovine Mammary Transcriptome during the Lactation Cycle},
    year = {2012},
    month = {03},
    volume = {7},
    url = {http://dx.doi.org/10.1371%2Fjournal.pone.0033268},
    pages = {e33268},
    abstract = {<p>The cow mammary transcriptome was explored at −30, −15, 1, 15, 30, 60, 120, 240, and 300 d relative to parturition. A total of 6,382 differentially expressed genes (DEG) at a false discovery rate ≤0.001 were found throughout lactation. The greatest number of DEG (&gt;3,500 DEG) was observed at 60 and 120 d vs. −30 d with the largest change between consecutive time points observed at −15 vs. 1 d and 120 vs. 240 d. Functional analysis of microarray data was performed using the Dynamic Impact Approach (DIA). The DIA analysis of KEGG pathways uncovered as the most impacted and induced ‘Galactose metabolism’, ‘Glycosylphosphatidylinositol (GPI)-anchor biosynthesis’, and ‘PPAR signaling’; whereas, ‘Antigen processing and presentation’ was among the most inhibited. The integrated interpretation of the results suggested an overall increase in metabolism during lactation, particularly synthesis of carbohydrates and lipid. A marked degree of utilization of amino acids as energy source, an increase of protein export, and a decrease of the protein synthesis machinery as well cell cycle also were suggested by the DIA analysis. The DIA analysis of Gene Ontology and other databases uncovered an induction of Golgi apparatus and angiogenesis, and the inhibition of both immune cell activity/migration and chromosome modifications during lactation. All of the highly-impacted and activated functions during lactation were evidently activated at the onset of lactation and inhibited when milk production declined. The overall analysis indicated that the bovine mammary gland relies heavily on a coordinated transcriptional regulation to begin and end lactation. The functional analysis using DIA underscored the importance of genes associated with lactose synthesis, lipid metabolism, protein synthesis, Golgi, transport, cell cycle/death, epigenetic regulation, angiogenesis, and immune function during lactation.</p>},
    number = {3},
    doi = {10.1371/journal.pone.0033268}
}        




@article{Sanchez-Juanes2009,
abstract = {Several components of milk fat globule membranes (MFGMs) have been reported to display beneficial health properties and some of them have been implicated in the defense of newborns against pathogens. These observations prompted us to determine the glycosphingolipid content of MFGMs and their interaction with pathogens. A comparative study with whole milk components was also carried out. Milk fat globules and MFGMs were isolated from milk. Gangliosides and neutral glycosphingolipids were obtained from MFGMs and whole milk and their fatty acid contents were determined by gas chromatography-mass spectrometry (GC-MS). MFGMs and whole milk showed similar ganglioside and neutral glycosphingolipid contents, with whole milk having more GM3 and glucosylceramide and less GD3, O-acetyl GD3, O-acetyl GT3, and lactosylceramide. The fatty acid content of gangliosides from both sources showed a similar composition. However, the neutral glycosphingolipid fatty acid content seemed to be quite different. Whole milk had fewer very-long-chain fatty acids (18.1\% vs. 46.4\% in MFGMs) and more medium-chain and unsaturated C18:1 and C18:2 fatty acids. Milk fat globules, MFGMs, lactosylceramide, and gangliosides GM3 and GD3 were observed to bind enterotoxigenic Escherichia coli strains. Furthermore, bacterial hemagglutination was inhibited by MFGMs and glycosphingolipids.},
author = {S\'{a}nchez-Juanes, Fernando and Alonso, Josefa M. and Zancada, Lorena and Hueso, Pablo},
doi = {10.1515/BC.2009.003},
issn = {1437-4315},
journal = {Bio. Chem.},
keywords = {Bo's references,bacterial adhesion,fatty acids,gangliosides,newborn defense},
mendeley-tags = {Bo's references},
month = jan,
number = {1},
pages = {31--40},
title = {{Glycosphingolipids from bovine milk and milk fat globule membranes: a comparative study. Adhesion to enterotoxigenic \textit{Escherichia coli} strains}},
url = {http://www.degruyter.com/view/j/bchm.2009.390.issue-1/bc.2009.003/bc.2009.003.xml},
volume = {390},
year = {2009}
}

@article{Shih2009,
abstract = {Retinoic acid (RA) is a potent signaling molecule that is essential for many biological processes, and its levels are tightly regulated by mechanisms that are only partially understood. The synthesis of RA from its precursor retinol (vitamin A) is an important regulatory mechanism. Therefore, the esterification of retinol with fatty acyl moieties to generate retinyl esters, the main storage form of retinol, may also regulate RA levels. Here we show that the neutral lipid synthesis enzyme acyl-CoA:diacylglycerol acyltransferase 1 (DGAT1) functions as the major acyl-CoA:retinol acyltransferase (ARAT) in murine skin. When dietary retinol is abundant, DGAT1 deficiency results in elevated levels of RA in skin and cyclical hair loss; both are prevented by dietary retinol deprivation. Further, DGAT1-deficient skin exhibits enhanced sensitivity to topically administered retinol. Deletion of the enzyme specifically in the epidermis causes alopecia, indicating that the regulation of RA homeostasis by DGAT1 is autonomous in the epidermis. These findings show that DGAT1 functions as an ARAT in the skin, where it acts to maintain retinoid homeostasis and prevent retinoid toxicity. Our findings may have implications for human skin or hair disorders treated with agents that modulate RA signaling.},
author = {Shih, Michelle Y. S. and Kane, Maureen A. and Zhou, Ping and Yen, C. L. Eric and Streeper, Ryan S. and Napoli, Joseph L. and Farese, Robert V.},
doi = {10.1074/jbc.M807503200},
issn = {0021-9258},
journal = {J. Biol. Chem},
keywords = {Alopecia,Alopecia: enzymology,Alopecia: genetics,Animals,Bo's references,Diacylglycerol O-Acyltransferase,Diacylglycerol O-Acyltransferase: genetics,Diacylglycerol O-Acyltransferase: metabolism,Epidermis,Epidermis: enzymology,Female,Homeostasis,Homeostasis: drug effects,Homeostasis: physiology,Knockout,Male,Mice,Retinoids,Retinoids: genetics,Retinoids: metabolism,Retinol O-Fatty-Acyltransferase,Retinol O-Fatty-Acyltransferase: genetics,Retinol O-Fatty-Acyltransferase: metabolism,Signal Transduction,Signal Transduction: drug effects,Signal Transduction: physiology,Tretinoin,Tretinoin: metabolism,Tretinoin: pharmacology},
mendeley-tags = {Bo's references},
month = feb,
number = {7},
pages = {4292--9},
pmid = {19028692},
title = {{Retinol Esterification by DGAT1 Is Essential for Retinoid Homeostasis in Murine Skin}},
url = {http://www.jbc.org/content/284/7/4292.abstract?sid=f36fd069-4c5c-4397-b015-76f85b41f336},
volume = {284},
year = {2009}
}

@article{OByrne2013,
abstract = {By definition, a vitamin is a substance that must be obtained regularly from the diet. Vitamin A must be acquired from the diet, but unlike most vitamins, it can also be stored within the body in relatively high levels. For humans living in developed nations or animals living in present-day vivariums, stored vitamin A concentrations can become relatively high, reaching levels that can protect against the adverse effects of insufficient vitamin A dietary intake for six months, or even much longer. The ability to accumulate vitamin A stores lessens the need for routinely consuming vitamin A in the diet, and this provides a selective advantage to the organism. The molecular processes that underlie this selective advantage include efficient mechanisms to acquire vitamin A from the diet, efficient and overlapping mechanisms for the transport of vitamin A in the circulation, a specific mechanism allowing for vitamin A storage, and a mechanism for mobilizing vitamin A from these stores in response to tissue needs. These processes are considered in this review.},
author = {O'Byrne, Sheila M. and Blaner, William S.},
doi = {10.1194/jlr.R037648},
issn = {0022-2275},
journal = {J. Lipid. Res.},
keywords = {Bo's reference,DGAT1,RBP4,Stra6,Vitamin A,adipocyte,anhydro-retinoids,enterocyte,hepatic stellate cell,hepatocyte,lipid droplets,retinoic acid,retro-retinoids},
mendeley-tags = {Bo's reference},
month = jul,
number = {7},
pages = {1731--43},
pmid = {23625372},
title = {{Retinol and retinyl esters: biochemistry and physiology}},
url = {http://www.jlr.org/content/54/7/1731.abstract?sid=a0c2277a-1d6d-4f8a-8378-894c86062940},
volume = {54},
year = {2013}
}

@article{Wang2005,
abstract = {Retinoic acid (RA), a bioactive chemical compound synthesized from dietary derived vitamin A, has been successfully used as a chemopreventive and chemotherapeutic agent through the regulation of cell proliferation, differentiation, and apoptosis acting via the retinoic acid receptors. Despite two decades of research on the function of retinoic acid, the physiological role of RA in mammary gland development is still not well characterized. In this report, we demonstrate that RA is required for proper morphogenesis of mouse mammary gland in a novel transgenic mouse model system. It was found that inhibition of RA signaling in vivo leads to excessive mammary ductal morphogenesis through upregulation of cyclin D1 and MMP-3 expression. Furthermore, we show that the transgene-induced excessive branching morphogenesis could be reversed by treatment with RA, demonstrating the direct physiological effect of RA signaling in vivo. In addition, we demonstrate that excessive branching morphogenesis in the transgenic mammary gland are cell-autonomous and do not require stromal signals within the transgenic mammary gland. Finally, we provide evidence suggesting that retinoic acid signaling is required for appropriate mammary gland differentiation. Collectively, our data indicate for the first time that retinoic acid signaling is required to maintain the homeostasis of mammary gland morphogenesis.},
author = {Wang, Y Alan and Shen, Kate and Wang, Yaolin and Brooks, S C},
doi = {10.1002/dvdy.20570},
issn = {1058-8388},
journal = {Dev. Dynam.},
keywords = {Animal,Animal: embryology,Animals,Bo's references,Cell Proliferation,Cyclin D1,Cyclin D1: metabolism,Developmental,Gene Expression Regulation,Immunohistochemistry,Mammary Glands,Matrix Metalloproteinase 3,Matrix Metalloproteinase 3: metabolism,Mice,Morphogenesis,Morphogenesis: drug effects,Morphogenesis: physiology,Receptors,Retinoic Acid,Retinoic Acid: metabolism,Signal Transduction,Signal Transduction: physiology,Transgenic,Tretinoin,Tretinoin: metabolism,Tretinoin: pharmacology,Tretinoin: physiology},
mendeley-tags = {Bo's references},
month = dec,
number = {4},
pages = {892--9},
pmid = {16217742},
title = {{Retinoic acid signaling is required for proper morphogenesis of mammary gland}},
url = {http://www.ncbi.nlm.nih.gov/pubmed/16217742},
volume = {234},
year = {2005}
}

@article{Cho2012,
abstract = {Retinoic acid receptors (RARs), which are involved in retinoic acid signal transduction, are essential for maintaining the differentiated state of epithelial tissues. Mammary glands are skin appendages whose development is initiated through continuous cell–cell interactions between the ectoderm and the adjacent mesenchyme. Considerable progress has been made in elucidating the molecular basis of these interactions in mammary gland formation in mouse embryos, including the network of initiating signals comprising Fgfs, Wnts and Bmps involved in gland positioning and the transcription factors, Tbx3 and Lef1, essential for mammary gland development. Here, we provide evidence that retinoic acid signaling may also be involved in mammary gland development. We documented the expression of gene-encoding enzymes that produce retinoic acid (Raldh2) and enzymes that degrade it (Cyp26a1, Cyp26b1). We also analyzed the expression of RAR-$\beta$, a direct transcriptional target of retinoic acid signaling. Raldh2 and RAR-$\beta$ were expressed in E10–E10.5 mouse embryos in somites adjacent to the flank region where mammary buds 2, 3 and 4 develop. These expression patterns overlapped with that of Fgf10, which is known to be required for mammary gland formation. RAR-$\beta$ was also expressed in the mammary mesenchyme in E12 mouse embryos; RAR-$\beta$ protein was expressed in the mammary epithelium and developing fat pad. Retinoic acid levels in organ cultures of E10.5 mouse embryo flanks were manipulated by adding either retinoic acid or citral, a retinoic acid synthesis inhibitor. Reduced retinoic acid synthesis altered the expression of genes involved in retinoic acid homeostasis and also demonstrated that retinoic acid signaling is required for Tbx3 expression, whereas high levels of retinoic acid signaling inhibited Bmp4 expression and repressed Wnt signaling. The results of the experiments using RNAi against Tbx3 and Wnt10b suggested feedback interactions that regulate retinoic acid homeostasis in mammary gland-forming regions. We produced a molecular model for mammary gland initiation that incorporated retinoic acid signaling.},
author = {Cho, Kyoung-Won and Kwon, Hyuk-Jae and Shin, Jeong-Oh and Lee, Jong-Min and Cho, Sung-Won and Tickle, Cheryll and Jung, Han-Sung},
doi = {10.1016/j.ydbio.2012.02.020},
journal = {Dev. Biol.},
keywords = {Bo's references,Mammary gland development,RAR-$\beta$,Retinoic acid,Tbx3,Wnt10b},
mendeley-tags = {Bo's references},
number = {1},
pages = {259--266},
title = {{Retinoic acid signaling and the initiation of mammary gland development}},
url = {http://www.sciencedirect.com/science/article/pii/S0012160612000899},
volume = {365},
year = {2012}
}

@article{Habier2007,
author = {Habier, D. and Fernando, R. L. and Dekkers, J. C. M.}, 
title = {The Impact of Genetic Relationship Information on Genome-Assisted Breeding Values},
volume = {177}, 
number = {4}, 
pages = {2389-2397}, 
year = {2007}, 
doi = {10.1534/genetics.107.081190}, 
abstract ={The success of genomic selection depends on the potential to predict genome-assisted breeding values (GEBVs) with high accuracy over several generations without additional phenotyping after estimating marker effects. Results from both simulations and practical applications have to be evaluated for this potential, which requires linkage disequilibrium (LD) between markers and QTL. This study shows that markers can capture genetic relationships among genotyped animals, thereby affecting accuracies of GEBVs. Strategies to validate the accuracy of GEBVs due to LD are given. Simulations were used to show that accuracies of GEBVs obtained by fixed regression–least squares (FR–LS), random regression–best linear unbiased prediction (RR–BLUP), and Bayes-B are nonzero even without LD. When LD was present, accuracies decrease rapidly in generations after estimation due to the decay of genetic relationships. However, there is a persistent accuracy due to LD, which can be estimated by modeling the decay of genetic relationships and the decay of LD. The impact of genetic relationships was greatest for RR–BLUP. The accuracy of GEBVs can result entirely from genetic relationships captured by markers, and to validate the potential of genomic selection, several generations have to be analyzed to estimate the accuracy due to LD. The method of choice was Bayes-B; FR–LS should be investigated further, whereas RR–BLUP cannot be recommended.}, 
URL = {http://www.genetics.org/content/177/4/2389.abstract}, 
eprint = {http://www.genetics.org/content/177/4/2389.full.pdf+html}, 
journal = {Genetics} 
}
@article{SelfLiang1987,
     jstor_articletype = {research-article},
     title = {Asymptotic Properties of Maximum Likelihood Estimators and Likelihood Ratio Tests Under Nonstandard Conditions},
     author = {Self, Steven G. and Liang, Kung-Yee},
     journal = {J. Am. Stat. Assoc.},
     jstor_issuetitle = {},
     volume = {82},
     number = {398},
     jstor_formatteddate = {Jun., 1987},
     pages = {pp. 605-610},
     url = {http://www.jstor.org/stable/2289471},
     ISSN = {01621459},
     abstract = {Large sample properties of the likelihood function when the true parameter value may be on the boundary of the parameter space are described. Specifically, the asymptotic distribution of maximum likelihood estimators and likelihood ratio statistics are derived. These results generalize the work of Moran (1971), Chant (1974), and Chernoff (1954). Some of Chant's results are shown to be incorrect. The approach used in deriving these results follows from comments made by Moran and Chant. The problem is shown to be asymptotically equivalent to the problem of estimating the restricted mean of a multivariate Gaussian distribution from a sample of size 1. In this representation the Gaussian random variable corresponds to the limit of the normalized score statistic and the estimate of the mean corresponds to the limit of the normalized maximum likelihood estimator. Thus the limiting distribution of the maximum likelihood estimator is the same as the distribution of the projection of the Gaussian random variable onto the region of admissible values for the mean. A variety of examples is provided for which the limiting distributions of likelihood ratio statistics are mixtures of chi-squared distributions. One example is provided with a nuisance parameter on the boundary for which the asymptotic distribution is not a mixture of chi-squared distributions.},
     language = {English},
     year = {1987},
     publisher = {American Statistical Association},
     copyright = {Copyright © 1987 American Statistical Association},
}

@article{Listgarten2013,
abstract = {MOTIVATION: Approaches for testing sets of variants, such as a set of rare or common variants within a gene or pathway, for association with complex traits are important. In particular, set tests allow for aggregation of weak signal within a set, can capture interplay among variants and reduce the burden of multiple hypothesis testing. Until now, these approaches did not address confounding by family relatedness and population structure, a problem that is becoming more important as larger datasets are used to increase power. RESULTS: We introduce a new approach for set tests that handles confounders. Our model is based on the linear mixed model and uses two random effects-one to capture the set association signal and one to capture confounders. We also introduce a computational speedup for two random-effects models that makes this approach feasible even for extremely large cohorts. Using this model with both the likelihood ratio test and score test, we find that the former yields more power while controlling type I error. Application of our approach to richly structured Genetic Analysis Workshop 14 data demonstrates that our method successfully corrects for population structure and family relatedness, whereas application of our method to a 15 000 individual Crohn's disease case-control cohort demonstrates that it additionally recovers genes not recoverable by univariate analysis. AVAILABILITY: A Python-based library implementing our approach is available at http://mscompbio.codeplex.com. CONTACT: jennl@microsoft.com or lippert@microsoft.com or heckerma@microsoft.com SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.},
author = {Listgarten, Jennifer and Lippert, Christoph and Kang, Eun Yong and Xiang, Jing and Kadie, Carl M and Heckerman, David},
doi = {10.1093/bioinformatics/btt177},
issn = {1367-4811},
journal = {Bioinformatics (Oxford, England)},
keywords = {Peters references},
mendeley-groups = {Manuscript1},
mendeley-tags = {Peters references},
month = may,
number = {12},
pages = {1526--1533},
pmid = {23599503},
title = {{A powerful and efficient set test for genetic markers that handles confounders.}},
url = {http://bioinformatics.oxfordjournals.org/content/29/12/1526.abstract},
volume = {29},
year = {2013}
}

@Article{Btau4,
AUTHOR = {Liu, Yue and Qin, Xiang and Song, Xing-Zhi and Jiang, Huaiyang and Shen, Yufeng and Durbin, K James and Lien, Sigbjorn and Kent, Matthew and Sodeland, Marte and Ren, Yanru and Zhang, Lan and Sodergren, Erica and Havlak, Paul and Worley, Kim and Weinstock, George and Gibbs, Richard},
TITLE = {\textit{Bos taurus} genome assembly},
JOURNAL = {BMC Genomics},
VOLUME = {10},
YEAR = {2009},
NUMBER = {1},
PAGES = {180},
URL = {http://www.biomedcentral.com/1471-2164/10/180},
DOI = {10.1186/1471-2164-10-180},
PubMedID = {19393050},
ISSN = {1471-2164},
ABSTRACT = {BACKGROUND:We present here the assembly of the bovine genome. The assembly method combines the BAC plus WGS local assembly used for the rat and sea urchin with the whole genome shotgun (WGS) only assembly used for many other animal genomes including the rhesus macaque.RESULTS:The assembly process consisted of multiple phases: First, BACs were assembled with BAC generated sequence, then subsequently in combination with the individual overlapping WGS reads. Different assembly parameters were tested to separately optimize the performance for each BAC assembly of the BAC and WGS reads. In parallel, a second assembly was produced using only the WGS sequences and a global whole genome assembly method. The two assemblies were combined to create a more complete genome representation that retained the high quality BAC-based local assembly information, but with gaps between BACs filled in with the WGS-only assembly. Finally, the entire assembly was placed on chromosomes using the available map information.Over 90% of the assembly is now placed on chromosomes. The estimated genome size is 2.87 Gb which represents a high degree of completeness, with 95% of the available EST sequences found in assembled contigs. The quality of the assembly was evaluated by comparison to 73 finished BACs, where the draft assembly covers between 92.5 and 100% (average 98.5%) of the finished BACs. The assembly contigs and scaffolds align linearly to the finished BACs, suggesting that misassemblies are rare. Genotyping and genetic mapping of 17,482 SNPs revealed that more than 99.2% were correctly positioned within the Btau_4.0 assembly, confirming the accuracy of the assembly.CONCLUSION:The biological analysis of this bovine genome assembly is being published, and the sequence data is available to support future bovine research.},
}
@Article{Jensen2012,
AUTHOR = {Jensen, Just and Su, Guosheng and Madsen, Per},
TITLE = {Partitioning additive genetic variance into genomic and remaining polygenic components for complex traits in dairy cattle},
JOURNAL = {BMC Genetics},
VOLUME = {13},
YEAR = {2012},
NUMBER = {1},
PAGES = {44},
URL = {http://www.biomedcentral.com/1471-2156/13/44},
DOI = {10.1186/1471-2156-13-44},
PubMedID = {22694746},
ISSN = {1471-2156},
ABSTRACT = {BACKGROUND:Low cost genotyping of individuals using high density genomic markers were recently introduced as genomic selection in genetic improvement programs in dairy cattle. Most implementations of genomic selection only use marker information, in the models used for prediction of genetic merit. However, in other species it has been shown that only a fraction of the total genetic variance can be explained by markers. Using 5217 bulls in the Nordic Holstein population that were genotyped and had genetic evaluations based on progeny, we partitioned the total additive genetic variance into a genomic component explained by markers and a remaining component explained by familial relationships. The traits analyzed were production and fitness related traits in dairy cattle. Furthermore, we estimated the genomic variance that can be attributed to individual chromosomes and we illustrate methods that can predict the amount of additive genetic variance that can be explained by sets of markers with different density.RESULTS:The amount of additive genetic variance that can be explained by markers was estimated by an analysis of the matrix of genomic relationships. For the traits in the analysis, most of the additive genetic variance can be explained by 44K informative SNP markers. The same amount of variance can be attributed to individual chromosomes but surprisingly the relation between chromosomal variance and chromosome length was weak. In models including both genomic (marker) and familial (pedigree) effects most (on average 77.2%) of total additive genetic variance was explained by genomic effects while the remaining was explained by familial relationships.CONCLUSIONS:Most of the additive genetic variance for the traits in the Nordic Holstein population can be explained using 44K informative SNP markers. By analyzing the genomic relationship matrix it is possible to predict the amount of additive genetic variance that can be explained by a reduced (or increased) set of markers. For the population analyzed the improvement of genomic prediction by increasing marker density beyond 44K is limited.},
}


@article{Yamamoto2009,
abstract = {Epistasis is an important feature of the genetic architecture of quantitative traits. Previously, we showed that startle-induced locomotor behaviour of Drosophila melanogaster, a critical survival trait, is highly polygenic and exhibits epistasis. Here, we characterize epistatic interactions among homozygous P-element mutations affecting startle-induced locomotion in the Canton-S isogenic background and in 21 wild-derived inbred genetic backgrounds. We find pervasive epistasis for pairwise combinations of homozygous P-element insertional mutations as well as for mutations in wild-derived backgrounds. In all cases, the direction of the epistatic effects is to suppress the mutant phenotypes. The magnitude of the epistatic interactions in wild-derived backgrounds is highly correlated with the magnitude of the main effects of mutations, leading to phenotypic robustness of the startle response in the face of deleterious mutations. There is variation in the magnitude of epistasis among the wild-derived genetic backgrounds, indicating evolutionary potential for enhancing or suppressing effects of single mutations. These results provide a partial glimpse of the complex genetic network underlying the genetic architecture of startle behaviour and provide empirical support for the hypothesis that suppressing epistasis is the mechanism underlying genetic canalization of traits under strong stabilizing selection. Widespread suppressing epistasis will lead to underestimates of the main effects of quantitative trait loci (QTLs) in mapping experiments when not explicitly accounted for. In addition, suppressing epistasis could lead to underestimates of mutational variation for quantitative traits and overestimates of the strength of stabilizing selection, which has implications for maintenance of variation of complex traits by mutation-selection balance.},
author = {Yamamoto, Akihiko and Anholt, Robert R .H. and MacKay, Trudy F. C.},
doi = {10.1017/S0016672309990279},
issn = {1469-5073},
journal = {Genet. Res. (Camb).},
keywords = {Animals,Drosophila melanogaster,Drosophila melanogaster: genetics,Epistasis,Genetic,Genome,Insect,Mutation,Phenotype,Quantitative Trait Loci,Selection,Startle Reaction,Startle Reaction: genetics},
language = {English},
mendeley-groups = {DGRP genomic features},
month = dec,
number = {6},
pages = {373--82},
pmid = {19968911},
publisher = {Cambridge University Press},
title = {{Epistatic interactions attenuate mutations affecting startle behaviour in \textit{Drosophila melanogaster}.}},
url = {http://journals.cambridge.org/abstract\_S0016672309990279},
volume = {91},
year = {2009}
}

@article{Ober2012,
abstract = {Predicting organismal phenotypes from genotype data is important for plant and animal breeding, medicine, and evolutionary biology. Genomic-based phenotype prediction has been applied for single-nucleotide polymorphism (SNP) genotyping platforms, but not using complete genome sequences. Here, we report genomic prediction for starvation stress resistance and startle response in Drosophila melanogaster, using 2.5 million SNPs determined by sequencing the Drosophila Genetic Reference Panel population of inbred lines. We constructed a genomic relationship matrix from the SNP data and used it in a genomic best linear unbiased prediction (GBLUP) model. We assessed predictive ability as the correlation between predicted genetic values and observed phenotypes by cross-validation, and found a predictive ability of 0.239±0.008 (0.230±0.012) for starvation resistance (startle response). The predictive ability of BayesB, a Bayesian method with internal SNP selection, was not greater than GBLUP. Selection of the 5\% SNPs with either the highest absolute effect or variance explained did not improve predictive ability. Predictive ability decreased only when fewer than 150,000 SNPs were used to construct the genomic relationship matrix. We hypothesize that predictive power in this population stems from the SNP-based modeling of the subtle relationship structure caused by long-range linkage disequilibrium and not from population structure or SNPs in linkage disequilibrium with causal variants. We discuss the implications of these results for genomic prediction in other organisms.},
author = {Ober, Ulrike and Ayroles, Julien F and Stone, Eric A and Richards, Stephen and Zhu, Dianhui and Gibbs, Richard A and Stricker, Christian and Gianola, Daniel and Schlather, Martin and Mackay, Trudy F C and Simianer, Henner},
doi = {10.1371/journal.pgen.1002685},
editor = {Wray, Naomi R.},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/PLoS genetics/Ober et al. - 2012 - Using whole-genome sequence data to predict quantitative trait phenotypes in Drosophila melanogaster.pdf:pdf},
issn = {1553-7404},
journal = {PLoS Genet.},
keywords = {Animals,Bayes Theorem,Chromosome Mapping,Drosophila melanogaster,Drosophila melanogaster: genetics,Effective population size,Genetics, Population,Genome, Insect,Genotype,Linkage Disequilibrium,Models, Genetic,Models, Theoretical,Phenotype,Polymorphism, Single Nucleotide,Quantitative Trait Loci,Selection, Genetic,Sequence Analysis, DNA},
mendeley-groups = {DGRP genomic features,Thesis},
mendeley-tags = {Effective population size},
month = jan,
number = {5},
pages = {e1002685},
pmid = {22570636},
publisher = {Public Library of Science},
title = {{Using whole-genome sequence data to predict quantitative trait phenotypes in \textit{Drosophila melanogaster}.}},
url = {http://dx.plos.org/10.1371/journal.pgen.1002685},
volume = {8},
year = {2012}
}

@article{LegarraMisztal2008,
abstract = {Genome-wide genetic evaluation might involve the computation of BLUP-like estimations, potentially including thousands of covariates (i.e., single-nucleotide polymorphism markers) for each record. This implies dense Henderson's mixed-model equations and considerable computing resources in time and storage, even for a few thousand records. Possible computing options include the type of storage and the solving algorithm. This work evaluated several computing options, including half-stored Cholesky decomposition, Gauss-Seidel, and 3 matrix-free strategies: Gauss-Seidel, Gauss-Seidel with residuals update, and preconditioned conjugate gradients. Matrix-free Gauss-Seidel with residuals update adjusts the residuals after computing the solution for each effect. This avoids adjusting the left-hand side of the equations by all other effects at every step of the algorithm and saves considerable computing time. Any Gauss-Seidel algorithm can easily be extended for variance component estimation by Markov chain-Monte Carlo. Let m and n be the number of records and markers, respectively. Computing time for Cholesky decomposition is proportional to n3. Computing times per round are proportional to mn2 in matrix-free Gauss-Seidel, to n2 for half-stored Gauss-Seidel, and to n and m for the rest of the algorithms. Algorithms were tested on a real mouse data set, which included 1,928 records and 10,946 single-nucleotide polymorphism markers. Computing times were in the order of a few minutes for Gauss-Seidel with residuals update and preconditioned conjugate gradients, more than 1 h for half-stored Gauss-Seidel, 2 h for Cholesky decomposition, and 4 d for matrix-free Gauss-Seidel. Preconditioned conjugate gradients was the fastest. Gauss-Seidel with residuals update would be the method of choice for variance component estimation as well as solving.},
author = {Legarra, A. and Misztal, I.},
doi = {10.3168/jds.2007-0403},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/Journal of dairy science/Legarra, Misztal - 2008 - Technical note Computing strategies in genome-wide selection.pdf:pdf},
issn = {1525-3198},
journal = {J. Dairy Sci.},
keywords = {Algorithms,Animals,Body Weight,Computational Biology,Computational Biology: methods,Female,Genetic,Genomics,Genomics: methods,Male,Mice,Models,Polymorphism,Single Nucleotide},
mendeley-groups = {Manuscript1,Thesis},
month = jan,
number = {1},
pages = {360--6},
pmid = {18096959},
title = {{Technical note: Computing strategies in genome-wide selection.}},
url = {http://www.ncbi.nlm.nih.gov/pubmed/18096959},
volume = {91},
year = {2008}
}


@article{Fisher1922,
author = {Fisher, R. A.},
doi = {10.1098/rsta.1922.0009},
issn = {1364-503X},
journal = {Philos. Trans. R. Soc. London},
mendeley-groups = {Thesis},
number = {594-604},
pages = {309--368},
title = {{On the Mathematical Foundations of Theoretical Statistics}},
url = {http://rsta.royalsocietypublishing.org/cgi/doi/10.1098/rsta.1922.0009},
volume = {222},
year = {1922}
}
@article{Goldberger1962,
author = {Goldberger, Arthur S.},
journal = {J. Am. Stat. Assoc.},
mendeley-groups = {Thesis},
number = {298},
pages = {369--375},
publisher = {Taylor \& Francis Group},
title = {{Best linear unbiased prediction in the generalized linear regression model}},
volume = {57},
year = {1962}
}
@article{Hartley1967,
author = {Hartley, H. O. and Rao, J. N. K.},
journal = {Biometrika},
mendeley-groups = {Thesis},
number = {1},
pages = {93--108},
title = {{Maximum-likelihood estimation for the mixed analysis of variance model}},
url = {http://biomet.oxfordjournals.org/content/54/1-2/93.short},
volume = {54},
year = {1967}
}
@article{Henderson1949,
author = {Henderson, C. R.},
doi = {10.3168/jds.S0022-0302(49)92104-9},
journal = {J. Dairy Sci.},
mendeley-groups = {Thesis},
number = {8},
pages = {706 (Abstract)},
title = {{Estimation of changes in herd environment}},
volume = {32},
year = {1949}
}
@article{Henderson1959,
author = {Henderson, C. R. and Kempthorne, Oscar and Searle, S. R. and von Krosigk, C. N.},
doi = {10.2307/2527669},
journal = {Biometrics},
mendeley-groups = {Thesis},
number = {2},
pages = {192--218},
title = {{The Estimation of Environmental and Genetic Trends from Records Subject to Culling}},
url = {http://www.jstor.org/stable/10.2307/2527669},
volume = {15},
year = {1959}
}
@incollection{Henderson1963,
author = {Henderson, Charles R.},
booktitle = {Statistical Genetics and Plant Breeding},
chapter = {141-163},
editor = {Hanson, Warren Durward and Robinson, Harold Frank},
journal = {Stat. Genet. Plant Breed.},
mendeley-groups = {Thesis},
pages = {623},
publisher = {National Academy of Sciences -- National Research Council, Washington, DC},
title = {{Selection index and expected genetic advance}},
volume = {982},
year = {1963}
}
@article{Luan2009,
abstract = {Genomic Selection (GS) is a newly developed tool for the estimation of breeding values for quantitative traits through the use of dense markers covering the whole genome. For a successful application of GS, accuracy of the prediction of genomewide breeding value (GW-EBV) is a key issue to consider. Here we investigated the accuracy and possible bias of GW-EBV prediction, using real bovine SNP genotyping (18,991 SNPs) and phenotypic data of 500 Norwegian Red bulls. The study was performed on milk yield, fat yield, protein yield, first lactation mastitis traits, and calving ease. Three methods, best linear unbiased prediction (G-BLUP), Bayesian statistics (BayesB), and a mixture model approach (MIXTURE), were used to estimate marker effects, and their accuracy and bias were estimated by using cross-validation. The accuracies of the GW-EBV prediction were found to vary widely between 0.12 and 0.62. G-BLUP gave overall the highest accuracy. We observed a strong relationship between the accuracy of the prediction and the heritability of the trait. GW-EBV prediction for production traits with high heritability achieved higher accuracy and also lower bias than health traits with low heritability. To achieve a similar accuracy for the health traits probably more records will be needed.},
author = {Luan, Tu and Woolliams, John A. and Lien, Sigbj{\o}rn and Kent, Matthew and Svendsen, Morten and Meuwissen, Theo H. E.},
doi = {10.1534/genetics.109.107391},
isbn = {0016-6731},
issn = {0016-6731},
journal = {Genetics},
keywords = {GWAS,stats},
mendeley-groups = {Thesis},
mendeley-tags = {GWAS,stats},
pages = {1119--1126},
pmid = {19704013},
title = {{The Accuracy of Genomic Selection in Norwegian Red Cattle Assessed by Cross-Validation}},
volume = {183},
year = {2009}
}

@article{Patterson1971,
author = {Patterson, H. D. and Thompson, R.},
doi = {10.2307/2334389},
issn = {00063444},
journal = {Biometrika},
mendeley-groups = {Thesis},
month = dec,
number = {3},
pages = {545--554},
title = {{Recovery of Inter-Block Information when Block Sizes are Unequal}},
url = {http://www.jstor.org/stable/2334389},
volume = {58},
year = {1971}
}

@article{Robinson1991,
author = {Robinson, G. K.},
doi = {10.1214/ss/1177011926},
issn = {2168-8745},
journal = {Stat. Sci.},
keywords = {Best linear unbiased predition (BLUP),Kalman filtering,credibility theory,estimation of random effects,fixed versus random effects,foundations of statistics,likelihood,parametric empirical Bayes methods,ranking and selection,selection index,small-area estimation},
language = {EN},
mendeley-groups = {Statistics,Thesis},
month = feb,
number = {1},
pages = {15--32},
publisher = {Institute of Mathematical Statistics},
title = {{That BLUP is a Good Thing: The Estimation of Random Effects}},
url = {http://projecteuclid.org/euclid.ss/1177011926},
volume = {6},
year = {1991}
}

@article{Legarra2008,
abstract = {Selection plans in plant and animal breeding are driven by genetic evaluation. Recent developments suggest using massive genetic marker information, known as "genomic selection." There is little evidence of its performance, though. We empirically compared three strategies for selection: (1) use of pedigree and phenotypic information, (2) use of genomewide markers and phenotypic information, and (3) the combination of both. We analyzed four traits from a heterogeneous mouse population (http://gscan.well.ox.ac.uk/), including 1884 individuals and 10,946 SNP markers. We used linear mixed models, using extensions of association analysis. Cross-validation techniques were used, providing assumption-free estimates of predictive ability. Sampling of validation and training data sets was carried out across and within families, which allows comparing across- and within-family information. Use of genomewide genetic markers increased predictive ability up to 0.22 across families and up to 0.03 within families. The latter is not statistically significant. These values are roughly comparable to increases of up to 0.57 (across family) and 0.14 (within family) in accuracy of prediction of genetic value. In this data set, within-family information was more accurate than across-family information, and populational linkage disequilibrium was not a completely accurate source of information for genetic evaluation. This fact questions some applications of genomic selection.},
author = {Legarra, Andr\'{e}s and Robert-Grani\'{e}, Christ\`{e}le and Manfredi, Eduardo and Elsen, Jean-Michel},
doi = {10.1534/genetics.108.088575},
file = {::},
issn = {0016-6731},
journal = {Genetics},
keywords = {Algorithms,Animals,Crosses, Genetic,Genetic Markers,Genome,Genomics,Mice,Models, Biological,Models, Genetic,Models, Statistical,Models, Theoretical,Phenotype,Polymorphism, Single Nucleotide,Reproducibility of Results,Selection, Genetic},
mendeley-groups = {Thesis},
month = sep,
number = {1},
pages = {611--8},
pmid = {18757934},
title = {{Performance of genomic selection in mice.}},
url = {http://www.genetics.org/content/180/1/611.long},
volume = {180},
year = {2008}
}

@article{GO2000,
abstract = {Genomic sequencing has made it clear that a large fraction of the genes specifying the core biological functions are shared by all eukaryotes. Knowledge of the biological role of such shared proteins in one organism can often be transferred to other organisms. The goal of the Gene Ontology Consortium is to produce a dynamic, controlled vocabulary that can be applied to all eukaryotes even as knowledge of gene and protein roles in cells is accumulating and changing. To this end, three independent ontologies accessible on the World-Wide Web (http://www.geneontology.org) are being constructed: biological process, molecular function and cellular component.},
author = {{The Gene Ontology Consortium}},
doi = {10.1038/75556},
journal = {Nat. Genet.},
mendeley-groups = {DGRP genomic features},
number = {1},
pages = {25--29},
title = {{Gene ontology: Tool for the unification of biology.}},
url = {http://www.nature.com/ng/journal/v25/n1/full/ng0500\_25.html},
volume = {25},
year = {2000}
}

@article{Tweedie2009,
abstract = {FlyBase (http://flybase.org) is a database of Drosophila genetic and genomic information. Gene Ontology (GO) terms are used to describe three attributes of wild-type gene products: their molecular function, the biological processes in which they play a role, and their subcellular location. This article describes recent changes to the FlyBase GO annotation strategy that are improving the quality of the GO annotation data. Many of these changes stem from our participation in the GO Reference Genome Annotation Project--a multi-database collaboration producing comprehensive GO annotation sets for 12 diverse species.},
author = {Tweedie, Susan and Ashburner, Michael and Falls, Kathleen and Leyland, Paul and McQuilton, Peter and Marygold, Steven and Millburn, Gillian and Osumi-Sutherland, David and Schroeder, Andrew and Seal, Ruth and Zhang, Haiyan},
doi = {10.1093/nar/gkn788},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/Nucleic acids research/Tweedie et al. - 2009 - FlyBase enhancing Drosophila Gene Ontology annotations.pdf:pdf},
issn = {1362-4962},
journal = {Nucleic Acids Res.},
keywords = {Animals,Databases, Genetic,Drosophila,Drosophila Proteins,Drosophila Proteins: genetics,Drosophila: genetics,Genes, Insect,Genome, Insect,Genomics,Vocabulary, Controlled},
mendeley-groups = {DGRP genomic features},
month = jan,
number = {Database issue},
pages = {D555--9},
pmid = {18948289},
title = {{FlyBase: enhancing Drosophila Gene Ontology annotations.}},
url = {http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=2686450\&tool=pmcentrez\&rendertype=abstract},
volume = {37},
year = {2009}
}

@misc{orgDmdb2013,
note = {R package version 2.13.1},
author = {Carlson, Marc},
mendeley-groups = {DGRP genomic features},
title = {{org.Dm.eg.db: Genome wide annotation for Fly}},
year = {2013}
}


@article{Ehsani2012,
author = {Ehsani, Alireza and S{\o}rensen, Peter and Pomp, Daniel and Allan, Mark and Janss, Luc},
doi = {10.1186/1471-2164-13-456},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/BMC genomics/Ehsani et al. - 2012 - Inferring genetic architecture of complex traits using Bayesian integrative analysis of genome and transcriptome.pdf:pdf},
issn = {1471-2164},
journal = {BMC Genomics},
keywords = {Animals,Bayes Theorem,Body Weight,Body Weight: genetics,Crosses, Genetic,Eating,Eating: genetics,Genetic Variation,Genome,Genome: genetics,Genome: physiology,Mice,Models, Genetic,Phenotype,Polymorphism, Single Nucleotide,Polymorphism, Single Nucleotide: genetics,Quantitative Trait Loci,Quantitative Trait Loci: genetics,Transcriptome,Transcriptome: genetics,Transcriptome: physiology},
mendeley-groups = {DGRP genomic features},
month = jan,
number = {1},
pages = {456},
pmid = {22950759},
title = {{Inferring genetic architecture of complex traits using Bayesian integrative analysis of genome and transcriptome data.}},
url = {http://www.biomedcentral.com/1471-2164/13/456},
volume = {13},
year = {2012}
}

@article{Skarman2012,
author = {Skarman, Axel and Shariati, Mohammad and Janss, Luc and Jiang, Li and S{\o}rensen, Peter},
doi = {10.1186/1471-2105-13-73},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/BMC Bioinformatics/Skarman et al. - 2012 - A Bayesian variable selection procedure to rank overlapping gene sets.pdf:pdf},
issn = {1471-2105},
journal = {BMC Bioinformatics},
keywords = {KEGG},
mendeley-groups = {DGRP genomic features},
mendeley-tags = {KEGG},
number = {1},
pages = {73},
title = {{A Bayesian variable selection procedure to rank overlapping gene sets}},
url = {http://www.biomedcentral.com/1471-2105/13/73},
volume = {13},
year = {2012}
}

@article{Shmueli2010,
archivePrefix = {arXiv},
arxivId = {arXiv:1101.0891v1},
author = {Shmueli, Galit},
doi = {10.1214/10-STS330},
eprint = {arXiv:1101.0891v1},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/Statistical Science/Shmueli - 2010 - To Explain or to Predict.pdf:pdf},
issn = {0883-4237},
journal = {Stat. Sci.},
keywords = {Explanatory modeling, causality, predictive modeli,and phrases,causality,data mining,explanatory modeling,modeling,predictive,predictive power,scientific,statistical strategy},
mendeley-groups = {DGRP genomic features},
month = aug,
number = {3},
pages = {289--310},
title = {{To Explain or to Predict?}},
url = {http://projecteuclid.org/euclid.ss/1294167961},
volume = {25},
year = {2010}
}
@article{DeLosCampos2013,
abstract = {Despite important advances from Genome Wide Association Studies (GWAS), for most complex human traits and diseases, a sizable proportion of genetic variance remains unexplained and prediction accuracy (PA) is usually low. Evidence suggests that PA can be improved using Whole-Genome Regression (WGR) models where phenotypes are regressed on hundreds of thousands of variants simultaneously. The Genomic Best Linear Unbiased Prediction (G-BLUP, a ridge-regression type method) is a commonly used WGR method and has shown good predictive performance when applied to plant and animal breeding populations. However, breeding and human populations differ greatly in a number of factors that can affect the predictive performance of G-BLUP. Using theory, simulations, and real data analysis, we study the performance of G-BLUP when applied to data from related and unrelated human subjects. Under perfect linkage disequilibrium (LD) between markers and QTL, the prediction R-squared (R(2)) of G-BLUP reaches trait-heritability, asymptotically. However, under imperfect LD between markers and QTL, prediction R(2) based on G-BLUP has a much lower upper bound. We show that the minimum decrease in prediction accuracy caused by imperfect LD between markers and QTL is given by (1-b)(2), where b is the regression of marker-derived genomic relationships on those realized at causal loci. For pairs of related individuals, due to within-family disequilibrium, the patterns of realized genomic similarity are similar across the genome; therefore b is close to one inducing small decrease in R(2). However, with distantly related individuals b reaches very low values imposing a very low upper bound on prediction R(2). Our simulations suggest that for the analysis of data from unrelated individuals, the asymptotic upper bound on R(2) may be of the order of 20\% of the trait heritability. We show how PA can be enhanced with use of variable selection or differential shrinkage of estimates of marker effects.},
author = {{de Los Campos}, Gustavo and Vazquez, Ana I and Fernando, Rohan and Klimentidis, Yann C and Sorensen, Daniel},
doi = {10.1371/journal.pgen.1003608},
file = {::},
issn = {1553-7404},
journal = {PLoS Genet.},
keywords = {Breeding,Genome,Genome-Wide Association Study,Humans,Linkage Disequilibrium,Models, Theoretical,Peter's references,Phenotype,Polymorphism, Single Nucleotide,Quantitative Trait Loci,Regression Analysis,Selection, Genetic},
mendeley-groups = {DGRP genomic features},
mendeley-tags = {Peter's references},
month = jan,
number = {7},
pages = {e1003608},
pmid = {23874214},
publisher = {Public Library of Science},
title = {{Prediction of complex human traits using the genomic best linear unbiased predictor.}},
url = {http://www.plosgenetics.org/article/info\%3Adoi\%2F10.1371\%2Fjournal.pgen.1003608;jsessionid=D8C15D3D5977C8ECBF72836D61FDBBBC},
volume = {9},
year = {2013}

}
@article{Goeman2007,
abstract = {MOTIVATION: Many statistical tests have been proposed in recent years for analyzing gene expression data in terms of gene sets, usually from Gene Ontology. These methods are based on widely different methodological assumptions. Some approaches test differential expression of each gene set against differential expression of the rest of the genes, whereas others test each gene set on its own. Also, some methods are based on a model in which the genes are the sampling units, whereas others treat the subjects as the sampling units. This article aims to clarify the assumptions behind different approaches and to indicate a preferential methodology of gene set testing. RESULTS: We identify some crucial assumptions which are needed by the majority of methods. P-values derived from methods that use a model which takes the genes as the sampling unit are easily misinterpreted, as they are based on a statistical model that does not resemble the biological experiment actually performed. Furthermore, because these models are based on a crucial and unrealistic independence assumption between genes, the P-values derived from such methods can be wildly anti-conservative, as a simulation experiment shows. We also argue that methods that competitively test each gene set against the rest of the genes create an unnecessary rift between single gene testing and gene set testing.},
author = {Goeman, Jelle J. and B\"{u}hlmann, Peter},
doi = {10.1093/bioinformatics/btm051},
issn = {1367-4803, 1460-2059},
journal = {Bioinformatics},
keywords = {Algorithms,Artifacts,Competitive tests,Competitive vs. self-contained,Data Interpretation,Databases,Gene Expression Profiling,Gene Expression Profiling: methods,Genetic,Information Storage and Retrieval,Information Storage and Retrieval: methods,Reproducibility of Results,Sensitivity and Specificity,Statistical,permutation,self-contained},
mendeley-groups = {Statistics,DGRP genomic features},
mendeley-tags = {Competitive tests,Competitive vs. self-contained,permutation,self-contained},
month = feb,
number = {8},
pages = {980--987},
pmid = {17303618},
shorttitle = {Analyzing gene expression data in terms of gene se},
title = {{Analyzing gene expression data in terms of gene sets: methodological issues}},
url = {http://bioinformatics.oxfordjournals.org/cgi/doi/10.1093/bioinformatics/btm051},
volume = {23},
year = {2007}
}

@article{Riquet1999,
abstract = {We previously mapped a quantitative trait locus (QTL) affecting milk production to bovine chromosome 14. To refine the map position of this QTL, we have increased the density of the genetic map of BTA14q11-16 by addition of nine microsatellites and three single nucleotide polymorphisms. Fine-mapping of the QTL was accomplished by a two-tiered approach. In the first phase, we identified seven sires heterozygous "Qq" for the QTL by marker-assisted segregation analysis in a Holstein-Friesian pedigree comprising 1,158 individuals. In a second phase, we genotyped the seven selected sires for the newly developed high-density marker map and searched for a shared haplotype flanking an hypothetical, identical-by-descent QTL allele with large substitution effect. The seven chromosomes increasing milk fat percentage were indeed shown to carry a common chromosome segment with an estimated size of 5 cM predicted to contain the studied QTL. The same haplotype was shown to be associated with increased fat percentage in the general population as well, providing additional support in favor of the location of the QTL within the corresponding interval.},
author = {Riquet, J. and Coppieters, W. and Cambisano, N. and Arranz, J.-J. and Berzi, P. and Davis, S. K. and Grisart, B. and Farnir, F. and Karim, L. and Mni, M. and Simon, P. and Taylor, J. F. and Vanmanshoven, P. and Wagenaar, D. and Womack, J. E. and Georges, M.},
doi = {10.1073/pnas.96.16.9252},
issn = {0027-8424},
journal = {Proc. Natl. Acad. Sci.},
keywords = {Holstein population size},
mendeley-groups = {DGRP genomic features},
mendeley-tags = {Holstein population size},
month = aug,
number = {16},
pages = {9252--9257},
title = {{Fine-mapping of quantitative trait loci by identity by descent in outbred populations: Application to milk production in dairy cattle}},
url = {http://www.pnas.org/content/96/16/9252.full},
volume = {96},
year = {1999}
}
@article{Jiang2007,
abstract = {MOTIVATION: Gene Set Enrichment Analysis (GSEA) has been developed recently to capture changes in the expression of pre-defined sets of genes. We propose number of extensions to GSEA, including the use of different statistics to describe the association between genes and phenotypes of interest. We make use of dimension reduction procedures, such as principle component analysis, to identify gene sets with correlated expression. We also address issues that arise when gene sets overlap. RESULTS: Our proposals extend the range of applicability of GSEA and allow for adjustments based on other covariates. We have provided a well-defined procedure to address interpretation issues that can raise when gene sets have substantial overlap. We have shown how standard dimension reduction methods, such as PCA, can be used to help further interpret GSEA. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.},
author = {Jiang, Zhen and Gentleman, Robert},
doi = {10.1093/bioinformatics/btl599},
issn = {1367-4811},
journal = {Bioinformatics},
keywords = {Algorithms,Cell Physiological Phenomena,Gene Expression,Gene Expression Profiling,Gene Expression Profiling: methods,Gene Expression Regulation,Gene Expression Regulation: physiology,Gene Expression: physiology,Oligonucleotide Array Sequence Analysis,Oligonucleotide Array Sequence Analysis: methods,Proteome,Proteome: metabolism},
mendeley-groups = {DGRP genomic features},
month = feb,
number = {3},
pages = {306--13},
pmid = {17127676},
title = {{Extensions to gene set enrichment.}},
url = {http://bioinformatics.oxfordjournals.org/content/23/3/306.long},
volume = {23},
year = {2007}
}

@unpublished{manuscript1,
note = {Manuscript in review.},
author = {Edwards, Stefan McKinnon and Thomsen, Bo and Madsen, Per and S{\o}rensen, Peter},
mendeley-groups = {Manuscript1,DGRP genomic features},
pages = {26},
title = {{Partitioning of Genomic Variance Reveals Biological Pathways Associated with Udder Health and Milk Production Traits in Dairy Cattle}},
year = {2014}
}

@article{Ayroles2009,
abstract = {Determining the genetic architecture of complex traits is challenging because phenotypic variation arises from interactions between multiple, environmentally sensitive alleles. We quantified genome-wide transcript abundance and phenotypes for six ecologically relevant traits in D. melanogaster wild-derived inbred lines. We observed 10,096 genetically variable transcripts and high heritabilities for all organismal phenotypes. The transcriptome is highly genetically intercorrelated, forming 241 transcriptional modules. Modules are enriched for transcripts in common pathways, gene ontology categories, tissue-specific expression and transcription factor binding sites. The high degree of transcriptional connectivity allows us to infer genetic networks and the function of predicted genes from annotations of other genes in the network. Regressions of organismal phenotypes on transcript abundance implicate several hundred candidate genes that form modules of biologically meaningful correlated transcripts affecting each phenotype. Overlapping transcripts in modules associated with different traits provide insight into the molecular basis of pleiotropy between complex traits.},
author = {Ayroles, Julien F. and Carbone, Mary Anna and Stone, Eric A. and Jordan, Katherine W. and Lyman, Richard F. and Magwire, Michael M. and Rollmann, Stephanie M. and Duncan, Laura H. and Lawrence, Faye and Anholt, Robert R. H. and Mackay, Trudy F. C.},
doi = {10.1038/ng.332},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/Nature genetics/Ayroles et al. - 2009 - Systems genetics of complex traits in Drosophila melanogaster.pdf:pdf},
issn = {1546-1718},
journal = {Nat. Genet.},
keywords = {Amino Acid,Amino Acid Sequence,Animals,Base Sequence,Chromosome Mapping,Drosophila melanogaster,Drosophila melanogaster: genetics,Female,Gene Regulatory Networks,Gene Regulatory Networks: physiology,Genetic Variation,Genetic Variation: physiology,Genetics,Heritable,Inbred Strains,Male,Messenger,Messenger: analysis,Messenger: genetics,Messenger: metabolism,Molecular Sequence Data,Phenotype,Population,Population: methods,Quantitative Trait,RNA,Sequence Homology,Tissue Distribution,fruitflies},
mendeley-tags = {fruitflies},
month = mar,
number = {3},
pages = {299--307},
pmid = {19234471},
publisher = {Nature Publishing Group},
shorttitle = {Nat Genet},
title = {{Systems genetics of complex traits in \textit{Drosophila melanogaster}.}},
url = {http://dx.doi.org/10.1038/ng.332},
volume = {41},
year = {2009}
}

@article{Ayyaz2013,
abstract = {Drosophila melanogaster is a useful model to investigate mucosal immunity. The immune response to intestinal infections is mediated partly by the Immune deficiency (IMD) pathway, which only gets activated by a type of peptidoglycan lacking in several medically important Gram-positive bacterial species such as Staphylococcus. Thus, the intestinal host defense against such bacterial strains remains poorly known. Here, we have used Staphylococcus xylosus to develop a model of intestinal infections by Gram-positive bacteria. S. xylosus behaves as an opportunistic pathogen in a septic injury model, being able to kill only flies immunodeficient either for the Toll pathway or the cellular response. When ingested, it is controlled by IMD-independent host intestinal defenses, yet flies eventually die. Having excluded an overreaction of the immune response and the action of toxins, we find that flies actually succumb to starvation, likely as a result of a competition for sucrose between the bacteria and the flies. Fat stores of wild-type flies are severely reduced within a day, a period when sucrose is not yet exhausted in the feeding solution. Interestingly, the Toll pathway mutant MyD88 is more resistant to the ingestion of S. xylosus and to starvation than wild-type flies. MyD88 flies do not rapidly deplete their fat stores when starved, in contrast to wild-type flies. Thus, we have uncovered a novel function of MyD88 in the regulation of metabolism that appears to be independent of its known roles in immunity and development.},
author = {Ayyaz, Arshad and Giammarinaro, Philippe and Li\'{e}geois, Samuel and Lestradet, Matthieu and Ferrandon, Dominique},
doi = {10.1016/j.imbio.2012.07.027},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/Immunobiology/Ayyaz et al. - 2013 - A negative role for MyD88 in the resistance to starvation as revealed in an intestinal infection of Drosophila mel.pdf:pdf},
issn = {1878-3279},
journal = {Immunobiology},
keywords = {Adaptor Proteins, Signal Transducing,Adaptor Proteins, Signal Transducing: genetics,Adaptor Proteins, Signal Transducing: immunology,Adaptor Proteins, Signal Transducing: metabolism,Animals,Antigens, Differentiation,Antigens, Differentiation: genetics,Antigens, Differentiation: immunology,Antigens, Differentiation: metabolism,Disease Models, Animal,Drosophila Proteins,Drosophila Proteins: genetics,Drosophila Proteins: immunology,Drosophila Proteins: metabolism,Drosophila melanogaster,Immunity, Innate,Immunity, Mucosal,Intestinal Diseases,Intestinal Diseases: genetics,Intestinal Diseases: immunology,Intestinal Diseases: metabolism,Intestinal Diseases: microbiology,Intestinal Diseases: pathology,Mutation,Pernille's reference,Receptors, Immunologic,Receptors, Immunologic: genetics,Receptors, Immunologic: immunology,Receptors, Immunologic: metabolism,Staphylococcal Infections,Staphylococcal Infections: genetics,Staphylococcal Infections: immunology,Staphylococcal Infections: metabolism,Staphylococcal Infections: pathology,Staphylococcus,Staphylococcus: immunology,Starvation,Starvation: genetics,Starvation: immunology,Starvation: metabolism,Starvation: microbiology,Starvation: pathology,Toll-Like Receptors,Toll-Like Receptors: genetics,Toll-Like Receptors: immunology,Toll-Like Receptors: metabolism},
mendeley-groups = {DGRP genomic features},
mendeley-tags = {Pernille's reference},
month = apr,
number = {4},
pages = {635--44},
pmid = {23083631},
title = {{A negative role for MyD88 in the resistance to starvation as revealed in an intestinal infection of \textit{Drosophila melanogaster} with the Gram-positive bacterium \textit{Staphylococcus xylosus}.}},
url = {http://www.sciencedirect.com/science/article/pii/S017129851200191X},
volume = {218},
year = {2013}
}
@article{Kahsai2010,
abstract = {In Drosophila, neurosecretory cells that release peptide hormones play a prominent role in the regulation of development, growth, metabolism, and reproduction. Several types of peptidergic neurosecretory cells have been identified in the brain of Drosophila with release sites in the corpora cardiaca and anterior aorta. We show here that in adult flies the products of three neuropeptide precursors are colocalized in five pairs of large protocerebral neurosecretory cells in two clusters (designated ipc-1 and ipc-2a): Drosophila tachykinin (DTK), short neuropeptide F (sNPF) and ion transport peptide (ITP). These peptides were detected by immunocytochemistry in combination with GFP expression driven by the enhancer trap Gal4 lines c929 and Kurs-6, both of which are expressed in ipc-1 and 2a cells. This mix of colocalized peptides with seemingly unrelated functions is intriguing and prompted us to initiate analysis of the function of the ten neurosecretory cells. We investigated the role of peptide signaling from large ipc-1 and 2a cells in stress responses by monitoring the effect of starvation and desiccation in flies with levels of DTK or sNPF diminished by RNA interference. Using the Gal4-UAS system we targeted the peptide knockdown specifically to ipc-1 and 2a cells with the c929 and Kurs-6 drivers. Flies with reduced DTK or sNPF levels in these cells displayed decreased survival time at desiccation and starvation, as well as increased water loss at desiccation. Our data suggest that homeostasis during metabolic stress requires intact peptide signaling by ipc-1 and 2a neurosecretory cells.},
author = {Kahsai, Lily and Kapan, Neval and Dircksen, Heinrich and Winther, Asa M. E. and N\"{a}ssel, Dick R.},
doi = {10.1371/journal.pone.0011480},
editor = {Callaerts, Patrick},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/PloS ONE/Kahsai et al. - 2010 - Metabolic stress responses in Drosophila are modulated by brain neurosecretory cells that produce multiple neurop.pdf:pdf},
issn = {1932-6203},
journal = {PLoS ONE},
keywords = {Animals,Brain,Brain: cytology,Brain: metabolism,Drosophila,Drosophila Proteins,Drosophila Proteins: genetics,Drosophila Proteins: metabolism,Immunohistochemistry,Motor Activity,Motor Activity: genetics,Motor Activity: physiology,Neuropeptides,Neuropeptides: genetics,Neuropeptides: metabolism,Neurosecretion,Neurosecretion: physiology,Pernille's reference,Starvation,Starvation: genetics,Starvation: metabolism,Tachykinins,Tachykinins: genetics,Tachykinins: metabolism},
mendeley-groups = {DGRP genomic features},
mendeley-tags = {Pernille's reference},
month = jan,
number = {7},
pages = {e11480},
pmid = {20628603},
publisher = {Public Library of Science},
title = {{Metabolic stress responses in \textit{Drosophila} are modulated by brain neurosecretory cells that produce multiple neuropeptides.}},
url = {http://dx.plos.org/10.1371/journal.pone.0011480},
volume = {5},
year = {2010}
}
@article{Kapan2012,
abstract = {Insulin/IGF-like signaling regulates the development, growth, fecundity, metabolic homeostasis, stress resistance and lifespan in worms, flies and mammals. Eight insulin-like peptides (DILP1-8) are found in Drosophila. Three of these (DILP2, 3 and 5) are produced by a set of median neurosecretory cells (insulin-producing cells, IPCs) in the brain. Activity in the IPCs of adult flies is regulated by glucose and several neurotransmitters and neuropeptides. One of these, short neuropeptide F (sNPF), regulates food intake, growth and Dilp transcript levels in IPCs via the sNPF receptor (sNPFR1) expressed on IPCs. Here we identify a set of brain neurons that utilizes sNPF to activate the IPCs. These sNPF-expressing neurons (dorsal lateral peptidergic neurons, DLPs) also produce the neuropeptide corazonin (CRZ) and have axon terminations impinging on IPCs. Knockdown of either sNPF or CRZ in DLPs extends survival in flies exposed to starvation and alters carbohydrate and lipid metabolism. Expression of sNPF in DLPs in the sNPF mutant background is sufficient to rescue wild-type metabolism and response to starvation. Since CRZ receptor RNAi in IPCs affects starvation resistance and metabolism, similar to peptide knockdown in DLPs, it is likely that also CRZ targets the IPCs. Knockdown of sNPF, but not CRZ in DLPs decreases transcription of Dilp2 and 5 in the brain, suggesting different mechanisms of action on IPCs of the two co-released peptides. Our findings indicate that sNPF and CRZ co-released from a small set of neurons regulate IPCs, stress resistance and metabolism in adult Drosophila.},
author = {Kapan, Neval and Lushchak, Oleh V. and Luo, Jiangnan and N\"{a}ssel, Dick R.},
doi = {10.1007/s00018-012-1097-z},
issn = {1420-9071},
journal = {Cell. Mol. Life Sci.},
keywords = {Pernille's reference},
mendeley-groups = {DGRP genomic features},
mendeley-tags = {Pernille's reference},
month = jul,
pmid = {22828865},
title = {{Identified peptidergic neurons in the \textit{Drosophila} brain regulate insulin-producing cells, stress responses and metabolism by coexpressed short neuropeptide F and corazonin.}},
url = {http://www.ncbi.nlm.nih.gov/pubmed/22828865},
year = {2012}
}
@article{Maman2013,
abstract = {In the nematode Caenorhabditis elegans, the heat shock response (HSR) is regulated at the organismal level by a network of thermosensory neurons that senses elevated temperatures and activates the HSR in remote tissues. Which neuronal receptors are required for this signaling mechanism and in which neurons they function are largely unanswered questions. Here we used worms that were engineered to exhibit RNA interference hypersensitivity in neurons to screen for neuronal receptors that are required for the activation of the HSR and identified a putative G-protein coupled receptor (GPCR) as a novel key component of this mechanism. This gene, which we termed GPCR thermal receptor 1 (gtr-1), is expressed in chemosensory neurons and has no role in heat sensing but is critically required for the induction of genes that encode heat shock proteins in non-neural tissues upon exposure to heat. Surprisingly, the knock-down of gtr-1 by RNA interference protected worms expressing the Alzheimer's-disease-linked aggregative peptide A$\beta$3-42 from proteotoxicity but had no effect on lifespan. This study provides several novel insights: (1) it shows that chemosensory neurons play important roles in the nematode's HSR-regulating mechanism, (2) it shows that lifespan and heat stress resistance are separable, and (3) it strengthens the emerging notion that the ability to respond to heat comes at the expense of protein homeostasis (proteostasis).},
author = {Maman, Moria and {Carvalhal Marques}, Filipa and Volovik, Yuli and Dubnikov, Tatyana and Bejerano-Sagie, Michal and Cohen, Ehud},
doi = {10.1523/JNEUROSCI.4023-12.2013},
issn = {1529-2401},
journal = {J. Neurosci.},
keywords = {Amyloid beta-Peptides,Amyloid beta-Peptides: metabolism,Animal,Animals,Bacterial Infections,Bacterial Infections: prevention \& control,Caenorhabditis elegans,Caenorhabditis elegans Proteins,Caenorhabditis elegans Proteins: genetics,Eggs,G-Protein-Coupled,G-Protein-Coupled: genetics,G-Protein-Coupled: metabolism,Gene Expression Regulation,Gene Expression Regulation: genetics,Gene Expression Regulation: physiology,Genetically Modified,Green Fluorescent Proteins,Green Fluorescent Proteins: genetics,Green Fluorescent Proteins: metabolism,Heat-Shock Proteins,Heat-Shock Proteins: genetics,Heat-Shock Proteins: metabolism,Heat-Shock Response,Heat-Shock Response: genetics,Heat-Shock Response: physiology,Hot Temperature,Messenger,Messenger: genetics,Muscles,Muscles: metabolism,Mutation,Mutation: genetics,Neurons,Neurons: metabolism,Paralysis,Paralysis: genetics,Peptide Fragments,Peptide Fragments: metabolism,Pernille's reference,Physiological,Physiological: genetics,Physiological: physiology,Plant Lectins,Plant Lectins: genetics,Plant Lectins: metabolism,RNA,RNA Interference,Receptors,Sexual Behavior,Signal Transduction,Signal Transduction: genetics,Signal Transduction: physiology,Stress,Thermosensing,Thermosensing: genetics,Thermosensing: physiology,Transcription Factors,Transcription Factors: genetics,Transcription Factors: metabolism},
mendeley-groups = {DGRP genomic features},
mendeley-tags = {Pernille's reference},
month = apr,
number = {14},
pages = {6102--11},
pmid = {23554491},
title = {{A neuronal GPCR is critical for the induction of the heat shock response in the nematode C. elegans.}},
url = {http://www.jneurosci.org/content/33/14/6102},
volume = {33},
year = {2013}
}
@article{Rion2007,
abstract = {Most animals face periods of food shortage and are thus expected to evolve adaptations enhancing starvation resistance (SR). Most of our knowledge of the genetic and physiological bases of those adaptations, their evolutionary correlates and trade-offs, and patterns of within- and among-population variation, comes from studies on Drosophila. In this review, we attempt to synthesize the various facets of evolutionary biology of SR emerging from those studies. Heritable variation for SR is ubiquitous in Drosophila populations, allowing for large responses to experimental selection. Individual flies can also inducibly increase their SR in response to mild nutritional stress (dietary restriction). Both the evolutionary change and the physiological plasticity involve increased accumulation of lipids, changes in carbohydrate and lipid metabolism and reduction in reproduction. They are also typically associated with greater resistance to desiccation and oxidative stress, and with prolonged development and lifespan. These responses are increasingly seen as facets of a shift of the physiology towards a 'survival mode', which helps the animal to survive hard times. The last decade has seen a great progress in revealing the molecular bases of induced responses to starvation, and the first genes contributing to genetic variation in SR have been identified. In contrast, little progress has been made in understanding the ecological significance of SR in Drosophila; in particular it remains unclear to what extent geographical variation in SR reflect differences in natural selection acting on this trait rather than correlated responses to selection on other traits. Drosophila offers a unique opportunity for an integrated study of the manifold aspects of adaptation to nutritional stress. Given that at least some major molecular mechanisms of response to nutritional stress seem common to animals, the insights from Drosophila are likely to apply more generally than just to dipterans or insects.},
author = {Rion, S. and Kawecki, T. J.},
doi = {10.1111/j.1420-9101.2007.01405.x},
issn = {1010-061X},
journal = {J. Evol. Biol.},
keywords = {Adaptation,Animals,Biological,Biological Evolution,Drosophila melanogaster,Drosophila melanogaster: genetics,Drosophila melanogaster: physiology,Food Deprivation,Genetic Variation,Pernille's reference},
mendeley-groups = {DGRP genomic features},
mendeley-tags = {Pernille's reference},
month = sep,
number = {5},
pages = {1655--64},
pmid = {17714282},
title = {{Evolutionary biology of starvation resistance: what we have learned from \textit{Drosophila}.}},
url = {http://www.ncbi.nlm.nih.gov/pubmed/17714282},
volume = {20},
year = {2007}
}
@article{Sarup2011,
abstract = {Whole genome transcriptomic studies can point to potential candidate genes for organismal traits. However, the importance of potential candidates is rarely followed up through functional studies and/or by comparing results across independent studies. We have analysed the overlap of candidate genes identified from studies of gene expression in Drosophila melanogaster using similar technical platforms. We found little overlap across studies between putative candidate genes for the same traits in the same sex. Instead there was a high degree of overlap between different traits and sexes within the same genetic backgrounds. Putative candidates found using transcriptomics therefore appear very sensitive to genetic background and this can mask or override effects of treatments. The functional importance of putative candidate genes emerging from transcriptome studies needs to be validated through additional experiments and in future studies we suggest a focus on the genes, networks and pathways affecting traits in a consistent manner across backgrounds.},
author = {Sarup, Pernille and S{\o}rensen, Jesper G. and Kristensen, Torsten N. and Hoffmann, Ary A. and Loeschcke, Volker and Paige, Ken N. and S{\o}rensen, Peter},
doi = {10.1371/journal.pone.0015644},
editor = {Michalak, Pawel},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/PloS ONE/Sarup et al. - 2011 - Candidate genes detected in transcriptome studies are strongly dependent on genetic background.pdf:pdf},
issn = {1932-6203},
journal = {PLoS ONE},
keywords = {Animals,Drosophila melanogaster,Drosophila melanogaster: genetics,Gene Expression Profiling,Gene Expression Profiling: standards,Genes,Insect,Observer Variation,Pernille's reference},
mendeley-groups = {DGRP genomic features},
mendeley-tags = {Pernille's reference},
month = jan,
number = {1},
pages = {e15644},
pmid = {21283582},
publisher = {Public Library of Science},
title = {{Candidate genes detected in transcriptome studies are strongly dependent on genetic background.}},
url = {http://dx.plos.org/10.1371/journal.pone.0015644},
volume = {6},
year = {2011}
}
@article{Lochmiller2000,
     jstor_articletype = {research-article},
     title = {Trade-Offs in Evolutionary Immunology: Just What Is the Cost of Immunity?},
     author = {Lochmiller, Robert L. and Deerenberg, Charlotte},
     journal = {Oikos},
     jstor_issuetitle = {},
     volume = {88},
     number = {1},
     jstor_formatteddate = {Jan., 2000},
     pages = {pp. 87-98},
     url = {http://www.jstor.org/stable/3546398},
     ISSN = {00301299},
     language = {English},
     year = {2000},
     publisher = {Wiley on behalf of Nordic Society Oikos},
     copyright = {Copyright © 2000 Nordic Society Oikos},
    }
@article{Sorensen2007,
abstract = {Here, we report a detailed analysis of changes in gene expression in Drosophila melanogaster selected for ecologically relevant environmental stress resistance traits. We analysed females from seven replicated selection regimes and one control regime using whole genome gene expression arrays. When compared with gene expression profiles of control lines, we were able to detect consistent selection responses at the transcript level in each specific selection regime and also found a group of differentially expressed genes that were changed among all selected lines. Replicated selection lines showed similar changes in gene expression (compared with controls) and thus showed that 10 generations of artificial selection give a clear signal with respect to the resulting gene expression profile. The changes in gene expression in lines selected for increased longevity, desiccation and starvation resistance, respectively, showed high similarities. Cold resistance-selected lines showed little differentiation from controls. Different methods of heat selection (heat survival, heat knock down and constant 30 degrees C) showed little similarity verifying that different mechanisms are involved in high temperature adaptation. For most individual selection regimes, and in the comparison of all selected lines and controls, the gene expression changes were exclusively in one direction, although the different selection regimes varied in the direction of response. The responses to selection restricted to individual selection regimes can be interpreted as stress specific, whereas the response shared among all selected lines can be considered as a general stress response. Here, we identified genes belonging to both types of responses to selection for stress resistance.},
author = {S{\o}rensen, J G and Nielsen, M M and Loeschcke, V},
doi = {10.1111/j.1420-9101.2007.01326.x},
issn = {1010-061X},
journal = {J. Evol. Biol.},
keywords = {Animals,Drosophila melanogaster,Drosophila melanogaster: genetics,Drosophila melanogaster: physiology,Environment,Gene Expression Profiling,Genes,Genetic,Insect,Pernille's reference,Selection},
mendeley-groups = {DGRP genomic features},
mendeley-tags = {Pernille's reference},
month = jul,
number = {4},
pages = {1624--36},
pmid = {17584255},
title = {{Gene expression profile analysis of Drosophila melanogaster selected for resistance to environmental stressors.}},
url = {http://www.ncbi.nlm.nih.gov/pubmed/17584255},
volume = {20},
year = {2007}
}

@book{Hastie2009,
  address = {New York, NY, USA},
  author = {Hastie, Trevor and Tibshirani, Robert and Friedman, Jerome},
  doi = {10.1007/b94608},
  isbn = {978-0-387-84857-0},
  publisher = {Springer New York Inc.},
  series = {Springer Series in Statistics},
  title = {The Elements of Statistical Learning},
  year = {2009}
}

@book{SearleMatrix,
address = {Hoboken, New Jersey},
author = {Searle, Shayle R.},
edition = {1st},
isbn = {978-0-470-00961-1},
mendeley-groups = {Thesis},
pages = {476},
publisher = {{John Wiley \& Sons}},
title = {{Matrix Algebra Useful for Statistics}},
year = {1982},
note={Reprinted in 2006},
series = {Wiley Series in Probability and Statistics}
}
@book{SearleVC,
address = {Hoboken, New Jersey},
author = {Searle, Shayle R. and Casella, George and McCulloch, Charles E.},
isbn = {978-0-470-00959-8},
mendeley-groups = {Thesis},
pages = {536},
publisher = {{John Wiley \& Sons}},
title = {{Variance Components}},
year={1992},
note={Reprinted in 2006},
series = {Wiley Series in Probability and Statistics}
}

@phdthesis{Knight2008,
author = {Knight, Emma},
mendeley-groups = {Thesis},
pages = {298},
school = {School of Agriculture, Food and Wine, University of Adelaide},
title = {{Improved Iterative Schemes for REML Estimation of Variance Parameters in Linear Mixed Models}},
type = {PhD Thesis},
year = {2008}
}

@article{Misztal1994,
author = {Misztal, I.},
doi = {10.1111/j.1439-0388.1994.tb00473.x},
issn = {0931-2668},
journal = {J. Anim. Breed. Genet.},
mendeley-groups = {Thesis},
month = jan,
number = {1-6},
pages = {346--55},
pmid = {21395785},
title = {{Comparison of computing properties of derivative and derivative-free algorithms in variance-component estimation by REML.}},
url = {http://www.ncbi.nlm.nih.gov/pubmed/21395785},
volume = {111},
year = {1994}
}

@article{Powell2010,
author = {Powell, Joseph E. and Visscher, Peter M. and Goddard, Michael E.},
doi = {10.1038/nrg2865},
issn = {1471-0056},
journal = {Nat. Rev. Genet.},
keywords = {NOVA course},
mendeley-groups = {Thesis},
mendeley-tags = {NOVA course},
month = sep,
number = {11},
pages = {800--805},
title = {{Reconciling the analysis of IBD and IBS in complex trait studies}},
url = {http://www.nature.com/doifinder/10.1038/nrg2865},
volume = {11},
year = {2010}
}

@article{Peng2009,
author = {Peng, Roger D.}, 
title = {Reproducible research and Biostatistics},
volume = {10}, 
number = {3}, 
pages = {405-408}, 
year = {2009}, 
doi = {10.1093/biostatistics/kxp014}, 
URL = {http://biostatistics.oxfordjournals.org/content/10/3/405.short}, 
eprint = {http://biostatistics.oxfordjournals.org/content/10/3/405.full.pdf+html}, 
journal = {Biostatistics} 
}

@article{Baggerly2009,
journal = "Ann. Appl. Stat.",
author = "Baggerly, Keith A. and Coombes, Kevin R.",
doi = "10.1214/09-AOAS291",
ljournal = "The Annals of Applied Statistics",
month = "12",
number = "4",
pages = "1309--1334",
publisher = "The Institute of Mathematical Statistics",
title = "Deriving chemosensitivity from cell lines:
 Forensic bioinformatics and reproducible research in high-throughput
 biology",
url={http://projecteuclid.org/euclid.aoas/1267453942},
volume = "3",
year = "2009"
}

@article{Napolitano2013,
author = {Napolitano, Francesco and Mariani-Costantini, Renato and Tagliaferri, Roberto},
doi = {10.1186/1471-2105-14-201},
file = {::},
issn = {1471-2105},
journal = {BMC Bioinformatics},
keywords = {Computational Biology,Computational Biology: methods,DNA Copy Number Variations,Software},
mendeley-groups = {Software,Thesis},
month = jan,
number = {1},
pages = {201},
pmid = {23786315},
title = {{Bioinformatic pipelines in Python with Leaf.}},
url = {http://www.biomedcentral.com/1471-2105/14/201},
volume = {14},
year = {2013}
}

@article{Wilson2012,
abstract = {Scientists spend an increasing amount of time building and using software. However, most scientists are never taught how to do this efficiently. As a result, many are unaware of tools and practices that would allow them to write more reliable and maintainable code with less effort. We describe a set of best practices for scientific software development that have solid foundations in research and experience, and that improve scientists' productivity and the reliability of their software.},
archivePrefix = {arXiv},
arxivId = {1210.0530v4},
author = {Wilson, Greg and Aruliah, D. A. and Brown, C. Titus and Hong, Neil P. Chue and Davis, Matt and Guy, Richard T. and Haddock, Steven H. D. and Huff, Katy and Mitchell, Ian M. and Plumbley, Mark and Waugh, Ben and White, Ethan P. and Wilson, Paul},
eprint = {1210.0530v4},
journal = {CoRR},
month = sep,
pages = {18},
title = {{Best Practices for Scientific Computing}},
url = {http://arxiv.org/abs/1210.0530v4},
volume = {abs/1210.0},
year = {2012}
}

@inproceedings{Sweave2002,
address = {Heidelberg},
author = {Leisch, Friedrich},
booktitle = {Compstat 2002 --- Proc. Comput. Stat.},
editor = {H\"{a}rdle, Wolfgang and R\"{o}nz, Bernd},
mendeley-groups = {Software,Thesis},
pages = {575--580},
publisher = {Physica Verlag},
title = {{Sweave: Dynamic Generation of Statistical Reports Using Literate Data Analysis}},
url = {http://www.stat.uni-muenchen.de/~leisch/Sweave},
year = {2002}
}

  @Manual{knitr2014,
    title = {knitr: A general-purpose package for dynamic report
      generation in R},
    author = {Yihui Xie},
    year = {2014},
    note = {R package version 1.6},
    url = {http://yihui.name/knitr/},
  }
  @Book{Xie2013,
    title = {Dynamic Documents with {R} and knitr},
    author = {Yihui Xie},
    publisher = {Chapman and Hall/CRC},
    address = {Boca Raton, Florida},
    year = {2013},
    note = {ISBN 978-1482203530},
    url = {http://yihui.name/knitr/},
  }
  @InCollection{Xie2014,
    booktitle = {Implementing Reproducible Computational Research},
    editor = {Victoria Stodden and Friedrich Leisch and Roger D. Peng},
    title = {knitr: A Comprehensive Tool for Reproducible Research in
      {R}},
    author = {Yihui Xie},
    publisher = {Chapman and Hall/CRC},
    year = {2014},
    note = {ISBN 978-1466561595},
    url = {http://www.crcpress.com/product/isbn/9781466561595},
  }
  
@Article{ipython2007,
  Author    = {P\'erez, Fernando and Granger, Brian E.},
  Title     = {{IP}ython: a System for Interactive Scientific Computing},
  Journal   = {Computing in Science and Engineering},
  Volume    = {9},
  Number    = {3},
  Pages     = {21--29},
  month     = may,
  year      = 2007,
  url       = "http://ipython.org",
  ISSN      = "1521-9615",
  doi       = {10.1109/MCSE.2007.53},
  publisher = {IEEE Computer Society},
}

@article{Graser1987,
author = {Graser, H.-U. and Smith, S P and Tier, B.},
journal = {J. Anim. Sci.},
keywords = {REML},
mendeley-groups = {Thesis},
mendeley-tags = {REML},
number = {5},
pages = {1362--1370},
title = {{A Derivative-Free Approach for Estimating Variance Components in Animal Models by Restricted Maximum Likelihood}},
url = {http://www.journalofanimalscience.org/content/64/5/1362.short},
volume = {64},
year = {1987}
}

@article{Dempster1977,
abstract = {A broadly applicable algorithm for computing maximum likelihood estimates from incomplete data is presented at various levels of generality. Theory showing the monotone behaviour of the likelihood and convergence of the algorithm is derived. Many examples are sketched, including missing value situations, applications to grouped, censored or truncated data, finite mixture models, variance component estimation, hyperparameter estimation, iteratively reweighted least squares and factor analysis.},
author = {Dempster, A. P. and Laird, N. M. and Rubin, D. B.},
issn = {00359246},
journal = {J. R. Stat. Soc. Ser. B},
keywords = {REML},
mendeley-groups = {Thesis},
mendeley-tags = {REML},
number = {1},
pages = {pp. 1--38},
publisher = {Wiley for the Royal Statistical Society},
title = {{Maximum Likelihood from Incomplete Data via the EM Algorithm}},
url = {http://www.jstor.org/stable/2984875},
volume = {39},
year = {1977}
}

@article{Smith1986,
author = {Smith, S.P. and Graser, H.-U.},
doi = {10.3168/jds.S0022-0302(86)80516-1},
file = {::},
issn = {00220302},
journal = {J. Dairy Sci.},
keywords = {REML},
mendeley-tags = {REML},
month = apr,
number = {4},
pages = {1156--1165},
publisher = {Elsevier},
title = {{Estimating Variance Components in a Class of Mixed Models by Restricted Maximum Likelihood}},
url = {http://www.journalofdairyscience.org/article/S0022-0302(86)80516-1/abstract},
volume = {69},
year = {1986}
}

@article{Hofer1998,
author = {Hofer, A.},
doi = {10.1111/j.1439-0388.1998.tb00347.x},
issn = {09312668},
journal = {J. Anim. Breed. Genet.},
keywords = {REML},
mendeley-tags = {REML},
month = jan,
number = {1-6},
pages = {247--265},
title = {{Variance component estimation in animal breeding: a review}},
url = {http://doi.wiley.com/10.1111/j.1439-0388.1998.tb00347.x},
volume = {115},
year = {1998}
}

@article{Nelder1965,
author = {Nelder, J. A. and Mead, R.}, 
title = {A Simplex Method for Function Minimization},
volume = {7}, 
number = {4}, 
pages = {308-313}, 
year = {1965}, 
doi = {10.1093/comjnl/7.4.308}, 
URL = {http://comjnl.oxfordjournals.org/content/7/4/308.abstract}, 
eprint = {http://comjnl.oxfordjournals.org/content/7/4/308.full.pdf+html}, 
journal = {Comput. J.} 
}

@article{McCullough2008,
abstract = {Excel 2007, like its predecessors, fails a standard set of intermediate-level accuracy tests in three areas: statistical distributions, random number generation, and estimation. Additional errors in specific Excel procedures are discussed. Microsoft’s continuing inability to correctly fix errors is discussed. No statistical procedure in Excel should be used until Microsoft documents that the procedure is correct; it is not safe to assume that Microsoft Excel’s statistical procedures give the correct answer. Persons who wish to conduct statistical analyses should use some other package.},
author = {McCullough, B.D. and Heiser, David A.},
doi = {10.1016/j.csda.2008.03.004},
file = {::},
issn = {01679473},
journal = {Comput. Stat. Data Anal.},
keywords = {Excel},
mendeley-groups = {Scientific practice},
mendeley-tags = {Excel},
month = jun,
number = {10},
pages = {4570--4578},
title = {{On the accuracy of statistical procedures in Microsoft Excel 2007}},
url = {http://www.sciencedirect.com/science/article/pii/S0167947308001606},
volume = {52},
year = {2008}
}

@techreport{Herdon2013,
address = {Amhert, Massachusetts},
author = {Herdon, Thomas and Ash, Michael and Pollin, Robert},
institution = {Political Economy Research Institute, University of Massachusetts Amherst},
keywords = {Excel},
mendeley-groups = {Thesis},
mendeley-tags = {Excel},
title = {{Does High Public Debt Consistently Stifle Economic Growth? A Critique of Reinhart and Rogoff}},
url = {http://www.peri.umass.edu/236/hash/31e2ff374b6377b2ddec04deaa6388b1/publication/566/},
year = {2013}
}

@misc{ wiki:Reinhart-Rogoff,
 author = "Wikipedia",
 title = "Growth in a Time of Debt --- Wikipedia{,} The Free Encyclopedia",
 year = "2014",
 url = "http://en.wikipedia.org/w/index.php?title=Growth_in_a_Time_of_Debt&oldid=610741315",
 note = "[Online; accessed 3-June-2014]"
}
 
@article{Pigliucci2006,
year={2006},
issn={0169-3867},
journal={Biol. Philos.},
volume={21},
number={1},
doi={10.1007/s10539-005-0399-z},
title={Genetic Variance-covariance Matrices: A Critique of the Evolutionary Quantitative Genetics Research Program},
url={http://dx.doi.org/10.1007/s10539-005-0399-z},
publisher={Kluwer Academic Publishers},
keywords={Evolutionary theory; Genetic covariances; Heritability; Pattern vs. process; Quantitative genetics},
author={Pigliucci, Massimo},
pages={1-23},
language={English}
}

@article{Ram2013,
author = {Ram, Karthik},
doi = {10.1186/1751-0473-8-7},
file = {::},
issn = {1751-0473},
journal = {Source Code Biol. Med.},
keywords = {git,svn},
mendeley-groups = {Software,Thesis},
mendeley-tags = {git,svn},
number = {1},
pages = {7},
title = {git can facilitate greater reproducibility and increased transparency in science},
url = {http://www.scfbm.org/content/8/1/7},
volume = {8},
year = {2013}
}

@article{Rao2009,
author = {Rao, C. Radhakrishna},
doi = {10.4249/scholarpedia.8220},
title   = {{R}ao score test},
year	= 2009,
journal	= {Scholarpedia},
volume  = 4,
number  = 10,
pages   = 8220,
note   = {{Revision \#121946}},
}

@article{Wang2013,
author = {Wang, Xuefeng and Morris, Nathan J. and Zhu, Xiaofeng and Elston, Robert C.},
doi = {10.1186/1471-2156-14-17},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/BMC Genetics/Wang et al. - 2013 - A variance component based multi-marker association test using family and unrelated data.pdf:pdf},
issn = {1471-2156},
journal = {BMC Genet.},
keywords = {Computer Simulation,Family,Female,Gene set test,Genetic,Genetic Association Studies,Genotype,Humans,Male,Models,Polymorphism,Single Nucleotide,Software},
mendeley-tags = {Gene set test},
month = jan,
number = {1},
pages = {17},
pmid = {23497289},
publisher = {BMC Genetics},
title = {{A variance component based multi-marker association test using family and unrelated data.}},
url = {http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3614458\&tool=pmcentrez\&rendertype=abstract},
volume = {14},
year = {2013}
}

@article{Huang2013,
author = {Huang, Yen-Tsung and Lin, Xihong},
doi = {10.1186/1471-2105-14-210},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/BMC bioinformatics/Huang, Lin - 2013 - Gene set analysis using variance component tests.pdf:pdf},
issn = {1471-2105},
journal = {BMC Bioinformatics},
keywords = {Diabetes Mellitus,Gene Expression Profiling,Gene Expression Profiling: methods,Gene set test,Humans,Linear Models,Oligonucleotide Array Sequence Analysis,Oligonucleotide Array Sequence Analysis: methods,Type 2,Type 2: genetics,Type 2: metabolism},
mendeley-groups = {Statistics,Integrative Genomics},
mendeley-tags = {Gene set test},
month = jan,
number = {1},
pages = {210},
pmid = {23806107},
title = {{Gene set analysis using variance component tests.}},
url = {http://www.biomedcentral.com/1471-2105/14/210},
volume = {14},
year = {2013}
}

@article{Rivals2007,
author = {Rivals, Isabelle and Personnaz, L\'{e}on and Taing, Lieng and Potier, Marie-Claude},
doi = {10.1093/bioinformatics/btl633},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/Bioinformatics/Rivals et al. - 2007 - Enrichment or depletion of a GO category within a class of genes which test.pdf:pdf},
issn = {1367-4811},
journal = {Bioinformatics},
keywords = {Data Interpretation,Database Management Systems,Databases,Gene Expression Profiling,Gene Expression Profiling: methods,Gene set test,Information Storage and Retrieval,Information Storage and Retrieval: methods,Multigene Family,Multigene Family: physiology,Oligonucleotide Array Sequence Analysis,Oligonucleotide Array Sequence Analysis: methods,Protein,Proteins,Proteins: classification,Proteins: metabolism,Statistical},
mendeley-tags = {Gene set test},
month = feb,
number = {4},
pages = {401--7},
pmid = {17182697},
title = {{Enrichment or depletion of a GO category within a class of genes: which test?}},
url = {http://www.ncbi.nlm.nih.gov/pubmed/17182697},
volume = {23},
year = {2007}
}

@Article{Cule2011,
author = {Cule, Erika and Vineis, Paolo and De Iorio, Maria},
title = {Significance testing in ridge regression for genetic data},
journal = {BMC Bioinformatics},
volume = {12},
year = {2011},
number = {1},
pages = {372},
url = {http://www.biomedcentral.com/1471-2105/12/372},
doi = {10.1186/1471-2105-12-372},
PubMedID = {21929786},
ISSN = {1471-2105},
}

@misc{Orenti2012,
author = {Orenti, Annalisa and Marano, Giuseppe and Boracchi, Patrizia and Marubini, Ettore},
booktitle = {Ital. J. Public Health},
doi = {10.2427/8663},
issn = {1723-7815},
keywords = {Anova,Hat matrix,Outliers},
language = {en},
mendeley-groups = {Thesis},
mendeley-tags = {Hat matrix},
number = {4},
title = {{Pinpointing outliers in experimental data: the Hat matrix in Anova for fixed and mixed effects models}},
url = {http://ijphjournal.it/article/view/8663},
volume = {9},
year = {2012}
}

@article{Maciejewski2013,
abstract = {Many methods of gene set analysis developed in recent years have been compared empirically in a number of comprehensive review articles. Although it is recognized that different methods tend to identify different gene sets as significant, no consensus has been worked out as to which method is preferable, as the recommendations are often contradictory. In this article, we want to group and compare different methods in terms of the methodological assumptions pertaining to definition of a sample and formulation of the actual null hypothesis. We discuss four models of statistical experiment explicitly or implicitly assumed by most if not all currently available methods of gene set analysis. We analyse validity of the models in the context of the actual biological experiment. Based on this, we recommend a group of methods that provide biologically interpretable results in statistically sound way. Finally, we demonstrate how correlated or low signal-to-noise data affects performance of different methods, observed in terms of the false-positive rate and power.},
author = {Maciejewski, Henryk},
doi = {10.1093/bib/bbt002},
issn = {1477-4054},
journal = {Brief. Bioinform.},
keywords = {Competitive tests,Competitive vs. self-contained},
mendeley-groups = {Statistics,Thesis},
mendeley-tags = {Competitive tests,Competitive vs. self-contained},
month = feb,
pages = {bbt002--},
pmid = {23413432},
title = {{Gene set analysis methods: statistical models and methodological differences.}},
url = {http://bib.oxfordjournals.org/content/early/2013/02/09/bib.bbt002.full},
year = {2013}
}

@article{Noble2009,
    author = {Noble, William Stafford},
    journal = {PLoS Comput Biol},
    publisher = {Public Library of Science},
    title = {A Quick Guide to Organizing Computational Biology Projects},
    year = {2009},
    month = {07},
    volume = {5},
    url = {http://dx.doi.org/10.1371%2Fjournal.pcbi.1000424},
    pages = {e1000424},
    abstract = {},
    number = {7},
    doi = {10.1371/journal.pcbi.1000424}
}        

@article{Goecks2010galaxy,
  title={Galaxy: a comprehensive approach for supporting accessible, reproducible, and transparent computational research in the life sciences},
  author={Goecks, Jeremy and Nekrutenko, Anton and Taylor, James and The Galaxy Team},
  journal={Genome Biol},
  volume={11},
  number={8},
  pages={R86},
  year={2010}
}

@article{Blankenberg2010galaxy,
  title={Galaxy: A Web-Based Genome Analysis Tool for Experimentalists},
  author={Blankenberg, Daniel and Kuster, Gregory Von and Coraor, Nathaniel and Ananda, Guruprasad and Lazarus, Ross and Mangan, Mary and Nekrutenko, Anton and Taylor, James},
  journal={Current protocols in molecular biology},
  pages={19--10},
  year={2010},
  publisher={John Wiley \& Sons, Inc.}
}

@article{Giardine2005galaxy,
  title={Galaxy: a platform for interactive large-scale genome analysis},
  author={Giardine, Belinda and Riemer, Cathy and Hardison, Ross C and Burhans, Richard and Elnitski, Laura and Shah, Prachi and Zhang, Yi and Blankenberg, Daniel and Albert, Istvan and Taylor, James and Miller, Webb C and Kent, W James and Nekrutenko, Anton},
  journal={Genome research},
  volume={15},
  number={10},
  pages={1451--1455},
  year={2005},
  publisher={Cold Spring Harbor Lab}
}

@article{Chial2008,
author = {Chial, Heidi},
journal = {Nature Education},
mendeley-groups = {Thesis},
number = {1},
pages = {63},
title = {{Mendelian Genetics: Patterns of Inheritance and Single-Gene Disorders}},
url = {http://www.nature.com/scitable/topicpage/mendelian-genetics-patterns-of-inheritance-and-single-966},
volume = {1},
year = {2008}
}

@article{LaFramboise2009,
author = {LaFramboise, Thomas},
doi = {10.1093/nar/gkp552},
issn = {1362-4962},
journal = {Nucleic Acids Res.},
keywords = {Genetic Variation,Genome-Wide Association Study,Genomics,Genomics: history,Genomics: trends,Genotype,History, 20th Century,History, 21st Century,Humans,Linkage Disequilibrium,Neoplasms,Neoplasms: genetics,Oligonucleotide Array Sequence Analysis,Oligonucleotide Array Sequence Analysis: history,Oligonucleotide Array Sequence Analysis: methods,Oligonucleotide Array Sequence Analysis: trends,Polymorphism, Single Nucleotide},
mendeley-groups = {Thesis},
month = jul,
number = {13},
pages = {4181--93},
pmid = {19570852},
title = {{Single nucleotide polymorphism arrays: a decade of biological, computational and technological advances.}},
url = {http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=2715261\&tool=pmcentrez\&rendertype=abstract},
volume = {37},
year = {2009}
}

@article{Mackay2001,
author = {Mackay, Trudy F. C.},
doi = {10.1146/annurev.genet.35.102401.090633},
issn = {0066-4197},
journal = {Annu. Rev. Genet.},
keywords = {Animals,Chromosome Mapping,Genetic,Genetic Architecture,Genetic Linkage,Genotype,Heritable,Humans,Models,Mutation,Polymorphism,Quantitative Trait,Single Nucleotide,Single Nucleotide: genetics},
language = {en},
mendeley-groups = {GWAS,Thesis},
mendeley-tags = {Genetic Architecture},
month = jan,
pages = {303--39},
pmid = {11700286},
publisher = {Annual Reviews 4139 El Camino Way, P.O. Box 10139, Palo Alto, CA 94303-0139, USA},
title = {{The genetic architecture of quantitative traits.}},
url = {http://www.annualreviews.org/doi/abs/10.1146/annurev.genet.35.102401.090633},
volume = {35},
year = {2001}
}

@article{Weller2012,
author = {Weller, Joel Ira and Glick, Giora and Shirak, Andrey and Ezra, Ephraim and Zeron, Yoel and Ron, Micha},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/Interbull Bulletin/Weller et al. - 2012 - Predictive Ability of Selected Subsets of Single Nucleotide Polymorphisms (SNPs) for Moderately Sized Dairy Cattl.pdf:pdf},
journal = {Interbull Bull.},
keywords = {dairy cattle,genetic evaluation,genomic selection,snp},
mendeley-groups = {Thesis},
title = {{Predictive Ability of Selected Subsets of Single Nucleotide Polymorphisms (SNPs) for Moderately Sized Dairy Cattle Populations}},
url = {https://journal.interbull.org/index.php/ib/article/view/1252},
volume = {46},
year = {2012}
}

@article{Hayes2010,
author = {Hayes, Ben J. and Pryce, Jennie and Chamberlain, Amanda J. and Bowman, Phil J. and Goddard, Mike E.},
doi = {10.1371/journal.pgen.1001139},
file = {:C$\backslash$:/Users/STME/Documents/Mendeley Desktop/PLoS genetics/Hayes et al. - 2010 - Genetic architecture of complex traits and accuracy of genomic prediction coat colour, milk-fat percentage, and ty.pdf:pdf},
issn = {1553-7404},
journal = {PLoS Genet.},
keywords = {Animals,Breeding,Cattle,Cattle: genetics,Chromosomes,Genome,Genome-Wide Association Study,Genome: genetics,Genomics,Genomics: methods,Heritable,Lipids,Lipids: chemistry,Male,Mammalian,Mammalian: genetics,Milk,Milk: chemistry,Phenotype,Polymorphism,Quantitative Trait,Quantitative Trait Loci,Quantitative Trait Loci: genetics,Reproducibility of Results,Single Nucleotide,Single Nucleotide: genetics,Skin Pigmentation,Skin Pigmentation: genetics,complex traits},
mendeley-groups = {Needs Review,Thesis},
mendeley-tags = {complex traits},
month = sep,
number = {9},
pages = {e1001139},
pmid = {20927186},
publisher = {Public Library of Science},
title = {{Genetic architecture of complex traits and accuracy of genomic prediction: coat colour, milk-fat percentage, and type in Holstein cattle as contrasting model traits.}},
url = {http://www.plosgenetics.org/article/info:doi/10.1371/journal.pgen.1001139\#s3},
volume = {6},
year = {2010}
}

@article{Erbe2012,
title = "Improving accuracy of genomic predictions within and between dairy cattle breeds with imputed high-density single nucleotide polymorphism panels ",
journal = "J. Dairy Sci.",
volume = "95",
number = "7",
pages = "4114 - 4129",
year = "2012",
note = "",
issn = "0022-0302",
doi = "http://dx.doi.org/10.3168/jds.2011-5019",
url = "http://www.sciencedirect.com/science/article/pii/S0022030212003918",
author = "M. Erbe and B.J. Hayes and L.K. Matukumalli and S. Goswami and P.J. Bowman and C.M. Reich and B.A. Mason and M.E. Goddard",
keywords = "genomic selection",
keywords = "multiple breeds "
}


@book{Wackerly1996,
address = {Belmont},
author = {Wackerly, Dennis D. and Mendenhall, III, William and Scheaffer, Richard L.},
edition = {5},
isbn = {0-534-20916-5},
mendeley-groups = {Thesis},
publisher = {Duxbury Press},
title = {{Mathematical Statistics with Applications}},
year = {1996}
}

@article{Freedman2007,
author = {Freedman, David A},
doi = {10.1198/000313007X243061},
issn = {0003-1305},
journal = {Am. Stat.},
mendeley-groups = {Thesis},
month = nov,
number = {4},
pages = {291--295},
publisher = {Taylor \& Francis},
title = {{How Can the Score Test Be Inconsistent?}},
url = {http://dx.doi.org/10.1198/000313007X243061},
volume = {61},
year = {2007}
}

@article{deRoos2008,
author = {de Roos, A. P. W. and Hayes, B. J. and Spelman, R. J. and Goddard, M. E.}, 
title = {{Linkage Disequilibrium and Persistence of Phase in Holstein-Friesian, Jersey and Angus Cattle}},
volume = {179}, 
number = {3}, 
pages = {1503-1512}, 
year = {2008}, 
doi = {10.1534/genetics.107.084301}, 
abstract ={When a genetic marker and a quantitative trait locus (QTL) are in linkage disequilibrium (LD) in one population, they may not be in LD in another population or their LD phase may be reversed. The objectives of this study were to compare the extent of LD and the persistence of LD phase across multiple cattle populations. LD measures r and r2 were calculated for syntenic marker pairs using genomewide single-nucleotide polymorphisms (SNP) that were genotyped in Dutch and Australian Holstein–Friesian (HF) bulls, Australian Angus cattle, and New Zealand Friesian and Jersey cows. Average r2 was ∼0.35, 0.25, 0.22, 0.14, and 0.06 at marker distances 10, 20, 40, 100, and 1000 kb, respectively, which indicates that genomic selection within cattle breeds with r2 ≥ 0.20 between adjacent markers would require ∼50,000 SNPs. The correlation of r values between populations for the same marker pairs was close to 1 for pairs of very close markers (<10 kb) and decreased with increasing marker distance and the extent of divergence between the populations. To find markers that are in LD with QTL across diverged breeds, such as HF, Jersey, and Angus, would require ∼300,000 markers.}, 
URL = {http://www.genetics.org/content/179/3/1503.abstract}, 
eprint = {http://www.genetics.org/content/179/3/1503.full.pdf+html}, 
journal = {Genetics} 
}