From 3459dd9826feb3a21a665877ea69caa17e82577e Mon Sep 17 00:00:00 2001 From: David L Gibbs Date: Tue, 28 May 2024 16:34:23 -0700 Subject: [PATCH 1/6] multiplex cite-seq added to data model. Four levels were added plus five new features (at end of model): -Associated mRNA Library Data File ID -Single Cell Barcode Method Applied -Feature Barcode Library Type -Barcode Folder Synapse ID -Barcode Folder File List some higher level intermediate features were used: -read1 -read2 -cDNA read1 contains "Cell Barcode and UMI" which in turn contains six other features related to barcodes. --- HTAN.model.csv | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/HTAN.model.csv b/HTAN.model.csv index e60ec5af..9a6d517c 100644 --- a/HTAN.model.csv +++ b/HTAN.model.csv @@ -66,6 +66,10 @@ scmC-seq Level 2,"Files contain scmC-seq files containing aligned sequence data, scATAC-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, scATACseq Workflow Type, scATACseq Workflow Parameters Description, Workflow Version, Workflow Link",,FALSE,Sequencing,scATAC-seq Level 3,, scDNA-seq Level 1,Single-cell DNA-seq,,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Sequencing Batch ID, Library Layout, Nucleic Acid Source, Library Selection Method, Read Length, Library Preparation Kit Name, Library Preparation Kit Vendor, Library Preparation Kit Version, 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, 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,, scDNA-seq Level 2,Alignment workflows downstream of scDNA-seq Level 1,,"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, Proportion Mitochondrial Reads, Contamination, Contamination Error",,FALSE,Sequencing,scDNA-seq Level 1,, +Multiplexed CITE-seq Level 1,Raw sequencing files for the multiplexed CITE-seq assay,,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Nucleic Acid Source,Cryopreserved Cells in Sample, Single Cell Isolation Method, Dissociation Method, Library Construction Method,Read Indicator, Read1, Read2, cDNA, End Bias, Reverse Transcription Primer, Spike In, Spike In Concentration, Sequencing Platform, Total Number of Input Cells, Input Cells and Nuclei, Library Preparation Days from Index, Single Cell Dissociation Days from Index, Sequencing Library Construction Days from Index, Nucleic Acid Capture Days from Index, Protocol Link, Technical Replicate Group, Input Cells and Nuclei,Empty Well Barcode,Well Index,Feature Reference Id, Associated mRNA Library Data File ID, Single Cell Barcode Method Applied, Feature Barcode Library Type, Barcode Folder Synapse ID, Barcode Folder File List",, FALSE,Sequencing,Biospecimen,, +Multiplexed CITE-seq Level 2,Alignment workflows downstream of Multiplexed CITE-seq Level 1,,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Parent Data File ID, HTAN Data File ID, Associated mRNA Library 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,Multiplexed CITE-seq Level 1,, +Multiplexed CITE-seq Level 3,Gene and Isoform expression files,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Parent Biospecimen ID, HTAN Data File ID, Associated mRNA Library 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,, +Multiplexed CITE-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 Parent Biospecimen ID, HTAN Data File ID, Associated mRNA Library Data File ID, scRNAseq Workflow Type, scRNAseq Workflow Parameters Description, Workflow Version, Workflow Link",,FALSE,Sequencing,Multiplexed CITE-seq Level 3,, Bulk Methylation-seq Level 1,"Raw data for bulk methylation sequencing, such as FASTQs and unaligned BAMs",,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Nucleic Acid Source, Bisulfite Conversion, Sequencing Platform, Replicate Type, Bulk Methylation Assay Type, Total DNA Input",,FALSE,Sequencing,Biospecimen,, Bulk Methylation-seq Level 2,"Aligned primary data for bulk methylation sequencing, such as gene expression matrix files, VCFs, etc.",,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Alignment Workflow Url, Trimmer, Bulk Methylation Genomic Reference, Genomic Reference URL, Index File Name, Alignment Workflow Type, Duplicate Removal Software, Mean Coverage, Library Layout, Average Base Quality, Average Insert Size, Average Read Length, Contamination, Contamination Error, 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 of Minimum CpG Coverage 10X, Proportion Coverage 30X",,FALSE,Sequencing,"Bulk Methylation-seq Level 1, Biospecimen",, Bulk Methylation-seq Level 3,"Sample level summary data for bulk methylation sequencing, such as t-SNE plot coordinates, etc.",,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID,DMC Calling Tool, DMC Calling Workflow URL, DMR Calling Tool, DMR Calling Workflow URL, pUC19 methylation ratio, Lambda methylation ratio, DMC data file format, DMR data file Format",,FALSE,Sequencing,"Bulk Methylation-seq Level 2, Biospecimen",, @@ -1030,3 +1034,8 @@ Barretts Esophagus Goblet Cells Present,Presence or absennce of Barretts esophag Pancreatitis Onset Year,Date of onset of pancreatitis.,,,,FALSE,Follow Up,,,num HTAN Parent Channel Metadata ID,HTAN ID for a level 3 channels table.,,,,TRUE, Imaging Level 4,,, Single Nucleus Capture,Nuclei isolation method,"Plates, 10x, droplet",,,FALSE,scmC-seq Level 1,,, +Associated mRNA Library Data File ID,Sample Level HTAN Data File ID for the associated level - HTAN ID of this file HTAN ID SOP (eg HTANx_yyy_zzz),,,,TRUE,Multiplexed CITE-seq Level 1,,, +Single Cell Barcode Method Applied,The method by which cells are multiplex or labeled with cell surface markers or probes,"Cite-seq custom panel,Biolegend Total seq A Custom,Biolegend Total seq B Custom,Biolegend Total seq C Custom,Biolegend Total seq A Human,Universal cocktail V1.0,Biolegend Total seq B Human Universal cocktail V1.0,Biolegend Total seq C Human Universal cocktail V1.0,Cell,Hashtag- multiplex,Nuclear Hashtag- multiplex,Other",,,TRUE,Multiplexed CITE-seq Level 1,,, +Feature Barcode Library Type,The library construction methods for the feature barcode library,"10x ADT – citeseq/hashing,10x TCR,10x BCR",,,TRUE,Multiplexed CITE-seq Level 1,,, +Barcode Folder Synapse ID,Synapse ID of the folder containing the barcode lists,,,,TRUE,Multiplexed CITE-seq Level 1,,, +Barcode Folder File List,A comma separated list of filenames in the gzipped folder detailing what barcodes are specific to demultiplexing samples versus providing surface protein data,,,,TRUE,Multiplexed CITE-seq Level 1,,, From 058f9bcf3cdda2afd847325e670345fbb47813ad Mon Sep 17 00:00:00 2001 From: David L Gibbs Date: Tue, 28 May 2024 16:42:54 -0700 Subject: [PATCH 2/6] Update HTAN.model.csv bug fix, changing " FALSE" to "FALSE" --- HTAN.model.csv | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/HTAN.model.csv b/HTAN.model.csv index 9a6d517c..f04e9685 100644 --- a/HTAN.model.csv +++ b/HTAN.model.csv @@ -66,7 +66,7 @@ scmC-seq Level 2,"Files contain scmC-seq files containing aligned sequence data, scATAC-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, scATACseq Workflow Type, scATACseq Workflow Parameters Description, Workflow Version, Workflow Link",,FALSE,Sequencing,scATAC-seq Level 3,, scDNA-seq Level 1,Single-cell DNA-seq,,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Sequencing Batch ID, Library Layout, Nucleic Acid Source, Library Selection Method, Read Length, Library Preparation Kit Name, Library Preparation Kit Vendor, Library Preparation Kit Version, 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, 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,, scDNA-seq Level 2,Alignment workflows downstream of scDNA-seq Level 1,,"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, Proportion Mitochondrial Reads, Contamination, Contamination Error",,FALSE,Sequencing,scDNA-seq Level 1,, -Multiplexed CITE-seq Level 1,Raw sequencing files for the multiplexed CITE-seq assay,,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Nucleic Acid Source,Cryopreserved Cells in Sample, Single Cell Isolation Method, Dissociation Method, Library Construction Method,Read Indicator, Read1, Read2, cDNA, End Bias, Reverse Transcription Primer, Spike In, Spike In Concentration, Sequencing Platform, Total Number of Input Cells, Input Cells and Nuclei, Library Preparation Days from Index, Single Cell Dissociation Days from Index, Sequencing Library Construction Days from Index, Nucleic Acid Capture Days from Index, Protocol Link, Technical Replicate Group, Input Cells and Nuclei,Empty Well Barcode,Well Index,Feature Reference Id, Associated mRNA Library Data File ID, Single Cell Barcode Method Applied, Feature Barcode Library Type, Barcode Folder Synapse ID, Barcode Folder File List",, FALSE,Sequencing,Biospecimen,, +Multiplexed CITE-seq Level 1,Raw sequencing files for the multiplexed CITE-seq assay,,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Nucleic Acid Source,Cryopreserved Cells in Sample, Single Cell Isolation Method, Dissociation Method, Library Construction Method,Read Indicator, Read1, Read2, cDNA, End Bias, Reverse Transcription Primer, Spike In, Spike In Concentration, Sequencing Platform, Total Number of Input Cells, Input Cells and Nuclei, Library Preparation Days from Index, Single Cell Dissociation Days from Index, Sequencing Library Construction Days from Index, Nucleic Acid Capture Days from Index, Protocol Link, Technical Replicate Group, Input Cells and Nuclei,Empty Well Barcode,Well Index,Feature Reference Id, Associated mRNA Library Data File ID, Single Cell Barcode Method Applied, Feature Barcode Library Type, Barcode Folder Synapse ID, Barcode Folder File List",,FALSE,Sequencing,Biospecimen,, Multiplexed CITE-seq Level 2,Alignment workflows downstream of Multiplexed CITE-seq Level 1,,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Parent Data File ID, HTAN Data File ID, Associated mRNA Library 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,Multiplexed CITE-seq Level 1,, Multiplexed CITE-seq Level 3,Gene and Isoform expression files,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Parent Biospecimen ID, HTAN Data File ID, Associated mRNA Library 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,, Multiplexed CITE-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 Parent Biospecimen ID, HTAN Data File ID, Associated mRNA Library Data File ID, scRNAseq Workflow Type, scRNAseq Workflow Parameters Description, Workflow Version, Workflow Link",,FALSE,Sequencing,Multiplexed CITE-seq Level 3,, From 26598ba71189a440b62032bc34aed835e25122c9 Mon Sep 17 00:00:00 2001 From: David L Gibbs Date: Tue, 28 May 2024 16:44:47 -0700 Subject: [PATCH 3/6] Update HTAN.model.csv removing duplicate item --- HTAN.model.csv | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/HTAN.model.csv b/HTAN.model.csv index f04e9685..5c264a91 100644 --- a/HTAN.model.csv +++ b/HTAN.model.csv @@ -66,7 +66,7 @@ scmC-seq Level 2,"Files contain scmC-seq files containing aligned sequence data, scATAC-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, scATACseq Workflow Type, scATACseq Workflow Parameters Description, Workflow Version, Workflow Link",,FALSE,Sequencing,scATAC-seq Level 3,, scDNA-seq Level 1,Single-cell DNA-seq,,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Sequencing Batch ID, Library Layout, Nucleic Acid Source, Library Selection Method, Read Length, Library Preparation Kit Name, Library Preparation Kit Vendor, Library Preparation Kit Version, 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, 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,, scDNA-seq Level 2,Alignment workflows downstream of scDNA-seq Level 1,,"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, Proportion Mitochondrial Reads, Contamination, Contamination Error",,FALSE,Sequencing,scDNA-seq Level 1,, -Multiplexed CITE-seq Level 1,Raw sequencing files for the multiplexed CITE-seq assay,,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Nucleic Acid Source,Cryopreserved Cells in Sample, Single Cell Isolation Method, Dissociation Method, Library Construction Method,Read Indicator, Read1, Read2, cDNA, End Bias, Reverse Transcription Primer, Spike In, Spike In Concentration, Sequencing Platform, Total Number of Input Cells, Input Cells and Nuclei, Library Preparation Days from Index, Single Cell Dissociation Days from Index, Sequencing Library Construction Days from Index, Nucleic Acid Capture Days from Index, Protocol Link, Technical Replicate Group, Input Cells and Nuclei,Empty Well Barcode,Well Index,Feature Reference Id, Associated mRNA Library Data File ID, Single Cell Barcode Method Applied, Feature Barcode Library Type, Barcode Folder Synapse ID, Barcode Folder File List",,FALSE,Sequencing,Biospecimen,, +Multiplexed CITE-seq Level 1,Raw sequencing files for the multiplexed CITE-seq assay,,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Nucleic Acid Source,Cryopreserved Cells in Sample, Single Cell Isolation Method, Dissociation Method, Library Construction Method,Read Indicator, Read1, Read2, cDNA, End Bias, Reverse Transcription Primer, Spike In, Spike In Concentration, Sequencing Platform, Total Number of Input Cells, Input Cells and Nuclei, Library Preparation Days from Index, Single Cell Dissociation Days from Index, Sequencing Library Construction Days from Index, Nucleic Acid Capture Days from Index, Protocol Link, Technical Replicate Group, Empty Well Barcode,Well Index,Feature Reference Id, Associated mRNA Library Data File ID, Single Cell Barcode Method Applied, Feature Barcode Library Type, Barcode Folder Synapse ID, Barcode Folder File List",,FALSE,Sequencing,Biospecimen,, Multiplexed CITE-seq Level 2,Alignment workflows downstream of Multiplexed CITE-seq Level 1,,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Parent Data File ID, HTAN Data File ID, Associated mRNA Library 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,Multiplexed CITE-seq Level 1,, Multiplexed CITE-seq Level 3,Gene and Isoform expression files,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Parent Biospecimen ID, HTAN Data File ID, Associated mRNA Library 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,, Multiplexed CITE-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 Parent Biospecimen ID, HTAN Data File ID, Associated mRNA Library Data File ID, scRNAseq Workflow Type, scRNAseq Workflow Parameters Description, Workflow Version, Workflow Link",,FALSE,Sequencing,Multiplexed CITE-seq Level 3,, From a7c47e83e8e4b4691ab1b8d5b33acecf52805a2b Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" <41898282+github-actions[bot]@users.noreply.github.com> Date: Tue, 28 May 2024 23:49:33 +0000 Subject: [PATCH 4/6] GitHub Action: convert *.model.csv to *.model.jsonld --- HTAN.model.jsonld | 961 ++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 839 insertions(+), 122 deletions(-) diff --git a/HTAN.model.jsonld b/HTAN.model.jsonld index de8bd16b..fed2319c 100644 --- a/HTAN.model.jsonld +++ b/HTAN.model.jsonld @@ -36971,6 +36971,604 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:MultiplexedCITE-seqLevel1", + "@type": "rdfs:Class", + "rdfs:comment": "Raw sequencing files for the multiplexed CITE-seq assay", + "rdfs:label": "MultiplexedCITE-seqLevel1", + "rdfs:subClassOf": [ + { + "@id": "bts:Sequencing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Multiplexed CITE-seq Level 1", + "sms:required": "sms:false", + "sms:requiresComponent": [ + { + "@id": "bts:Biospecimen" + } + ], + "sms:requiresDependency": [ + { + "@id": "bts:Component" + }, + { + "@id": "bts:Filename" + }, + { + "@id": "bts:FileFormat" + }, + { + "@id": "bts:HTANParentBiospecimenID" + }, + { + "@id": "bts:HTANDataFileID" + }, + { + "@id": "bts:NucleicAcidSource" + }, + { + "@id": "bts:CryopreservedCellsinSample" + }, + { + "@id": "bts:SingleCellIsolationMethod" + }, + { + "@id": "bts:DissociationMethod" + }, + { + "@id": "bts:LibraryConstructionMethod" + }, + { + "@id": "bts:ReadIndicator" + }, + { + "@id": "bts:Read1" + }, + { + "@id": "bts:Read2" + }, + { + "@id": "bts:CDNA" + }, + { + "@id": "bts:EndBias" + }, + { + "@id": "bts:ReverseTranscriptionPrimer" + }, + { + "@id": "bts:SpikeIn" + }, + { + "@id": "bts:SpikeInConcentration" + }, + { + "@id": "bts:SequencingPlatform" + }, + { + "@id": "bts:TotalNumberofInputCells" + }, + { + "@id": "bts:InputCellsandNuclei" + }, + { + "@id": "bts:LibraryPreparationDaysfromIndex" + }, + { + "@id": "bts:SingleCellDissociationDaysfromIndex" + }, + { + "@id": "bts:SequencingLibraryConstructionDaysfromIndex" + }, + { + "@id": "bts:NucleicAcidCaptureDaysfromIndex" + }, + { + "@id": "bts:ProtocolLink" + }, + { + "@id": "bts:TechnicalReplicateGroup" + }, + { + "@id": "bts:EmptyWellBarcode" + }, + { + "@id": "bts:WellIndex" + }, + { + "@id": "bts:FeatureReferenceId" + }, + { + "@id": "bts:AssociatedmRNALibraryDataFileID" + }, + { + "@id": "bts:SingleCellBarcodeMethodApplied" + }, + { + "@id": "bts:FeatureBarcodeLibraryType" + }, + { + "@id": "bts:BarcodeFolderSynapseID" + }, + { + "@id": "bts:BarcodeFolderFileList" + } + ], + "sms:validationRules": [] + }, + { + "@id": "bts:CDNA", + "@type": "rdfs:Class", + "rdfs:comment": "Complementary DNA. A DNA copy of an mRNA or complex sample of mRNAs, made using reverse transcriptase", + "rdfs:label": "CDNA", + "rdfs:subClassOf": [ + { + "@id": "bts:Sequencing" + }, + { + "@id": "bts:SpatialRead1" + }, + { + "@id": "bts:SpatialRead2" + }, + { + "@id": "bts:ScmCseqRead1" + }, + { + "@id": "bts:ScmCseqRead2" + }, + { + "@id": "bts:ScmCseqRead3" + }, + { + "@id": "bts:Read1" + }, + { + "@id": "bts:Read2" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "cDNA", + "sms:required": "sms:false", + "sms:requiresDependency": [ + { + "@id": "bts:CDNAOffset" + }, + { + "@id": "bts:CDNALength" + } + ], + "sms:validationRules": [] + }, + { + "@id": "bts:SpikeInConcentration", + "@type": "rdfs:Class", + "rdfs:comment": "The final concentration or dilution (for commercial sets) of the spike in mix [PMID:21816910]", + "rdfs:label": "SpikeInConcentration", + "rdfs:subClassOf": [ + { + "@id": "bts:ERCC" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Spike In Concentration", + "sms:required": "sms:true", + "sms:validationRules": [] + }, + { + "@id": "bts:EmptyWellBarcode", + "@type": "rdfs:Class", + "rdfs:comment": "Unique cell barcode assigned to empty cells used as controls in CEL-seq2 assays.", + "rdfs:label": "EmptyWellBarcode", + "rdfs:subClassOf": [ + { + "@id": "bts:ScRNA-seqLevel1" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Empty Well Barcode", + "sms:required": "sms:true", + "sms:validationRules": [] + }, + { + "@id": "bts:WellIndex", + "@type": "rdfs:Class", + "rdfs:comment": "Indicate if protein expression (EPCAM/CD45) positive/negative data is available for each cell in CEL-seq2 assays", + "rdfs:label": "WellIndex", + "rdfs:subClassOf": [ + { + "@id": "bts:ScRNA-seqLevel1" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "schema:rangeIncludes": [ + { + "@id": "bts:Yes" + }, + { + "@id": "bts:No" + } + ], + "sms:displayName": "Well Index", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:FeatureReferenceId", + "@type": "rdfs:Class", + "rdfs:comment": "Unique ID for this feature. Must not contain whitespace, quote or comma characters. Each ID must be unique and must not collide with a gene identifier from the transcriptome [https://support.10xgenomics.com/single-cell-gene-expression/software/pipelines/latest/using/feature-bc-analysis#feature-ref]", + "rdfs:label": "FeatureReferenceId", + "rdfs:subClassOf": [ + { + "@id": "bts:ScRNA-seqLevel1" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Feature Reference Id", + "sms:required": "sms:true", + "sms:validationRules": [] + }, + { + "@id": "bts:AssociatedmRNALibraryDataFileID", + "@type": "rdfs:Class", + "rdfs:comment": "Sample Level HTAN Data File ID for the associated level - HTAN ID of this file HTAN ID SOP (eg HTANx_yyy_zzz)", + "rdfs:label": "AssociatedmRNALibraryDataFileID", + "rdfs:subClassOf": [ + { + "@id": "bts:MultiplexedCITE-seqLevel1" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Associated mRNA Library Data File ID", + "sms:required": "sms:true", + "sms:validationRules": [] + }, + { + "@id": "bts:SingleCellBarcodeMethodApplied", + "@type": "rdfs:Class", + "rdfs:comment": "The method by which cells are multiplex or labeled with cell surface markers or probes", + "rdfs:label": "SingleCellBarcodeMethodApplied", + "rdfs:subClassOf": [ + { + "@id": "bts:MultiplexedCITE-seqLevel1" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "schema:rangeIncludes": [ + { + "@id": "bts:Cite-seqcustompanel" + }, + { + "@id": "bts:BiolegendTotalseqACustom" + }, + { + "@id": "bts:BiolegendTotalseqBCustom" + }, + { + "@id": "bts:BiolegendTotalseqCCustom" + }, + { + "@id": "bts:BiolegendTotalseqAHuman" + }, + { + "@id": "bts:UniversalcocktailV1.0" + }, + { + "@id": "bts:BiolegendTotalseqBHumanUniversalcocktailV1.0" + }, + { + "@id": "bts:BiolegendTotalseqCHumanUniversalcocktailV1.0" + }, + { + "@id": "bts:Cell" + }, + { + "@id": "bts:Hashtag-multiplex" + }, + { + "@id": "bts:NuclearHashtag-multiplex" + }, + { + "@id": "bts:Other" + } + ], + "sms:displayName": "Single Cell Barcode Method Applied", + "sms:required": "sms:true", + "sms:validationRules": [] + }, + { + "@id": "bts:FeatureBarcodeLibraryType", + "@type": "rdfs:Class", + "rdfs:comment": "The library construction methods for the feature barcode library", + "rdfs:label": "FeatureBarcodeLibraryType", + "rdfs:subClassOf": [ + { + "@id": "bts:MultiplexedCITE-seqLevel1" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "schema:rangeIncludes": [ + { + "@id": "bts:10xADT–citeseq/hashing" + }, + { + "@id": "bts:10xTCR" + }, + { + "@id": "bts:10xBCR" + } + ], + "sms:displayName": "Feature Barcode Library Type", + "sms:required": "sms:true", + "sms:validationRules": [] + }, + { + "@id": "bts:BarcodeFolderSynapseID", + "@type": "rdfs:Class", + "rdfs:comment": "Synapse ID of the folder containing the barcode lists", + "rdfs:label": "BarcodeFolderSynapseID", + "rdfs:subClassOf": [ + { + "@id": "bts:MultiplexedCITE-seqLevel1" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Barcode Folder Synapse ID", + "sms:required": "sms:true", + "sms:validationRules": [] + }, + { + "@id": "bts:BarcodeFolderFileList", + "@type": "rdfs:Class", + "rdfs:comment": "A comma separated list of filenames in the gzipped folder detailing what barcodes are specific to demultiplexing samples versus providing surface protein data", + "rdfs:label": "BarcodeFolderFileList", + "rdfs:subClassOf": [ + { + "@id": "bts:MultiplexedCITE-seqLevel1" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Barcode Folder File List", + "sms:required": "sms:true", + "sms:validationRules": [] + }, + { + "@id": "bts:MultiplexedCITE-seqLevel2", + "@type": "rdfs:Class", + "rdfs:comment": "Alignment workflows downstream of Multiplexed CITE-seq Level 1", + "rdfs:label": "MultiplexedCITE-seqLevel2", + "rdfs:subClassOf": [ + { + "@id": "bts:Sequencing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Multiplexed CITE-seq Level 2", + "sms:required": "sms:false", + "sms:requiresComponent": [ + { + "@id": "bts:MultiplexedCITE-seqLevel1" + } + ], + "sms:requiresDependency": [ + { + "@id": "bts:Component" + }, + { + "@id": "bts:Filename" + }, + { + "@id": "bts:FileFormat" + }, + { + "@id": "bts:HTANParentBiospecimenID" + }, + { + "@id": "bts:HTANParentDataFileID" + }, + { + "@id": "bts:HTANDataFileID" + }, + { + "@id": "bts:AssociatedmRNALibraryDataFileID" + }, + { + "@id": "bts:ScRNAseqWorkflowType" + }, + { + "@id": "bts:WorkflowVersion" + }, + { + "@id": "bts:ScRNAseqWorkflowParametersDescription" + }, + { + "@id": "bts:WorkflowLink" + }, + { + "@id": "bts:GenomicReference" + }, + { + "@id": "bts:GenomicReferenceURL" + }, + { + "@id": "bts:GenomeAnnotationURL" + }, + { + "@id": "bts:Checksum" + }, + { + "@id": "bts:WhitelistCellBarcodeFileLink" + }, + { + "@id": "bts:CellBarcodeTag" + }, + { + "@id": "bts:UMITag" + }, + { + "@id": "bts:AppliedHardTrimming" + } + ], + "sms:validationRules": [] + }, + { + "@id": "bts:MultiplexedCITE-seqLevel3", + "@type": "rdfs:Class", + "rdfs:comment": "Gene and Isoform expression files", + "rdfs:label": "MultiplexedCITE-seqLevel3", + "rdfs:subClassOf": [ + { + "@id": "bts:Sequencing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Multiplexed CITE-seq Level 3", + "sms:required": "sms:false", + "sms:requiresComponent": [ + { + "@id": "bts:ScRNA-seqLevel2" + } + ], + "sms:requiresDependency": [ + { + "@id": "bts:Component" + }, + { + "@id": "bts:Filename" + }, + { + "@id": "bts:FileFormat" + }, + { + "@id": "bts:HTANParentDataFileID" + }, + { + "@id": "bts:HTANParentBiospecimenID" + }, + { + "@id": "bts:HTANDataFileID" + }, + { + "@id": "bts:AssociatedmRNALibraryDataFileID" + }, + { + "@id": "bts:DataCategory" + }, + { + "@id": "bts:MatrixType" + }, + { + "@id": "bts:LinkedMatrices" + }, + { + "@id": "bts:CellMedianNumberReads" + }, + { + "@id": "bts:CellMedianNumberGenes" + }, + { + "@id": "bts:CellTotal" + }, + { + "@id": "bts:ScRNAseqWorkflowType" + }, + { + "@id": "bts:ScRNAseqWorkflowParametersDescription" + }, + { + "@id": "bts:WorkflowLink" + }, + { + "@id": "bts:WorkflowVersion" + } + ], + "sms:validationRules": [] + }, + { + "@id": "bts:MultiplexedCITE-seqLevel4", + "@type": "rdfs:Class", + "rdfs:comment": "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)", + "rdfs:label": "MultiplexedCITE-seqLevel4", + "rdfs:subClassOf": [ + { + "@id": "bts:Sequencing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Multiplexed CITE-seq Level 4", + "sms:required": "sms:false", + "sms:requiresComponent": [ + { + "@id": "bts:MultiplexedCITE-seqLevel3" + } + ], + "sms:requiresDependency": [ + { + "@id": "bts:Component" + }, + { + "@id": "bts:Filename" + }, + { + "@id": "bts:FileFormat" + }, + { + "@id": "bts:HTANParentDataFileID" + }, + { + "@id": "bts:HTANParentBiospecimenID" + }, + { + "@id": "bts:HTANDataFileID" + }, + { + "@id": "bts:AssociatedmRNALibraryDataFileID" + }, + { + "@id": "bts:ScRNAseqWorkflowType" + }, + { + "@id": "bts:ScRNAseqWorkflowParametersDescription" + }, + { + "@id": "bts:WorkflowVersion" + }, + { + "@id": "bts:WorkflowLink" + } + ], + "sms:validationRules": [] + }, { "@id": "bts:BulkMethylation-seqLevel1", "@type": "rdfs:Class", @@ -40516,52 +41114,6 @@ "sms:required": "sms:true", "sms:validationRules": [] }, - { - "@id": "bts:CDNA", - "@type": "rdfs:Class", - "rdfs:comment": "Complementary DNA. A DNA copy of an mRNA or complex sample of mRNAs, made using reverse transcriptase", - "rdfs:label": "CDNA", - "rdfs:subClassOf": [ - { - "@id": "bts:Sequencing" - }, - { - "@id": "bts:SpatialRead1" - }, - { - "@id": "bts:SpatialRead2" - }, - { - "@id": "bts:ScmCseqRead1" - }, - { - "@id": "bts:ScmCseqRead2" - }, - { - "@id": "bts:ScmCseqRead3" - }, - { - "@id": "bts:Read1" - }, - { - "@id": "bts:Read2" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "cDNA", - "sms:required": "sms:false", - "sms:requiresDependency": [ - { - "@id": "bts:CDNAOffset" - }, - { - "@id": "bts:CDNALength" - } - ], - "sms:validationRules": [] - }, { "@id": "bts:Smart-seq2", "@type": "rdfs:Class", @@ -42917,6 +43469,9 @@ { "@id": "bts:MolecularAnalysisMethod" }, + { + "@id": "bts:SingleCellBarcodeMethodApplied" + }, { "@id": "bts:LungAdjacentHistologyType" }, @@ -49907,48 +50462,6 @@ "sms:required": "sms:false", "sms:validationRules": [] }, - { - "@id": "bts:EmptyWellBarcode", - "@type": "rdfs:Class", - "rdfs:comment": "Unique cell barcode assigned to empty cells used as controls in CEL-seq2 assays.", - "rdfs:label": "EmptyWellBarcode", - "rdfs:subClassOf": [ - { - "@id": "bts:ScRNA-seqLevel1" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "Empty Well Barcode", - "sms:required": "sms:true", - "sms:validationRules": [] - }, - { - "@id": "bts:WellIndex", - "@type": "rdfs:Class", - "rdfs:comment": "Indicate if protein expression (EPCAM/CD45) positive/negative data is available for each cell in CEL-seq2 assays", - "rdfs:label": "WellIndex", - "rdfs:subClassOf": [ - { - "@id": "bts:ScRNA-seqLevel1" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "schema:rangeIncludes": [ - { - "@id": "bts:Yes" - }, - { - "@id": "bts:No" - } - ], - "sms:displayName": "Well Index", - "sms:required": "sms:false", - "sms:validationRules": [] - }, { "@id": "bts:3Prime", "@type": "rdfs:Class", @@ -50079,23 +50592,6 @@ "sms:required": "sms:false", "sms:validationRules": [] }, - { - "@id": "bts:FeatureReferenceId", - "@type": "rdfs:Class", - "rdfs:comment": "Unique ID for this feature. Must not contain whitespace, quote or comma characters. Each ID must be unique and must not collide with a gene identifier from the transcriptome [https://support.10xgenomics.com/single-cell-gene-expression/software/pipelines/latest/using/feature-bc-analysis#feature-ref]", - "rdfs:label": "FeatureReferenceId", - "rdfs:subClassOf": [ - { - "@id": "bts:ScRNA-seqLevel1" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "Feature Reference Id", - "sms:required": "sms:true", - "sms:validationRules": [] - }, { "@id": "bts:ERCC", "@type": "rdfs:Class", @@ -50169,23 +50665,6 @@ "sms:required": "sms:false", "sms:validationRules": [] }, - { - "@id": "bts:SpikeInConcentration", - "@type": "rdfs:Class", - "rdfs:comment": "The final concentration or dilution (for commercial sets) of the spike in mix [PMID:21816910]", - "rdfs:label": "SpikeInConcentration", - "rdfs:subClassOf": [ - { - "@id": "bts:ERCC" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "Spike In Concentration", - "sms:required": "sms:true", - "sms:validationRules": [] - }, { "@id": "bts:IlluminaNextSeq500", "@type": "rdfs:Class", @@ -150902,6 +151381,244 @@ "sms:displayName": "droplet", "sms:required": "sms:false", "sms:validationRules": [] + }, + { + "@id": "bts:Cite-seqcustompanel", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "Cite-seqcustompanel", + "rdfs:subClassOf": [ + { + "@id": "bts:SingleCellBarcodeMethodApplied" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Cite-seq custom panel", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:BiolegendTotalseqACustom", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "BiolegendTotalseqACustom", + "rdfs:subClassOf": [ + { + "@id": "bts:SingleCellBarcodeMethodApplied" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Biolegend Total seq A Custom", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:BiolegendTotalseqBCustom", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "BiolegendTotalseqBCustom", + "rdfs:subClassOf": [ + { + "@id": "bts:SingleCellBarcodeMethodApplied" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Biolegend Total seq B Custom", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:BiolegendTotalseqCCustom", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "BiolegendTotalseqCCustom", + "rdfs:subClassOf": [ + { + "@id": "bts:SingleCellBarcodeMethodApplied" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Biolegend Total seq C Custom", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:BiolegendTotalseqAHuman", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "BiolegendTotalseqAHuman", + "rdfs:subClassOf": [ + { + "@id": "bts:SingleCellBarcodeMethodApplied" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Biolegend Total seq A Human", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:UniversalcocktailV1.0", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "UniversalcocktailV1.0", + "rdfs:subClassOf": [ + { + "@id": "bts:SingleCellBarcodeMethodApplied" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Universal cocktail V1.0", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:BiolegendTotalseqBHumanUniversalcocktailV1.0", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "BiolegendTotalseqBHumanUniversalcocktailV1.0", + "rdfs:subClassOf": [ + { + "@id": "bts:SingleCellBarcodeMethodApplied" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Biolegend Total seq B Human Universal cocktail V1.0", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:BiolegendTotalseqCHumanUniversalcocktailV1.0", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "BiolegendTotalseqCHumanUniversalcocktailV1.0", + "rdfs:subClassOf": [ + { + "@id": "bts:SingleCellBarcodeMethodApplied" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Biolegend Total seq C Human Universal cocktail V1.0", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:Cell", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "Cell", + "rdfs:subClassOf": [ + { + "@id": "bts:SingleCellBarcodeMethodApplied" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Cell", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:Hashtag-multiplex", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "Hashtag-multiplex", + "rdfs:subClassOf": [ + { + "@id": "bts:SingleCellBarcodeMethodApplied" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Hashtag- multiplex", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:NuclearHashtag-multiplex", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "NuclearHashtag-multiplex", + "rdfs:subClassOf": [ + { + "@id": "bts:SingleCellBarcodeMethodApplied" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Nuclear Hashtag- multiplex", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:10xADT–citeseq/hashing", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "10xADT–citeseq/hashing", + "rdfs:subClassOf": [ + { + "@id": "bts:FeatureBarcodeLibraryType" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "10x ADT – citeseq/hashing", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:10xTCR", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "10xTCR", + "rdfs:subClassOf": [ + { + "@id": "bts:FeatureBarcodeLibraryType" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "10x TCR", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:10xBCR", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "10xBCR", + "rdfs:subClassOf": [ + { + "@id": "bts:FeatureBarcodeLibraryType" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "10x BCR", + "sms:required": "sms:false", + "sms:validationRules": [] } ], "@id": "http://schema.biothings.io/#0.1" From 32d35130a7fd57c6cdfeeb0f02a82e84399ca269 Mon Sep 17 00:00:00 2001 From: Adam Taylor Date: Thu, 6 Jun 2024 12:32:38 +0100 Subject: [PATCH 5/6] Add to config --- dca-template-config.json | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/dca-template-config.json b/dca-template-config.json index bd4dd061..c1badeed 100644 --- a/dca-template-config.json +++ b/dca-template-config.json @@ -165,6 +165,26 @@ "schema_name": "MassSpectrometryLevel4", "type": "file" }, + { + "display_name": "Multiplexed CITE-seq Level 1", + "schema_name": "MultiplexedCITE-seqLevel1", + "type": "file" + }, + { + "display_name": "Multiplexed CITE-seq Level 2", + "schema_name": "MultiplexedCITE-seqLevel2", + "type": "file" + }, + { + "display_name": "Multiplexed CITE-seq Level 3", + "schema_name": "MultiplexedCITE-seqLevel3", + "type": "file" + }, + { + "display_name": "Multiplexed CITE-seq Level 4", + "schema_name": "MultiplexedCITE-seqLevel4", + "type": "file" + }, { "display_name": "Nanostring CosMx SMI Experiment", "schema_name": "NanostringCosMxSMIExperiment", From 7bf977c10609df4b7c13d4a8d3f4bfff80f6e336 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" <41898282+github-actions[bot]@users.noreply.github.com> Date: Thu, 6 Jun 2024 11:42:17 +0000 Subject: [PATCH 6/6] GitHub Action: convert *.model.csv to *.model.jsonld --- HTAN.model.jsonld | 689 ++++++++++++++++++++++++++++------------------ 1 file changed, 416 insertions(+), 273 deletions(-) diff --git a/HTAN.model.jsonld b/HTAN.model.jsonld index 002b9dab..fd311f9f 100644 --- a/HTAN.model.jsonld +++ b/HTAN.model.jsonld @@ -5018,6 +5018,9 @@ { "@id": "bts:MolecularAnalysisMethod" }, + { + "@id": "bts:SingleCellBarcodeMethodApplied" + }, { "@id": "bts:LungAdjacentHistologyType" }, @@ -40990,52 +40993,6 @@ ], "sms:validationRules": [] }, - { - "@id": "bts:CDNA", - "@type": "rdfs:Class", - "rdfs:comment": "Complementary DNA. A DNA copy of an mRNA or complex sample of mRNAs, made using reverse transcriptase", - "rdfs:label": "CDNA", - "rdfs:subClassOf": [ - { - "@id": "bts:Sequencing" - }, - { - "@id": "bts:SpatialRead1" - }, - { - "@id": "bts:SpatialRead2" - }, - { - "@id": "bts:ScmCseqRead1" - }, - { - "@id": "bts:ScmCseqRead2" - }, - { - "@id": "bts:ScmCseqRead3" - }, - { - "@id": "bts:Read1" - }, - { - "@id": "bts:Read2" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "cDNA", - "sms:required": "sms:false", - "sms:requiresDependency": [ - { - "@id": "bts:CDNAOffset" - }, - { - "@id": "bts:CDNALength" - } - ], - "sms:validationRules": [] - }, { "@id": "bts:SpikeInConcentration", "@type": "rdfs:Class", @@ -47184,233 +47141,6 @@ "sms:required": "sms:false", "sms:validationRules": [] }, - { - "@id": "bts:Other", - "@type": "rdfs:Class", - "rdfs:comment": "TBD", - "rdfs:label": "Other", - "rdfs:subClassOf": [ - { - "@id": "bts:StripeCalling" - }, - { - "@id": "bts:StripeWindow" - }, - { - "@id": "bts:HistologyAssessmentBy" - }, - { - "@id": "bts:HistologyAssessmentMedium" - }, - { - "@id": "bts:AlcoholType" - }, - { - "@id": "bts:ColorectalCancerTumorBorderConfiguration" - }, - { - "@id": "bts:BreastCancerGenomicTestPerformed" - }, - { - "@id": "bts:DataCollectionMode" - }, - { - "@id": "bts:Immersion" - }, - { - "@id": "bts:TypeofTobaccoUsed" - }, - { - "@id": "bts:PrecancerousConditionType" - }, - { - "@id": "bts:COVID19ComplicationsSeverity" - }, - { - "@id": "bts:ClassificationofTumor" - }, - { - "@id": "bts:BreastCarcinomaDetectionMethodType" - }, - { - "@id": "bts:PriorInvasiveBreastDisease" - }, - { - "@id": "bts:BreastCarcinomaSurgicalProcedureName" - }, - { - "@id": "bts:OvarianCancerSurgicalOutcome" - }, - { - "@id": "bts:MSScanMode" - }, - { - "@id": "bts:ReadIndicator" - }, - { - "@id": "bts:ExpressionUnits" - }, - { - "@id": "bts:SlideChargeType" - }, - { - "@id": "bts:FiducialMarker" - }, - { - "@id": "bts:ReasonTreatmentEnded" - }, - { - "@id": "bts:LabTestsforMMRStatus" - }, - { - "@id": "bts:BreastCarcinomaHistologyCategory" - }, - { - "@id": "bts:GliomaSpecificMetastasisSites" - }, - { - "@id": "bts:AdditonalFindingsUninvolvedProstate" - }, - { - "@id": "bts:SlicingMethod" - }, - { - "@id": "bts:ImmunosuppressiveTreatmentType" - }, - { - "@id": "bts:LungCancerDetectionMethodType" - }, - { - "@id": "bts:ColorectalCancerDetectionMethodType" - }, - { - "@id": "bts:BreastBiopsyProcedureFindingType" - }, - { - "@id": "bts:BreastCancerAssessmentTests" - }, - { - "@id": "bts:ProstateCancerCytologicMorphologicSubtypes" - }, - { - "@id": "bts:SarcomaTumorExtensionType" - }, - { - "@id": "bts:PancreaticIPMNPathologyEpithelialSubtype" - }, - { - "@id": "bts:Pre-processingCompleted" - }, - { - "@id": "bts:Pre-processingRequired" - }, - { - "@id": "bts:MSSource" - }, - { - "@id": "bts:Race" - }, - { - "@id": "bts:DataCategory" - }, - { - "@id": "bts:ExtentofTumorResection" - }, - { - "@id": "bts:ColorectalPolypType" - }, - { - "@id": "bts:BreastCarcinomaERStainingIntensity" - }, - { - "@id": "bts:BreastCarcinomaPRStainingIntensity" - }, - { - "@id": "bts:SarcomaSubtype" - }, - { - "@id": "bts:LibrarySelectionMethod" - }, - { - "@id": "bts:CutaneousMelanomaAdditionalFindings" - }, - { - "@id": "bts:DiabetesTreatmentType" - }, - { - "@id": "bts:OvarianCancerHistologicSubtype" - }, - { - "@id": "bts:InvasiveDuctalBreastCarcinomaHistologicCategory" - }, - { - "@id": "bts:ProstateCarcinomaHistologicType" - }, - { - "@id": "bts:ScRNAseqWorkflowType" - }, - { - "@id": "bts:MolecularAnalysisMethod" - }, - { - "@id": "bts:LungAdjacentHistologyType" - }, - { - "@id": "bts:VariantType" - }, - { - "@id": "bts:LungCancerParticipantProcedureHistory" - }, - { - "@id": "bts:MethodofDiagnosis" - }, - { - "@id": "bts:FixativeType" - }, - { - "@id": "bts:HPVPositiveType" - }, - { - "@id": "bts:ConcomitantMedicationReceivedType" - }, - { - "@id": "bts:TreatmentType" - }, - { - "@id": "bts:CurrentLungCancerSymptoms" - }, - { - "@id": "bts:SequencingPlatform" - }, - { - "@id": "bts:MutationalSignatures" - }, - { - "@id": "bts:LungCancerHarboringGenomicAberrations" - }, - { - "@id": "bts:RelationshipType" - }, - { - "@id": "bts:LungTopography" - }, - { - "@id": "bts:Comorbidity" - }, - { - "@id": "bts:PriorSitesofRadiation" - }, - { - "@id": "bts:License" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "other", - "sms:required": "sms:false", - "sms:validationRules": [] - }, { "@id": "bts:HiCCUPS", "@type": "rdfs:Class", @@ -154952,6 +154682,419 @@ "sms:displayName": "droplet", "sms:required": "sms:false", "sms:validationRules": [] + }, + { + "@id": "bts:Cite-seqcustompanel", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "Cite-seqcustompanel", + "rdfs:subClassOf": [ + { + "@id": "bts:SingleCellBarcodeMethodApplied" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Cite-seq custom panel", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:BiolegendTotalseqACustom", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "BiolegendTotalseqACustom", + "rdfs:subClassOf": [ + { + "@id": "bts:SingleCellBarcodeMethodApplied" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Biolegend Total seq A Custom", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:BiolegendTotalseqBCustom", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "BiolegendTotalseqBCustom", + "rdfs:subClassOf": [ + { + "@id": "bts:SingleCellBarcodeMethodApplied" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Biolegend Total seq B Custom", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:BiolegendTotalseqCCustom", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "BiolegendTotalseqCCustom", + "rdfs:subClassOf": [ + { + "@id": "bts:SingleCellBarcodeMethodApplied" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Biolegend Total seq C Custom", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:BiolegendTotalseqAHuman", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "BiolegendTotalseqAHuman", + "rdfs:subClassOf": [ + { + "@id": "bts:SingleCellBarcodeMethodApplied" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Biolegend Total seq A Human", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:UniversalcocktailV1.0", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "UniversalcocktailV1.0", + "rdfs:subClassOf": [ + { + "@id": "bts:SingleCellBarcodeMethodApplied" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Universal cocktail V1.0", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:BiolegendTotalseqBHumanUniversalcocktailV1.0", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "BiolegendTotalseqBHumanUniversalcocktailV1.0", + "rdfs:subClassOf": [ + { + "@id": "bts:SingleCellBarcodeMethodApplied" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Biolegend Total seq B Human Universal cocktail V1.0", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:BiolegendTotalseqCHumanUniversalcocktailV1.0", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "BiolegendTotalseqCHumanUniversalcocktailV1.0", + "rdfs:subClassOf": [ + { + "@id": "bts:SingleCellBarcodeMethodApplied" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Biolegend Total seq C Human Universal cocktail V1.0", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:Cell", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "Cell", + "rdfs:subClassOf": [ + { + "@id": "bts:SingleCellBarcodeMethodApplied" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Cell", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:Hashtag-multiplex", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "Hashtag-multiplex", + "rdfs:subClassOf": [ + { + "@id": "bts:SingleCellBarcodeMethodApplied" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Hashtag- multiplex", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:NuclearHashtag-multiplex", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "NuclearHashtag-multiplex", + "rdfs:subClassOf": [ + { + "@id": "bts:SingleCellBarcodeMethodApplied" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Nuclear Hashtag- multiplex", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:10xADT–citeseq/hashing", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "10xADT–citeseq/hashing", + "rdfs:subClassOf": [ + { + "@id": "bts:FeatureBarcodeLibraryType" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "10x ADT – citeseq/hashing", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:10xTCR", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "10xTCR", + "rdfs:subClassOf": [ + { + "@id": "bts:FeatureBarcodeLibraryType" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "10x TCR", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:10xBCR", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "10xBCR", + "rdfs:subClassOf": [ + { + "@id": "bts:FeatureBarcodeLibraryType" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "10x BCR", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:ParticipantVitalStatusUpdate", + "@type": "rdfs:Class", + "rdfs:comment": "Updates to a participants vital status", + "rdfs:label": "ParticipantVitalStatusUpdate", + "rdfs:subClassOf": [ + { + "@id": "bts:Patient" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Participant Vital Status Update", + "sms:required": "sms:false", + "sms:requiresDependency": [ + { + "@id": "bts:Component" + }, + { + "@id": "bts:HTANParticipantID" + }, + { + "@id": "bts:VitalStatus" + } + ], + "sms:validationRules": [] + }, + { + "@id": "bts:PrecancerDiagnosis", + "@type": "rdfs:Class", + "rdfs:comment": "Diagnosis of a precancerous condition", + "rdfs:label": "PrecancerDiagnosis", + "rdfs:subClassOf": [ + { + "@id": "bts:Patient" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Precancer Diagnosis", + "sms:required": "sms:false", + "sms:requiresDependency": [ + { + "@id": "bts:Component" + }, + { + "@id": "bts:HTANParticipantID" + }, + { + "@id": "bts:PrecancerCase" + } + ], + "sms:validationRules": [] + }, + { + "@id": "bts:PrecancerCase", + "@type": "rdfs:Class", + "rdfs:comment": "Yes/No indicator to designate the participant for whom precancerous lesion(s) was identified (premalignancy only).", + "rdfs:label": "PrecancerCase", + "rdfs:subClassOf": [ + { + "@id": "bts:Patient" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "schema:rangeIncludes": [ + { + "@id": "bts:Yes-PrecancerCase" + }, + { + "@id": "bts:No" + }, + { + "@id": "bts:NotReported" + }, + { + "@id": "bts:Unknown" + } + ], + "sms:displayName": "Precancer Case", + "sms:required": "sms:true", + "sms:validationRules": [] + }, + { + "@id": "bts:DaystoVitalStatusReference", + "@type": "rdfs:Class", + "rdfs:comment": "Number of days between the date used for index and the reference date for designation of vital status", + "rdfs:label": "DaystoVitalStatusReference", + "rdfs:subClassOf": [ + { + "@id": "bts:Patient" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Days to Vital Status Reference", + "sms:required": "sms:true", + "sms:validationRules": [ + "int" + ] + }, + { + "@id": "bts:Yes-PrecancerCase", + "@type": "rdfs:Class", + "rdfs:comment": "Indicates that the participant is a precancer case", + "rdfs:label": "Yes-PrecancerCase", + "rdfs:subClassOf": [ + { + "@id": "bts:Patient" + }, + { + "@id": "bts:PrecancerCase" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Yes - Precancer Case", + "sms:required": "sms:false", + "sms:requiresDependency": [ + { + "@id": "bts:PrecancerousConditionType" + }, + { + "@id": "bts:DaystoPrecancerCaseDesignation" + }, + { + "@id": "bts:WHOPrecursorLesionCode" + } + ], + "sms:validationRules": [] + }, + { + "@id": "bts:DaystoPrecancerCaseDesignation", + "@type": "rdfs:Class", + "rdfs:comment": "Number of days between the date used for index and the reference date for designation of precancer status.", + "rdfs:label": "DaystoPrecancerCaseDesignation", + "rdfs:subClassOf": [ + { + "@id": "bts:Patient" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Days to Precancer Case Designation", + "sms:required": "sms:false", + "sms:validationRules": [ + "int" + ] + }, + { + "@id": "bts:WHOPrecursorLesionCode", + "@type": "rdfs:Class", + "rdfs:comment": "World Health Organization Classification of Tumour cytopathology-based coding system, includes 'precursor lesion' designations for precancers. ICD-O-3 morphology axis format eg 1234/1", + "rdfs:label": "WHOPrecursorLesionCode", + "rdfs:subClassOf": [ + { + "@id": "bts:Patient" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "WHO Precursor Lesion Code", + "sms:required": "sms:false", + "sms:validationRules": [ + "regex match ^\\d{4}\\/[0-3]$" + ] } ], "@id": "http://schema.biothings.io/#0.1"