d3b-center · sickler-alex · Aug 6, 2026 · Oct 31, 2025 · Oct 31, 2025 · Nov 5, 2025
diff --git a/README.md b/README.md
@@ -1,7 +1,7 @@
 # Pathogenicity Preprocessing Workflow
-To run, please see the [CAVATICA app](https://cavatica.sbgenomics.com/public/apps/cavatica/apps-publisher/d3b-diskin-pathogenicity-preprocess-wf). Each version should correspond with a git release. This repo makes use of the git submodule feature for ease of code maintenance. To properly retrieve all relevant code:
+This repo makes use of the git submodule feature for ease of code maintenance. To properly retrieve all relevant code:
 ```sh
-git clone  https://github.com/d3b-center/D3b-Pathogenicity-Preprocessing
+git clone https://github.com/d3b-center/D3b-Pathogenicity-Preprocessing
 git submodule init
 git submodule update
 ```

diff --git a/tools/autogvp_annotate_cavatica.cwl b/tools/autogvp_annotate_cavatica.cwl
@@ -1,33 +1,33 @@
 cwlVersion: v1.2
 class: CommandLineTool
-id: autogvp_annotate_cavatica
+id: autogvp_annotate
 doc: |
-  Tool for the 02-annotate_variants_CAVATICA_input.R script from AutoGVP
+  Tool for the 02-annotate_variants.R script from AutoGVP
 requirements:
   - class: ShellCommandRequirement
   - class: InlineJavascriptRequirement
   - class: ResourceRequirement
     ramMin: $(inputs.ram * 1000)
     coresMin: $(inputs.cpu)
   - class: DockerRequirement
-    dockerPull: 'pgc-images.sbgenomics.com/diskin-lab/autogvp:v1.0.3'
+    dockerPull: 'pgc-images.sbgenomics.com/diskin-lab/autogvp:v2.0.1'
 
 baseCommand: []
 arguments:
   - position: 0
     shellQuote: false
     valueFrom: >-
-      Rscript /rocker-build/AutoGVP/scripts/02-annotate_variants_CAVATICA_input.R --outdir .
+      Rscript /rocker-build/AutoGVP/scripts/02-annotate_variants.R --outdir .
 
 inputs:
   vcf_file: { type: 'File', inputBinding: { position: 2, prefix: "--vcf" }, doc: "Input vcf file with VEP annotations" }
-  clinvar_file: { type: 'File?', inputBinding: { position: 2, prefix: "--clinvar" }, doc: "specific clinVar file (format: clinvar_20211225.vcf.gz)" }
+  clinvar_file: { type: 'File', inputBinding: { position: 2, prefix: "--clinvar" }, doc: "ClinVar resolved clinical significance file (format: resolved-clinvar-interpretations.tsv)" }
   multianno_file: { type: 'File', inputBinding: { position: 2, prefix: "--multianno" }, doc: "input multianno file" }
   autopvs1_file: { type: 'File', inputBinding: { position: 2, prefix: "--autopvs1" }, doc: "input autopvs1 file" }
   intervar_file: { type: 'File', inputBinding: { position: 2, prefix: "--intervar" }, doc: "input intervar file" }
-  variant_summary: { type: 'File', inputBinding: { position: 2, prefix: "--variant_summary" }, doc: "variant_summary file (format: variant_summary_2023-02.txt)" }
   output_basename: { type: 'string?', default: "test", inputBinding: { position: 2, prefix: "--output" }, doc: "String to use as base for output filenames" }
+  sample_id: {type: 'string', inputBinding: { position: 2, prefix: "--sample_id" }, doc: "Input sample bioassay id."}
   cpu: { type: 'int?', default: 1, doc: "CPUs to allocate to this task" }
   ram: { type: 'int?', default: 2, doc: "GB of RAM to allocate to this task" }
 outputs:
-  annotation_report: { type: 'File', outputBinding: { glob: '*.cavatica_input.annotations_report.abridged.tsv' }}
+  annotation_report: { type: 'File', outputBinding: { glob: '*.annotations_report.abridged.tsv' }}
diff --git a/tools/autogvp_annotate_custom.cwl b/tools/autogvp_annotate_custom.cwl
diff --git a/tools/autogvp_filter_annotations.cwl b/tools/autogvp_filter_annotations.cwl
@@ -15,7 +15,7 @@ requirements:
     ramMin: $(inputs.ram * 1000)
     coresMin: $(inputs.cpu)
   - class: DockerRequirement
-    dockerPull: 'pgc-images.sbgenomics.com/diskin-lab/autogvp:v1.0.3'
+    dockerPull: 'pgc-images.sbgenomics.com/diskin-lab/autogvp:v2.0.1'
   - class: InitialWorkDirRequirement
     listing:
       - $(inputs.csq_subfields)
@@ -30,7 +30,7 @@ arguments:
 inputs:
   vcf_file: { type: 'File', inputBinding: { position: 2, prefix: "--vcf" }, doc: "Input filtered and parsed VEP VCF file" }
   autogvp_file: { type: 'File', inputBinding: { position: 2, prefix: "--autogvp" }, doc: "input AutoGVP annotated file" }
-  colnames_file: { type: 'File', inputBinding: { position: 2, prefix: "--colnames" }, doc: "file listing output colnames" }
+  output_colnames_file: { type: 'File?', inputBinding: { position: 2, prefix: "--output_colnames" }, doc: "file listing custom output colnames" }
   csq_subfields: { type: 'File', doc: "VCF file CSQ field names" }
   output_basename: { type: 'string?', default: "test", inputBinding: { position: 2, prefix: "--output" }, doc: "String to use as base for output filenames" }
   cpu: { type: 'int?', default: 1, doc: "CPUs to allocate to this task" }

diff --git a/tools/autogvp_filter_vcf.cwl b/tools/autogvp_filter_vcf.cwl
@@ -10,7 +10,7 @@ requirements:
     ramMin: $(inputs.ram * 1000)
     coresMin: $(inputs.cpu)
   - class: DockerRequirement
-    dockerPull: 'pgc-images.sbgenomics.com/diskin-lab/autogvp:v1.0.3'
+    dockerPull: 'pgc-images.sbgenomics.com/diskin-lab/autogvp:v2.0.1'
 
 baseCommand: []
 arguments:
@@ -34,5 +34,5 @@ inputs:
 outputs:
   filtered_vcf: { type: File, outputBinding: { glob: '*.filtered.vcf' }}
   filtered_multianno: { type: File, outputBinding: { glob: '*_multianno_filtered.txt' }}
-  filtered_autopsv: { type: File, outputBinding: { glob: '*_autopvs1_filtered.tsv' }}
+  filtered_autopvs1: { type: File, outputBinding: { glob: '*_autopvs1_filtered.tsv' }}
   filtered_intervar: { type: File, outputBinding: { glob: '*_intervar_filtered.txt' }}
diff --git a/tools/autogvp_parse_vcf.cwl b/tools/autogvp_parse_vcf.cwl
@@ -10,7 +10,7 @@ requirements:
     ramMin: $(inputs.ram * 1000)
     coresMin: $(inputs.cpu)
   - class: DockerRequirement
-    dockerPull: 'pgc-images.sbgenomics.com/diskin-lab/autogvp:v1.0.3'
+    dockerPull: 'pgc-images.sbgenomics.com/diskin-lab/autogvp:v2.0.1'
   - class: InitialWorkDirRequirement
     listing:
       - $(inputs.vcf_file)

diff --git a/tools/autogvp_select_clinvar_subs.cwl b/tools/autogvp_select_clinvar_subs.cwl
@@ -1,23 +1,23 @@
 cwlVersion: v1.2
 class: CommandLineTool
-id: antogvp_select_clinvar_subs
+id: autogvp_select_clinvar_subs
 doc: |
-  Tool for the select-clinVar-submissions.R script from AutoGVP
+  Tool for the resolve-clinvar-intepretations.R script from AutoGVP
 requirements:
   - class: ShellCommandRequirement
   - class: InlineJavascriptRequirement
   - class: ResourceRequirement
     ramMin: $(inputs.ram * 1000)
     coresMin: $(inputs.cpu)
   - class: DockerRequirement
-    dockerPull: 'pgc-images.sbgenomics.com/diskin-lab/autogvp:v1.0.3'
+    dockerPull: 'pgc-images.sbgenomics.com/diskin-lab/autogvp:v2.0.1'
 
 baseCommand: []
 arguments:
   - position: 0
     shellQuote: false
     valueFrom: >-
-      Rscript /rocker-build/AutoGVP/scripts/select-clinVar-submissions.R --outdir .
+      Rscript /rocker-build/AutoGVP/scripts/resolve-clinvar-intepretations.R --outdir .
 
 inputs:
   variant_summary: { type: 'File', inputBinding: { prefix: "--variant_summary", position: 2 }, doc: "ClinVar variant summary file." }
@@ -27,4 +27,4 @@ inputs:
   cpu: { type: 'int?', default: 1, doc: "CPUs to allocate to this task." }
   ram: { type: 'int?', default: 2, doc: "GB of RAM to allocate to this task." }
 outputs:
-  clinvar_submissions: { type: File, outputBinding: { glob: 'ClinVar-selected-submissions.tsv'} }
+  clinvar_submissions: { type: File, outputBinding: { glob: "resolved-clinvar-*.tsv"} }
diff --git a/tools/autogvp_update_intervar.cwl b/tools/autogvp_update_intervar.cwl
@@ -0,0 +1,27 @@
+cwlVersion: v1.2
+class: CommandLineTool
+id: autogvp_filter_vcf
+doc: |
+  Tool for the 01-filter_vcf script from AutoGVP
+requirements:
+  - class: ShellCommandRequirement
+  - class: InlineJavascriptRequirement
+  - class: ResourceRequirement
+    ramMin: $(inputs.ram * 1000)
+    coresMin: $(inputs.cpu)
+  - class: DockerRequirement
+    dockerPull: 'pgc-images.sbgenomics.com/diskin-lab/autogvp:v2.0.1'
+
+baseCommand: []
+arguments:
+  - position: 0
+    shellQuote: false
+    valueFrom: >-
+      Rscript /rocker-build/AutoGVP/scripts/update_intervar.R --outdir .
+
+inputs:
+  intervar_file: { type: 'File', inputBinding: { position: 2, prefix: "--intervar_file" }, doc: "intervar results file" }
+  clinvar_file: { type: 'File', inputBinding: { position: 2, prefix: "--clinvar_file" }, doc: "ClinVar resolved clinical significance file (format: resolved-clinvar-interpretations.tsv)" }
+  clinvar_hgvs4_file: { type: 'File', inputBinding: { position: 2, prefix: "--clinvar_hgvs4_file" }, doc: "ClinVar hgvs4 file with amino acid changes" }
+outputs:
+  updated_intervar: { type: File, outputBinding: { glob: '*updated*' }}
diff --git a/tools/compress_annovar_output.cwl b/tools/compress_annovar_output.cwl
@@ -9,7 +9,7 @@ requirements:
     ramMin: 16000
     coresMin: 8
   - class: DockerRequirement
-    dockerPull: 'pgc-images.sbgenomics.com/d3b-bixu/autopvs1:v1.0.1'
+    dockerPull: 'pgc-images.sbgenomics.com/d3b-bixu/autopvs1:v2.0.0'
 
 baseCommand: [pigz, -c, -p 8]
 arguments:

diff --git a/workflows/autogvp.cwl b/workflows/autogvp.cwl
@@ -22,14 +22,12 @@ doc: |
   ## Inputs
 
   ```yaml
-  workflow: Indicate whether the input VCF is from a cavatica or custom workflow
   vcf_file: Input VCF file. Can be either VEP-annotated VCF file or or VEP- and ClinVar-annotated VCF file
   filter_criteria: Any additional VCF filtering criteria
-  clinvar_file: ClinVar file. Required for inputs from a custom workflow!
-  intevar_file: InterVar results file
-  autopsv1_file: AutoPVS1 results file
+  intervar_file: InterVar results file
+  autopvs1_file: AutoPVS1 results file
   multianno_file: ANNOVAR multianno file
-  output_colnames: File with column name information
+  output_colnames: File with custom column name information
   output_basename: String to use as the basename for stored outputs
   selected_clinvar_submissions: ClinVar variant file with conflicts resolved. If not provided, this file will be generated in the workflow
   variant_summary_file: ClinVar variant summary file
@@ -39,14 +37,13 @@ doc: |
   ```
 
   The following files can be obtained from the [AutoGVP GitHub data directory](https://github.com/diskin-lab-chop/AutoGVP/tree/main/data):
-  - `autopsv1_file`
+  - `autopvs1_file`
   - `concept_ids`
-  - `intevar_file`
+  - `intervar_file`
   - `multianno_file`
   - `output_colnames`
 
   Additionally, AutoGVP provides [a bash script](https://github.com/diskin-lab-chop/AutoGVP/blob/main/scripts/download_db_files.sh) to obtain:
-  - `clinvar_file`
   - `submission_summary_file`
   - `variant_summary_file`
 
@@ -59,29 +56,33 @@ doc: |
 
   ## Resources
 
-  Dockerfile: pgc-images.sbgenomics.com/diskin-lab/autogvp:v1.0.3
+  Dockerfile: pgc-images.sbgenomics.com/diskin-lab/autogvp:v2.0.1
   AutoGVP Paper: https://doi.org/10.1093/bioinformatics/btae114
   AutoGVP GitHub: https://github.com/diskin-lab-chop/AutoGVP
 requirements:
 - class: InlineJavascriptRequirement
 - class: StepInputExpressionRequirement
 - class: MultipleInputFeatureRequirement
 inputs:
-  workflow: {type: {type: enum, symbols: ["cavatica", "custom"], name: "workflow"}, doc: "Indicate whether the input VCF is from a
-      cavatica or custom workflow"}
   vcf_file: {type: 'File', doc: "Input VCF file. Can be either VEP-annotated VCF file or or VEP- and ClinVar-annotated VCF file"}
   filter_criteria: {type: 'string[]?', doc: "Any additional VCF filtering criteria"}
-  clinvar_file: {type: 'File?', doc: "ClinVar file. Required for inputs from a custom workflow!"}
-  intevar_file: {type: 'File', doc: "InterVar results file"}
-  autopsv1_file: {type: 'File', doc: "AutoPVS1 results file"}
+  intervar_file: {type: 'File', doc: "InterVar results file"}
+  autopvs1_file: {type: 'File', doc: "AutoPVS1 results file"}
   multianno_file: {type: 'File', doc: "ANNOVAR multianno file"}
-  output_colnames: {type: 'File', doc: "File with column name information."}
+  output_colnames: {type: 'File?', doc: "File with custom column name information."}
   output_basename: {type: 'string?', default: "out", doc: "String to use as the basename for stored outputs."}
+  sample_id: {type: 'string', doc: "Input sample bioassay id."}
   selected_clinvar_submissions: {type: 'File?', doc: "ClinVar variant file with conflicts resolved. If not provided, this file will
-      be generated in the workflow"}
-  variant_summary_file: {type: 'File?', doc: "ClinVar variant summary file"}
-  submission_summary_file: {type: 'File?', doc: "ClinVar submission summary file"}
-  concept_ids: {type: 'File?', doc: "File containing list of conceptIDs to prioritize submissions for ClinVar variant conflict resolution"}
+      be generated in the workflow", "sbg:suggestedValue": {class: File,
+      path: 6a322ff1b729272b1d1bbea4, name: resolved-clinvar-2026-06-cancer-latest.tsv}}
+  variant_summary_file: {type: 'File?', doc: "ClinVar variant summary file", "sbg:suggestedValue": {class: File,
+      path: 6a322ff1b729272b1d1bbe9b, name: variant_summary_2026-06.txt.gz}}
+  clinvar_hgvs4_file: {type: 'File?', doc: "ClinVar hgvs4 file with amino acid changes", "sbg:suggestedValue": {class: File,
+      path: 6a68726f08505474f85a109b, name: hgvs4variation-2026-07.txt.gz}}
+  submission_summary_file: {type: 'File?', doc: "ClinVar submission summary file", "sbg:suggestedValue": {class: File,
+      path: 6a322ff1b729272b1d1bbea2, name: submission_summary_2026-06.txt.gz}}
+  concept_ids: {type: 'File?', doc: "File containing list of conceptIDs to prioritize submissions for ClinVar variant conflict resolution",
+      "sbg:suggestedValue": {class: File, path: 6a322ff1b729272b1d1bbe93, name: clinvar_cancer_concept_ids_20260130.txt}}
   conflict_res: {type: ['null', {type: enum, symbols: ["latest", "most_severe"], name: "conflict_resolution"}], doc: "How to resolve
       conflicts associated with conceptIDs: latest or most_severe"}
   annotate_cpu: { type: 'int?', default: 1, doc: "CPUs to allocate to AutoGVP annotation" }
@@ -108,42 +109,32 @@ steps:
     in:
       vcf_file: vcf_file
       multianno_file: multianno_file
-      autopvs1_file: autopsv1_file
-      intervar_file: intevar_file
+      autopvs1_file: autopvs1_file
+      intervar_file: intervar_file
       output_basename: output_basename
       filter_criteria: filter_criteria
-    out: [filtered_vcf, filtered_multianno, filtered_autopsv, filtered_intervar]
-  annotate_cavatica:
-    run: ../tools/autogvp_annotate_cavatica.cwl
-    when: $(inputs.workflow == "cavatica")
+    out: [filtered_vcf, filtered_multianno, filtered_autopvs1, filtered_intervar]
+  update_intervar:
+    run: ../tools/autogvp_update_intervar.cwl
     in:
-      workflow: workflow
-      vcf_file: filter_vcf/filtered_vcf
-      clinvar_file: clinvar_file
-      multianno_file: filter_vcf/filtered_multianno
-      autopvs1_file: filter_vcf/filtered_autopsv
       intervar_file: filter_vcf/filtered_intervar
-      variant_summary:
+      clinvar_file:
         source: [selected_clinvar_submissions, select_clinvar_subs/clinvar_submissions]
         pickValue: first_non_null
-      output_basename: output_basename
-      cpu: annotate_cpu
-      ram: annotate_ram
-    out: [annotation_report]
-  annotate_custom:
-    run: ../tools/autogvp_annotate_custom.cwl
-    when: $(inputs.workflow == "custom")
+      clinvar_hgvs4_file: clinvar_hgvs4_file
+    out: [updated_intervar]
+  annotate:
+    run: ../tools/autogvp_annotate_cavatica.cwl
     in:
-      workflow: workflow
       vcf_file: filter_vcf/filtered_vcf
-      clinvar_file: clinvar_file
-      multianno_file: filter_vcf/filtered_multianno
-      autopvs1_file: filter_vcf/filtered_autopsv
-      intervar_file: filter_vcf/filtered_intervar
-      variant_summary:
+      clinvar_file:
         source: [selected_clinvar_submissions, select_clinvar_subs/clinvar_submissions]
         pickValue: first_non_null
+      multianno_file: filter_vcf/filtered_multianno
+      autopvs1_file: filter_vcf/filtered_autopvs1
+      intervar_file: update_intervar/updated_intervar
       output_basename: output_basename
+      sample_id: sample_id
       cpu: annotate_cpu
       ram: annotate_ram
     out: [annotation_report]
@@ -156,10 +147,8 @@ steps:
     run: ../tools/autogvp_filter_annotations.cwl
     in:
       vcf_file: parse_vcf/parsed_tsv
-      autogvp_file:
-        source: [annotate_cavatica/annotation_report, annotate_custom/annotation_report]
-        pickValue: the_only_non_null
-      colnames_file: output_colnames
+      autogvp_file: annotate/annotation_report
+      output_colnames_file: output_colnames
       csq_subfields: parse_vcf/csq_subfields_tsv
       output_basename: output_basename
       cpu: filter_annot_cpu
@@ -172,7 +161,7 @@ hints:
 - class: sbg:maxNumberOfParallelInstances
   value: 2
 "sbg:links":
-- id: 'https://github.com/d3b-center/D3b-Pathogenicity-Preprocessing/releases/tag/v1.2.0'
+- id: 'https://github.com/d3b-center/D3b-Pathogenicity-Assessment/releases/tag/v2.0.0'
   label: github-release
 sbg:license: Apache License 2.0
 sbg:publisher: KFDRC