IGVF-3608-methylation-content-types

src/igvfd/audit/file_set.py

@@ -1322,6 +1322,7 @@ def audit_missing_genome_transcriptome_references(value, system):
         'pseudobulk annotations',
         'sample sort parameters',
         'spatial transcriptomics cell metadata',
+        'spatial transcriptomics slide-level cell boundaries',
         'spatial transcriptomics slide-level cell coordinates',
         'spatial transcriptomics slide-level transcripts',
         'studies_variants_phenotypes',

src/igvfd/schemas/changelogs/analysis_step.md

@@ -2,6 +2,16 @@
 
 ### Minor changes since schema version 15
 
+* Extend `input_content_types` enum list to include `chromatin conformation compartments`.
+* Extend `output_content_types` enum list to include `chromatin conformation compartments`.
+* Extend `input_content_types` enum list to include `differentially methylated regions`.
+* Extend `output_content_types` enum list to include `differentially methylated regions`.
+* Extend `input_content_types` enum list to include `methylation regions`.
+* Extend `output_content_types` enum list to include `methylation regions`.
+* Extend `input_content_types` enum list to include `topologically associating domains`.
+* Extend `output_content_types` enum list to include `topologically associating domains`.
+* Extend `input_content_types` enum list to include `spatial transcriptomics slide-level cell boundaries`.
+* Extend `output_content_types` enum list to include `spatial transcriptomics slide-level cell boundaries`.
 * Extend `input_content_types` enum list to include `cell by gene program matrix`.
 * Extend `output_content_types` enum list to include `cell by gene program matrix`.
 * Extend `input_content_types` enum list to include `program-program correlation`.

src/igvfd/schemas/changelogs/tabular_file.md

@@ -2,6 +2,11 @@
 
 ### Minor changes since schema version 25
 
+* Extend `content_type` enum list to include `chromatin conformation compartments`.
+* Extend `content_type` enum list to include `differentially methylated regions`.
+* Extend `content_type` enum list to include `methylation regions`.
+* Extend `content_type` enum list to include `topologically associating domains`.
+* Extend `content_type` enum list to include `spatial transcriptomics slide-level cell boundaries`.
 * Extend `catalog_collections` enum list to include `genomic_elements_phenotypes`.
 * Extend `content_type` enum list to include `program-program correlation`.
 * Extend `content_type` enum list to include `regulator-regulator correlation`.

src/igvfd/schemas/tabular_file.json

@@ -154,6 +154,7 @@
                                 "bin paired count",
                                 "calibrated coding variant effects",
                                 "caQTL",
+                                "chromatin conformation compartments",
                                 "chromatin contact quantifications",
                                 "cis-trans regulatory differences",
                                 "co-localization scores",
@@ -168,6 +169,7 @@
                                 "motif-overlapping differential guide quantifications",
                                 "differential peak quantifications",
                                 "differential transcript expression quantifications",
+                                "differentially methylated regions",
                                 "domain constraint",
                                 "DNA footprint scores",
                                 "DUAL-IPA score",
@@ -191,6 +193,7 @@
                                 "local differential expression",
                                 "loci",
                                 "methylation counts",
+                                "methylation regions",
                                 "minus strand modification state",
                                 "modification state",
                                 "MPRA sequence designs",
@@ -219,6 +222,7 @@
                                 "reporter variants",
                                 "spliceQTL",
                                 "target transcripts",
+                                "topologically associating domains",
                                 "trans differential expression quantifications per element",
                                 "trans differential expression quantifications per guide",
                                 "transcript quantifications",
@@ -296,6 +300,7 @@
                                 "sample sort parameters",
                                 "selected normalized variants profile",
                                 "spatial transcriptomics cell metadata",
+                                "spatial transcriptomics slide-level cell boundaries",
                                 "spatial transcriptomics slide-level cell coordinates",
                                 "spatial transcriptomics slide-level transcripts",
                                 "studies_variants_phenotypes",
@@ -361,6 +366,7 @@
                 "caQTL",
                 "cell annotations",
                 "cell hashing barcodes",
+                "chromatin conformation compartments",
                 "chromatin contact quantifications",
                 "cis differential expression quantifications per element",
                 "cis differential expression quantifications per guide",
@@ -376,6 +382,7 @@
                 "motif-overlapping differential guide quantifications",
                 "differential peak quantifications",
                 "differential transcript expression quantifications",
+                "differentially methylated regions",
                 "domain constraint",
                 "DNA footprint scores",
                 "DUAL-IPA score",
@@ -408,6 +415,7 @@
                 "motifs",
                 "marker gene activity",
                 "methylation counts",
+                "methylation regions",
                 "minus strand modification state",
                 "modification state",
                 "MPRA sequence designs",
@@ -448,10 +456,12 @@
                 "sample sort parameters",
                 "selected normalized variants profile",
                 "spatial transcriptomics cell metadata",
+                "spatial transcriptomics slide-level cell boundaries",
                 "spatial transcriptomics slide-level cell coordinates",
                 "spatial transcriptomics slide-level transcripts",
                 "spliceQTL",
                 "target transcripts",
+                "topologically associating domains",
                 "trans differential expression quantifications per element",
                 "trans differential expression quantifications per guide",
                 "tissue positions",
@@ -485,6 +495,7 @@
                 "calibrated coding variant effect thresholds": "A file contains calibration thresholds for coding variant effects defining score ranges for ACMG/AMP evidence levels (PS3/BS3 Supporting through Very Strong) for all functional assays.",
                 "cell annotations": "A file containing cell classifications and/or labels based on their unique transcriptome and genomic signatures, usually generated from single cell sequencing experiments.",
                 "cell hashing barcodes": "The barcodes used for cell hashing.",
+                "chromatin conformation compartments": "A BED file containing genomic intervals and their compartment annotation.",
                 "chromatin contact quantifications": "A file containing chromatin conformation contacts.",
                 "cis differential expression quantifications per element": "Element-level differential expression results aggregated across guides targeting each element for nearby genes within a configured interval.",
                 "cis differential expression quantifications per guide": "Guide-level differential expression results for nearby genes within a configured interval around the guide target.",
@@ -499,6 +510,7 @@
                 "motif-overlapping differential guide quantifications": "The quantified differences in guide RNA (gRNA) abundance between experimental conditions, for gRNAs overlapping specific motifs.",
                 "differential peak quantifications": "The quantified changes in peaks detected between experimental conditions.",
                 "differential transcript expression quantifications": "The quantified changes in expression levels of transcripts between conditions or groups.",
+                "differentially methylated regions": "A BED file containing regions that are called as differentially methylated between samples.",
                 "domain constraint": "A file containing model estimates for the probability that a variant observed in the population is missense within a protein domain or interdomain region.",
                 "DNA footprint scores": "A file containing DNA footprint scores, which represents the binding sites between DNA and proteins called from assays like ATAC-seq data.",
                 "DUAL-IPA score": "A z-score that quantifies the relative abundance of a protein variant by comparing its GFP expression in HEK293T cells to that of the reference allele, with both signals normalized to mCherry expression as a control.",
@@ -530,6 +542,7 @@
                 "motifs": "A table listing sequence motifs.",
                 "marker gene activity": "A set of cell-type-specific genes identified in pseudobulked data sets with gene activity scores (GAS). These scores infer potential expression levels from single-cell ATAC-seq data by quantifying chromatin accessibility within and around specific gene loci.",
                 "methylation counts": "A CpG-level summary of methylation counts and coverage.",
+                "methylation regions": "A BED file containing methylation summaries at genomic intervals.",
                 "minus strand modification state": "A file with the bases on the minus strand where a DNA or RNA modification was detected.",
                 "modification state": "An unstranded file with the bases where a DNA or RNA modification was detected.",
                 "MPRA sequence designs": "Sequences designed for an MPRA experiment. Formatting should follow https://github.com/IGVF-DACC/checkfiles/blob/dev/src/schemas/table_schemas/mpra_sequence_designs.json.",
@@ -572,11 +585,13 @@
                 "reporter genomic element effects": "Defines the activity of an element/region within a genome associated with a reporter assay. Formatting should follow https://github.com/IGVF-DACC/checkfiles/blob/dev/src/schemas/as/reporter_genomic_element_effects.as.",
                 "reporter genomic variant effects": "Defines the activity of a variant within a genome associated with a reporter assay. Formatting should follow https://github.com/IGVF-DACC/checkfiles/blob/dev/src/schemas/as/reporter_genomic_variant_effects.as.",
                 "sample sort parameters": "The parameters/quantifications used for sorting biological samples, such as those in flow cytometry.",
-                "spatial transcriptomics cell metadata": "A csv file containing cell morphology descriptions and transcript summaries.",
-                "spatial transcriptomics slide-level cell coordinates": "A csv file containing field of view, cell, and spatial coordinates based on cell segmentation.",
-                "spatial transcriptomics slide-level transcripts": "A csv file containing spatial information of transcriptomics data.",
+                "spatial transcriptomics cell metadata": "A CSV file containing cell morphology descriptions and transcript summaries.",
+                "spatial transcriptomics slide-level cell boundaries": "A CSV file containing per-cell polygon boundary coordinates.",
+                "spatial transcriptomics slide-level cell coordinates": "A CSV file containing field of view, cell, and spatial coordinates based on cell segmentation.",
+                "spatial transcriptomics slide-level transcripts": "A CSV file containing spatial information of transcriptomics data.",
                 "target transcripts": "A GTF file containing annotations of targeted transcripts by the TAP-seq primer panel.",
                 "tissue positions": "The spatial coordinates or positions of tissue samples or sections in experiments.",
+                "topologically associating domains": "A BED file containing genomic intervals and their TAD/boundary annotation.",
                 "transcript quantifications": "The quantified levels of transcripts.",
                 "trans differential expression quantifications per guide": "Guide-level differential expression results across the full gene annotation.",
                 "trans differential expression quantifications per element": "Element-level differential expression results aggregated across guides targeting each element across the full gene annotation.",

src/igvfd/tests/data/inserts/tabular_file.json

@@ -2096,5 +2096,111 @@
         "filtered": false,
         "file_set": "igvf:curated_set_pathway_gene_mapping",
         "controlled_access": false
+    },
+    {
+        "uuid": "29f29094-2802-415b-a7bf-c7a510faae2c",
+        "accession": "IGVFFI0021MTHR",
+        "lab": "danwei-huangfu",
+        "award": "1U01HG012051-01",
+        "aliases": [
+            "igvf:tabular_file_methylation_regions"
+        ],
+        "md5sum": "effd99bdcb39037446aecdd991adcd96",
+        "file_format": "bed",
+        "file_format_type": "bed3+",
+        "content_type": "methylation regions",
+        "submitted_file_name": "/Users/igvf/igvf_files/methylation_regions.bed.gz",
+        "file_size": 388200,
+        "upload_status": "validated",
+        "filtered": false,
+        "file_set": "igvf:curated_set_pathway_gene_mapping",
+        "reference_files": [
+            "IGVFFI0001GNRF"
+        ],
+        "controlled_access": false
+    },
+    {
+        "uuid": "fc64cb1d-2802-415b-a7bf-c7a510faae2c",
+        "accession": "IGVFFI0022TADS",
+        "lab": "danwei-huangfu",
+        "award": "1U01HG012051-01",
+        "aliases": [
+            "igvf:tabular_file_topologically_associating_domains"
+        ],
+        "md5sum": "919d969454cf6acdda446ae99bdcb390",
+        "file_format": "bed",
+        "file_format_type": "bed3+",
+        "content_type": "topologically associating domains",
+        "submitted_file_name": "/Users/igvf/igvf_files/topologically_associating_domains.bed.gz",
+        "file_size": 4200,
+        "upload_status": "validated",
+        "filtered": false,
+        "file_set": "igvf:curated_set_pathway_gene_mapping",
+        "reference_files": [
+            "IGVFFI0001GNRF"
+        ],
+        "controlled_access": false
+    },
+    {
+        "uuid": "0db6840d-2802-415b-a7bf-c7a510faae2c",
+        "accession": "IGVFFI0023CHCC",
+        "lab": "danwei-huangfu",
+        "award": "1U01HG012051-01",
+        "aliases": [
+            "igvf:tabular_file_chromatin_conformation_compartments"
+        ],
+        "md5sum": "ebefa6cd1acdd0446aeb39d9673c6959",
+        "file_format": "bed",
+        "file_format_type": "bed3+",
+        "content_type": "chromatin conformation compartments",
+        "submitted_file_name": "/Users/igvf/igvf_files/chromatin_conformation_compartments.bed.gz",
+        "file_size": 4200,
+        "upload_status": "validated",
+        "filtered": false,
+        "file_set": "igvf:curated_set_pathway_gene_mapping",
+        "reference_files": [
+            "IGVFFI0001GNRF"
+        ],
+        "controlled_access": false
+    },
+    {
+        "uuid": "0873c695-2802-415b-40e7-c7a510faae2c",
+        "accession": "IGVFFI0024DMRS",
+        "lab": "danwei-huangfu",
+        "award": "1U01HG012051-01",
+        "aliases": [
+            "igvf:tabular_file_differentially_methylated_regions"
+        ],
+        "md5sum": "c9edb26ae99fee0d969f439091acdd94",
+        "file_format": "bed",
+        "file_format_type": "bed3+",
+        "content_type": "differentially methylated regions",
+        "submitted_file_name": "/Users/igvf/igvf_files/differentially_methylated_regions.bed.gz",
+        "file_size": 4200,
+        "upload_status": "validated",
+        "filtered": false,
+        "file_set": "igvf:curated_set_pathway_gene_mapping",
+        "reference_files": [
+            "IGVFFI0001GNRF"
+        ],
+        "controlled_access": false
+    },
+    {
+        "uuid": "b7e4a128-6d48-415b-8e4c-c7a510faae2c",
+        "accession": "IGVFFI0025CEBO",
+        "lab": "danwei-huangfu",
+        "award": "1U01HG012051-01",
+        "aliases": [
+            "igvf:tabular_file_spatial_transcriptomics_slide-level_cell_boundaries"
+        ],
+        "md5sum": "7cdfd4466b00b39091f6d6ae99bdc9ca",
+        "file_format": "csv",
+        "content_type": "spatial transcriptomics slide-level cell boundaries",
+        "submitted_file_name": "/Users/igvf/igvf_files/spatial_transcriptomics_slide-level_cell boundaries.csv.gz",
+        "file_size": 4200,
+        "upload_status": "validated",
+        "filtered": false,
+        "file_set": "igvf:curated_set_pathway_gene_mapping",
+        "controlled_access": false
     }
 ]