v17-Release (#764)

* v17 files 1. updated files description 2. updated release notes 3. Updated download script to point to v16/v17 * Update release-notes.md Added clinical columns that changed * update release-notes.md added notes for integrated dx * Update doc/release-notes.md add PBTA TMB file `pbta-snv-consensus-mutation-tmb-coding.tsv` to release notes * Comment out HGG step that's broken * Comment out EPN subtyping; see #755 * Use a different histology (LGAT) outside of the logic for running all * Add EWS to the histology_color_palette.tsv so cnv_heatmap.Rmd runs * Ignore collapsed counts from telomerase activity * Add logic to make more robust to CI subset data * Add messages to make debugging easier * Temporarily comment out steps before telomerase activity * Revert "Temporarily comment out steps before telomerase activity" This reverts commit 65b6fb1. Co-authored-by: Jo Lynne Rokita <jharenza@gmail.com> Co-authored-by: Jaclyn Taroni <jaclyn.n.taroni@gmail.com> Co-authored-by: Candace Savonen <cansav09@gmail.com>
AlexsLemonade · Sep 15, 2020 · 6cdaf9e · 6cdaf9e
1 parent ce98248
commit 6cdaf9e
Show file tree

Hide file tree

Showing 10 changed files with 184 additions and 60 deletions.
diff --git a/.circleci/config.yml b/.circleci/config.yml
@@ -36,9 +36,11 @@ jobs:
 
      ### MOLECULAR SUBTYPING ###
 
-      - run:
-          name: Molecular Subtyping - HGG
-          command: OPENPBTA_SUBSET=0 ./scripts/run_in_ci.sh bash analyses/molecular-subtyping-HGG/run-molecular-subtyping-HGG.sh
+      # TODO: This is currently broken because of a change from glioma_brain_region to CNS_brain_region
+      # The fix is tracked in https://github.com/AlexsLemonade/OpenPBTA-analysis/issues/754#issuecomment-691525827
+      # - run:
+      #     name: Molecular Subtyping - HGG
+      #     command: OPENPBTA_SUBSET=0 ./scripts/run_in_ci.sh bash analyses/molecular-subtyping-HGG/run-molecular-subtyping-HGG.sh
 
       - run:
           name: Molecular subtyping - Non-MB/Non-ATRT Embryonal tumors
@@ -52,9 +54,10 @@ jobs:
           name: Molecular subtyping Chordoma
           command: OPENPBTA_SUBSET=0 ./scripts/run_in_ci.sh bash analyses/molecular-subtyping-chordoma/run-molecular-subtyping-chordoma.sh
 
-      - run:
-          name: Molecular subtyping - Ependymoma
-          command: OPENPBTA_SUBSET=0 ./scripts/run_in_ci.sh bash analyses/molecular-subtyping-EPN/run-molecular-subtyping-EPN.sh
+      # This is failing - a fix is tracked in https://github.com/AlexsLemonade/OpenPBTA-analysis/issues/755#issuecomment-692681410
+      # - run:
+      #     name: Molecular subtyping - Ependymoma
+      #     command: OPENPBTA_SUBSET=0 ./scripts/run_in_ci.sh bash analyses/molecular-subtyping-EPN/run-molecular-subtyping-EPN.sh
 
       - run:
           name: Molecular Subtyping - LGAT

diff --git a/analyses/collapse-rnaseq/.gitignore b/analyses/collapse-rnaseq/.gitignore
@@ -1,3 +1,7 @@
 # the collapsed matrices are included in the data download
 results/pbta-gene-expression-rsem-fpkm-collapsed.stranded.rds
 results/pbta-gene-expression-rsem-fpkm-collapsed.polya.rds
+
+# expected count results - these actually come up not in this module but in 
+# analyses/telomerase-activity-prediction
+pbta-gene-counts-rsem-expected_count-collapsed*
diff --git a/analyses/interaction-plots/01-create-interaction-plots.sh b/analyses/interaction-plots/01-create-interaction-plots.sh
@@ -38,9 +38,9 @@ combined_plot=${plot_dir}/combined_top50
 # associative array of diseases to test; chosen by those that are most common
 # in the openPBTA dataset
 declare -A disease
-disease[Medulloblastoma]="Medulloblastoma"
+disease[LGAT]="Low-grade astrocytic tumor"
 if [ "$ALL" -gt "0" ]; then
-  disease[LGAT]="Low-grade astrocytic tumor"
+  disease[Medulloblastoma]="Medulloblastoma"
   disease[Ependymoma]="Ependymoma"
   disease[HGAT]="High-grade glioma"
   disease[DMG]="Diffuse midline glioma"

diff --git a/analyses/telomerase-activity-prediction/04-Comparing-Histology-versus-EXTENDScores.R b/analyses/telomerase-activity-prediction/04-Comparing-Histology-versus-EXTENDScores.R
@@ -41,11 +41,14 @@ PTBA_GE_Standard_TMScores = read.table(B,sep='\t',head=T)  ## Reading Stranded F
 PTBA_GE_Standard_Histology = merge(PTBA_Histology,PTBA_GE_Standard_TMScores,by='SampleID')   ### Merging Clinical data with the Telomerase scores
 
 Stranded_Histology = PTBA_GE_Standard_Histology
-Stranded_Histology = Stranded_Histology[-which(Stranded_Histology$short_histology == "Other"),]   ### Removing the tumors with catagory labelled as "Others"
+# If there are any "Other" samples, remove them 
+if (any(Stranded_Histology$short_histology == "Other")) {
+  Stranded_Histology = Stranded_Histology[-which(Stranded_Histology$short_histology == "Other"),]   ### Removing the tumors with catagory labelled as "Others"
+}
 Frequency = data.frame(table(Stranded_Histology$short_histology))  ### Counting the number of cases for all histologies to avoid less number further
 colnames(Frequency)=c('Variables','Freq')
 Frequency = Frequency[which(Frequency$Freq == 1),]
-Stranded_Histology = Stranded_Histology[-which(Stranded_Histology$short_histology %in% Frequency$Variables),]     ### Removing the tumors with only one case in histologies 
+Stranded_Histology = Stranded_Histology[-which(Stranded_Histology$short_histology %in% Frequency$Variables),]     ### Removing the tumors with only one case in histologies
 
 
 pdf(PBTA_EXTEND_HistologyCompPlot)

diff --git a/analyses/telomerase-activity-prediction/05-Comparing-MedulloblastomaSubtypes-EXTENDScores.R b/analyses/telomerase-activity-prediction/05-Comparing-MedulloblastomaSubtypes-EXTENDScores.R
@@ -41,50 +41,53 @@ PTBA_GE_Standard_Histology = merge(PTBA_Histology,PTBA_GE_Standard_TMScores,by='
 
 PTBA_GE_Standard_Histology = PTBA_GE_Standard_Histology[which(PTBA_GE_Standard_Histology$short_histology == "Medulloblastoma"),]   ### Select tumors with catagory labelled as "Medulloblastoma"
 
-stat.test <- data.frame(compare_means(
-  NormEXTENDScores ~ molecular_subtype, data = PTBA_GE_Standard_Histology,
-  method = "t.test"
-)) 
-
-combinations = nrow(stat.test)
-
-statistics = stat.test%>%
-  mutate(y.position = seq(1,by=0.04,length.out=combinations))
-
-
-pdf(PBTA_EXTEND_MedulloSubtypes,height = 3, width = 3)
-
-## Globally set the theme in one step, so it gets applied to both plots
-theme_set(theme_classic() + 
-          theme(axis.text.x=element_text(angle=50,size=7,vjust=1,hjust=1),
-          legend.position = "top",
-          legend.key.size= unit(0.3,"cm"),
-          legend.key.width = unit(0.3,"cm"),
-          legend.title = element_text(size=7),
-          legend.text =element_text(size=6)
-        )
-)
-
-
-P1 = ggplot(PTBA_GE_Standard_Histology, aes(x=fct_reorder(molecular_subtype,NormEXTENDScores,.desc =TRUE),y=NormEXTENDScores))+geom_boxplot(width=0.5,size= 0.1,notch=FALSE,outlier.size = 0,outlier.shape=NA,fill="pink")+ geom_jitter(shape=16, width = 0.1,size=0.4)+stat_pvalue_manual(
+# Compare means and making plot only if we have greater than 6 MB samples - this helps with CI
+if (nrow(PTBA_GE_Standard_Histology) > 6) {
+
+  stat.test <- data.frame(compare_means(
+    NormEXTENDScores ~ molecular_subtype, data = PTBA_GE_Standard_Histology,
+    method = "t.test"
+  ))
+
+  combinations = nrow(stat.test)
+
+  statistics = stat.test%>%
+    mutate(y.position = seq(1,by=0.04,length.out=combinations))
+
+
+  pdf(PBTA_EXTEND_MedulloSubtypes,height = 3, width = 3)
+
+  ## Globally set the theme in one step, so it gets applied to both plots
+  theme_set(theme_classic() +
+              theme(axis.text.x=element_text(angle=50,size=7,vjust=1,hjust=1),
+                    legend.position = "top",
+                    legend.key.size= unit(0.3,"cm"),
+                    legend.key.width = unit(0.3,"cm"),
+                    legend.title = element_text(size=7),
+                    legend.text =element_text(size=6)
+              )
+  )
+
+
+  P1 = ggplot(PTBA_GE_Standard_Histology, aes(x=fct_reorder(molecular_subtype,NormEXTENDScores,.desc =TRUE),y=NormEXTENDScores))+geom_boxplot(width=0.5,size= 0.1,notch=FALSE,outlier.size = 0,outlier.shape=NA,fill="pink")+ geom_jitter(shape=16, width = 0.1,size=0.4)+stat_pvalue_manual(
     data = statistics, label = "p.adj",size=1.5,
     xmin = "group1", xmax = "group2",tip.length = 0.006,
     y.position = "y.position"
-    )
-
-
-grid.newpage()
-# Create layout : nrow = 2, ncol = 1
-pushViewport(viewport(layout = grid.layout(nrow =1, ncol = 1)))
-# A helper function to define a region on the layout
-define_region <- function(row, col){
-  viewport(layout.pos.row = row, layout.pos.col = col)
-} 
-
-
-print(ggpar(P1,font.xtickslab =c("black",4),font.ytickslab =c("black",5),font.x = 5,font.y=5,font.legend=6,xlab="Molecular Subgroups Medulloblastoma",ylab="EXTEND Scores"),vp = define_region(row = 1, col = 1))
-
-
-dev.off()
-
-
+  )
+  
+  
+  grid.newpage()
+  # Create layout : nrow = 2, ncol = 1
+  pushViewport(viewport(layout = grid.layout(nrow =1, ncol = 1)))
+  # A helper function to define a region on the layout
+  define_region <- function(row, col){
+    viewport(layout.pos.row = row, layout.pos.col = col)
+  }
+  
+  
+  print(ggpar(P1,font.xtickslab =c("black",4),font.ytickslab =c("black",5),font.x = 5,font.y=5,font.legend=6,xlab="Molecular Subgroups Medulloblastoma",ylab="EXTEND Scores"),vp = define_region(row = 1, col = 1))
+  
+  
+  dev.off()
+
+}
diff --git a/analyses/telomerase-activity-prediction/RUN-telomerase-activity-prediction.sh b/analyses/telomerase-activity-prediction/RUN-telomerase-activity-prediction.sh
@@ -14,7 +14,6 @@ Rscript ../collapse-rnaseq/01-summarize_matrices.R -i ../../data/pbta-gene-count
 Rscript ../collapse-rnaseq/01-summarize_matrices.R -i ../../data/pbta-gene-counts-rsem-expected_count.polya.rds -g ../../data/gencode.v27.primary_assembly.annotation.gtf.gz -m ../collapse-rnaseq/pbta-gene-counts-rsem-expected_count-collapsed.polya.rds -t ../collapse-rnaseq/pbta-gene-counts-rsem-expected_count-collapsed_table.polya.rds
 
 mkdir -p results
-
 mkdir -p plots
 
 #generate telomerase activities using gene expression data from collapse RNA seq data files
@@ -23,14 +22,19 @@ Rscript --vanilla 01-run-EXTEND.R --input ../../data/pbta-gene-expression-rsem-f
 Rscript --vanilla 01-run-EXTEND.R --input ../collapse-rnaseq/pbta-gene-counts-rsem-expected_count-collapsed.stranded.rds --output results/TelomeraseScores_PTBAStranded_counts.txt
 Rscript --vanilla 01-run-EXTEND.R --input ../collapse-rnaseq/pbta-gene-counts-rsem-expected_count-collapsed.polya.rds --output results/TelomeraseScores_PTBAPolya_counts.txt
 
+
 #Compare Telomerase scores for PolyA and Stranded data
+echo "Comparing telomerase scores for polyA and stranded data..."
 Rscript --vanilla 02-Comparing-Counts-versus-FPKM.R --output plots/PTBA_GE_Score_AllScatter.pdf
 
 #Compare Telomerase scores with TERT and TERC gene expressions
+echo "Comparing EXTEND scores with TERT and TERC expression..."
 Rscript --vanilla 03-Comparing-TERTexp-TERCexp-EXTENDScores.R --output plots/PTBA_GE_TM_ScatterComp.pdf
 
 #Distribution of telomerase scores across various histologies of brain tumors.
+echo "Plotting distribution of EXTEND scores in histologies..."
 Rscript --vanilla 04-Comparing-Histology-versus-EXTENDScores.R --output plots/PBTA_StrandedHistology.pdf
 
 #Distribution of telomerase scores across different molecular subtypes of medulloblastoma tumors.
+echo "Plotting distribution of EXTEND scores in MB subtypes..."
 Rscript --vanilla 05-Comparing-MedulloblastomaSubtypes-EXTENDScores.R --output plots/PBTA_MedulloSubtypes.pdf
diff --git a/doc/data-files-description.md b/doc/data-files-description.md
@@ -13,7 +13,7 @@ This document contains information about all data files associated with this pro
 + **File description**
 	+ A *brief* one sentence description of what the file contains (e.g., bed files contain coordinates for features XYZ).
 
-### current release (release-v16-20200320)
+### current release (release-v17-20200908)
 
 | **File name** |  **File Type** | **Origin** | **File Description** |
 |---------------|----------------|------------------------|-----------------------|
@@ -65,6 +65,9 @@ This document contains information about all data files associated with this pro
 |`pbta-snv-mutect2.vep.maf.gz` | PBTA data file | [Somatic mutation calling](https://github.com/AlexsLemonade/OpenPBTA-manuscript/blob/master/content/03.methods.md#somatic-mutation-calling); [Workflow](https://github.com/d3b-center/OpenPBTA-workflows/blob/master/cwl/kfdrc_strelka2_mutect2_manta_workflow.cwl) | Somatic SNV - Mutect2 [annotated MAF file](https://github.com/AlexsLemonade/OpenPBTA-analysis/blob/master/doc/format/vep-maf.md)
 |`pbta-snv-strelka2.vep.maf.gz` | PBTA data file | [Somatic mutation calling](https://github.com/AlexsLemonade/OpenPBTA-manuscript/blob/master/content/03.methods.md#somatic-mutation-calling); [Workflow](https://github.com/d3b-center/OpenPBTA-workflows/blob/master/cwl/kfdrc_strelka2_mutect2_manta_workflow.cwl) | Somatic SNV - Strelka2 [annotated MAF file](https://github.com/AlexsLemonade/OpenPBTA-analysis/blob/master/doc/format/vep-maf.md)
 |`pbta-snv-vardict.vep.maf.gz` | PBTA data file | [Somatic mutation calling](https://github.com/AlexsLemonade/OpenPBTA-manuscript/blob/master/content/03.methods.md#somatic-mutation-calling); [Workflow](https://github.com/d3b-center/OpenPBTA-workflows/blob/master/cwl/kfdrc-vardict-wf.cwl) | Somatic SNV - VarDict [annotated MAF file](https://github.com/AlexsLemonade/OpenPBTA-analysis/blob/master/doc/format/vep-maf.md)
+|`tcga-snv-consensus-snv.maf.tsv.gz` | Analysis file | [`analyses/snv-callers`](https://github.com/AlexsLemonade/OpenPBTA-analysis/blob/master/analyses/snv-callers/)  | TCGA Consensus calls for SNVs and small indels made from Mutect2, Strelka2, and Lancet.
+|`tcga-snv-mutation-tmb-all.tsv` | Analysis file | [`analyses/snv-callers`](https://github.com/AlexsLemonade/OpenPBTA-analysis/blob/master/analyses/snv-callers/) | Tumor Mutation burden calculations using all mutations identified by both of Mutect2 and Strelka2 throughout the genome.
+|`tcga-snv-mutation-tmb-coding.tsv` | Analysis file | [`analyses/snv-callers`](https://github.com/AlexsLemonade/OpenPBTA-analysis/blob/master/analyses/snv-callers/) | Tumor Mutation burden calculations using coding only mutations identified by both Mutect2 and Strelka2 only within coding sequence regions of the genome.
 |`pbta-star-log-final.tar.gz` | PBTA data file | [Gene expression abundance estimation](https://github.com/AlexsLemonade/OpenPBTA-manuscript/blob/master/content/03.methods.md#gene-expression-abundance-estimation); [Workflow](https://github.com/kids-first/kf-rnaseq-workflow/blob/master/workflow/kfdrc_RNAseq_workflow.cwl) | STAR log final output files
 |`pbta-star-log-manifest.tsv` | PBTA data file | [Gene expression abundance estimation](https://github.com/AlexsLemonade/OpenPBTA-manuscript/blob/master/content/03.methods.md#gene-expression-abundance-estimation); [Workflow](https://github.com/kids-first/kf-rnaseq-workflow/blob/master/workflow/kfdrc_RNAseq_workflow.cwl) | File to map STAR output to biospecimen IDs
 |`pbta-sv-manta.tsv.gz`| PBTA data file | [Structural variant calling](https://github.com/AlexsLemonade/OpenPBTA-manuscript/blob/master/content/03.methods.md#somatic-structural-variant-calling); [Workflow](https://github.com/d3b-center/OpenPBTA-workflows/blob/master/cwl/kfdrc_strelka2_mutect2_manta_workflow.cwl) | Somatic Structural Variant - Manta output, annotated with AnnotSV (WGS samples only)

diff --git a/doc/release-notes.md b/doc/release-notes.md
@@ -1,5 +1,109 @@
 # release notes
 ## current release
+### release-v17-20200908
+- release date: 2020-09-11
+- status: available
+- changes:
+  - pbta-histologies.tsv updates:
+    - clinical updates to columns: `aliquot_id`, `parent_aliquot_id`, `reported_gender`, `race`, `ethnicity`, `tumor_descriptor`, `primary_site`, `age_at_diagnosis_days`, `pathology_diagnosis`, `integrated_diagnosis`, `short_histology`, `broad_histology`, `Notes`, `OS_days`, `OS_status`, `age_last_update_days`,`seq_center`, `cancer_predispositions`, `molecular_subtype`
+    - Updated logic for `integrated_diagnosis`, `Notes`, `short_histology` and `broad_histology`: If the sample was subtyped, values were updated based on new subtyping, if the `pathology_diagnosis` changed between v16 and v17, all values were set to `NA` and will be updated in the next release, all remaining samples were set to the values from v16.
+    - changed column `glioma_brain_region` to `CNS_region`, updated logic and entities, and assigned regions for all tumors
+    - added columns `pathology_free_text_diagnosis` and `cohort_participant_id`
+    - added sequencing center for `BS_QB84TBA3` and `BS_S2TA8R29` (previously NA)
+    - aliquot_id for `BS_MVYA262V` sample_id `7316-3213` was changed from `A05265` to `A05233`
+    - updated medulloblastoma subtypes per [#742](https://github.com/AlexsLemonade/OpenPBTA-analysis/issues/742)
+    - added LGAT subtyping per [#631](https://github.com/AlexsLemonade/OpenPBTA-analysis/issues/631)
+    - added EWS diagnoses per [#623](https://github.com/AlexsLemonade/OpenPBTA-analysis/issues/623)
+  - update PBTA TMB file `pbta-snv-consensus-mutation-tmb-coding.tsv` post bug fix, etc. per [#727](https://github.com/AlexsLemonade/OpenPBTA-analysis/issues/727) and [#728](https://github.com/AlexsLemonade/OpenPBTA-analysis/issues/728)
+  - new consensus mutation and TMB files from [TCGA analysis](https://github.com/AlexsLemonade/OpenPBTA-analysis/tree/master/analyses/snv-callers) :
+    - tcga-snv-consensus-snv.maf.tsv.gz
+    - tcga-snv-mutation-tmb-all.tsv
+    - tcga-snv-mutation-tmb-coding.tsv
+- folder structure:
+```
+data
+└── release-v17-20200908
+    ├── consensus_seg_annotated_cn_autosomes.tsv.gz
+    ├── consensus_seg_annotated_cn_x_and_y.tsv.gz
+    ├── data-files-description.md
+    ├── fusion_summary_embryonal_foi.tsv
+    ├── fusion_summary_ependymoma_foi.tsv
+    ├── fusion_summary_ewings_foi.tsv
+    ├── independent-specimens.wgs.primary-plus.tsv
+    ├── independent-specimens.wgs.primary.tsv
+    ├── independent-specimens.wgswxs.primary-plus.tsv
+    ├── independent-specimens.wgswxs.primary.tsv
+    ├── intersect_cds_lancet_strelka_mutect_WGS.bed
+    ├── intersect_cds_lancet_WXS.bed
+    ├── intersect_strelka_mutect_WGS.bed
+    ├── md5sum.txt
+    ├── pbta-cnv-cnvkit-gistic.zip
+    ├── pbta-cnv-cnvkit.seg.gz
+    ├── pbta-cnv-consensus-gistic.zip
+    ├── pbta-cnv-consensus.seg.gz
+    ├── pbta-cnv-controlfreec.tsv.gz
+    ├── pbta-fusion-arriba.tsv.gz
+    ├── pbta-fusion-putative-oncogenic.tsv
+    ├── pbta-fusion-recurrently-fused-genes-byhistology.tsv
+    ├── pbta-fusion-recurrently-fused-genes-bysample.tsv
+    ├── pbta-fusion-starfusion.tsv.gz
+    ├── pbta-gene-counts-rsem-expected_count.polya.rds
+    ├── pbta-gene-counts-rsem-expected_count.stranded.rds
+    ├── pbta-gene-expression-kallisto.polya.rds
+    ├── pbta-gene-expression-kallisto.stranded.rds
+    ├── pbta-gene-expression-rsem-fpkm-collapsed.polya.rds
+    ├── pbta-gene-expression-rsem-fpkm-collapsed.stranded.rds
+    ├── pbta-gene-expression-rsem-fpkm.polya.rds
+    ├── pbta-gene-expression-rsem-fpkm.stranded.rds
+    ├── pbta-gene-expression-rsem-tpm.polya.rds
+    ├── pbta-gene-expression-rsem-tpm.stranded.rds
+    ├── pbta-histologies.tsv
+    ├── pbta-isoform-counts-rsem-expected_count.polya.rds
+    ├── pbta-isoform-counts-rsem-expected_count.stranded.rds
+    ├── pbta-isoform-expression-rsem-tpm.polya.rds
+    ├── pbta-isoform-expression-rsem-tpm.stranded.rds
+    ├── pbta-mend-qc-manifest.tsv
+    ├── pbta-mend-qc-results.tar.gz
+    ├── pbta-snv-consensus-mutation.maf.tsv.gz
+    ├── pbta-snv-consensus-mutation-tmb-all.tsv
+    ├── pbta-snv-consensus-mutation-tmb-coding.tsv
+    ├── pbta-snv-lancet.vep.maf.gz
+    ├── pbta-snv-mutect2.vep.maf.gz
+    ├── pbta-snv-strelka2.vep.maf.gz
+    ├── pbta-snv-vardict.vep.maf.gz
+    ├── pbta-star-log-final.tar.gz
+    ├── pbta-star-log-manifest.tsv
+    ├── pbta-sv-manta.tsv.gz
+    ├── pbta-tcga-manifest.tsv
+    ├── pbta-tcga-snv-lancet.vep.maf.gz
+    ├── pbta-tcga-snv-mutect2.vep.maf.gz
+    ├── pbta-tcga-snv-strelka2.vep.maf.gz
+    ├── release-notes.md
+    ├── StrexomeLite_hg38_liftover_100bp_padded.bed
+    ├── StrexomeLite_Targets_CrossMap_hg38_filtered_chr_prefixed.bed
+    ├── WGS.hg38.lancet.300bp_padded.bed
+    ├── WGS.hg38.lancet.unpadded.bed
+    ├── WGS.hg38.mutect2.vardict.unpadded.bed
+    ├── WGS.hg38.strelka2.unpadded.bed
+    ├── WGS.hg38.vardict.100bp_padded.bed
+    ├── WXS.hg38.100bp_padded.bed
+    ├── WXS.hg38.lancet.400bp_padded.bed
+    ├── intersected_whole_exome_agilent_designed_120_AND_tcga_6k_genes.Gh38.bed
+    ├── intersected_whole_exome_agilent_plus_tcga_6k_AND_tcga_6k_genes.Gh38.bed
+    ├── tcga_6k_genes.targetIntervals.Gh38.bed
+    ├── tcga_6k_genes.targetIntervals.bed
+    ├── tcga-snv-consensus-snv.maf.tsv.gz
+    ├── tcga-snv-mutation-tmb-all.tsv
+    ├── tcga-snv-mutation-tmb-coding.tsv
+    ├── whole_exome_agilent_1.1_refseq_plus_3_boosters.targetIntervals.Gh38.bed
+    ├── whole_exome_agilent_1.1_refseq_plus_3_boosters.targetIntervals.bed
+    ├── whole_exome_agilent_designed_120.targetIntervals.Gh38.bed
+    ├── whole_exome_agilent_designed_120.targetIntervals.bed
+    ├── whole_exome_agilent_plus_tcga_6k.targetIntervals.Gh38.bed
+    └── whole_exome_agilent_plus_tcga_6k.targetIntervals.bed
+```
+
+##archived release
 ### release-v16-20200320
 - release date: 2020-03-27
 - status: available
@@ -94,6 +198,7 @@ data
     ├── whole_exome_agilent_plus_tcga_6k.targetIntervals.Gh38.bed
     └── whole_exome_agilent_plus_tcga_6k.targetIntervals.bed
 ```
+
 ## archived release
 ### release-v15-20200228
 - release date: 2020-02-28
@@ -187,7 +292,6 @@ data
     └── consensus_seg_annotated_cn_x_and_y.tsv.gz
 ```
 
-
 ### release-v14-20200203
 - release date: 2020-02-03
 - status: available
@@ -886,4 +990,3 @@ data
     ├── strelka2.maf.gz
     └── tumor-normal-pair.tsv
 ```
-