From ff9da5bf0f0e9f0a8a30eb1d9a91316c9a6cab1a Mon Sep 17 00:00:00 2001 From: PozhidayevaDarya <106110175+PozhidayevaDarya@users.noreply.github.com> Date: Thu, 20 Jul 2023 11:26:42 -0700 Subject: [PATCH 1/9] Add Pick-Seq attributes as discussed. Modifying nuc. acid source and adding new attribs. --- HTAN.model.csv | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/HTAN.model.csv b/HTAN.model.csv index a506fba4..fd270774 100644 --- a/HTAN.model.csv +++ b/HTAN.model.csv @@ -197,7 +197,9 @@ Imaging Object Class Description,Free text description of object class [string], Number of Objects,The number of objects (eg cells) described,,,,TRUE,Imaging,,https://www.miti-consortium.org/,int Number of Features,The number of features (eg channels) described,,,,TRUE,Imaging,,https://www.miti-consortium.org/,int Imaging Summary Statistic,Function used to summarize object/feature intensity,"Mean,Median,Not Specified",,,FALSE,Imaging,,https://www.miti-consortium.org/, -Nucleic Acid Source,The source of the input nucleic molecule,"Single Cell, Bulk Whole Cell, Single Nucleus, Bulk Nuclei",,,TRUE,Sequencing,,, +Nucleic Acid Source,The source of the input nucleic molecule,"Single Cell, Bulk Whole Cell, Single Nucleus, Bulk Nuclei, Micro-region",,,TRUE,Sequencing,,, +Mirco-region Seq Platform,The platform used for micro-regional RNA sequencing (if applicable),"Rarecyte Pick-Seq, Laser Capture Microdissection",,,FALSE,Sequencing,,, +ROI Tag,The tag or grouping used to identify the ROI in micro-regional RNA sequencing (if applicable). Must match the ROI tag within the count matrix in level 3.,,,,FALSE,Sequencing,,, Single Cell Isolation Method,"The method by which cells are isolated into individual reaction containers at a single cell resolution (e.g. wells, micro-droplets)","Microfluidics Chip, Droplets, FACS, Plates, 10x, Nuclei Isolation",,,TRUE,scRNA-seq Level 1,,, Dissociation Method,The tissue dissociation method used for scRNASeq or scATAC-seq assays,"gentleMACS, Dounce, Enzymatic Digestion, Not Applicable",,,TRUE,scRNA-seq Level 1,,, Library Layout,Sequencing read type,"Paired End, Single Read, Mid-length, Long Read",,,TRUE,Sequencing,,, From 97b06cfb8df3e5f487e415775cbeba8454cc2ea2 Mon Sep 17 00:00:00 2001 From: PozhidayevaDarya Date: Thu, 20 Jul 2023 18:42:23 +0000 Subject: [PATCH 2/9] GitHub Action: convert *.model.csv to *.model.jsonld --- HTAN.model.jsonld | 96 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 96 insertions(+) diff --git a/HTAN.model.jsonld b/HTAN.model.jsonld index ea16680b..25be3ab5 100644 --- a/HTAN.model.jsonld +++ b/HTAN.model.jsonld @@ -11847,12 +11847,57 @@ }, { "@id": "bts:BulkNuclei" + }, + { + "@id": "bts:Micro-region" } ], "sms:displayName": "Nucleic Acid Source", "sms:required": "sms:true", "sms:validationRules": [] }, + { + "@id": "bts:Mirco-regionSeqPlatform", + "@type": "rdfs:Class", + "rdfs:comment": "The platform used for micro-regional RNA sequencing (if applicable)", + "rdfs:label": "Mirco-regionSeqPlatform", + "rdfs:subClassOf": [ + { + "@id": "bts:Sequencing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "schema:rangeIncludes": [ + { + "@id": "bts:RarecytePick-Seq" + }, + { + "@id": "bts:LaserCaptureMicrodissection" + } + ], + "sms:displayName": "Mirco-region Seq Platform", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:ROITag", + "@type": "rdfs:Class", + "rdfs:comment": "The tag or grouping used to identify the ROI in micro-regional RNA sequencing (if applicable). Must match the ROI tag within the count matrix in level 3.", + "rdfs:label": "ROITag", + "rdfs:subClassOf": [ + { + "@id": "bts:Sequencing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "ROI Tag", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:SingleCellIsolationMethod", "@type": "rdfs:Class", @@ -55875,6 +55920,57 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:Micro-region", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "Micro-region", + "rdfs:subClassOf": [ + { + "@id": "bts:NucleicAcidSource" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Micro-region", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:RarecytePick-Seq", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "RarecytePick-Seq", + "rdfs:subClassOf": [ + { + "@id": "bts:Mirco-regionSeqPlatform" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Rarecyte Pick-Seq", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:LaserCaptureMicrodissection", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "LaserCaptureMicrodissection", + "rdfs:subClassOf": [ + { + "@id": "bts:Mirco-regionSeqPlatform" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Laser Capture Microdissection", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:MicrofluidicsChip", "@type": "rdfs:Class", From 72d6d581f2ac1190aba49c84392e3a80cbb5a14f Mon Sep 17 00:00:00 2001 From: PozhidayevaDarya <106110175+PozhidayevaDarya@users.noreply.github.com> Date: Mon, 24 Jul 2023 09:50:30 -0700 Subject: [PATCH 3/9] Fixing mistakes in update. --- HTAN.model.csv | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/HTAN.model.csv b/HTAN.model.csv index fd270774..139a1d70 100644 --- a/HTAN.model.csv +++ b/HTAN.model.csv @@ -48,7 +48,7 @@ scRNA-seq Level 4,"Data represents the relationships between cells derived from Bulk RNA-seq Level 1,Bulk RNA-seq [EFO_0003738],,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Library Layout, Read Indicator, Nucleic Acid Source, Sequencing Platform, Sequencing Batch ID, Read Length, Library Selection Method, Library Preparation Kit Name, Library Preparation Kit Vendor, Library Preparation Kit Version, Library Preparation Days from Index, Spike In, Adapter Name, Adapter Sequence, Base Caller Name, Base Caller Version, Flow, Cell Barcode, Fragment Maximum Length, Fragment Mean Length, Fragment Minimum Length, Fragment Standard Deviation Length, Lane Number, Library Strand, Multiplex Barcode, Size Selection Range, Target Depth, To Trim Adapter Sequence, Transcript Integrity Number, RIN, DV200, Adapter Content, Basic Statistics, Encoding, Kmer Content, Overrepresented Sequences, Per Base N Content, Per Base Sequence Content, Per Base Sequence Quality, Per Sequence GC Content, Per Sequence Quality Score, Per Tile Sequence Quality, Percent GC Content, Sequence Duplication Levels, Sequence Length Distribution, Total Reads, QC Workflow Type, QC Workflow Version, QC Workflow Link",,FALSE,Sequencing,Biospecimen,http://www.ebi.ac.uk/efo/EFO_0003738, Bulk RNA-seq Level 2,Bulk RNA-seq alignment protocol description,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, HTAN Parent Data File ID, Alignment Workflow Url, Alignment Workflow Type, Genomic Reference, Genomic Reference URL, Index File Name, Average Base Quality, Average Insert Size, Average Read Length, Contamination, Contamination Error, Mean Coverage, MSI Workflow Link, MSI Score, MSI Status, Pairs On Diff CHR, Total Reads, Total Uniquely Mapped, Total Unmapped reads, Proportion Reads Duplicated, Proportion Reads Mapped, Proportion, Targets No Coverage, Proportion Base Mismatch, Short Reads, Is lowest level",,FALSE,Sequencing,Bulk RNA-seq Level 1,, Bulk RNA-seq Level 3,Bulk RNA-seq gene expression matrices,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Pseudo Alignment Used, Data Category, Expression Units, Matrix Type, Fusion Gene Detected, Fusion Gene Identity",,FALSE,Sequencing,Bulk RNA-seq Level 2,, -Bulk WES Level 1,Bulk Whole Exome Sequencing raw files,,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Sequencing Batch ID, Library Layout, Read Indicator, Library Selection Method, Read Length, Target Capture Kit, Library Preparation Kit Name, Library Preparation Kit Vendor, Library Preparation Kit Version, Sequencing Platform, Adapter Name, Adapter Sequence, Base Caller Name, Base Caller Version, Flow Cell Barcode, Fragment Maximum Length, Fragment Mean Length, Fragment Minimum Length, Fragment Standard Deviation Length, Lane Number, Multiplex Barcode, Library Preparation Days from Index, Size Selection Range, Target Depth, To Trim Adapter Sequence",,FALSE,Sequencing,Biospecimen,, +Bulk WES Level 1,Bulk Whole Exome Sequencing raw files,,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Sequencing Batch ID, Library Layout, Read Indicator, Library Selection Method, Read Length, Target Capture Kit, Library Preparation Kit Name, Library Preparation Kit Vendor, Library Preparation Kit Version, Sequencing Platform, Adapter Name, Adapter Sequence, Base Caller Name, Base Caller Version, Flow Cell Barcode, Fragment Maximum Length, Fragment Mean Length, Fragment Minimum Length, Fragment Standard Deviation Length, Lane Number, Multiplex Barcode, Library Preparation Days from Index, Size Selection Range, Target Depth, To Trim Adapter Sequence, Mirco-region Seq Platform, ROI Tag",,FALSE,Sequencing,Biospecimen,, Bulk WES Level 2,Bulk Whole Exome Sequencing aligned files and QC,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Alignment Workflow Type, Genomic Reference, Genomic Reference URL, Index File Name, Average Base Quality, Average Insert Size, Average Read Length, Contamination, Contamination Error, Mean Coverage, Adapter Content, Basic Statistics, Encoding, Overrepresented Sequences, Per Base N Content, Per Base Sequence Content, Per Base Sequence Quality, Per Sequence GC Content, Per Sequence Quality Score, Per Tile Sequence Quality, Percent GC Content, Sequence Duplication Levels, Sequence Length Distribution, QC Workflow Type, QC Workflow Version, QC Workflow Link, MSI Workflow Link, MSI Score, MSI Status, Pairs On Diff CHR, Total Reads, Total Uniquely Mapped, Total Unmapped reads, Proportion Reads Duplicated, Proportion Reads Mapped, Proportion Targets No Coverage, Proportion Base Mismatch, Short Reads, Proportion Coverage 10x, Proportion Coverage 30X,Is lowest level",,FALSE,Sequencing,Bulk WES Level 1,, Bulk WES Level 3,Bulk Whole Exome Sequencing called variants,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Genomic Reference, Genomic Reference URL, Germline Variants Workflow URL, Germline Variants Workflow Type, Germline Variants Workflow Type, Somatic Variants Workflow URL, Somatic Variants Workflow Type, Somatic Variants Sample Type, Structural Variant Workflow URL, Structural Variant Workflow Type",,FALSE,Sequencing,Bulk WES Level 2,, scATAC-seq Level 1,"scATAC-seq files containing sequence read information, with or without alignment, as FASTQ or BAM files",,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Nucleic Acid Source, Dissociation Method, Single Nucleus Buffer, Single Cell Isolation Method, Transposition Reaction, scATACseq Library Layout, Nucleus Identifier, Nuclei Barcode Length, Nuclei Barcode Read, scATACseq Read1, scATACseq Read2, scATACseq Read3, Library Construction Method, Sequencing Platform, Threshold for Minimum Passing Reads, Total Number of Passing Nuclei, Median Fraction of Reads in Peaks, Median Fraction of Reads in Annotated cis DNA Elements, Median Passing Read Percentage, Median Percentage of Mitochondrial Reads per Nucleus,Technical Replicate Group, Total Reads, Protocol Link",,FALSE,Sequencing,Biospecimen,, @@ -198,7 +198,7 @@ Number of Objects,The number of objects (eg cells) described,,,,TRUE,Imaging,,ht Number of Features,The number of features (eg channels) described,,,,TRUE,Imaging,,https://www.miti-consortium.org/,int Imaging Summary Statistic,Function used to summarize object/feature intensity,"Mean,Median,Not Specified",,,FALSE,Imaging,,https://www.miti-consortium.org/, Nucleic Acid Source,The source of the input nucleic molecule,"Single Cell, Bulk Whole Cell, Single Nucleus, Bulk Nuclei, Micro-region",,,TRUE,Sequencing,,, -Mirco-region Seq Platform,The platform used for micro-regional RNA sequencing (if applicable),"Rarecyte Pick-Seq, Laser Capture Microdissection",,,FALSE,Sequencing,,, +Micro-region Seq Platform,The platform used for micro-regional RNA sequencing (if applicable),"Rarecyte Pick-Seq, Laser Capture Microdissection",,,FALSE,Sequencing,,, ROI Tag,The tag or grouping used to identify the ROI in micro-regional RNA sequencing (if applicable). Must match the ROI tag within the count matrix in level 3.,,,,FALSE,Sequencing,,, Single Cell Isolation Method,"The method by which cells are isolated into individual reaction containers at a single cell resolution (e.g. wells, micro-droplets)","Microfluidics Chip, Droplets, FACS, Plates, 10x, Nuclei Isolation",,,TRUE,scRNA-seq Level 1,,, Dissociation Method,The tissue dissociation method used for scRNASeq or scATAC-seq assays,"gentleMACS, Dounce, Enzymatic Digestion, Not Applicable",,,TRUE,scRNA-seq Level 1,,, From 800b9a6b861874cafe5e4239bed97f2ec14731e6 Mon Sep 17 00:00:00 2001 From: PozhidayevaDarya <106110175+PozhidayevaDarya@users.noreply.github.com> Date: Mon, 24 Jul 2023 09:56:59 -0700 Subject: [PATCH 4/9] Update HTAN.model.csv --- HTAN.model.csv | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/HTAN.model.csv b/HTAN.model.csv index 139a1d70..cc40ab8c 100644 --- a/HTAN.model.csv +++ b/HTAN.model.csv @@ -45,11 +45,11 @@ scRNA-seq Level 1,Single-cell RNA-seq [EFO_0008913],,"Component, Filename, File scRNA-seq Level 2,Alignment workflows downstream of scRNA-seq Level 1,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, scRNAseq Workflow Type, Workflow Version, scRNAseq Workflow Parameters Description, Workflow Link, Genomic Reference, Genomic Reference URL, Genome Annotation URL, Checksum, Whitelist Cell Barcode File Link, Cell Barcode Tag, UMI Tag, Applied Hard Trimming",,FALSE,Sequencing,scRNA-seq Level 1,, scRNA-seq Level 3,Gene and Isoform expression files,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Data Category, Matrix Type, Linked Matrices, Cell Median Number Reads, Cell Median Number Genes, Cell Total, scRNAseq Workflow Type, scRNAseq Workflow Parameters Description, Workflow Link, Workflow Version",,FALSE,Sequencing,scRNA-seq Level 2,, scRNA-seq Level 4,"Data represents the relationships between cells derived from Level 3 expression data and shown as tSNE or UMAP coordinates per cell, plus all other cell-specific meta information (e.g., cell type)",,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, scRNAseq Workflow Type, scRNAseq Workflow Parameters Description, Workflow Version, Workflow Link",,FALSE,Sequencing,scRNA-seq Level 3,, -Bulk RNA-seq Level 1,Bulk RNA-seq [EFO_0003738],,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Library Layout, Read Indicator, Nucleic Acid Source, Sequencing Platform, Sequencing Batch ID, Read Length, Library Selection Method, Library Preparation Kit Name, Library Preparation Kit Vendor, Library Preparation Kit Version, Library Preparation Days from Index, Spike In, Adapter Name, Adapter Sequence, Base Caller Name, Base Caller Version, Flow, Cell Barcode, Fragment Maximum Length, Fragment Mean Length, Fragment Minimum Length, Fragment Standard Deviation Length, Lane Number, Library Strand, Multiplex Barcode, Size Selection Range, Target Depth, To Trim Adapter Sequence, Transcript Integrity Number, RIN, DV200, Adapter Content, Basic Statistics, Encoding, Kmer Content, Overrepresented Sequences, Per Base N Content, Per Base Sequence Content, Per Base Sequence Quality, Per Sequence GC Content, Per Sequence Quality Score, Per Tile Sequence Quality, Percent GC Content, Sequence Duplication Levels, Sequence Length Distribution, Total Reads, QC Workflow Type, QC Workflow Version, QC Workflow Link",,FALSE,Sequencing,Biospecimen,http://www.ebi.ac.uk/efo/EFO_0003738, +Bulk RNA-seq Level 1,Bulk RNA-seq [EFO_0003738],,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Library Layout, Read Indicator, Nucleic Acid Source, Micro-region Seq Platform, ROI Tag, Sequencing Platform, Sequencing Batch ID, Read Length, Library Selection Method, Library Preparation Kit Name, Library Preparation Kit Vendor, Library Preparation Kit Version, Library Preparation Days from Index, Spike In, Adapter Name, Adapter Sequence, Base Caller Name, Base Caller Version, Flow, Cell Barcode, Fragment Maximum Length, Fragment Mean Length, Fragment Minimum Length, Fragment Standard Deviation Length, Lane Number, Library Strand, Multiplex Barcode, Size Selection Range, Target Depth, To Trim Adapter Sequence, Transcript Integrity Number, RIN, DV200, Adapter Content, Basic Statistics, Encoding, Kmer Content, Overrepresented Sequences, Per Base N Content, Per Base Sequence Content, Per Base Sequence Quality, Per Sequence GC Content, Per Sequence Quality Score, Per Tile Sequence Quality, Percent GC Content, Sequence Duplication Levels, Sequence Length Distribution, Total Reads, QC Workflow Type, QC Workflow Version, QC Workflow Link",,FALSE,Sequencing,Biospecimen,http://www.ebi.ac.uk/efo/EFO_0003738, Bulk RNA-seq Level 2,Bulk RNA-seq alignment protocol description,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, HTAN Parent Data File ID, Alignment Workflow Url, Alignment Workflow Type, Genomic Reference, Genomic Reference URL, Index File Name, Average Base Quality, Average Insert Size, Average Read Length, Contamination, Contamination Error, Mean Coverage, MSI Workflow Link, MSI Score, MSI Status, Pairs On Diff CHR, Total Reads, Total Uniquely Mapped, Total Unmapped reads, Proportion Reads Duplicated, Proportion Reads Mapped, Proportion, Targets No Coverage, Proportion Base Mismatch, Short Reads, Is lowest level",,FALSE,Sequencing,Bulk RNA-seq Level 1,, Bulk RNA-seq Level 3,Bulk RNA-seq gene expression matrices,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Pseudo Alignment Used, Data Category, Expression Units, Matrix Type, Fusion Gene Detected, Fusion Gene Identity",,FALSE,Sequencing,Bulk RNA-seq Level 2,, -Bulk WES Level 1,Bulk Whole Exome Sequencing raw files,,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Sequencing Batch ID, Library Layout, Read Indicator, Library Selection Method, Read Length, Target Capture Kit, Library Preparation Kit Name, Library Preparation Kit Vendor, Library Preparation Kit Version, Sequencing Platform, Adapter Name, Adapter Sequence, Base Caller Name, Base Caller Version, Flow Cell Barcode, Fragment Maximum Length, Fragment Mean Length, Fragment Minimum Length, Fragment Standard Deviation Length, Lane Number, Multiplex Barcode, Library Preparation Days from Index, Size Selection Range, Target Depth, To Trim Adapter Sequence, Mirco-region Seq Platform, ROI Tag",,FALSE,Sequencing,Biospecimen,, -Bulk WES Level 2,Bulk Whole Exome Sequencing aligned files and QC,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Alignment Workflow Type, Genomic Reference, Genomic Reference URL, Index File Name, Average Base Quality, Average Insert Size, Average Read Length, Contamination, Contamination Error, Mean Coverage, Adapter Content, Basic Statistics, Encoding, Overrepresented Sequences, Per Base N Content, Per Base Sequence Content, Per Base Sequence Quality, Per Sequence GC Content, Per Sequence Quality Score, Per Tile Sequence Quality, Percent GC Content, Sequence Duplication Levels, Sequence Length Distribution, QC Workflow Type, QC Workflow Version, QC Workflow Link, MSI Workflow Link, MSI Score, MSI Status, Pairs On Diff CHR, Total Reads, Total Uniquely Mapped, Total Unmapped reads, Proportion Reads Duplicated, Proportion Reads Mapped, Proportion Targets No Coverage, Proportion Base Mismatch, Short Reads, Proportion Coverage 10x, Proportion Coverage 30X,Is lowest level",,FALSE,Sequencing,Bulk WES Level 1,, +Bulk WES Level 1,Bulk Whole Exome Sequencing raw files,,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Sequencing Batch ID, Library Layout, Read Indicator, Library Selection Method, Read Length, Target Capture Kit, Library Preparation Kit Name, Library Preparation Kit Vendor, Library Preparation Kit Version, Sequencing Platform, Adapter Name, Adapter Sequence, Base Caller Name, Base Caller Version, Flow Cell Barcode, Fragment Maximum Length, Fragment Mean Length, Fragment Minimum Length, Fragment Standard Deviation Length, Lane Number, Multiplex Barcode, Library Preparation Days from Index, Size Selection Range, Target Depth, To Trim Adapter Sequence",,FALSE,Sequencing,Biospecimen,, +Bulk RNA Level 2,Bulk Whole Exome Sequencing aligned files and QC,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Alignment Workflow Type, Genomic Reference, Genomic Reference URL, Index File Name, Average Base Quality, Average Insert Size, Average Read Length, Contamination, Contamination Error, Mean Coverage, Adapter Content, Basic Statistics, Encoding, Overrepresented Sequences, Per Base N Content, Per Base Sequence Content, Per Base Sequence Quality, Per Sequence GC Content, Per Sequence Quality Score, Per Tile Sequence Quality, Percent GC Content, Sequence Duplication Levels, Sequence Length Distribution, QC Workflow Type, QC Workflow Version, QC Workflow Link, MSI Workflow Link, MSI Score, MSI Status, Pairs On Diff CHR, Total Reads, Total Uniquely Mapped, Total Unmapped reads, Proportion Reads Duplicated, Proportion Reads Mapped, Proportion Targets No Coverage, Proportion Base Mismatch, Short Reads, Proportion Coverage 10x, Proportion Coverage 30X,Is lowest level",,FALSE,Sequencing,Bulk RNA Level 1,, Bulk WES Level 3,Bulk Whole Exome Sequencing called variants,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Genomic Reference, Genomic Reference URL, Germline Variants Workflow URL, Germline Variants Workflow Type, Germline Variants Workflow Type, Somatic Variants Workflow URL, Somatic Variants Workflow Type, Somatic Variants Sample Type, Structural Variant Workflow URL, Structural Variant Workflow Type",,FALSE,Sequencing,Bulk WES Level 2,, scATAC-seq Level 1,"scATAC-seq files containing sequence read information, with or without alignment, as FASTQ or BAM files",,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Nucleic Acid Source, Dissociation Method, Single Nucleus Buffer, Single Cell Isolation Method, Transposition Reaction, scATACseq Library Layout, Nucleus Identifier, Nuclei Barcode Length, Nuclei Barcode Read, scATACseq Read1, scATACseq Read2, scATACseq Read3, Library Construction Method, Sequencing Platform, Threshold for Minimum Passing Reads, Total Number of Passing Nuclei, Median Fraction of Reads in Peaks, Median Fraction of Reads in Annotated cis DNA Elements, Median Passing Read Percentage, Median Percentage of Mitochondrial Reads per Nucleus,Technical Replicate Group, Total Reads, Protocol Link",,FALSE,Sequencing,Biospecimen,, scATAC-seq Level 2,"scATAC-seq files containing aligned sequence data, as a BAM file",,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Alignment Workflow Url, Alignment Workflow Type, Genomic Reference, Genomic, Reference URL, Index File Name, Average Base Quality, Average Insert Size, Average Read Length, Mean Coverage, Pairs On Diff CHR, Total Reads, Proportion Reads Mapped, MapQ30, Total Uniquely Mapped, Total Unmapped reads, Proportion Reads Duplicated, Short Reads, Proportion Coverage 10x, Proportion Coverage 30X, Proportion Targets No Coverage, Proportion Base Mismatch, Median Percentage of Mitochondrial Reads per Nucleus, Contamination,Contamination Error",,FALSE,Sequencing,scATAC-seq Level 1,, From 92566a8e076ad797045540bc7321a8789e3110d8 Mon Sep 17 00:00:00 2001 From: PozhidayevaDarya Date: Mon, 24 Jul 2023 17:10:21 +0000 Subject: [PATCH 5/9] GitHub Action: convert *.model.csv to *.model.jsonld --- HTAN.model.jsonld | 58 +++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 49 insertions(+), 9 deletions(-) diff --git a/HTAN.model.jsonld b/HTAN.model.jsonld index 25be3ab5..e5bf2b41 100644 --- a/HTAN.model.jsonld +++ b/HTAN.model.jsonld @@ -5371,6 +5371,12 @@ { "@id": "bts:NucleicAcidSource" }, + { + "@id": "bts:Micro-regionSeqPlatform" + }, + { + "@id": "bts:ROITag" + }, { "@id": "bts:SequencingPlatform" }, @@ -5801,10 +5807,10 @@ "sms:validationRules": [] }, { - "@id": "bts:BulkWESLevel2", + "@id": "bts:BulkRNALevel2", "@type": "rdfs:Class", "rdfs:comment": "Bulk Whole Exome Sequencing aligned files and QC", - "rdfs:label": "BulkWESLevel2", + "rdfs:label": "BulkRNALevel2", "rdfs:subClassOf": [ { "@id": "bts:Sequencing" @@ -5813,11 +5819,11 @@ "schema:isPartOf": { "@id": "http://schema.biothings.io" }, - "sms:displayName": "Bulk WES Level 2", + "sms:displayName": "Bulk RNA Level 2", "sms:required": "sms:false", "sms:requiresComponent": [ { - "@id": "bts:BulkWESLevel1" + "@id": "bts:BulkRNALevel1" } ], "sms:requiresDependency": [ @@ -11857,10 +11863,10 @@ "sms:validationRules": [] }, { - "@id": "bts:Mirco-regionSeqPlatform", + "@id": "bts:Micro-regionSeqPlatform", "@type": "rdfs:Class", "rdfs:comment": "The platform used for micro-regional RNA sequencing (if applicable)", - "rdfs:label": "Mirco-regionSeqPlatform", + "rdfs:label": "Micro-regionSeqPlatform", "rdfs:subClassOf": [ { "@id": "bts:Sequencing" @@ -11877,7 +11883,7 @@ "@id": "bts:LaserCaptureMicrodissection" } ], - "sms:displayName": "Mirco-region Seq Platform", + "sms:displayName": "Micro-region Seq Platform", "sms:required": "sms:false", "sms:validationRules": [] }, @@ -51874,6 +51880,40 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:BulkRNALevel1", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "BulkRNALevel1", + "rdfs:subClassOf": [ + { + "@id": "schema:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Bulk RNA Level 1", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:BulkWESLevel2", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "BulkWESLevel2", + "rdfs:subClassOf": [ + { + "@id": "schema:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Bulk WES Level 2", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:Genomic", "@type": "rdfs:Class", @@ -55944,7 +55984,7 @@ "rdfs:label": "RarecytePick-Seq", "rdfs:subClassOf": [ { - "@id": "bts:Mirco-regionSeqPlatform" + "@id": "bts:Micro-regionSeqPlatform" } ], "schema:isPartOf": { @@ -55961,7 +56001,7 @@ "rdfs:label": "LaserCaptureMicrodissection", "rdfs:subClassOf": [ { - "@id": "bts:Mirco-regionSeqPlatform" + "@id": "bts:Micro-regionSeqPlatform" } ], "schema:isPartOf": { From 0f1b6fa72eb316a40d3bfc6a7576402891d850ab Mon Sep 17 00:00:00 2001 From: PozhidayevaDarya <106110175+PozhidayevaDarya@users.noreply.github.com> Date: Mon, 24 Jul 2023 10:34:17 -0700 Subject: [PATCH 6/9] Fix erroneous component name. --- HTAN.model.csv | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/HTAN.model.csv b/HTAN.model.csv index cc40ab8c..776a56a7 100644 --- a/HTAN.model.csv +++ b/HTAN.model.csv @@ -49,7 +49,7 @@ Bulk RNA-seq Level 1,Bulk RNA-seq [EFO_0003738],,"Component, Filename, File Form Bulk RNA-seq Level 2,Bulk RNA-seq alignment protocol description,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, HTAN Parent Data File ID, Alignment Workflow Url, Alignment Workflow Type, Genomic Reference, Genomic Reference URL, Index File Name, Average Base Quality, Average Insert Size, Average Read Length, Contamination, Contamination Error, Mean Coverage, MSI Workflow Link, MSI Score, MSI Status, Pairs On Diff CHR, Total Reads, Total Uniquely Mapped, Total Unmapped reads, Proportion Reads Duplicated, Proportion Reads Mapped, Proportion, Targets No Coverage, Proportion Base Mismatch, Short Reads, Is lowest level",,FALSE,Sequencing,Bulk RNA-seq Level 1,, Bulk RNA-seq Level 3,Bulk RNA-seq gene expression matrices,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Pseudo Alignment Used, Data Category, Expression Units, Matrix Type, Fusion Gene Detected, Fusion Gene Identity",,FALSE,Sequencing,Bulk RNA-seq Level 2,, Bulk WES Level 1,Bulk Whole Exome Sequencing raw files,,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Sequencing Batch ID, Library Layout, Read Indicator, Library Selection Method, Read Length, Target Capture Kit, Library Preparation Kit Name, Library Preparation Kit Vendor, Library Preparation Kit Version, Sequencing Platform, Adapter Name, Adapter Sequence, Base Caller Name, Base Caller Version, Flow Cell Barcode, Fragment Maximum Length, Fragment Mean Length, Fragment Minimum Length, Fragment Standard Deviation Length, Lane Number, Multiplex Barcode, Library Preparation Days from Index, Size Selection Range, Target Depth, To Trim Adapter Sequence",,FALSE,Sequencing,Biospecimen,, -Bulk RNA Level 2,Bulk Whole Exome Sequencing aligned files and QC,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Alignment Workflow Type, Genomic Reference, Genomic Reference URL, Index File Name, Average Base Quality, Average Insert Size, Average Read Length, Contamination, Contamination Error, Mean Coverage, Adapter Content, Basic Statistics, Encoding, Overrepresented Sequences, Per Base N Content, Per Base Sequence Content, Per Base Sequence Quality, Per Sequence GC Content, Per Sequence Quality Score, Per Tile Sequence Quality, Percent GC Content, Sequence Duplication Levels, Sequence Length Distribution, QC Workflow Type, QC Workflow Version, QC Workflow Link, MSI Workflow Link, MSI Score, MSI Status, Pairs On Diff CHR, Total Reads, Total Uniquely Mapped, Total Unmapped reads, Proportion Reads Duplicated, Proportion Reads Mapped, Proportion Targets No Coverage, Proportion Base Mismatch, Short Reads, Proportion Coverage 10x, Proportion Coverage 30X,Is lowest level",,FALSE,Sequencing,Bulk RNA Level 1,, +Bulk WES Level 2,Bulk Whole Exome Sequencing aligned files and QC,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Alignment Workflow Type, Genomic Reference, Genomic Reference URL, Index File Name, Average Base Quality, Average Insert Size, Average Read Length, Contamination, Contamination Error, Mean Coverage, Adapter Content, Basic Statistics, Encoding, Overrepresented Sequences, Per Base N Content, Per Base Sequence Content, Per Base Sequence Quality, Per Sequence GC Content, Per Sequence Quality Score, Per Tile Sequence Quality, Percent GC Content, Sequence Duplication Levels, Sequence Length Distribution, QC Workflow Type, QC Workflow Version, QC Workflow Link, MSI Workflow Link, MSI Score, MSI Status, Pairs On Diff CHR, Total Reads, Total Uniquely Mapped, Total Unmapped reads, Proportion Reads Duplicated, Proportion Reads Mapped, Proportion Targets No Coverage, Proportion Base Mismatch, Short Reads, Proportion Coverage 10x, Proportion Coverage 30X,Is lowest level",,FALSE,Sequencing,Bulk RNA Level 1,, Bulk WES Level 3,Bulk Whole Exome Sequencing called variants,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Genomic Reference, Genomic Reference URL, Germline Variants Workflow URL, Germline Variants Workflow Type, Germline Variants Workflow Type, Somatic Variants Workflow URL, Somatic Variants Workflow Type, Somatic Variants Sample Type, Structural Variant Workflow URL, Structural Variant Workflow Type",,FALSE,Sequencing,Bulk WES Level 2,, scATAC-seq Level 1,"scATAC-seq files containing sequence read information, with or without alignment, as FASTQ or BAM files",,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Nucleic Acid Source, Dissociation Method, Single Nucleus Buffer, Single Cell Isolation Method, Transposition Reaction, scATACseq Library Layout, Nucleus Identifier, Nuclei Barcode Length, Nuclei Barcode Read, scATACseq Read1, scATACseq Read2, scATACseq Read3, Library Construction Method, Sequencing Platform, Threshold for Minimum Passing Reads, Total Number of Passing Nuclei, Median Fraction of Reads in Peaks, Median Fraction of Reads in Annotated cis DNA Elements, Median Passing Read Percentage, Median Percentage of Mitochondrial Reads per Nucleus,Technical Replicate Group, Total Reads, Protocol Link",,FALSE,Sequencing,Biospecimen,, scATAC-seq Level 2,"scATAC-seq files containing aligned sequence data, as a BAM file",,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Alignment Workflow Url, Alignment Workflow Type, Genomic Reference, Genomic, Reference URL, Index File Name, Average Base Quality, Average Insert Size, Average Read Length, Mean Coverage, Pairs On Diff CHR, Total Reads, Proportion Reads Mapped, MapQ30, Total Uniquely Mapped, Total Unmapped reads, Proportion Reads Duplicated, Short Reads, Proportion Coverage 10x, Proportion Coverage 30X, Proportion Targets No Coverage, Proportion Base Mismatch, Median Percentage of Mitochondrial Reads per Nucleus, Contamination,Contamination Error",,FALSE,Sequencing,scATAC-seq Level 1,, From ed75f275beb3e99d7604854d0cd165fd6bf7f2ce Mon Sep 17 00:00:00 2001 From: PozhidayevaDarya Date: Mon, 24 Jul 2023 17:44:46 +0000 Subject: [PATCH 7/9] GitHub Action: convert *.model.csv to *.model.jsonld --- HTAN.model.jsonld | 23 +++-------------------- 1 file changed, 3 insertions(+), 20 deletions(-) diff --git a/HTAN.model.jsonld b/HTAN.model.jsonld index e5bf2b41..77c88cd4 100644 --- a/HTAN.model.jsonld +++ b/HTAN.model.jsonld @@ -5807,10 +5807,10 @@ "sms:validationRules": [] }, { - "@id": "bts:BulkRNALevel2", + "@id": "bts:BulkWESLevel2", "@type": "rdfs:Class", "rdfs:comment": "Bulk Whole Exome Sequencing aligned files and QC", - "rdfs:label": "BulkRNALevel2", + "rdfs:label": "BulkWESLevel2", "rdfs:subClassOf": [ { "@id": "bts:Sequencing" @@ -5819,7 +5819,7 @@ "schema:isPartOf": { "@id": "http://schema.biothings.io" }, - "sms:displayName": "Bulk RNA Level 2", + "sms:displayName": "Bulk WES Level 2", "sms:required": "sms:false", "sms:requiresComponent": [ { @@ -51897,23 +51897,6 @@ "sms:required": "sms:false", "sms:validationRules": [] }, - { - "@id": "bts:BulkWESLevel2", - "@type": "rdfs:Class", - "rdfs:comment": "TBD", - "rdfs:label": "BulkWESLevel2", - "rdfs:subClassOf": [ - { - "@id": "schema:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "Bulk WES Level 2", - "sms:required": "sms:false", - "sms:validationRules": [] - }, { "@id": "bts:Genomic", "@type": "rdfs:Class", From 68a5f2c040fb2621c5e66fb80d044a5b94d77f51 Mon Sep 17 00:00:00 2001 From: PozhidayevaDarya <106110175+PozhidayevaDarya@users.noreply.github.com> Date: Mon, 24 Jul 2023 13:49:39 -0700 Subject: [PATCH 8/9] Update HTAN.model.csv --- HTAN.model.csv | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/HTAN.model.csv b/HTAN.model.csv index 776a56a7..bd90e0ae 100644 --- a/HTAN.model.csv +++ b/HTAN.model.csv @@ -49,7 +49,7 @@ Bulk RNA-seq Level 1,Bulk RNA-seq [EFO_0003738],,"Component, Filename, File Form Bulk RNA-seq Level 2,Bulk RNA-seq alignment protocol description,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, HTAN Parent Data File ID, Alignment Workflow Url, Alignment Workflow Type, Genomic Reference, Genomic Reference URL, Index File Name, Average Base Quality, Average Insert Size, Average Read Length, Contamination, Contamination Error, Mean Coverage, MSI Workflow Link, MSI Score, MSI Status, Pairs On Diff CHR, Total Reads, Total Uniquely Mapped, Total Unmapped reads, Proportion Reads Duplicated, Proportion Reads Mapped, Proportion, Targets No Coverage, Proportion Base Mismatch, Short Reads, Is lowest level",,FALSE,Sequencing,Bulk RNA-seq Level 1,, Bulk RNA-seq Level 3,Bulk RNA-seq gene expression matrices,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Pseudo Alignment Used, Data Category, Expression Units, Matrix Type, Fusion Gene Detected, Fusion Gene Identity",,FALSE,Sequencing,Bulk RNA-seq Level 2,, Bulk WES Level 1,Bulk Whole Exome Sequencing raw files,,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Sequencing Batch ID, Library Layout, Read Indicator, Library Selection Method, Read Length, Target Capture Kit, Library Preparation Kit Name, Library Preparation Kit Vendor, Library Preparation Kit Version, Sequencing Platform, Adapter Name, Adapter Sequence, Base Caller Name, Base Caller Version, Flow Cell Barcode, Fragment Maximum Length, Fragment Mean Length, Fragment Minimum Length, Fragment Standard Deviation Length, Lane Number, Multiplex Barcode, Library Preparation Days from Index, Size Selection Range, Target Depth, To Trim Adapter Sequence",,FALSE,Sequencing,Biospecimen,, -Bulk WES Level 2,Bulk Whole Exome Sequencing aligned files and QC,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Alignment Workflow Type, Genomic Reference, Genomic Reference URL, Index File Name, Average Base Quality, Average Insert Size, Average Read Length, Contamination, Contamination Error, Mean Coverage, Adapter Content, Basic Statistics, Encoding, Overrepresented Sequences, Per Base N Content, Per Base Sequence Content, Per Base Sequence Quality, Per Sequence GC Content, Per Sequence Quality Score, Per Tile Sequence Quality, Percent GC Content, Sequence Duplication Levels, Sequence Length Distribution, QC Workflow Type, QC Workflow Version, QC Workflow Link, MSI Workflow Link, MSI Score, MSI Status, Pairs On Diff CHR, Total Reads, Total Uniquely Mapped, Total Unmapped reads, Proportion Reads Duplicated, Proportion Reads Mapped, Proportion Targets No Coverage, Proportion Base Mismatch, Short Reads, Proportion Coverage 10x, Proportion Coverage 30X,Is lowest level",,FALSE,Sequencing,Bulk RNA Level 1,, +Bulk WES Level 2,Bulk Whole Exome Sequencing aligned files and QC,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Alignment Workflow Type, Genomic Reference, Genomic Reference URL, Index File Name, Average Base Quality, Average Insert Size, Average Read Length, Contamination, Contamination Error, Mean Coverage, Adapter Content, Basic Statistics, Encoding, Overrepresented Sequences, Per Base N Content, Per Base Sequence Content, Per Base Sequence Quality, Per Sequence GC Content, Per Sequence Quality Score, Per Tile Sequence Quality, Percent GC Content, Sequence Duplication Levels, Sequence Length Distribution, QC Workflow Type, QC Workflow Version, QC Workflow Link, MSI Workflow Link, MSI Score, MSI Status, Pairs On Diff CHR, Total Reads, Total Uniquely Mapped, Total Unmapped reads, Proportion Reads Duplicated, Proportion Reads Mapped, Proportion Targets No Coverage, Proportion Base Mismatch, Short Reads, Proportion Coverage 10x, Proportion Coverage 30X,Is lowest level",,FALSE,Sequencing,Bulk WES Level 1,, Bulk WES Level 3,Bulk Whole Exome Sequencing called variants,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Genomic Reference, Genomic Reference URL, Germline Variants Workflow URL, Germline Variants Workflow Type, Germline Variants Workflow Type, Somatic Variants Workflow URL, Somatic Variants Workflow Type, Somatic Variants Sample Type, Structural Variant Workflow URL, Structural Variant Workflow Type",,FALSE,Sequencing,Bulk WES Level 2,, scATAC-seq Level 1,"scATAC-seq files containing sequence read information, with or without alignment, as FASTQ or BAM files",,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Nucleic Acid Source, Dissociation Method, Single Nucleus Buffer, Single Cell Isolation Method, Transposition Reaction, scATACseq Library Layout, Nucleus Identifier, Nuclei Barcode Length, Nuclei Barcode Read, scATACseq Read1, scATACseq Read2, scATACseq Read3, Library Construction Method, Sequencing Platform, Threshold for Minimum Passing Reads, Total Number of Passing Nuclei, Median Fraction of Reads in Peaks, Median Fraction of Reads in Annotated cis DNA Elements, Median Passing Read Percentage, Median Percentage of Mitochondrial Reads per Nucleus,Technical Replicate Group, Total Reads, Protocol Link",,FALSE,Sequencing,Biospecimen,, scATAC-seq Level 2,"scATAC-seq files containing aligned sequence data, as a BAM file",,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Alignment Workflow Url, Alignment Workflow Type, Genomic Reference, Genomic, Reference URL, Index File Name, Average Base Quality, Average Insert Size, Average Read Length, Mean Coverage, Pairs On Diff CHR, Total Reads, Proportion Reads Mapped, MapQ30, Total Uniquely Mapped, Total Unmapped reads, Proportion Reads Duplicated, Short Reads, Proportion Coverage 10x, Proportion Coverage 30X, Proportion Targets No Coverage, Proportion Base Mismatch, Median Percentage of Mitochondrial Reads per Nucleus, Contamination,Contamination Error",,FALSE,Sequencing,scATAC-seq Level 1,, From 2b4506679758a3f7600e0a4c7f74fff179c832ae Mon Sep 17 00:00:00 2001 From: PozhidayevaDarya Date: Mon, 24 Jul 2023 21:02:25 +0000 Subject: [PATCH 9/9] GitHub Action: convert *.model.csv to *.model.jsonld --- HTAN.model.jsonld | 19 +------------------ 1 file changed, 1 insertion(+), 18 deletions(-) diff --git a/HTAN.model.jsonld b/HTAN.model.jsonld index 77c88cd4..4780e1d7 100644 --- a/HTAN.model.jsonld +++ b/HTAN.model.jsonld @@ -5823,7 +5823,7 @@ "sms:required": "sms:false", "sms:requiresComponent": [ { - "@id": "bts:BulkRNALevel1" + "@id": "bts:BulkWESLevel1" } ], "sms:requiresDependency": [ @@ -51880,23 +51880,6 @@ "sms:required": "sms:false", "sms:validationRules": [] }, - { - "@id": "bts:BulkRNALevel1", - "@type": "rdfs:Class", - "rdfs:comment": "TBD", - "rdfs:label": "BulkRNALevel1", - "rdfs:subClassOf": [ - { - "@id": "schema:Thing" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "Bulk RNA Level 1", - "sms:required": "sms:false", - "sms:validationRules": [] - }, { "@id": "bts:Genomic", "@type": "rdfs:Class",