From ad46e43f922fb0a533bd291b496ad2a0262ed42a Mon Sep 17 00:00:00 2001 From: PozhidayevaDarya <106110175+PozhidayevaDarya@users.noreply.github.com> Date: Thu, 21 Sep 2023 10:55:11 -0700 Subject: [PATCH 1/4] Model updates for Slide-Seq Adressing issue here: --- HTAN.model.csv | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/HTAN.model.csv b/HTAN.model.csv index 74ed9d8f..a97cd5e3 100644 --- a/HTAN.model.csv +++ b/HTAN.model.csv @@ -42,6 +42,14 @@ 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,, +Slide-seq Level 1,"Raw sequencing files for the Slide-seq assay.",,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Nucleic Acid Source, Library Construction Method, Read Indicator, Spatial Read1, Spatial Read2, End Bias, Reverse Transcription Primer, Spatial Barcode Offset, Spatial Barcode and UMI, Spike In, Sequencing Platform, Run ID, Sequencing Batch ID, Total Number Beads in Puck, Technical Replicate Group, Protocol Link, Spatial Library Construction Method, Library Preparation Days from Index, Sequencing Library Construction Days from Index, Nucleic Acid Capture Days from Index",,FALSE,Spatial Transcriptomics,Biospecimen,, +Slide-seq Level 2,"Aligned sequencing files and QC for the Slide-seq assay.",,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Slide-seq Workflow Type, Workflow Version, Slide-seq Worflow Parameter Description, Workflow Link, Genomic Reference, Genomic Reference URL, Genome Annotation URL, Checksum, Spatial Barcode Tag, UMI Tag, Applied Hard Trimming",,FALSE,Spatial Transcriptomics,Slide-seq Level 1,, +Slide-seq Level 3,"Gene matrices with features and barcodes for Slide-seq as well as spatial information (bead location files).",,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Data Category, Matrix Type, Slide-seq Workflow Type, Workflow Version, Slide-seq Worflow Parameter Description, Workflow Link, Workflow Version, Beads Total, Median UMI Counts per Spot, Median Number Genes per Spatial Spot, Slide-seq Bead File Type",,FALSE,Spatial Transcriptomics,Slide-seq Level 2,, +Total Number Beads in Puck,Number of beads in the Slide-seq puck. Integer,,,,TRUE,Spatial Transcriptomics,,, +Beads Total,Number of sequenced beads. Applies to raw counts matrix only. Integer,,,,FALSE,Spatial Transcriptomics,,, +Slide-seq Workflow Type,Generic name for the workflow used to analyze the Slide-seq data set. String,,,,TRUE,Spatial Transcriptomics,,, +Slide-seq Worflow Parameter Description,Parameters used to run the Slide-seq workflow. String,,,,TRUE,Spatial Transcriptomics,,, +Slide-seq Bead File Type,The type of Level 3 file submitted as part of the Slide-seq workflow.,"Features, Barcodes, Bead Locations, Bead Barcodes, Matched Bead Barcodes, Matched Bead Locations, Not Applicable",,,TRUE,Spatial Transcriptomics,,, 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, 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,, From d6c781ef920545c6abbc357927838edba017d027 Mon Sep 17 00:00:00 2001 From: PozhidayevaDarya Date: Thu, 21 Sep 2023 18:10:54 +0000 Subject: [PATCH 2/4] GitHub Action: convert *.model.csv to *.model.jsonld --- HTAN.model.jsonld | 521 +++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 470 insertions(+), 51 deletions(-) diff --git a/HTAN.model.jsonld b/HTAN.model.jsonld index 248d1a3e..19a5637d 100644 --- a/HTAN.model.jsonld +++ b/HTAN.model.jsonld @@ -5244,6 +5244,357 @@ ], "sms:validationRules": [] }, + { + "@id": "bts:Slide-seqLevel1", + "@type": "rdfs:Class", + "rdfs:comment": "Raw sequencing files for the Slide-seq assay.", + "rdfs:label": "Slide-seqLevel1", + "rdfs:subClassOf": [ + { + "@id": "bts:SpatialTranscriptomics" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Slide-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:LibraryConstructionMethod" + }, + { + "@id": "bts:ReadIndicator" + }, + { + "@id": "bts:SpatialRead1" + }, + { + "@id": "bts:SpatialRead2" + }, + { + "@id": "bts:EndBias" + }, + { + "@id": "bts:ReverseTranscriptionPrimer" + }, + { + "@id": "bts:SpatialBarcodeOffset" + }, + { + "@id": "bts:SpatialBarcodeandUMI" + }, + { + "@id": "bts:SpikeIn" + }, + { + "@id": "bts:SequencingPlatform" + }, + { + "@id": "bts:RunID" + }, + { + "@id": "bts:SequencingBatchID" + }, + { + "@id": "bts:TotalNumberBeadsinPuck" + }, + { + "@id": "bts:TechnicalReplicateGroup" + }, + { + "@id": "bts:ProtocolLink" + }, + { + "@id": "bts:SpatialLibraryConstructionMethod" + }, + { + "@id": "bts:LibraryPreparationDaysfromIndex" + }, + { + "@id": "bts:SequencingLibraryConstructionDaysfromIndex" + }, + { + "@id": "bts:NucleicAcidCaptureDaysfromIndex" + } + ], + "sms:validationRules": [] + }, + { + "@id": "bts:Slide-seqLevel2", + "@type": "rdfs:Class", + "rdfs:comment": "Aligned sequencing files and QC for the Slide-seq assay.", + "rdfs:label": "Slide-seqLevel2", + "rdfs:subClassOf": [ + { + "@id": "bts:SpatialTranscriptomics" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Slide-seq Level 2", + "sms:required": "sms:false", + "sms:requiresComponent": [ + { + "@id": "bts:Slide-seqLevel1" + } + ], + "sms:requiresDependency": [ + { + "@id": "bts:Component" + }, + { + "@id": "bts:Filename" + }, + { + "@id": "bts:FileFormat" + }, + { + "@id": "bts:HTANParentDataFileID" + }, + { + "@id": "bts:HTANDataFileID" + }, + { + "@id": "bts:Slide-seqWorkflowType" + }, + { + "@id": "bts:WorkflowVersion" + }, + { + "@id": "bts:Slide-seqWorflowParameterDescription" + }, + { + "@id": "bts:WorkflowLink" + }, + { + "@id": "bts:GenomicReference" + }, + { + "@id": "bts:GenomicReferenceURL" + }, + { + "@id": "bts:GenomeAnnotationURL" + }, + { + "@id": "bts:Checksum" + }, + { + "@id": "bts:SpatialBarcodeTag" + }, + { + "@id": "bts:UMITag" + }, + { + "@id": "bts:AppliedHardTrimming" + } + ], + "sms:validationRules": [] + }, + { + "@id": "bts:Slide-seqLevel3", + "@type": "rdfs:Class", + "rdfs:comment": "Gene matrices with features and barcodes for Slide-seq as well as spatial information (bead location files).", + "rdfs:label": "Slide-seqLevel3", + "rdfs:subClassOf": [ + { + "@id": "bts:SpatialTranscriptomics" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Slide-seq Level 3", + "sms:required": "sms:false", + "sms:requiresComponent": [ + { + "@id": "bts:Slide-seqLevel2" + } + ], + "sms:requiresDependency": [ + { + "@id": "bts:Component" + }, + { + "@id": "bts:Filename" + }, + { + "@id": "bts:FileFormat" + }, + { + "@id": "bts:HTANParentDataFileID" + }, + { + "@id": "bts:HTANDataFileID" + }, + { + "@id": "bts:DataCategory" + }, + { + "@id": "bts:MatrixType" + }, + { + "@id": "bts:Slide-seqWorkflowType" + }, + { + "@id": "bts:WorkflowVersion" + }, + { + "@id": "bts:Slide-seqWorflowParameterDescription" + }, + { + "@id": "bts:WorkflowLink" + }, + { + "@id": "bts:WorkflowVersion" + }, + { + "@id": "bts:BeadsTotal" + }, + { + "@id": "bts:MedianUMICountsperSpot" + }, + { + "@id": "bts:MedianNumberGenesperSpatialSpot" + }, + { + "@id": "bts:Slide-seqBeadFileType" + } + ], + "sms:validationRules": [] + }, + { + "@id": "bts:TotalNumberBeadsinPuck", + "@type": "rdfs:Class", + "rdfs:comment": "Number of beads in the Slide-seq puck. Integer", + "rdfs:label": "TotalNumberBeadsinPuck", + "rdfs:subClassOf": [ + { + "@id": "bts:SpatialTranscriptomics" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Total Number Beads in Puck", + "sms:required": "sms:true", + "sms:validationRules": [] + }, + { + "@id": "bts:BeadsTotal", + "@type": "rdfs:Class", + "rdfs:comment": "Number of sequenced beads. Applies to raw counts matrix only. Integer", + "rdfs:label": "BeadsTotal", + "rdfs:subClassOf": [ + { + "@id": "bts:SpatialTranscriptomics" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Beads Total", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:Slide-seqWorkflowType", + "@type": "rdfs:Class", + "rdfs:comment": "Generic name for the workflow used to analyze the Slide-seq data set. String", + "rdfs:label": "Slide-seqWorkflowType", + "rdfs:subClassOf": [ + { + "@id": "bts:SpatialTranscriptomics" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Slide-seq Workflow Type", + "sms:required": "sms:true", + "sms:validationRules": [] + }, + { + "@id": "bts:Slide-seqWorflowParameterDescription", + "@type": "rdfs:Class", + "rdfs:comment": "Parameters used to run the Slide-seq workflow. String", + "rdfs:label": "Slide-seqWorflowParameterDescription", + "rdfs:subClassOf": [ + { + "@id": "bts:SpatialTranscriptomics" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Slide-seq Worflow Parameter Description", + "sms:required": "sms:true", + "sms:validationRules": [] + }, + { + "@id": "bts:Slide-seqBeadFileType", + "@type": "rdfs:Class", + "rdfs:comment": "The type of Level 3 file submitted as part of the Slide-seq workflow.", + "rdfs:label": "Slide-seqBeadFileType", + "rdfs:subClassOf": [ + { + "@id": "bts:SpatialTranscriptomics" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "schema:rangeIncludes": [ + { + "@id": "bts:Features" + }, + { + "@id": "bts:Barcodes" + }, + { + "@id": "bts:BeadLocations" + }, + { + "@id": "bts:BeadBarcodes" + }, + { + "@id": "bts:MatchedBeadBarcodes" + }, + { + "@id": "bts:MatchedBeadLocations" + }, + { + "@id": "bts:NotApplicable" + } + ], + "sms:displayName": "Slide-seq Bead File Type", + "sms:required": "sms:true", + "sms:validationRules": [] + }, { "@id": "bts:BulkRNA-seqLevel1", "@type": "rdfs:Class", @@ -51542,6 +51893,125 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:Features", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "Features", + "rdfs:subClassOf": [ + { + "@id": "bts:Slide-seqBeadFileType" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Features", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:Barcodes", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "Barcodes", + "rdfs:subClassOf": [ + { + "@id": "bts:Slide-seqBeadFileType" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Barcodes", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:BeadLocations", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "BeadLocations", + "rdfs:subClassOf": [ + { + "@id": "bts:Slide-seqBeadFileType" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Bead Locations", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:BeadBarcodes", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "BeadBarcodes", + "rdfs:subClassOf": [ + { + "@id": "bts:Slide-seqBeadFileType" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Bead Barcodes", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:MatchedBeadBarcodes", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "MatchedBeadBarcodes", + "rdfs:subClassOf": [ + { + "@id": "bts:Slide-seqBeadFileType" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Matched Bead Barcodes", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:MatchedBeadLocations", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "MatchedBeadLocations", + "rdfs:subClassOf": [ + { + "@id": "bts:Slide-seqBeadFileType" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Matched Bead Locations", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:NotApplicable", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "NotApplicable", + "rdfs:subClassOf": [ + { + "@id": "bts:Slide-seqBeadFileType" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Not Applicable", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:Spotsundertissue", "@type": "rdfs:Class", @@ -51695,40 +52165,6 @@ "sms:required": "sms:false", "sms:validationRules": [] }, - { - "@id": "bts:Barcodes", - "@type": "rdfs:Class", - "rdfs:comment": "TBD", - "rdfs:label": "Barcodes", - "rdfs:subClassOf": [ - { - "@id": "bts:VisiumFileType" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "barcodes", - "sms:required": "sms:false", - "sms:validationRules": [] - }, - { - "@id": "bts:Features", - "@type": "rdfs:Class", - "rdfs:comment": "TBD", - "rdfs:label": "Features", - "rdfs:subClassOf": [ - { - "@id": "bts:VisiumFileType" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "features", - "sms:required": "sms:false", - "sms:validationRules": [] - }, { "@id": "bts:Fiducialimagepng", "@type": "rdfs:Class", @@ -54687,23 +55123,6 @@ "sms:required": "sms:false", "sms:validationRules": [] }, - { - "@id": "bts:NotApplicable", - "@type": "rdfs:Class", - "rdfs:comment": "TBD", - "rdfs:label": "NotApplicable", - "rdfs:subClassOf": [ - { - "@id": "bts:ImagingAssayType" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "Not Applicable", - "sms:required": "sms:false", - "sms:validationRules": [] - }, { "@id": "bts:Cm", "@type": "rdfs:Class", From 7900a6424990b2a8045f0619a9f235049365d8de Mon Sep 17 00:00:00 2001 From: Adam Taylor Date: Wed, 27 Sep 2023 14:28:38 +0100 Subject: [PATCH 3/4] Spelling correction 'Worflow' -> 'Workflow' --- HTAN.model.csv | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/HTAN.model.csv b/HTAN.model.csv index a97cd5e3..c212b8c9 100644 --- a/HTAN.model.csv +++ b/HTAN.model.csv @@ -43,12 +43,12 @@ scRNA-seq Level 2,Alignment workflows downstream of scRNA-seq Level 1,,"Componen 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,, Slide-seq Level 1,"Raw sequencing files for the Slide-seq assay.",,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Nucleic Acid Source, Library Construction Method, Read Indicator, Spatial Read1, Spatial Read2, End Bias, Reverse Transcription Primer, Spatial Barcode Offset, Spatial Barcode and UMI, Spike In, Sequencing Platform, Run ID, Sequencing Batch ID, Total Number Beads in Puck, Technical Replicate Group, Protocol Link, Spatial Library Construction Method, Library Preparation Days from Index, Sequencing Library Construction Days from Index, Nucleic Acid Capture Days from Index",,FALSE,Spatial Transcriptomics,Biospecimen,, -Slide-seq Level 2,"Aligned sequencing files and QC for the Slide-seq assay.",,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Slide-seq Workflow Type, Workflow Version, Slide-seq Worflow Parameter Description, Workflow Link, Genomic Reference, Genomic Reference URL, Genome Annotation URL, Checksum, Spatial Barcode Tag, UMI Tag, Applied Hard Trimming",,FALSE,Spatial Transcriptomics,Slide-seq Level 1,, -Slide-seq Level 3,"Gene matrices with features and barcodes for Slide-seq as well as spatial information (bead location files).",,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Data Category, Matrix Type, Slide-seq Workflow Type, Workflow Version, Slide-seq Worflow Parameter Description, Workflow Link, Workflow Version, Beads Total, Median UMI Counts per Spot, Median Number Genes per Spatial Spot, Slide-seq Bead File Type",,FALSE,Spatial Transcriptomics,Slide-seq Level 2,, +Slide-seq Level 2,"Aligned sequencing files and QC for the Slide-seq assay.",,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Slide-seq Workflow Type, Workflow Version, Slide-seq Workflow Parameter Description, Workflow Link, Genomic Reference, Genomic Reference URL, Genome Annotation URL, Checksum, Spatial Barcode Tag, UMI Tag, Applied Hard Trimming",,FALSE,Spatial Transcriptomics,Slide-seq Level 1,, +Slide-seq Level 3,"Gene matrices with features and barcodes for Slide-seq as well as spatial information (bead location files).",,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Data File ID, Data Category, Matrix Type, Slide-seq Workflow Type, Workflow Version, Slide-seq Workflow Parameter Description, Workflow Link, Workflow Version, Beads Total, Median UMI Counts per Spot, Median Number Genes per Spatial Spot, Slide-seq Bead File Type",,FALSE,Spatial Transcriptomics,Slide-seq Level 2,, Total Number Beads in Puck,Number of beads in the Slide-seq puck. Integer,,,,TRUE,Spatial Transcriptomics,,, Beads Total,Number of sequenced beads. Applies to raw counts matrix only. Integer,,,,FALSE,Spatial Transcriptomics,,, Slide-seq Workflow Type,Generic name for the workflow used to analyze the Slide-seq data set. String,,,,TRUE,Spatial Transcriptomics,,, -Slide-seq Worflow Parameter Description,Parameters used to run the Slide-seq workflow. String,,,,TRUE,Spatial Transcriptomics,,, +Slide-seq Workflow Parameter Description,Parameters used to run the Slide-seq workflow. String,,,,TRUE,Spatial Transcriptomics,,, Slide-seq Bead File Type,The type of Level 3 file submitted as part of the Slide-seq workflow.,"Features, Barcodes, Bead Locations, Bead Barcodes, Matched Bead Barcodes, Matched Bead Locations, Not Applicable",,,TRUE,Spatial Transcriptomics,,, 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, 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,, From b477e5ae3ce29b34ed26ba14ab7de9b5456b9fcd Mon Sep 17 00:00:00 2001 From: adamjtaylor Date: Wed, 27 Sep 2023 13:41:45 +0000 Subject: [PATCH 4/4] GitHub Action: convert *.model.csv to *.model.jsonld --- HTAN.model.jsonld | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/HTAN.model.jsonld b/HTAN.model.jsonld index 19a5637d..20f0ede3 100644 --- a/HTAN.model.jsonld +++ b/HTAN.model.jsonld @@ -5386,7 +5386,7 @@ "@id": "bts:WorkflowVersion" }, { - "@id": "bts:Slide-seqWorflowParameterDescription" + "@id": "bts:Slide-seqWorkflowParameterDescription" }, { "@id": "bts:WorkflowLink" @@ -5464,7 +5464,7 @@ "@id": "bts:WorkflowVersion" }, { - "@id": "bts:Slide-seqWorflowParameterDescription" + "@id": "bts:Slide-seqWorkflowParameterDescription" }, { "@id": "bts:WorkflowLink" @@ -5539,10 +5539,10 @@ "sms:validationRules": [] }, { - "@id": "bts:Slide-seqWorflowParameterDescription", + "@id": "bts:Slide-seqWorkflowParameterDescription", "@type": "rdfs:Class", "rdfs:comment": "Parameters used to run the Slide-seq workflow. String", - "rdfs:label": "Slide-seqWorflowParameterDescription", + "rdfs:label": "Slide-seqWorkflowParameterDescription", "rdfs:subClassOf": [ { "@id": "bts:SpatialTranscriptomics" @@ -5551,7 +5551,7 @@ "schema:isPartOf": { "@id": "http://schema.biothings.io" }, - "sms:displayName": "Slide-seq Worflow Parameter Description", + "sms:displayName": "Slide-seq Workflow Parameter Description", "sms:required": "sms:true", "sms:validationRules": [] },