📝 update hotspot file refs

README.md

@@ -199,7 +199,7 @@ You can use the `include_expression` `Filter="PASS"` to achieve this.
    - `exac_common_vcf`: [small_exac_common_3.hg38.vcf.gz](https://console.cloud.google.com/storage/browser/gatk-best-practices/somatic-hg38) - need a valid google account, this is a link to the best practices google bucket from Broad GATK.
    - `vep_cache`: `homo_sapiens_merged_vep_105_indexed_GRCh38.tar.gz` from [VEP release 105](https://ftp.ensembl.org/pub/release-105/variation/indexed_vep_cache/) - variant effect predictor cache. Current production workflow uses this version.
    - `genomic_hotspots`: `tert.bed`. Tab-delimited BED formatted file(s) containing hg38 genomic positions corresponding to hotspots
-   - `protein_snv_hotspots`: [protein_snv_cancer_hotspots_v2.ENS105_liftover.tsv](https://www.cancerhotspots.org/files/hotspots_v2.xls). Column-name-containing, tab-delimited file(s) containing protein names and amino acid positions corresponding to hotspots. Recommend pulling the two relevant columns for SNVs only, and convert to TSV
+   - `protein_snv_hotspots`: `kfdrc_protein_snv_cancer_hotspots_20240718.txt`. Column-name-containing, tab-delimited file(s) containing protein names and amino acid positions corresponding to hotspots. File header contains generation history
    - `protein_indel_hotspots`: [protein_indel_cancer_hotspots_v2.ENS105_liftover.tsv](https://www.cancerhotspots.org/files/hotspots_v2.xls). Column-name-containing, tab-delimited file(s) containing protein names and amino acid position ranges corresponding to hotspots.
    - `echtvar_anno_zips`: `gnomad_3_1_1.vwb_subset.echtvar_0_1_9.zip`.Echtvar annotation ZIP file. For more info on how this file was created, see our [Ectvar documentation](./docs/echtvar_gnomad_annotation.md).
    - `custom_enst`: `kf_isoform_override.tsv`. As of VEP 104, several genes have had their canonical transcripts redefined. While the VCF will have all possible isoforms, this affects MAF file output and may results in representative protein changes that defy historical expectations

docs/kfdrc_annotation_wf.md

@@ -43,7 +43,7 @@ Secondary files needed for each reference file will be a sub-bullet point
  - `gatk_filter_expression`: ["vc.getGenotype('insert_normal_sample_name').getDP() <= 7", "gnomad_3_1_1_AF != '.' && gnomad_3_1_1_AF > 0.001"] # NOTE!! Replace `insert_normal_sample_name` with the value you'd use for `input_normal_name`! # NOTE!! For the AF filtration to pass, dot values must first be excluded! If they are not, GATK will error trying to convert those values!
  - `vep_cache`: `homo_sapiens_merged_vep_105_indexed_GRCh38.tar.gz`
  - `genomic_hotspots`: `tert.bed` # This file has two common TERT promoter gene hot spots
- - `protein_snv_hotspots`: `protein_snv_cancer_hotspots_v2.ENS105_liftover.tsv` # A tsv formatted SNV + MNV subset of https://www.cancerhotspots.org/files/hotspots_v2.xls
+ - `protein_snv_hotspots`: `kfdrc_protein_snv_cancer_hotspots_20240718.txt` # A text formatted SNV + MNV version of https://www.cancerhotspots.org/files/hotspots_v2.xls. See file header for details
  - `protein_indel_hotspots`: `protein_indel_cancer_hotspots_v2.ENS105_liftover.tsv` # A tsv formatted INDEL subset of https://www.cancerhotspots.org/files/hotspots_v2.xls
  - `custom_enst`: `kf_isoform_override.tsv` # As of VEP 104, several genes have had their canonical transcripts redefined. While the VCF will have all possible isoforms, this affects maf file output and may results in representative protein changes that defy historical expectations
 

docs/kfdrc_lancet_sub_wf.md

@@ -47,7 +47,7 @@ inputs:
 
   # annotation vars
   genomic_hotspots: { type: 'File[]?', doc: "Tab-delimited BED formatted file(s) containing hg38 genomic positions corresponding to hotspots", "sbg:suggestedValue": [{class: File, path: 607713829360f10e3982a423, name: tert.bed}] }
-  protein_snv_hotspots: { type: 'File[]?', doc: "Column-name-containing, tab-delimited file(s) containing protein names and amino acid positions corresponding to hotspots", "sbg:suggestedValue": [{class: File, path: 663d2bcc27374715fccd8c6a, name: protein_snv_cancer_hotspots_v2.ENS105_liftover.tsv}] }
+  protein_snv_hotspots: { type: 'File[]?', doc: "Column-name-containing, tab-delimited file(s) containing protein names and amino acid positions corresponding to hotspots", "sbg:suggestedValue": [{class: File, path: 66980e845a58091951d53984, name: kfdrc_protein_snv_cancer_hotspots_20240718.txt}] }
   protein_indel_hotspots: { type: 'File[]?', doc: "Column-name-containing, tab-delimited file(s) containing protein names and amino acid position ranges corresponding to hotspots", "sbg:suggestedValue": [{class: File, path: 663d2bcc27374715fccd8c6f, name: protein_indel_cancer_hotspots_v2.ENS105_liftover.tsv}] }
   retain_info: {type: 'string?', doc: "csv string with INFO fields that you want to keep", default: "gnomad_3_1_1_AC,gnomad_3_1_1_AN,gnomad_3_1_1_AF,gnomad_3_1_1_nhomalt,gnomad_3_1_1_AC_popmax,gnomad_3_1_1_AN_popmax,gnomad_3_1_1_AF_popmax,gnomad_3_1_1_nhomalt_popmax,gnomad_3_1_1_AC_controls_and_biobanks,gnomad_3_1_1_AN_controls_and_biobanks,gnomad_3_1_1_AF_controls_and_biobanks,gnomad_3_1_1_AF_non_cancer,gnomad_3_1_1_primate_ai_score,gnomad_3_1_1_splice_ai_consequence,MBQ,TLOD,HotSpotAllele"}
   retain_fmt: {type: 'string?', doc: "csv string with FORMAT fields that you want to keep"}

docs/kfdrc_mutect2_sub_wf.md

@@ -80,7 +80,7 @@ inputs:
 
   # annotation vars
   genomic_hotspots: { type: 'File[]?', doc: "Tab-delimited BED formatted file(s) containing hg38 genomic positions corresponding to hotspots", "sbg:suggestedValue": [{class: File, path: 607713829360f10e3982a423, name: tert.bed}] }
-  protein_snv_hotspots: { type: 'File[]?', doc: "Column-name-containing, tab-delimited file(s) containing protein names and amino acid positions corresponding to hotspots", "sbg:suggestedValue": [{class: File, path: 663d2bcc27374715fccd8c6a, name: protein_snv_cancer_hotspots_v2.ENS105_liftover.tsv}] }
+  protein_snv_hotspots: { type: 'File[]?', doc: "Column-name-containing, tab-delimited file(s) containing protein names and amino acid positions corresponding to hotspots", "sbg:suggestedValue": [{class: File, path: 66980e845a58091951d53984, name: kfdrc_protein_snv_cancer_hotspots_20240718.txt}] }
   protein_indel_hotspots: { type: 'File[]?', doc: "Column-name-containing, tab-delimited file(s) containing protein names and amino acid position ranges corresponding to hotspots", "sbg:suggestedValue": [{class: File, path: 663d2bcc27374715fccd8c6f, name: protein_indel_cancer_hotspots_v2.ENS105_liftover.tsv}] }
   retain_info: {type: 'string?', doc: "csv string with INFO fields that you want to keep", default: "gnomad_3_1_1_AC,gnomad_3_1_1_AN,gnomad_3_1_1_AF,gnomad_3_1_1_nhomalt,gnomad_3_1_1_AC_popmax,gnomad_3_1_1_AN_popmax,gnomad_3_1_1_AF_popmax,gnomad_3_1_1_nhomalt_popmax,gnomad_3_1_1_AC_controls_and_biobanks,gnomad_3_1_1_AN_controls_and_biobanks,gnomad_3_1_1_AF_controls_and_biobanks,gnomad_3_1_1_AF_non_cancer,gnomad_3_1_1_primate_ai_score,gnomad_3_1_1_splice_ai_consequence,MBQ,TLOD,HotSpotAllele"}
   retain_fmt: {type: 'string?', doc: "csv string with FORMAT fields that you want to keep"}

docs/kfdrc_strelka2_subworkflow.md

@@ -73,7 +73,7 @@ inputs:
 
   # annotation vars
   genomic_hotspots: { type: 'File[]?', doc: "Tab-delimited BED formatted file(s) containing hg38 genomic positions corresponding to hotspots", "sbg:suggestedValue": [{class: File, path: 607713829360f10e3982a423, name: tert.bed}] }
-  protein_snv_hotspots: { type: 'File[]?', doc: "Column-name-containing, tab-delimited file(s) containing protein names and amino acid positions corresponding to hotspots", "sbg:suggestedValue": [{class: File, path: 663d2bcc27374715fccd8c6a, name: protein_snv_cancer_hotspots_v2.ENS105_liftover.tsv}] }
+  protein_snv_hotspots: { type: 'File[]?', doc: "Column-name-containing, tab-delimited file(s) containing protein names and amino acid positions corresponding to hotspots", "sbg:suggestedValue": [{class: File, path: 66980e845a58091951d53984, name: kfdrc_protein_snv_cancer_hotspots_20240718.txt}] }
   protein_indel_hotspots: { type: 'File[]?', doc: "Column-name-containing, tab-delimited file(s) containing protein names and amino acid position ranges corresponding to hotspots", "sbg:suggestedValue": [{class: File, path: 663d2bcc27374715fccd8c6f, name: protein_indel_cancer_hotspots_v2.ENS105_liftover.tsv}] }
   retain_info: {type: 'string?', doc: "csv string with INFO fields that you want to keep", default: "gnomad_3_1_1_AC,gnomad_3_1_1_AN,gnomad_3_1_1_AF,gnomad_3_1_1_nhomalt,gnomad_3_1_1_AC_popmax,gnomad_3_1_1_AN_popmax,gnomad_3_1_1_AF_popmax,gnomad_3_1_1_nhomalt_popmax,gnomad_3_1_1_AC_controls_and_biobanks,gnomad_3_1_1_AN_controls_and_biobanks,gnomad_3_1_1_AF_controls_and_biobanks,gnomad_3_1_1_AF_non_cancer,gnomad_3_1_1_primate_ai_score,gnomad_3_1_1_splice_ai_consequence,MBQ,TLOD,HotSpotAllele"}
   retain_fmt: {type: 'string?', doc: "csv string with FORMAT fields that you want to keep"}

docs/kfdrc_vardict_sub_wf.md

@@ -50,7 +50,7 @@ inputs:
 
   # annotation vars
   genomic_hotspots: { type: 'File[]?', doc: "Tab-delimited BED formatted file(s) containing hg38 genomic positions corresponding to hotspots", "sbg:suggestedValue": [{class: File, path: 607713829360f10e3982a423, name: tert.bed}] }
-  protein_snv_hotspots: { type: 'File[]?', doc: "Column-name-containing, tab-delimited file(s) containing protein names and amino acid positions corresponding to hotspots", "sbg:suggestedValue": [{class: File, path: 663d2bcc27374715fccd8c6a, name: protein_snv_cancer_hotspots_v2.ENS105_liftover.tsv}] }
+  protein_snv_hotspots: { type: 'File[]?', doc: "Column-name-containing, tab-delimited file(s) containing protein names and amino acid positions corresponding to hotspots", "sbg:suggestedValue": [{class: File, path: 66980e845a58091951d53984, name: kfdrc_protein_snv_cancer_hotspots_20240718.txt}] }
   protein_indel_hotspots: { type: 'File[]?', doc: "Column-name-containing, tab-delimited file(s) containing protein names and amino acid position ranges corresponding to hotspots", "sbg:suggestedValue": [{class: File, path: 663d2bcc27374715fccd8c6f, name: protein_indel_cancer_hotspots_v2.ENS105_liftover.tsv}] }
   retain_info: {type: 'string?', doc: "csv string with INFO fields that you want to keep", default: "gnomad_3_1_1_AC,gnomad_3_1_1_AN,gnomad_3_1_1_AF,gnomad_3_1_1_nhomalt,gnomad_3_1_1_AC_popmax,gnomad_3_1_1_AN_popmax,gnomad_3_1_1_AF_popmax,gnomad_3_1_1_nhomalt_popmax,gnomad_3_1_1_AC_controls_and_biobanks,gnomad_3_1_1_AN_controls_and_biobanks,gnomad_3_1_1_AF_controls_and_biobanks,gnomad_3_1_1_AF_non_cancer,gnomad_3_1_1_primate_ai_score,gnomad_3_1_1_splice_ai_consequence,MBQ,TLOD,HotSpotAllele"}
   retain_fmt: {type: 'string?', doc: "csv string with FORMAT fields that you want to keep"}

workflow/kfdrc-somatic-variant-workflow.cwl

@@ -203,7 +203,7 @@ doc: |
      - `exac_common_vcf`: [small_exac_common_3.hg38.vcf.gz](https://console.cloud.google.com/storage/browser/gatk-best-practices/somatic-hg38) - need a valid google account, this is a link to the best practices google bucket from Broad GATK.
      - `vep_cache`: `homo_sapiens_merged_vep_105_indexed_GRCh38.tar.gz` from [VEP release 105](https://ftp.ensembl.org/pub/release-105/variation/indexed_vep_cache/) - variant effect predictor cache. Current production workflow uses this version.
      - `genomic_hotspots`: `tert.bed`. Tab-delimited BED formatted file(s) containing hg38 genomic positions corresponding to hotspots
-     - `protein_snv_hotspots`: [protein_snv_cancer_hotspots_v2.ENS105_liftover.tsv](https://www.cancerhotspots.org/files/hotspots_v2.xls). Column-name-containing, tab-delimited file(s) containing protein names and amino acid positions corresponding to hotspots. Recommend pulling the two relevant columns for SNVs only, and convert to TSV
+     - `protein_snv_hotspots`: [kfdrc_protein_snv_cancer_hotspots_20240718.txt](https://www.cancerhotspots.org/files/hotspots_v2.xls). Column-name-containing, tab-delimited file(s) containing protein names and amino acid positions corresponding to hotspots. Recommend pulling the two relevant columns for SNVs only, and convert to TSV
      - `protein_indel_hotspots`: [protein_indel_cancer_hotspots_v2.ENS105_liftover.tsv](https://www.cancerhotspots.org/files/hotspots_v2.xls). Column-name-containing, tab-delimited file(s) containing protein names and amino acid position ranges corresponding to hotspots.
      - `echtvar_anno_zips`: `gnomad_3_1_1.vwb_subset.echtvar_0_1_9.zip`.Echtvar annotation ZIP file. For more info on how this file was created, see our [Ectvar documentation](./docs/echtvar_gnomad_annotation.md).
      - `custom_enst`: `kf_isoform_override.tsv`. As of VEP 104, several genes have had their canonical transcripts redefined. While the VCF will have all possible isoforms, this affects MAF file output and may results in representative protein changes that defy historical expectations
@@ -485,7 +485,7 @@ inputs:
   genomic_hotspots: {type: 'File[]?', doc: "Tab-delimited BED formatted file(s) containing hg38 genomic positions corresponding to
       hotspots", "sbg:suggestedValue": [{class: File, path: 607713829360f10e3982a423, name: tert.bed}]}
   protein_snv_hotspots: {type: 'File[]?', doc: "Column-name-containing, tab-delimited file(s) containing protein names and amino acid
-      positions corresponding to hotspots", "sbg:suggestedValue": [{class: File, path: 663d2bcc27374715fccd8c6a, name: protein_snv_cancer_hotspots_v2.ENS105_liftover.tsv}]}
+      positions corresponding to hotspots", "sbg:suggestedValue": [{class: File, path: 66980e845a58091951d53984, name: kfdrc_protein_snv_cancer_hotspots_20240718.txt}]}
   protein_indel_hotspots: {type: 'File[]?', doc: "Column-name-containing, tab-delimited file(s) containing protein names and amino
       acid position ranges corresponding to hotspots", "sbg:suggestedValue": [{class: File, path: 663d2bcc27374715fccd8c6f, name: protein_indel_cancer_hotspots_v2.ENS105_liftover.tsv}]}
   bcftools_public_filter: {type: 'string?', doc: "Will hard filter final result to

workflow/kfdrc_consensus_calling.cwl

@@ -107,7 +107,7 @@ inputs:
   genomic_hotspots: {type: 'File[]?', doc: "Tab-delimited BED formatted file(s) containing hg38 genomic positions corresponding to
       hotspots", "sbg:suggestedValue": [{class: File, path: 607713829360f10e3982a423, name: tert.bed}]}
   protein_snv_hotspots: {type: 'File[]?', doc: "Column-name-containing, tab-delimited file(s) containing protein names and amino acid
-      positions corresponding to hotspots", "sbg:suggestedValue": [{class: File, path: 663d2bcc27374715fccd8c6a, name: protein_snv_cancer_hotspots_v2.ENS105_liftover.tsv}]}
+      positions corresponding to hotspots", "sbg:suggestedValue": [{class: File, path: 66980e845a58091951d53984, name: kfdrc_protein_snv_cancer_hotspots_20240718.txt}]}
   protein_indel_hotspots: {type: 'File[]?', doc: "Column-name-containing, tab-delimited file(s) containing protein names and amino
       acid position ranges corresponding to hotspots", "sbg:suggestedValue": [{class: File, path: 663d2bcc27374715fccd8c6f, name: protein_indel_cancer_hotspots_v2.ENS105_liftover.tsv}]}
   retain_info: {type: 'string?', doc: "csv string with INFO fields that you want to keep", default: "gnomad_3_1_1_AC,gnomad_3_1_1_AN,gnomad_3_1_1_AF,gnomad_3_1_1_nhomalt,gnomad_3_1_1_AC_popmax,gnomad_3_1_1_AN_popmax,gnomad_3_1_1_AF_popmax,gnomad_3_1_1_nhomalt_popmax,gnomad_3_1_1_AC_controls_and_biobanks,gnomad_3_1_1_AN_controls_and_biobanks,gnomad_3_1_1_AF_controls_and_biobanks,gnomad_3_1_1_AF_non_cancer,gnomad_3_1_1_primate_ai_score,gnomad_3_1_1_splice_ai_consequence,gnomad_3_1_1_AF_non_cancer_afr,gnomad_3_1_1_AF_non_cancer_ami,gnomad_3_1_1_AF_non_cancer_asj,gnomad_3_1_1_AF_non_cancer_eas,gnomad_3_1_1_AF_non_cancer_fin,gnomad_3_1_1_AF_non_cancer_mid,gnomad_3_1_1_AF_non_cancer_nfe,gnomad_3_1_1_AF_non_cancer_oth,gnomad_3_1_1_AF_non_cancer_raw,gnomad_3_1_1_AF_non_cancer_sas,gnomad_3_1_1_AF_non_cancer_amr,gnomad_3_1_1_AF_non_cancer_popmax,gnomad_3_1_1_AF_non_cancer_all_popmax,gnomad_3_1_1_FILTER,MQ,MQ0,CAL,HotSpotAllele"}