Merge pull request #79 from icgc-argo/update_experiment_workflow

update experiment and workflow for all schemas
icgc-argo · Jan 5, 2024 · b59ceef · b59ceef
2 parents 47f48ae + f86ef10
commit b59ceef
Show file tree

Hide file tree

Showing 15 changed files with 2,265 additions and 1,271 deletions.
diff --git a/example_payloads/dna-seq/qc_metrics.aln.json b/example_payloads/dna-seq/qc_metrics.aln.json
@@ -1,5 +1,4 @@
 {
-  "analysisId": "5a7860fe-9d97-4f83-b860-fe9d977f8382",
   "studyId": "TEST-PR",
   "samples": [
     {
@@ -84,6 +83,9 @@
   },
   "experiment": {
     "platform": "ILLUMINA",
-    "experimental_strategy": "WXS"
+    "experimental_strategy": "WXS",
+    "target_capture_kit": "test-1",
+    "primary_target_regions": "test-1-primary.bed",
+    "capture_target_regions": "test-1-capture.bed"
   }
 }
diff --git a/example_payloads/dna-seq/qc_metrics.mutect2.json b/example_payloads/dna-seq/qc_metrics.mutect2.json
@@ -1,5 +1,4 @@
 {
-  "analysisId": "bcd90fe1-94f0-46bb-990f-e194f0a6bb6e",
   "studyId": "TEST-PR",
   "samples": [
     {

diff --git a/example_payloads/dna-seq/qc_metrics.sanger-wgs.json b/example_payloads/dna-seq/qc_metrics.sanger-wgs.json
@@ -1,5 +1,4 @@
 {
-  "analysisId": "a02ef79d-469b-4df2-aef7-9d469bcdf299",
   "studyId": "TEST-PR",
   "samples": [
     {

diff --git a/example_payloads/dna-seq/sequencing_experiment.target_tumour.json b/example_payloads/dna-seq/sequencing_experiment.target_tumour.json
@@ -0,0 +1,92 @@
+{
+  "studyId": "TEST-PR",
+  "analysisType": {
+    "name": "sequencing_experiment"
+  },
+  "samples": [
+    {
+      "submitterSampleId": "HCC1143_BAM_INPUT",
+      "sampleType": "Total DNA",
+      "matchedNormalSubmitterSampleId": null,
+      "specimen": {
+        "submitterSpecimenId": "HCC1143_BAM_INPUT",
+        "tumourNormalDesignation": "Tumour",
+        "specimenTissueSource": "Blood derived",
+        "specimenType": "Tumour"
+      },
+      "donor": {
+        "gender": "Female",
+        "submitterDonorId": "HCC1143"
+      }
+    }
+  ],
+  "files": [
+    {
+      "info": {
+        "data_category": "Sequencing Reads"
+      },
+      "fileName": "ffa7767e7d2f6205ecf971a40ccdea44.bam",
+      "fileSize": 14988,
+      "fileType": "BAM",
+      "fileMd5sum": "da81a03e0a04f165f4a682e8e02a8e3c",
+      "fileAccess": "controlled",
+      "dataType": "Submitted Reads"
+    }
+  ],
+  "experiment": {
+    "experimental_strategy": "Targeted-Seq",
+    "platform": "ILLUMINA",
+    "target_capture_kit": "test-1",
+    "primary_target_regions": "test-1-primary.bed",
+    "capture_target_regions": "test-1-capture.bed",
+    "library_selection": "Hybrid Selection",
+    "number_of_genes": 400,
+    "gene_padding": 20,
+    "coverage": [
+      "Hotspot Regions",
+      "Promoters"
+    ]
+  },
+  "read_group_count": 3,
+  "read_groups": [
+    {
+      "file_r1": "ffa7767e7d2f6205ecf971a40ccdea44.bam",
+      "file_r2": "ffa7767e7d2f6205ecf971a40ccdea44.bam",
+      "insert_size": 298,
+      "is_paired_end": true,
+      "library_name": "Pond-147580",
+      "platform_unit": "74_8a",
+      "read_group_id_in_bam": "C0HVY.2",
+      "read_length_r1": 150,
+      "read_length_r2": 150,
+      "sample_barcode": null,
+      "submitter_read_group_id": "C0HVY_2"
+    },
+    {
+      "file_r1": "ffa7767e7d2f6205ecf971a40ccdea44.bam",
+      "file_r2": "ffa7767e7d2f6205ecf971a40ccdea44.bam",
+      "insert_size": 298,
+      "is_paired_end": true,
+      "library_name": "Pond-147580",
+      "platform_unit": "74_8b",
+      "read_group_id_in_bam": "D0RE2.1",
+      "read_length_r1": 150,
+      "read_length_r2": 150,
+      "sample_barcode": null,
+      "submitter_read_group_id": "D0RE2_1"
+    },
+    {
+      "file_r1": "ffa7767e7d2f6205ecf971a40ccdea44.bam",
+      "file_r2": "ffa7767e7d2f6205ecf971a40ccdea44.bam",
+      "insert_size": 298,
+      "is_paired_end": true,
+      "library_name": "Pond-147580",
+      "platform_unit": "74_8c",
+      "read_group_id_in_bam": "D0RH0.2",
+      "read_length_r1": 150,
+      "read_length_r2": 150,
+      "sample_barcode": null,
+      "submitter_read_group_id": "D0RH0_2"
+    }
+  ]
+}
diff --git a/example_payloads/dna-seq/sequencing_experiment.wgs_tumour.json b/example_payloads/dna-seq/sequencing_experiment.wgs_tumour.json
@@ -0,0 +1,82 @@
+{
+  "studyId": "TEST-PR",
+  "analysisType": {
+    "name": "sequencing_experiment"
+  },
+  "samples": [
+    {
+      "submitterSampleId": "HCC1143_BAM_INPUT",
+      "sampleType": "Total DNA",
+      "matchedNormalSubmitterSampleId": null,
+      "specimen": {
+        "submitterSpecimenId": "HCC1143_BAM_INPUT",
+        "tumourNormalDesignation": "Tumour",
+        "specimenTissueSource": "Blood derived",
+        "specimenType": "Tumour"
+      },
+      "donor": {
+        "gender": "Female",
+        "submitterDonorId": "HCC1143"
+      }
+    }
+  ],
+  "files": [
+    {
+      "info": {
+        "data_category": "Sequencing Reads"
+      },
+      "fileName": "ffa7767e7d2f6205ecf971a40ccdea44.bam",
+      "fileSize": 14988,
+      "fileType": "BAM",
+      "fileMd5sum": "da81a03e0a04f165f4a682e8e02a8e3c",
+      "fileAccess": "controlled",
+      "dataType": "Submitted Reads"
+    }
+  ],
+  "experiment": {
+    "experimental_strategy": "WGS",
+    "platform": "ILLUMINA"
+  },
+  "read_group_count": 3,
+  "read_groups": [
+    {
+      "file_r1": "ffa7767e7d2f6205ecf971a40ccdea44.bam",
+      "file_r2": "ffa7767e7d2f6205ecf971a40ccdea44.bam",
+      "insert_size": 298,
+      "is_paired_end": true,
+      "library_name": "Pond-147580",
+      "platform_unit": "74_8a",
+      "read_group_id_in_bam": "C0HVY.2",
+      "read_length_r1": 150,
+      "read_length_r2": 150,
+      "sample_barcode": null,
+      "submitter_read_group_id": "C0HVY_2"
+    },
+    {
+      "file_r1": "ffa7767e7d2f6205ecf971a40ccdea44.bam",
+      "file_r2": "ffa7767e7d2f6205ecf971a40ccdea44.bam",
+      "insert_size": 298,
+      "is_paired_end": true,
+      "library_name": "Pond-147580",
+      "platform_unit": "74_8b",
+      "read_group_id_in_bam": "D0RE2.1",
+      "read_length_r1": 150,
+      "read_length_r2": 150,
+      "sample_barcode": null,
+      "submitter_read_group_id": "D0RE2_1"
+    },
+    {
+      "file_r1": "ffa7767e7d2f6205ecf971a40ccdea44.bam",
+      "file_r2": "ffa7767e7d2f6205ecf971a40ccdea44.bam",
+      "insert_size": 298,
+      "is_paired_end": true,
+      "library_name": "Pond-147580",
+      "platform_unit": "74_8c",
+      "read_group_id_in_bam": "D0RH0.2",
+      "read_length_r1": 150,
+      "read_length_r2": 150,
+      "sample_barcode": null,
+      "submitter_read_group_id": "D0RH0_2"
+    }
+  ]
+}
diff --git a/example_payloads/dna-seq/variant_calling.mutect2.json b/example_payloads/dna-seq/variant_calling.mutect2.json
@@ -1,5 +1,4 @@
 {
-  "analysisId": "41b02476-803f-40f5-b024-76803f10f5ec",
   "studyId": "TEST-PR",
   "samples": [
     {
@@ -74,7 +73,10 @@
   },
   "experiment": {
     "platform": "ILLUMINA",
-    "experimental_strategy": "WXS"
+    "experimental_strategy": "WXS",
+    "target_capture_kit": "test-1",
+    "primary_target_regions": "test-1-primary.bed",
+    "capture_target_regions": "test-1-capture.bed"
   },
   "variant_class": "Somatic"
 }
diff --git a/example_payloads/dna-seq/variant_calling.sanger.json b/example_payloads/dna-seq/variant_calling.sanger.json
@@ -1,5 +1,4 @@
 {
-  "analysisId": "fddb136b-3074-41cd-9b13-6b307461cdd7",
   "studyId": "TEST-PR",
   "samples": [
     {
@@ -75,7 +74,10 @@
   },
   "experiment": {
     "platform": "ILLUMINA",
-    "experimental_strategy": "WXS"
+    "experimental_strategy": "WXS",
+    "target_capture_kit": "test-1",
+    "primary_target_regions": "test-1-primary.bed",
+    "capture_target_regions": "test-1-capture.bed"
   },
   "variant_class": "Somatic"
 }
diff --git a/example_payloads/dna-seq/variant_calling_supplement.json b/example_payloads/dna-seq/variant_calling_supplement.json
@@ -1,5 +1,4 @@
 {
-  "analysisId": "a97ed172-533f-4700-bed1-72533f37008a",
   "studyId": "TEST-PR",
   "samples": [
     {