fix: align bash/docs with Nextflow, add clinvar/pypgx fail-fast

- Add --tree [email protected] to bash haplogrep3 script and docs
- Add clinvar + clinvar_index and pypgx_bundle to startup validation
- README: add --hla_dat, --slivar_bin, --pypgx_bundle, --ancestry_ref
- docs/nextflow.md: fix vcfanno output dir (publishes to vep/), update
  BAM-required tool list
- docs/interpreting-results.md: PharmCAT output path for both paths

Author: GeiserX

README.md

@@ -295,13 +295,17 @@ nextflow run main.nf --input samplesheet.csv --reference /path/to/GRCh38.fasta -
 
 # Enable database-requiring tools (VEP, CPSR, ClinVar, ExpansionHunter)
 nextflow run main.nf --input samplesheet.csv --reference /path/to/GRCh38.fasta \
-    --tools 'pharmcat,cpic,vcfanno,roh,prs,mito_haplogroup,hla_typing,telomere_hunter,mosdepth,mito_variants,cyrius,html_report,multiqc,vep,slivar,clinical_filter,cpsr,clinvar,expansion_hunter' \
+    --tools 'pharmcat,cpic,vcfanno,roh,prs,mito_haplogroup,hla_typing,telomere_hunter,mosdepth,mito_variants,cyrius,html_report,multiqc,vep,slivar,clinical_filter,cpsr,clinvar,expansion_hunter,pypgx,ancestry' \
     --vep_cache /path/to/vep_cache \
     --pcgr_data /path/to/pcgr_data \
     --vep_cache_cpsr /path/to/vep_cache_113 \
     --clinvar /path/to/clinvar.vcf.gz \
     --clinvar_index /path/to/clinvar.vcf.gz.tbi \
     --expansion_catalog /path/to/variant_catalog.json \
+    --hla_dat /path/to/hla.dat \
+    --slivar_bin /path/to/slivar \
+    --pypgx_bundle /path/to/pypgx-bundle \
+    --ancestry_ref /path/to/1kg_common_snps.vcf.gz \
     -profile docker
 ```
 

docs/12-mito-haplogroup.md

@@ -26,6 +26,7 @@ docker run --rm -v ${GENOME_DIR}/${SAMPLE}/vcf:/data staphb/bcftools:1.21 \
 # Step 2: Run haplogrep3
 docker run --rm -v ${GENOME_DIR}/${SAMPLE}:/data jtb114/haplogrep3 \
   classify \
+    --tree [email protected] \
     --input /data/vcf/${SAMPLE}_chrM.vcf.gz \
     --output /data/mito/${SAMPLE}_haplogroup.txt \
     --extend-report

docs/interpreting-results.md

@@ -82,7 +82,7 @@ The most common "pathogenic" finding in any genome is **heterozygous carrier sta
 
 **What it tells you:** How your genes affect drug metabolism. These results are clinically relevant and should be shared with your prescribing physician.
 
-**Where to look:** `${SAMPLE}/vcf/` — PharmCAT writes its reports alongside the VCF. Open the HTML report in a browser.
+**Where to look:** `${SAMPLE}/pharmcat/` (Nextflow) or `${SAMPLE}/vcf/` (bash scripts) — PharmCAT writes its reports there. Open the HTML report in a browser.
 
 **Key genes to check:**
 | Gene | Affects | Common Impact |

docs/nextflow.md

@@ -63,7 +63,7 @@ Only the failed and downstream steps re-run.
 | `bam` | No* | Path to aligned BAM (needed for BAM-based steps like pypgx) |
 | `bam_index` | No* | Path to BAM index (`.bam.bai`) |
 
-\* BAM is technically optional (VCF-only runs are valid for annotation and PGx), but most default tools (mosdepth, expansion_hunter, telomere_hunter, cyrius, hla_typing, mito_variants) require BAM input. **Provide BAM for full analysis.**
+\* BAM is technically optional (VCF-only runs are valid for annotation and PGx), but most default tools (mosdepth, telomere_hunter, cyrius, mito_variants) and opt-in tools (expansion_hunter, hla_typing, pypgx) require BAM input. **Provide BAM for full analysis.**
 
 ### Using Sarek Output
 
@@ -116,8 +116,7 @@ results/
 │   ├── clinvar/            # ClinVar pathogenic variant screen
 │   ├── pypgx/              # pypgx star allele calling (optional)
 │   ├── cpic/               # CPIC drug-gene recommendations (optional)
-│   ├── vep/                # VEP variant annotation
-│   ├── vcfanno/            # Enriched VCF (CADD, SpliceAI, REVEL, AlphaMissense)
+│   ├── vep/                # VEP + vcfanno enriched VCF (CADD, SpliceAI, REVEL, AlphaMissense)
 │   ├── slivar/             # Prioritized variants + compound hets
 │   ├── clinical/           # Clinically relevant variant subset
 │   ├── cpsr/               # Cancer predisposition report

main.nf

@@ -37,6 +37,9 @@ def db_requirements = [
     ['expansion_hunter', 'expansion_catalog', '--expansion_catalog'],
     ['hla_typing',       'hla_dat',           '--hla_dat'],
     ['slivar',           'slivar_bin',        '--slivar_bin'],
+    ['clinvar',          'clinvar',           '--clinvar'],
+    ['clinvar',          'clinvar_index',     '--clinvar_index'],
+    ['pypgx',            'pypgx_bundle',      '--pypgx_bundle'],
 ]
 
 db_requirements.each { tool, param_name, flag ->

scripts/12-mito-haplogroup.sh

@@ -42,6 +42,7 @@ docker run --rm \
   -v "${GENOME_DIR}/${SAMPLE}:/data" \
   ${HAPLOGREP3_IMAGE} \
   classify \
+    --tree [email protected] \
     --input "/data/vcf/${SAMPLE}_chrM.vcf.gz" \
     --output "/data/mito/${SAMPLE}_haplogroup.txt" \
     --extend-report