LinkML meta cleanup

.gitignore

@@ -19,6 +19,7 @@ publish/**
 *.test.xlsx
 
 # IDE and code tools
+venv
 retold
 .idea
 .lsp

modules/Assay/Parameter.yaml

@@ -184,7 +184,6 @@ enums:
         meaning: http://purl.obolibrary.org/obo/OBI_0001852
       singleEnd:
         description: A library preparation that results in the creation of a library of 5' ends of DNA.
-        source: Sage Bionetworks
   StrandednessEnum:
     permissible_values:
       FirstStranded:

modules/Data/FileFormat.yaml

@@ -9,10 +9,10 @@ enums:
         meaning: http://purl.obolibrary.org/obo/NCIT_C49059
       MATLAB data:
         description: A MATLAB formatted data file with expected extension “.mat”.
-        source: Sage Bionetworks
+        source: https://synapse.org
       MATLAB script:
         description: A MATLAB script file with expected extension “.m”. Note that files with a “.mat” extension contains MATLAB formatted data.
-        source: Sage Bionetworks
+        source: https://synapse.org
       NWB:
         description: Neurodata Without Borders (NWB) is a data standard for neurophysiology data, designed to store data including from intracellular and extracellular electrophysiology experiments, data from optical physiology experiments, and tracking and stimulus data.
         source: https://www.nwb.org/
@@ -21,10 +21,10 @@ enums:
         source: https://nipy.org/nibabel/reference/nibabel.parrec.html
       Python script:
         description: Python script with expected extension “.py”.
-        source: Sage Bionetworks
+        source: https://synapse.org
       R script:
         description: R script with expected extension “.R”.
-        source: Sage Bionetworks
+        source: https://synapse.org
       RCC: 
         description: Reporter Code Count-A data file (.csv) output by the Nanostring nCounter Digital Analyzer, which contains gene sample information, probe information and probe counts.
         meaning: http://edamontology.org/format_3580
@@ -110,13 +110,16 @@ enums:
         source: https://cnvkit.readthedocs.io/en/stable/fileformats.html
       cram:
         description: A CRAM file is a compressed format for storing genomic sequence data.
-        source: ChatGPT (September 25, 2023 Version)
+        notes: 
+        - ChatGPT (September 25, 2023 Version)
       crai:
         description: A CRAI file is an index for a CRAM file, facilitating fast data retrieval.
-        source: ChatGPT (September 25, 2023 Version)
+        notes: 
+        - ChatGPT (September 25, 2023 Version)
       csi:
         description: A CSI file is a compressed sequence index used for efficiently accessing genomic data in large datasets.
-        source: ChatGPT (September 25, 2023 Version)
+        notes: 
+        - ChatGPT (September 25, 2023 Version)
       csv:
         description: Tabular data represented as comma-separated values in a text file
         meaning: http://edamontology.org/format_3752
@@ -225,7 +228,7 @@ enums:
         source: https://en.wikipedia.org/wiki/Markdown
       mov:
         description: A video file format with the .mov extension
-        meaning: Sage Bionetworks
+        source: https://synapse.org
       MPEG-4:
         description: A digital multimedia container format most commonly used to store video and audio.
         meaning: http://edamontology.org/format_3997
@@ -313,7 +316,8 @@ enums:
         meaning: https://en.wikipedia.org/wiki/Tar_(computing)
       tbi:
         description: A TBI file is an index for a TABIX-compressed genomic data file, enabling rapid region-based retrieval.
-        source: ChatGPT (September 25, 2023 Version)
+        notes: 
+        - ChatGPT (September 25, 2023 Version)
       tif:
         description: Tagged Image File Format, abbreviated TIFF or TIF, is a computer file format for storing raster graphics images
         meaning: https://en.wikipedia.org/wiki/TIFF

modules/Data/Resource.yaml

@@ -18,14 +18,14 @@ enums:
     permissible_values:
       experimentalData:
         description: Any file derived from or pertaining to a scientific experiment. Experimental data annotations should be applied, possibly disease-related
-        meaning: Sage Bionetworks
+        source: https://synapse.org
       result:
         description: Any file that reports data results. Examples include figures, presentations, analysis, etc.
         comments: This resource category is somewhat more general than `report`.
-        meaning: Sage Bionetworks
+        source: https://synapse.org
       tool:
         description: Any file or link that represents a tool, model, or algorithm; the tool annotations could be applied
-        meaning: Sage Bionetworks
+        source: https://synapse.org
       workflow report:
         description: Workflow-generated reports of analysis of primary data, usually created programmatically at completion of workflow step.
       report:

modules/Sample/Cell.yaml

@@ -9,7 +9,6 @@ enums:
         meaning: https://www.ebi.ac.uk/ols/ontologies/cl/terms?iri=http%3A%2F%2Fpurl.obolibrary.org%2Fobo%2FCL_0000235
       iPSC-derived neuron:
         description: ''
-        meaning: Sage Bionetworks
       lymphoblast:
         description: Often referred to as a blast cell. Unlike other usages of the suffix -blast a lymphoblast is a further differentiation of a lymphocyte, T- or B-, occasioned by an antigenic stimulus. The lymphoblast usually develops by enlargement of a lymphocyte, active re-entry to the S phase of the cell cycle, mitogenesis and production of much m-RNA and ribosomes.
         meaning: https://www.ebi.ac.uk/ols/ontologies/bto/terms?iri=http%3A%2F%2Fpurl.obolibrary.org%2Fobo%2FBTO_0000772
@@ -28,7 +27,6 @@ enums:
         meaning: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4519016/
       monocyte-derived microglia:
         description: ''
-        meaning: Sage Bionetworks
       microglia:
         description: The small, non-neural, interstitial cells of mesodermal origin that form part of the supporting structure of the central nervous system.
         meaning: https://www.ebi.ac.uk/ols/ontologies/bto/terms?iri=http%3A%2F%2Fpurl.obolibrary.org%2Fobo%2FBTO_0000078
@@ -73,13 +71,10 @@ enums:
         meaning: https://www.ebi.ac.uk/ols/ontologies/bto/terms?iri=http%3A%2F%2Fpurl.obolibrary.org%2Fobo%2FBTO_0001220
       iPSC-derived glia:
         description: ''
-        meaning: Sage Bionetworks
       iPSC-derived astrocytes:
         description: ''
-        meaning: Sage Bionetworks
       iPSC-derived neuronal progenitor cell:
         description: ''
-        meaning: Sage Bionetworks
       oligodendrocyte:
         description: A class of large neuroglial (macroglial) cells in the central nervous system. Form the insulating myelin sheath of axons in the central nervous system.
         meaning: http://purl.obolibrary.org/obo/CL_0000128

modules/Sample/CellLineModel.yaml

@@ -19,7 +19,7 @@ enums:
         description: Cell line generated by Ray Mattingly's lab.
       JHU 2-079-PDX:
         description: A PDX model derived from JHU NF1 Biobank tumor specimen JHU 2-079.
-        meaning: Sage Bionetworks
+        source: https://synapse.org
       HEK293 NF1 -/- with R192X mNf1 cDNA:
         description: '[From GFF:] This cell line is in development and not comprehensively characterized. Please contact the investigator for more information.  HEK293 NF1 -/- with R192X mNf1 cDNA'
       icNF98.4c:
@@ -32,7 +32,7 @@ enums:
         meaning: https://web.expasy.org/cellosaurus/CVCL_UI70
       icNF99.1:
         description: An hTERT-immortalized cutaneous neurofibroma cell line derived from a primary cell culture, developed by Dr. Peggy Wallace.
-        meaning: Sage Bionetworks
+        source: https://synapse.org
       cNF00.10a:
         description: A primary cutaneous neurofibroma cell line; not broadly available. See the immortalized version (icNF00.10a).
       iPSC Y489C; Exon 13 cryptic splice:
@@ -63,7 +63,7 @@ enums:
         description: A primary cutaneous neurofibroma cell line; not broadly available. See the immortalized version (icNF04.9a).
       JHU 2-103-PDX:
         description: A PDX model derived from JHU NF1 Biobank tumor specimen JHU 2-103.
-        meaning: Sage Bionetworks
+        source: https://synapse.org
       5PNF_TDiPSsv_PM_6:
         description: ''
         meaning: https://web.expasy.org/cellosaurus/CVCL_UN14
@@ -109,7 +109,7 @@ enums:
         description: '[From GFF:] This cell line is in development and not comprehensively characterized. Please contact the investigator for more information. Schwann cell NF1 -/- (iPN97.4 #24)'
       cNF97.5:
         description: A primary cell culture from a cutaneous neurofibroma developed by Dr. Peggy Wallace.
-        meaning: Sage Bionetworks
+        source: https://synapse.org
       NCC-MPNST4-C1:
         description: ''
         meaning: https://web.expasy.org/cellosaurus/CVCL_YU16
@@ -118,7 +118,7 @@ enums:
         meaning: https://www.cellosaurus.org/CVCL_4662
       cNF99.1:
         description: A primary cell culture from a cutaneous neurofibroma developed by Dr. Peggy Wallace.
-        meaning: Sage Bionetworks
+        source: https://synapse.org
       hiPSC:
         description: human iPSCs
         meaning: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7773355
@@ -137,12 +137,12 @@ enums:
         description: '[From GFF:] iPSC NF1 +/- BJFF.6 bkgd'
       JHU 2-079-CL:
         description: An MPNST cell line derived from JHU NF1 Biobank tumor specimen JHU 2-079.
-        meaning: Sage Bionetworks
+        source: https://synapse.org
       cNF97.2b:
         description: A primary cutaneous neurofibroma cell line; not broadly available. See the immortalized version (icNF97.2b).
       JHU 2-002-CL:
         description: An MPNST cell line derived from JHU NF1 Biobank tumor specimen JHU 2-002.
-        meaning: Sage Bionetworks
+        source: https://synapse.org
       NF1:
         description: ''
         meaning: https://web.expasy.org/cellosaurus/CVCL_JG80
@@ -159,7 +159,7 @@ enums:
         description: Derived from peripheral sciatic nerve from a donor without neurofibromatosis. No detectable NF1 mutation.
       JHU 2-103-CL:
         description: An MPNST cell line derived from JHU NF1 Biobank tumor specimen JHU 2-103.
-        meaning: Sage Bionetworks
+        source: https://synapse.org
       'HEK293 NF1 -/- Exon 17 #A15 G629R cryptic splice':
         description: '[From GFF:] HEK293 NF1 -/- Exon 17 #A15 G629R cryptic splice'
       Lis42_NF1_1N:
@@ -169,7 +169,7 @@ enums:
         description: '[From GFF:] This cell line is in development and not comprehensively characterized. Please contact the investigator for more information. ELK-TAD Luciferase Reporter HEK293 Stable NF1 -/-'
       human foreskin fibroblasts:
         description: generic human foreskin fibroblasts, often used as a control cell in toxicology experiments
-        meaning: Sage Bionetworks
+        source: https://synapse.org
       icNF00.10a:
         description: An hTERT-immortalized cutaneous neurofibroma cell line derived from a primary cell culture (cNF00.10a).
       HEK293 NF1 -/- with R1947X mNf1 cDNA:
@@ -185,7 +185,7 @@ enums:
         description: '[From GFF:] This cell line is in development and not comprehensively characterized. Please contact the investigator for more information.  HEK293 NF1 -/- with R461X mNf1 cDNA'
       i28cNF:
         description: An hTERT-immortalized cutaneous neurofibroma cell line derived from a primary cell culture, developed by Dr. Peggy Wallace.
-        meaning: Sage Bionetworks
+        source: https://synapse.org
       sNF94.3:
         description: ''
         meaning: https://web.expasy.org/cellosaurus/CVCL_K164
@@ -215,7 +215,7 @@ enums:
         meaning: https://web.expasy.org/cellosaurus/CVCL_5192
       M3 MPNST:
         description: A patient-derived MPNST cell line
-        meaning: Sage Bionetworks
+        source: https://synapse.org
       S462.TY:
         description: ''
         meaning: https://web.expasy.org/cellosaurus/VCL_JK02
@@ -260,12 +260,12 @@ enums:
         meaning: https://web.expasy.org/cellosaurus/CVCL_UI71
       i18cNF:
         description: An hTERT-immortalized cutaneous neurofibroma cell line derived from a primary cell culture, developed by Dr. Peggy Wallace.
-        meaning: Sage Bionetworks
+        source: https://synapse.org
       hTERT SC ipn97.4:
         description: Healthy Schwann cells.
       i21cNF:
         description: An hTERT-immortalized cutaneous neurofibroma cell line derived from a primary cell culture, developed by Dr. Peggy Wallace.
-        meaning: Sage Bionetworks
+        source: https://synapse.org
       cNF98.4d:
         description: A primary cutaneous neurofibroma cell line; not broadly available. See the immortalized version (icNF98.4d).
       28cNF:
@@ -275,7 +275,7 @@ enums:
         meaning: https://web.expasy.org/cellosaurus/CVCL_JK03
       cNF18.1a:
         description: A primary cell culture from a cutaneous neurofibroma developed by Dr. Peggy Wallace.
-        meaning: Sage Bionetworks
+        source: https://synapse.org
       Nf1Arg681*/Arg681* ES:
         description: '[From GFF:] Nf1Arg681*/Arg681* ES'
       GM11601:
@@ -320,7 +320,7 @@ enums:
         meaning: https://web.expasy.org/cellosaurus/CVCL_YU15
       JHU 2-002-PDX:
         description: A PDX model derived from JHU NF1 Biobank tumor specimen JHU 2-002.
-        meaning: Sage Bionetworks
+        source: https://synapse.org
       hTERT NF1 ipNF95.11b C:
         description: ''
         meaning: https://web.expasy.org/cellosaurus/CVCL_UI67
@@ -341,10 +341,10 @@ enums:
         source: https://www.nature.com/articles/s41418-022-00991-4
       HS02:
         description: 'NF2 schwannoma model'
-        source: Sage Bionetworks
+        source: https://synapse.org
       HS05:
         description: 'NF2 schwannoma model'
-        source: Sage Bionetworks
+        source: https://synapse.org
       primary cultured fibroblast cell: 
         description: A primary cultured cell that is derived from fibroblast cell in vivo.
         meaning: http://purl.obolibrary.org/obo/CLO_0037301

modules/Sample/Genotype.yaml

@@ -3,18 +3,13 @@ enums:
     permissible_values:
       '-/-':
         description: Homozygous deletion or mutation.
-        meaning: Sage Bionetworks
       '+/-':
         description: Heterozygous deletion or mutation
-        meaning: Sage Bionetworks
       '+/+':
         description: Homozygous wildtype
-        meaning: Sage Bionetworks
       Unknown:
         description: unknown
-        meaning: Sage Bionetworks
   NF1Variant:
     permissible_values:
       R816X:
         description: A pathogenic mutation in the NF1 gene (amino acid nomenclature) leading to a truncated protein
-        meaning: Sage Bionetworks

modules/Sample/SpecimenType.yaml

@@ -76,7 +76,7 @@ enums:
 
   OrganismSubstance:
     description: This preferred root in the UBERON ontology is meant to cover organism-produced substances (bodily secretions and excreta) commonly used as assay specimens.
-    meaning: http://purl.obolibrary.org/obo/UBERON_0000463
+    # meaning: http://purl.obolibrary.org/obo/UBERON_0000463
     permissible_values:
       saliva:
         description: The watery fluid in the mouth made by the salivary glands. Saliva moistens food to help digestion and it helps protect the mouth against infections.