From 4643e090cd50d203e7775ef437a1c766ea584e3e Mon Sep 17 00:00:00 2001 From: "james.moon" Date: Mon, 18 Nov 2024 07:54:47 -0800 Subject: [PATCH] ChIPSeq Template Created (#543) * ChIPSeq Template Created * Rebuild NF.jsonld, json * Update props.yaml added peakCallingAlgorithms for ChIP-Seq * Rebuild NF.jsonld, json * Update Data.yaml removed the comment for peakcallingalgorithm * Update dca-template-config.json added ChIP-SeqTemplate to the DCA App * typo fix Data.yaml replaced "EpigenomiscAssayTemplate" to "EpigenomicsAssayTemplate" * Rebuild NF.jsonld, json --------- Co-authored-by: nf-osi[bot] --- NF.jsonld | 736 ++++++++++++++++++++++++++++--------- dca-template-config.json | 1 + modules/Template/Data.yaml | 21 +- modules/props.yaml | 16 + 4 files changed, 598 insertions(+), 176 deletions(-) diff --git a/NF.jsonld b/NF.jsonld index 02aaaba8..166f43b3 100644 --- a/NF.jsonld +++ b/NF.jsonld @@ -9222,6 +9222,265 @@ "sms:required": "sms:false", "sms:validationRules": [] }, + { + "@id": "bts:PeakCallingAlgorithm", + "@type": "rdfs:Class", + "rdfs:comment": "A list of commonly used peak-calling algorithms for ChIP-Seq data analysis.", + "rdfs:label": "PeakCallingAlgorithm", + "rdfs:subClassOf": [ + { + "@id": "bts:Thing" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "schema:rangeIncludes": [ + { + "@id": "bts:MACS2" + }, + { + "@id": "bts:SICER" + }, + { + "@id": "bts:HOMER" + }, + { + "@id": "bts:Genrich" + }, + { + "@id": "bts:PeakRanger" + }, + { + "@id": "bts:SEACR" + }, + { + "@id": "bts:GEM" + }, + { + "@id": "bts:MUSIC" + }, + { + "@id": "bts:BroadPeak" + }, + { + "@id": "bts:SWEMBL" + }, + { + "@id": "bts:FSeq" + }, + { + "@id": "bts:ZINBA" + } + ], + "sms:displayName": "peakCallingAlgorithm", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:MACS2", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "MACS2", + "rdfs:subClassOf": [ + { + "@id": "bts:PeakCallingAlgorithm" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "MACS2", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:SICER", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "SICER", + "rdfs:subClassOf": [ + { + "@id": "bts:PeakCallingAlgorithm" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "SICER", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:HOMER", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "HOMER", + "rdfs:subClassOf": [ + { + "@id": "bts:PeakCallingAlgorithm" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "HOMER", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:Genrich", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "Genrich", + "rdfs:subClassOf": [ + { + "@id": "bts:PeakCallingAlgorithm" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "Genrich", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:PeakRanger", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "PeakRanger", + "rdfs:subClassOf": [ + { + "@id": "bts:PeakCallingAlgorithm" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "PeakRanger", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:SEACR", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "SEACR", + "rdfs:subClassOf": [ + { + "@id": "bts:PeakCallingAlgorithm" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "SEACR", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:GEM", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "GEM", + "rdfs:subClassOf": [ + { + "@id": "bts:PeakCallingAlgorithm" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "GEM", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:MUSIC", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "MUSIC", + "rdfs:subClassOf": [ + { + "@id": "bts:PeakCallingAlgorithm" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "MUSIC", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:BroadPeak", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "BroadPeak", + "rdfs:subClassOf": [ + { + "@id": "bts:PeakCallingAlgorithm" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "BroadPeak", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:SWEMBL", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "SWEMBL", + "rdfs:subClassOf": [ + { + "@id": "bts:PeakCallingAlgorithm" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "SWEMBL", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:FSeq", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "FSeq", + "rdfs:subClassOf": [ + { + "@id": "bts:PeakCallingAlgorithm" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "FSeq", + "sms:required": "sms:false", + "sms:validationRules": [] + }, + { + "@id": "bts:ZINBA", + "@type": "rdfs:Class", + "rdfs:comment": "TBD", + "rdfs:label": "ZINBA", + "rdfs:subClassOf": [ + { + "@id": "bts:PeakCallingAlgorithm" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "ZINBA", + "sms:required": "sms:false", + "sms:validationRules": [] + }, { "@id": "bts:ProtocolPurpose", "@type": "rdfs:Class", @@ -36451,19 +36710,19 @@ "sms:validationRules": [] }, { - "@id": "bts:LightScatteringAssayTemplate", + "@id": "bts:EpigenomicsAssayTemplate", "@type": "rdfs:Class", - "rdfs:comment": "Template for dynamic or static light scattering data adapted from ISA-TAB-Nano specs.", - "rdfs:label": "LightScatteringAssayTemplate", + "rdfs:comment": "Template for describing raw data from epigenetics sequencing assays such as bisulfite sequencing.", + "rdfs:label": "EpigenomicsAssayTemplate", "rdfs:subClassOf": [ { - "@id": "bts:MaterialScienceAssayTemplate" + "@id": "bts:BulkSequencingAssayTemplate" } ], "schema:isPartOf": { "@id": "http://schema.biothings.io" }, - "sms:displayName": "LightScatteringAssayTemplate", + "sms:displayName": "EpigenomicsAssayTemplate", "sms:required": "sms:false", "sms:requiresDependency": [ { @@ -36488,74 +36747,201 @@ "@id": "bts:Assay" }, { - "@id": "bts:Platform" + "@id": "bts:IndividualID" }, { - "@id": "bts:SpecimenID" + "@id": "bts:Species" }, { - "@id": "bts:MaterialType" + "@id": "bts:Sex" }, { - "@id": "bts:ConcentrationMaterial" + "@id": "bts:Age" }, { - "@id": "bts:ConcentrationMaterialUnit" + "@id": "bts:AgeUnit" }, { - "@id": "bts:ConcentrationNaCl" + "@id": "bts:Diagnosis" }, { - "@id": "bts:ConcentrationNaClUnit" + "@id": "bts:Nf1Genotype" }, { - "@id": "bts:PH" - } - ], - "sms:validationRules": [] - }, - { - "@id": "bts:ProcessedAlignedReadsTemplate", - "@type": "rdfs:Class", - "rdfs:comment": "Template for describing aligned reads (e.g. BAM/CRAM files) from a sequencing assay. The QC meta are extracted from samtools stats when available and are the same metrics preferred by GDC. \n", - "rdfs:label": "ProcessedAlignedReadsTemplate", - "rdfs:subClassOf": [ - { - "@id": "bts:BiologicalAssayDataTemplate" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "ProcessedAlignedReadsTemplate", - "sms:required": "sms:false", - "sms:requiresDependency": [ - { - "@id": "bts:Component" + "@id": "bts:Nf2Genotype" }, { - "@id": "bts:Filename" + "@id": "bts:TumorType" }, { - "@id": "bts:FileFormat" + "@id": "bts:ModelSystemName" }, { - "@id": "bts:ResourceType" + "@id": "bts:Organ" }, { - "@id": "bts:DataType" + "@id": "bts:Comments" }, { - "@id": "bts:DataSubtype" + "@id": "bts:ParentSpecimenID" }, { - "@id": "bts:Assay" + "@id": "bts:SpecimenID" }, { - "@id": "bts:IndividualID" + "@id": "bts:AliquotID" }, { - "@id": "bts:Species" + "@id": "bts:Platform" + }, + { + "@id": "bts:NucleicAcidSource" + }, + { + "@id": "bts:SpecimenPreparationMethod" + }, + { + "@id": "bts:SpecimenType" + }, + { + "@id": "bts:RunType" + }, + { + "@id": "bts:LibraryStrand" + }, + { + "@id": "bts:LibraryPrep" + }, + { + "@id": "bts:LibraryPreparationMethod" + }, + { + "@id": "bts:ReadPair" + }, + { + "@id": "bts:ReadLength" + }, + { + "@id": "bts:ReadDepth" + }, + { + "@id": "bts:TargetDepth" + }, + { + "@id": "bts:BatchID" + }, + { + "@id": "bts:BisulfiteConversionKitID" + } + ], + "sms:validationRules": [] + }, + { + "@id": "bts:LightScatteringAssayTemplate", + "@type": "rdfs:Class", + "rdfs:comment": "Template for dynamic or static light scattering data adapted from ISA-TAB-Nano specs.", + "rdfs:label": "LightScatteringAssayTemplate", + "rdfs:subClassOf": [ + { + "@id": "bts:MaterialScienceAssayTemplate" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "LightScatteringAssayTemplate", + "sms:required": "sms:false", + "sms:requiresDependency": [ + { + "@id": "bts:Component" + }, + { + "@id": "bts:Filename" + }, + { + "@id": "bts:FileFormat" + }, + { + "@id": "bts:ResourceType" + }, + { + "@id": "bts:DataType" + }, + { + "@id": "bts:DataSubtype" + }, + { + "@id": "bts:Assay" + }, + { + "@id": "bts:Platform" + }, + { + "@id": "bts:SpecimenID" + }, + { + "@id": "bts:MaterialType" + }, + { + "@id": "bts:ConcentrationMaterial" + }, + { + "@id": "bts:ConcentrationMaterialUnit" + }, + { + "@id": "bts:ConcentrationNaCl" + }, + { + "@id": "bts:ConcentrationNaClUnit" + }, + { + "@id": "bts:PH" + } + ], + "sms:validationRules": [] + }, + { + "@id": "bts:ProcessedAlignedReadsTemplate", + "@type": "rdfs:Class", + "rdfs:comment": "Template for describing aligned reads (e.g. BAM/CRAM files) from a sequencing assay. The QC meta are extracted from samtools stats when available and are the same metrics preferred by GDC. \n", + "rdfs:label": "ProcessedAlignedReadsTemplate", + "rdfs:subClassOf": [ + { + "@id": "bts:BiologicalAssayDataTemplate" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "ProcessedAlignedReadsTemplate", + "sms:required": "sms:false", + "sms:requiresDependency": [ + { + "@id": "bts:Component" + }, + { + "@id": "bts:Filename" + }, + { + "@id": "bts:FileFormat" + }, + { + "@id": "bts:ResourceType" + }, + { + "@id": "bts:DataType" + }, + { + "@id": "bts:DataSubtype" + }, + { + "@id": "bts:Assay" + }, + { + "@id": "bts:IndividualID" + }, + { + "@id": "bts:Species" }, { "@id": "bts:Sex" @@ -36641,6 +37027,139 @@ ], "sms:validationRules": [] }, + { + "@id": "bts:ChIPSeqTemplate", + "@type": "rdfs:Class", + "rdfs:comment": "Template for describing raw data from ChIP-Seq assays, typically used to identify DNA-protein interactions.", + "rdfs:label": "ChIPSeqTemplate", + "rdfs:subClassOf": [ + { + "@id": "bts:EpigenomicsAssayTemplate" + } + ], + "schema:isPartOf": { + "@id": "http://schema.biothings.io" + }, + "sms:displayName": "ChIPSeqTemplate", + "sms:required": "sms:false", + "sms:requiresDependency": [ + { + "@id": "bts:Component" + }, + { + "@id": "bts:Filename" + }, + { + "@id": "bts:FileFormat" + }, + { + "@id": "bts:ResourceType" + }, + { + "@id": "bts:DataType" + }, + { + "@id": "bts:DataSubtype" + }, + { + "@id": "bts:Assay" + }, + { + "@id": "bts:IndividualID" + }, + { + "@id": "bts:Species" + }, + { + "@id": "bts:Sex" + }, + { + "@id": "bts:Age" + }, + { + "@id": "bts:AgeUnit" + }, + { + "@id": "bts:Diagnosis" + }, + { + "@id": "bts:Nf1Genotype" + }, + { + "@id": "bts:Nf2Genotype" + }, + { + "@id": "bts:TumorType" + }, + { + "@id": "bts:ModelSystemName" + }, + { + "@id": "bts:Organ" + }, + { + "@id": "bts:Comments" + }, + { + "@id": "bts:ParentSpecimenID" + }, + { + "@id": "bts:SpecimenID" + }, + { + "@id": "bts:AliquotID" + }, + { + "@id": "bts:Platform" + }, + { + "@id": "bts:NucleicAcidSource" + }, + { + "@id": "bts:SpecimenPreparationMethod" + }, + { + "@id": "bts:SpecimenType" + }, + { + "@id": "bts:RunType" + }, + { + "@id": "bts:LibraryStrand" + }, + { + "@id": "bts:LibraryPrep" + }, + { + "@id": "bts:LibraryPreparationMethod" + }, + { + "@id": "bts:ReadPair" + }, + { + "@id": "bts:ReadLength" + }, + { + "@id": "bts:ReadDepth" + }, + { + "@id": "bts:TargetDepth" + }, + { + "@id": "bts:BatchID" + }, + { + "@id": "bts:BisulfiteConversionKitID" + }, + { + "@id": "bts:AntibodyID" + }, + { + "@id": "bts:PeakCallingAlgorithm" + } + ], + "sms:validationRules": [] + }, { "@id": "bts:HumanCohortTemplate", "@type": "rdfs:Class", @@ -36882,133 +37401,6 @@ ], "sms:validationRules": [] }, - { - "@id": "bts:EpigenomiscAssayTemplate", - "@type": "rdfs:Class", - "rdfs:comment": "Template for describing raw data from epigenetics sequencing assays such as bisulfite sequencing.", - "rdfs:label": "EpigenomiscAssayTemplate", - "rdfs:subClassOf": [ - { - "@id": "bts:BulkSequencingAssayTemplate" - } - ], - "schema:isPartOf": { - "@id": "http://schema.biothings.io" - }, - "sms:displayName": "EpigenomiscAssayTemplate", - "sms:required": "sms:false", - "sms:requiresDependency": [ - { - "@id": "bts:Component" - }, - { - "@id": "bts:Filename" - }, - { - "@id": "bts:FileFormat" - }, - { - "@id": "bts:ResourceType" - }, - { - "@id": "bts:DataType" - }, - { - "@id": "bts:DataSubtype" - }, - { - "@id": "bts:Assay" - }, - { - "@id": "bts:IndividualID" - }, - { - "@id": "bts:Species" - }, - { - "@id": "bts:Sex" - }, - { - "@id": "bts:Age" - }, - { - "@id": "bts:AgeUnit" - }, - { - "@id": "bts:Diagnosis" - }, - { - "@id": "bts:Nf1Genotype" - }, - { - "@id": "bts:Nf2Genotype" - }, - { - "@id": "bts:TumorType" - }, - { - "@id": "bts:ModelSystemName" - }, - { - "@id": "bts:Organ" - }, - { - "@id": "bts:Comments" - }, - { - "@id": "bts:ParentSpecimenID" - }, - { - "@id": "bts:SpecimenID" - }, - { - "@id": "bts:AliquotID" - }, - { - "@id": "bts:Platform" - }, - { - "@id": "bts:NucleicAcidSource" - }, - { - "@id": "bts:SpecimenPreparationMethod" - }, - { - "@id": "bts:SpecimenType" - }, - { - "@id": "bts:RunType" - }, - { - "@id": "bts:LibraryStrand" - }, - { - "@id": "bts:LibraryPrep" - }, - { - "@id": "bts:LibraryPreparationMethod" - }, - { - "@id": "bts:ReadPair" - }, - { - "@id": "bts:ReadLength" - }, - { - "@id": "bts:ReadDepth" - }, - { - "@id": "bts:TargetDepth" - }, - { - "@id": "bts:BatchID" - }, - { - "@id": "bts:BisulfiteConversionKitID" - } - ], - "sms:validationRules": [] - }, { "@id": "bts:ProcessedExpressionTemplate", "@type": "rdfs:Class", @@ -38571,11 +38963,11 @@ { "@id": "bts:EpigeneticsAssayTemplate", "@type": "rdfs:Class", - "rdfs:comment": "Alias for EpigenomiscAssayTemplate for backwards-compatibility.", + "rdfs:comment": "Alias for EpigenomicsAssayTemplate for backwards-compatibility.", "rdfs:label": "EpigeneticsAssayTemplate", "rdfs:subClassOf": [ { - "@id": "bts:EpigenomiscAssayTemplate" + "@id": "bts:EpigenomicsAssayTemplate" } ], "schema:isPartOf": { diff --git a/dca-template-config.json b/dca-template-config.json index d725d837..a264f416 100644 --- a/dca-template-config.json +++ b/dca-template-config.json @@ -21,6 +21,7 @@ {"display_name": "FACS Template", "schema_name": "FlowCytometryTemplate", "type": "file"}, {"display_name": "Light Scattering Assay", "schema_name": "LightScatteringAssayTemplate", "type": "file"}, {"display_name": "Protocols", "schema_name": "ProtocolTemplate", "type": "file"}, + {"display_name": "ChIP Sequencing Assay", "schema_name": "ChIPSeqTemplate", "type": "file"}, {"display_name": "Human Individuals (Extended Biobanking Data)", "schema_name": "HumanCohortTemplate", "type": "record"} ], "main_fileview" : "syn16858331", diff --git a/modules/Template/Data.yaml b/modules/Template/Data.yaml index 56c5e8a9..d3ff3b78 100644 --- a/modules/Template/Data.yaml +++ b/modules/Template/Data.yaml @@ -268,7 +268,7 @@ classes: close_mappings: - htan:BulkWESLevel1 - EpigenomiscAssayTemplate: + EpigenomicsAssayTemplate: is_a: BulkSequencingAssayTemplate description: Template for describing raw data from epigenetics sequencing assays such as bisulfite sequencing. slots: @@ -282,7 +282,6 @@ classes: - bisulfite sequencing - CAPP-seq - CUT&RUN - - ChIP-seq - ERR bisulfite sequencing - HI-C - NOMe-seq @@ -291,12 +290,26 @@ classes: - htan:BulkMethylation-seqLevel1 EpigeneticsAssayTemplate: - is_a: EpigenomiscAssayTemplate - description: Alias for EpigenomiscAssayTemplate for backwards-compatibility. + is_a: EpigenomicsAssayTemplate + description: Alias for EpigenomicsAssayTemplate for backwards-compatibility. + slots: + annotations: + requiresComponent: '' + required: false + + ChIPSeqTemplate: + is_a: EpigenomicsAssayTemplate + description: Template for describing raw data from ChIP-Seq assays, typically used to identify DNA-protein interactions. slots: + - antibodyID + - platform + - peakCallingAlgorithm annotations: requiresComponent: '' required: false + match: + assay: + - ChIP-seq GenomicsArrayTemplate: is_a: GeneticsAssayTemplate diff --git a/modules/props.yaml b/modules/props.yaml index 2ae4f60f..6b117406 100644 --- a/modules/props.yaml +++ b/modules/props.yaml @@ -1196,3 +1196,19 @@ slots: - portal range: integer required: false + peakCallingAlgorithm: + description: A list of commonly used peak-calling algorithms for ChIP-Seq data analysis. + enum_range: + - MACS2 + - SICER + - HOMER + - Genrich + - PeakRanger + - SEACR + - GEM + - MUSIC + - BroadPeak + - SWEMBL + - FSeq + - ZINBA + required: false