381-fix-hic

HTAN.model.csv

@@ -6,7 +6,7 @@ Component,"Category of metadata (e.g. Diagnosis, Biospecimen, scRNA-seq Level 1,
 Patient,HTAN patient,,"Component, HTAN Participant ID",,FALSE,Individual Organism,"Demographics, Family History, Exposure, Follow Up, Diagnosis, Therapy, Molecular Test",,
 File,A type of Information Content Entity specific to OS,,,,FALSE,Information Content Entity,,https://w3id.org/biolink/vocab/DataFile,
 Filename,Name of a file,,,,TRUE,,,,regex search ^.+\/\S*$
-File Format,"Format of a file (e.g. txt, csv, fastq, bam, etc.)","hdf5, bedgraph, idx, idat, bam, bai, excel, powerpoint, tif, tiff, OME-TIFF, png, doc, pdf, fasta, fastq, sam, vcf, bcf, maf, bed, chp, cel, sif, tsv, csv, txt, plink, bigwig, wiggle, gct, bgzip, zip, seg, html, mov, hyperlink, svs, md, flagstat, gtf, raw, msf, rmd, bed narrowPeak, bed broadPeak, bed gappedPeak, avi, pzfx, fig, xml, tar, R script, abf, bpm, dat, jpg, locs, Sentrix descriptor file, Python script, sav, gzip, sdf, RData, hic, ab1, 7z, gff3, json, sqlite, svg, sra, recal, tranches, mtx, tagAlign, dup, DICOM, czi, mex, cloupe, am, cell am, mpg, m, mzML,scn, dcc, rcc, pkc, sf",,,TRUE,,,,
+File Format,"Format of a file (e.g. txt, csv, fastq, bam, etc.)","hdf5, bedgraph, idx, idat, bam, bai, excel, powerpoint, tif, tiff, OME-TIFF, png, doc, pdf, fasta, fastq, sam, vcf, bcf, maf, bed, chp, cel, sif, tsv, csv, txt, plink, bigwig, wiggle, gct, bgzip, zip, seg, html, mov, hyperlink, svs, md, flagstat, gtf, raw, msf, rmd, bed narrowPeak, bed broadPeak, bed gappedPeak, avi, pzfx, fig, xml, tar, R script, abf, bpm, dat, jpg, locs, Sentrix descriptor file, Python script, sav, gzip, sdf, RData, hic, ab1, 7z, gff3, json, sqlite, svg, sra, recal, tranches, mtx, tagAlign, dup, DICOM, czi, mex, cloupe, am, cell am, mpg, m, mzML,scn, dcc, rcc, pkc, sf, bedpe",,,TRUE,,,,
 Checksum,MD5 checksum of the BAM file,,,,TRUE,Information Content Entity,,,
 HTAN Data File ID,Self-identifier for this data file - HTAN ID of this file HTAN ID SOP (eg HTANx_yyy_zzz),,,,TRUE,File,,https://docs.google.com/document/d/1podtPP8L1UNvVxx9_c_szlDcU1f8n7bige6XA_GoRVM/edit?usp=sharing,regex match ^(HTA([1-9]|1[0-6]))_((EXT)?([0-9]\d*|0000))_([0-9]\d*|0000)$ warning
 HTAN Participant ID,HTAN ID associated with a patient based on HTAN ID SOP (eg HTANx_yyy ),,,,TRUE,Patient,,https://docs.google.com/document/d/1podtPP8L1UNvVxx9_c_szlDcU1f8n7bige6XA_GoRVM/edit?usp=sharing,regex match ^(HTA([1-9]|1[0-6]))_((EXT)?([0-9]\d*|0000))$ warning
@@ -155,10 +155,10 @@ Ligation Condition,Name of ligase and condition for proximity ligation,,,,TRUE,S
 Biotin Enrichment,Whether biotin is used for enriching ligation product,"Yes, No",,,TRUE,Sequencing,,,
 DNA Input Amount,"Amount of DNA for library construction, in nanograms.",,,,TRUE,Sequencing,,,int
 Resolution,"Binning size used for generating contact matrix, in basepair.",,,,TRUE,Sequencing,,,
-Stripe Calling,"Tool used for identifying architectural stripe-forming, interaction hotspots.","MACS2, Other",,,TRUE,Sequencing,,,
-Loop Window,Binning size used for calling significant dot interactions (loops),,,,TRUE,Sequencing,,,int
-Stripe Window,"Binning size used for calling significant architectural stripes. Can be an integer or int/int, indicating bin size and sliding window size if different.","HiCCUPS, Cooltools, Other",,,TRUE,Sequencing,,,
-Loop Calling,Tool used for identifying loop interactions,,,,TRUE,Sequencing,,,
+Stripe Calling,"Tool used for identifying architectural stripe-forming, interaction hotspots.","MACS2, Other",,,TRUE,Sequencing,,,list::-?\d+
+Loop Window,Binning size used for calling significant dot interactions (loops),,,,TRUE,Sequencing,,,list like :: regex search -?\d+
+Stripe Window,Binning size used for calling significant architectural stripes. Can be an integer or comma-separated list of integers indicating bin size and sliding window size if different.,,,,TRUE,Sequencing,,,list like :: regex search -?\d+
+Loop Calling,Tool used for identifying loop interactions,"HiCCUPS, Cooltools, Other",,,TRUE,Sequencing,,,
 Imaging Level 4,Derived imaging data: Object-by-feature array,,"Component, Filename, File Format, HTAN Parent Data File ID, HTAN Parent Channel Metadata ID, HTAN Data File ID, Parameter file, Software and Version, Commit SHA,Number of Objects, Number of Features,Imaging Object Class, Imaging Summary Statistic",,FALSE,Assay,Imaging Level 3 Channels,,
 SRRS Imaging Level 2,SRRS-specific HTAN raw and pre-processed image data,,"Component, Filename, File Format, HTAN Participant ID, HTAN Parent Biospecimen ID,  HTAN Data File ID, Channel Metadata Filename, Imaging Assay Type, Protocol Link, Software and Version, Microscope, Objective, NominalMagnification, Pyramid, Zstack, Tseries, Passed QC, Frame Averaging, Image ID, DimensionOrder, PhysicalSizeX, PhysicalSizeXUnit, PhysicalSizeY, PhysicalSizeYUnit, Pixels BigEndian, PlaneCount, SizeC, SizeT, SizeX, SizeY, SizeZ, PixelType",,FALSE,Assay,Biospecimen,,
 10X Genomics Xenium ISS Experiment,All data pertaining to the 10X Genomics Xenium In-Situ Hybridization experiment,,"Component, Filename, File Format, HTAN Parent Biospecimen ID, HTAN Data File ID, Xenium Bundle Contents, Slide ID, ROI name, Panel Name, Protocol Link, Software and Version,Total Number of Cells, Total Number of Targets, Surface area, Experiment IF Channels, Transcripts per Cell, Percent of Transcripts within Cells, Decoded Transcripts, Xenium IF image HTAN File ID, Xenium HE image HTAN File ID",,FALSE,Spatial Transcriptomics,Biospecimen,,

HTAN.model.jsonld

@@ -1294,6 +1294,9 @@
                 },
                 {
                     "@id": "bts:Sf"
+                },
+                {
+                    "@id": "bts:Bedpe"
                 }
             ],
             "sms:displayName": "File Format",
@@ -2856,6 +2859,23 @@
             "sms:required": "sms:false",
             "sms:validationRules": []
         },
+        {
+            "@id": "bts:Bedpe",
+            "@type": "rdfs:Class",
+            "rdfs:comment": "TBD",
+            "rdfs:label": "Bedpe",
+            "rdfs:subClassOf": [
+                {
+                    "@id": "bts:FileFormat"
+                }
+            ],
+            "schema:isPartOf": {
+                "@id": "http://schema.biothings.io"
+            },
+            "sms:displayName": "bedpe",
+            "sms:required": "sms:false",
+            "sms:validationRules": []
+        },
         {
             "@id": "bts:Checksum",
             "@type": "rdfs:Class",
@@ -42305,7 +42325,10 @@
             ],
             "sms:displayName": "Stripe Calling",
             "sms:required": "sms:true",
-            "sms:validationRules": []
+            "sms:validationRules": [
+                "list",
+                "-?\\d+"
+            ]
         },
         {
             "@id": "bts:LoopWindow",
@@ -42323,13 +42346,14 @@
             "sms:displayName": "Loop Window",
             "sms:required": "sms:true",
             "sms:validationRules": [
-                "int"
+                "list like ",
+                " regex search -?\\d+"
             ]
         },
         {
             "@id": "bts:StripeWindow",
             "@type": "rdfs:Class",
-            "rdfs:comment": "Binning size used for calling significant architectural stripes. Can be an integer or int/int, indicating bin size and sliding window size if different.",
+            "rdfs:comment": "Binning size used for calling significant architectural stripes. Can be an integer or comma-separated list of integers indicating bin size and sliding window size if different.",
             "rdfs:label": "StripeWindow",
             "rdfs:subClassOf": [
                 {
@@ -42339,20 +42363,12 @@
             "schema:isPartOf": {
                 "@id": "http://schema.biothings.io"
             },
-            "schema:rangeIncludes": [
-                {
-                    "@id": "bts:HiCCUPS"
-                },
-                {
-                    "@id": "bts:Cooltools"
-                },
-                {
-                    "@id": "bts:Other"
-                }
-            ],
             "sms:displayName": "Stripe Window",
             "sms:required": "sms:true",
-            "sms:validationRules": []
+            "sms:validationRules": [
+                "list like ",
+                " regex search -?\\d+"
+            ]
         },
         {
             "@id": "bts:LoopCalling",
@@ -42367,6 +42383,17 @@
             "schema:isPartOf": {
                 "@id": "http://schema.biothings.io"
             },
+            "schema:rangeIncludes": [
+                {
+                    "@id": "bts:HiCCUPS"
+                },
+                {
+                    "@id": "bts:Cooltools"
+                },
+                {
+                    "@id": "bts:Other"
+                }
+            ],
             "sms:displayName": "Loop Calling",
             "sms:required": "sms:true",
             "sms:validationRules": []
@@ -42765,7 +42792,7 @@
                     "@id": "bts:StripeCalling"
                 },
                 {
-                    "@id": "bts:StripeWindow"
+                    "@id": "bts:LoopCalling"
                 },
                 {
                     "@id": "bts:HistologyAssessmentBy"
@@ -42989,7 +43016,7 @@
             "rdfs:label": "HiCCUPS",
             "rdfs:subClassOf": [
                 {
-                    "@id": "bts:StripeWindow"
+                    "@id": "bts:LoopCalling"
                 }
             ],
             "schema:isPartOf": {
@@ -43006,7 +43033,7 @@
             "rdfs:label": "Cooltools",
             "rdfs:subClassOf": [
                 {
-                    "@id": "bts:StripeWindow"
+                    "@id": "bts:LoopCalling"
                 }
             ],
             "schema:isPartOf": {