Merge pull request #18 from eastgenomics/CNV_integration_dev

GCNV-18 CNV integration (#18) Co-Authored-By: sophie22 <[email protected]>
eastgenomics · Oct 3, 2022 · 31f8a2d · 31f8a2d
2 parents dda56f8 + 677eff7
commit 31f8a2d
Showing 1 changed file with 129 additions and 2 deletions.
diff --git a/egg5_config.py b/egg5_config.py
@@ -9,7 +9,7 @@
 )
 
 assay_name = "CEN" # Core Endo Neuro
-assay_version = "v1.1.5"
+assay_version = "v1.2.0"
 
 ref_project_id = "project-Fkb6Gkj433GVVvj73J7x8KbV"
 
@@ -75,6 +75,24 @@
 mqc_applet_id = "app-G6FyybQ4f4xqqpFfGqg34y2Y"
 mqc_config_file = "{}:file-G82027Q433Gfx69zGvjq7PqQ".format(ref_project_id)
 
+
+# CNV calling
+
+cnvcall_app_id = "app-GF3J3Kj4jq2VZkJ2P46fJ9vv"
+cnvcalling_fixed_inputs = {
+    # GATK Docker image tar
+    "gatk_docker": "{}:file-GBBP9JQ433GxV97xBpQkzYZx".format(ref_project_id),
+    # CEN intervals for CNV calling and its annotation
+    "interval_list": "{}:file-GFPxzKj4V50pJX3F4vV58yyg".format(ref_project_id),
+    "annotation_tsv": "{}:file-GFPxzPQ4V50z4pv230p82G0q".format(ref_project_id),
+}
+
+cnvcalling_input_dict = {
+    "app": "sentieon-dnaseq",
+    "patterns": ["-E '(.*).bam$'", "-E '(.*).bai$'"]
+}
+
+
 # Reports
 
 xlsx_flanks = 495
@@ -172,4 +190,113 @@
     # inputs for athena
     "{}.exons_file ID".format(athena_stage_id): cds_file_for_athena,
     "{}.exons_file".format(athena_stage_id): ""
-}
+}
+
+
+# CNV Reports
+
+cnv_rpt_workflow_id =  "{}:workflow-GGpkk40433GQqXQj4j2FyV36".format(ref_project_id)
+
+cnv_generate_bed_excluded_stage_id = "stage-GFZQB7Q4qq8X6yjKG2pFQ58x"
+cnv_generate_bed_vep_stage_id = "stage-GG39Gq04qq8ZkfgV31yQy93v"
+cnv_annotate_excluded_regions_stage_id = "stage-GG1qYz84qq8yKzF1J2X48q62"
+cnv_vep_stage_id = "stage-GFYvJF04qq8VKgq34j30pZZ3"
+cnv_generate_workbook_stage_id = "stage-GFfYY9j4qq8ZxpFpP8zKG7G0"
+
+cnv_vep_config =  "{}:file-GGkJqk84GVVGqG6VFz60gkFF".format(ref_project_id)
+additional_regions = "{}:file-GGkz5B84GVV4KbX64gzBXqZ2".format(ref_project_id)
+
+cnv_rpt_stage_input_dict = {
+    # generate_bed for vep generate bed
+    "{}.sample_file".format(cnv_generate_bed_vep_stage_id): {
+        "app": "mosdepth", "subdir": "",
+        "pattern": "-E '{}(.*).per-base.bed.gz.csi$'"
+    },
+    # generate_bed for excluded generate bed
+    "{}.sample_file".format(cnv_generate_bed_excluded_stage_id): {
+        "app": "mosdepth", "subdir": "",
+        "pattern": "-E '{}(.*).per-base.bed.gz.csi$'"
+    },
+    # vep
+    # subdirectories always require the backward dash
+    "{}.vcf".format(cnv_vep_stage_id): {
+        "app": "eggd_GATKgCNV_call", "subdir": "CNV_vcfs/",
+        "pattern": "-E '{}(.*)_segments.vcf$'"
+    },
+    # excluded_annotate
+     # subdirectories always require the backward dash
+    "{}.excluded_regions".format(cnv_annotate_excluded_regions_stage_id): {
+        "app": "eggd_GATKgCNV_call", "subdir": "CNV_summary/",
+        "pattern": "-E '(.*)_excluded_intervals.bed$'"
+    },
+}
+
+cnv_rpt_dynamic_files = {
+    # inputs for generate bed for vep
+    "{}.exons_nirvana ID".format(cnv_generate_bed_vep_stage_id): cds_file,
+    "{}.exons_nirvana".format(cnv_generate_bed_vep_stage_id): "",
+    "{}.nirvana_genes2transcripts ID".format(cnv_generate_bed_vep_stage_id): genes2transcripts,
+    "{}.nirvana_genes2transcripts".format(cnv_generate_bed_vep_stage_id): "",
+    "{}.gene_panels ID".format(cnv_generate_bed_vep_stage_id): genepanels_file,
+    "{}.gene_panels".format(cnv_generate_bed_vep_stage_id): "",
+    "{}.manifest ID".format(cnv_generate_bed_vep_stage_id): bioinformatic_manifest,
+    "{}.manifest".format(cnv_generate_bed_vep_stage_id): "",
+    # inputs for generate bed for excluded app
+    "{}.exons_nirvana ID".format(cnv_generate_bed_excluded_stage_id): cds_file,
+    "{}.exons_nirvana".format(cnv_generate_bed_excluded_stage_id): "",
+    "{}.nirvana_genes2transcripts ID".format(cnv_generate_bed_excluded_stage_id): genes2transcripts,
+    "{}.nirvana_genes2transcripts".format(cnv_generate_bed_excluded_stage_id): "",
+    "{}.gene_panels ID".format(cnv_generate_bed_excluded_stage_id): genepanels_file,
+    "{}.gene_panels".format(cnv_generate_bed_excluded_stage_id): "",
+    "{}.manifest ID".format(cnv_generate_bed_excluded_stage_id): bioinformatic_manifest,
+    "{}.manifest".format(cnv_generate_bed_excluded_stage_id): "",
+    # inputs for excluded app
+    "{}.cds_hgnc ID".format(cnv_annotate_excluded_regions_stage_id): cds_file,
+    "{}.cds_hgnc".format(cnv_annotate_excluded_regions_stage_id): "",
+    "{}.cds_gene ID".format(cnv_annotate_excluded_regions_stage_id): cds_file_for_athena,
+    "{}.cds_gene".format(cnv_annotate_excluded_regions_stage_id): "",
+    "{}.additional_regions ID".format(cnv_annotate_excluded_regions_stage_id): additional_regions,
+    "{}.additional_regions".format(cnv_annotate_excluded_regions_stage_id): ""
+}
+
+# CNV reanalysis
+
+cnv_rea_stage_input_dict  = {
+    # vep
+    # subdirectories always require the backward dash
+    "{}.vcf".format(cnv_vep_stage_id): {
+        "app": "eggd_GATKgCNV_call", "subdir": "CNV_vcfs/",
+        "pattern": "-E '{}(.*)_segments.vcf$'"
+    },
+    # excluded_annotate
+     # subdirectories always require the backward dash
+    "{}.excluded_regions".format(cnv_annotate_excluded_regions_stage_id): {
+        "app": "eggd_GATKgCNV_call", "subdir": "CNV_summary/",
+        "pattern": "-E '(.*)_excluded_intervals.bed$'"
+    },
+}
+cnv_rea_dynamic_files = {
+    # inputs for generate bed for vep
+    "{}.exons_nirvana ID".format(cnv_generate_bed_vep_stage_id): cds_file,
+    "{}.exons_nirvana".format(cnv_generate_bed_vep_stage_id): "",
+    "{}.nirvana_genes2transcripts ID".format(cnv_generate_bed_vep_stage_id): genes2transcripts,
+    "{}.nirvana_genes2transcripts".format(cnv_generate_bed_vep_stage_id): "",
+    "{}.gene_panels ID".format(cnv_generate_bed_vep_stage_id): genepanels_file,
+    "{}.gene_panels".format(cnv_generate_bed_vep_stage_id): "",
+    # inputs for generate bed for excluded app
+    "{}.exons_nirvana ID".format(cnv_generate_bed_excluded_stage_id): cds_file,
+    "{}.exons_nirvana".format(cnv_generate_bed_excluded_stage_id): "",
+    "{}.nirvana_genes2transcripts ID".format(cnv_generate_bed_excluded_stage_id): genes2transcripts,
+    "{}.nirvana_genes2transcripts".format(cnv_generate_bed_excluded_stage_id): "",
+    "{}.gene_panels ID".format(cnv_generate_bed_excluded_stage_id): genepanels_file,
+    "{}.gene_panels".format(cnv_generate_bed_excluded_stage_id): "",
+    "{}.manifest ID".format(cnv_generate_bed_excluded_stage_id): bioinformatic_manifest,
+    "{}.manifest".format(cnv_generate_bed_excluded_stage_id): "",
+    # inputs for excluded app
+    "{}.cds_hgnc ID".format(cnv_annotate_excluded_regions_stage_id): cds_file,
+    "{}.cds_hgnc".format(cnv_annotate_excluded_regions_stage_id): "",
+    "{}.cds_gene ID".format(cnv_annotate_excluded_regions_stage_id): cds_file_for_athena,
+    "{}.cds_gene".format(cnv_annotate_excluded_regions_stage_id): "",
+    "{}.additional_regions ID".format(cnv_annotate_excluded_regions_stage_id): additional_regions,
+    "{}.additional_regions".format(cnv_annotate_excluded_regions_stage_id): ""
+}