Merge pull request #36 from eastgenomics/DI-366-v2.1.0

Di 366 v2.1.0 (#36)

Co-Authored-By: Jay Miles <jay.miles@addenbrookes.nhs.uk>

README.md

@@ -1,2 +1,26 @@
 # egg4_dias_TWE_config
-Config for the Dias TWE assay
+
+This repo contains a Python config file which is used with dias_batch_running to specify inputs for running the Dias pipeline for TWE data.
+
+## What does the config do?
+dias_batch_running ([https://github.com/eastgenomics/dias_batch_running](https://github.com/eastgenomics/dias_batch_running)) is a Python module that runs the Dias pipeline for germline sequence data analysis on DNAnexus. The egg5_dias_TWE_config specifies the executables and their input files to be used in the Dias pipeline for analysing TWE data.
+
+New versions of apps and app inputs for use in the Dias pipeline can be updated in the config without needing to update the pipeline itself.
+
+## Parts of the config
+* dias_reports
+    * specifies the workflow ID, stage IDs (matching those in the workflow), and dynamic files for dias_reports.
+
+## Versions of workflows and dynamic files in the config
+Workflows:
+* Dias reports: **dias_reports_v2.1.0**
+    * DNAnexus workflow ID: `workflow-GXzkfYj4QPQp9z4Jz4BF09y6`
+
+Dynamic files:
+| File      | File name | DNAnexus file ID |
+| --------- | --------- | ---------------- |
+| genepanels | **230602_genepanels.tsv** | `file-GVx0vkQ433Gvq63k1Kj4Y562` |
+| genes2transcripts | **230421_g2t.tsv** | `file-GV4P970433Gj6812zGVBZvB4` |
+| exons_nirvana | **GCF_000001405.25_GRCh37.p13_genomic.exon_5bp_v2.0.0.tsv** | `file-GF611Z8433Gk7gZ47gypK7ZZ` |
+| exons_file for eggd_athena | **GCF_000001405.25_GRCh37.p13_genomic.symbols.exon_5bp_v2.0.0.tsv** | `file-GF611Z8433Gf99pBPbJkV7bq` |
+| twe_vep_config for SNV reports | **twe_vep_config_v1.1.6.json** | `file-GYX8q204j4fpP18Qx7YGkJvX` |

egg4_config_v2.1.0.py

@@ -0,0 +1,89 @@
+assay_name = "TWE" # Twist Whole Exome
+assay_version = "v2.1.0"
+
+ref_project_id = "project-Fkb6Gkj433GVVvj73J7x8KbV"
+
+### Dynamic files:
+
+## for generate_bed
+# genepanels 230602
+genepanels_file = "{}:file-GVx0vkQ433Gvq63k1Kj4Y562".format(ref_project_id)
+# g2t 230421
+genes2transcripts = "{}:file-GV4P970433Gj6812zGVBZvB4".format(ref_project_id)
+# GCF_000001405.25_GRCh37.p13_genomic.exon_5bp_v2.0.0.tsv
+exons_nirvana = "{}:file-GF611Z8433Gk7gZ47gypK7ZZ".format(ref_project_id)
+
+# for generate_bed_for_VEP
+vep_bed_flank = 495
+
+## for eggd_Athena
+# GCF_000001405.25_GRCh37.p13_genomic.symbols.exon_5bp_v2.0.0.tsv
+exons_file = "{}:file-GF611Z8433Gf99pBPbJkV7bq".format(ref_project_id)
+
+## for eggd_VEP
+# VEP config file for SNV reports v1.1.6
+vep_config = "{}:file-GYX8q204j4fpP18Qx7YGkJvX".format(ref_project_id)
+
+
+### Apps and workflows:
+
+# dias_reports
+# v2.1.0
+rpt_workflow_id = "{}:workflow-GXzkfYj4QPQp9z4Jz4BF09y6".format(ref_project_id)
+
+generate_bed_vep_stage_id = "stage-rpt_generate_bed_vep"
+vep_stage_id = "stage-rpt_vep"
+generate_workbook_stage_id = "stage-rpt_generate_workbook"
+generate_bed_athena_stage_id = "stage-rpt_generate_bed_athena"
+athena_stage_id = "stage-rpt_athena"
+
+rpt_dynamic_files = {
+    # inputs for generate bed for vep
+    "{}.exons_nirvana ID".format(generate_bed_vep_stage_id): exons_nirvana,
+    "{}.exons_nirvana".format(generate_bed_vep_stage_id): "",
+    "{}.nirvana_genes2transcripts ID".format(generate_bed_vep_stage_id): genes2transcripts,
+    "{}.nirvana_genes2transcripts".format(generate_bed_vep_stage_id): "",
+    "{}.gene_panels ID".format(generate_bed_vep_stage_id): genepanels_file,
+    "{}.gene_panels".format(generate_bed_vep_stage_id): "",
+    # inputs for eggd_vep
+    "{}.config_file ID".format(vep_stage_id): vep_config,
+    "{}.config_file".format(vep_stage_id): "",
+    # inputs for generate_variant_workbook
+    "{}.exclude_columns".format(generate_workbook_stage_id): "BaseQRankSum ClippingRankSum DB ExcessHet FS MLEAC MLEAF MQ MQRankSum QD ReadPosRankSum SOR PL QUAL ID FILTER  CSQ_ClinVar_CLNSIGCONF  CSQ_Allele CSQ_HGNC_ID DP AC AF AN CSQ_SpliceAI_pred_DP_AL CSQ_SpliceAI_pred_DP_AG CSQ_SpliceAI_pred_DP_DG CSQ_SpliceAI_pred_DP_DL",
+    "{}.acmg".format(generate_workbook_stage_id): "true",
+    "{}.rename_columns".format(generate_workbook_stage_id): "CSQ_Feature=Transcript DP_FMT=DP",
+    "{}.add_comment_column".format(generate_workbook_stage_id): "true",
+    "{}.keep_tmp".format(generate_workbook_stage_id): "true",
+    "{}.summary".format(generate_workbook_stage_id): "dias",
+    "{}.filter".format(generate_workbook_stage_id): "bcftools filter -e '(CSQ_Consequence==\"synonymous_variant\" | CSQ_Consequence==\"intron_variant\" | CSQ_Consequence==\"upstream_gene_variant\" | CSQ_Consequence==\"downstream_gene_variant\" | CSQ_Consequence==\"intergenic_variant\" | CSQ_Consequence==\"5_prime_UTR_variant\" | CSQ_Consequence==\"3_prime_UTR_variant\" | CSQ_gnomADe_AF>0.01 | CSQ_gnomADg_AF>0.01 | CSQ_TWE_AF>0.05) & CSQ_HGMD_CLASS!~ \"DM\" & CSQ_ClinVar_CLNSIG!~ \"pathogenic\\/i\" & CSQ_ClinVar_CLNSIGCONF!~ \"pathogenic\\/i\"'",
+    "{}.human_filter".format(generate_workbook_stage_id): "excluded gnomAD exomes / genomes > 1%, TWE > 5%, synonymous / intronic / intergenic / upstream / downstream / UTRs EXCEPT pathogenic status in ClinVar OR DM in HGMD Class",
+    "{}.reorder_columns".format(generate_workbook_stage_id): "CHROM POS REF ALT GT GQ DP_FMT AD CSQ_SYMBOL CSQ_EXON CSQ_INTRON CSQ_HGVSc CSQ_HGVSp CSQ_Consequence CSQ_IMPACT CSQ_VARIANT_CLASS CSQ_gnomADe_AF CSQ_gnomADe_Hom CSQ_gnomADe_AC CSQ_gnomADe_AN CSQ_gnomADg_AF CSQ_gnomADg_AC CSQ_gnomADg_AN CSQ_TWE_AF CSQ_TWE_AC_Hom CSQ_TWE_AC_Het CSQ_TWE_AN CSQ_HGMD CSQ_HGMD_CLASS CSQ_HGMD_RANKSCORE CSQ_HGMD_PHEN CSQ_Existing_variation CSQ_ClinVar CSQ_ClinVar_CLNDN CSQ_ClinVar_CLNSIG CSQ_Mastermind_MMID3 CSQ_CADD_PHRED CSQ_REVEL CSQ_SpliceAI_pred_DS_AG CSQ_SpliceAI_pred_DS_AL CSQ_SpliceAI_pred_DS_DG CSQ_SpliceAI_pred_DS_DL CSQ_HGVS_OFFSET CSQ_STRAND CSQ_Feature",
+    # inputs for generate bed for athena
+    "{}.exons_nirvana ID".format(generate_bed_athena_stage_id): exons_nirvana,
+    "{}.exons_nirvana".format(generate_bed_athena_stage_id): "",
+    "{}.nirvana_genes2transcripts ID".format(generate_bed_athena_stage_id): genes2transcripts,
+    "{}.nirvana_genes2transcripts".format(generate_bed_athena_stage_id): "",
+    "{}.gene_panels ID".format(generate_bed_athena_stage_id): genepanels_file,
+    "{}.gene_panels".format(generate_bed_athena_stage_id): "",
+    # inputs for athena
+    "{}.exons_file ID".format(athena_stage_id): exons_file,
+    "{}.exons_file".format(athena_stage_id): "",
+    "{}.limit".format(athena_stage_id): "260",
+    "{}.summary".format(athena_stage_id): "true"
+}
+
+# Sample-specific input files and their search patterns
+rpt_stage_input_dict = {
+    # eggd_vep
+    "{}.vcf".format(vep_stage_id): {
+        "app": "sentieon-dnaseq", "subdir": "",
+        "pattern": "-E '{}(.*)[^g].vcf.gz$'"
+    },
+    # eggd_athena
+    "{}.mosdepth_files".format(athena_stage_id): {
+        "app": "mosdepth", "subdir": "",
+        # athena requires both per-base files and reference files
+        "pattern": "-E '{}(.*)(per-base.bed.gz$|reference)'"
+    },
+}
+