name: wes-clinical-report-en

description: >-

version: 1.0.0

author: Manuel Corpas

license: PROPRIETARY

tags: [WES, exome, clinical-report, english, pharmacogenomics, PDF, ANNOVAR]

inputs:

- name: WES markdown report

format: markdown (.md)

required: true

description: Structured WES report with sections 1-7 (Exome Summary through Methods)

- name: Logo left

format: image (JPG/PNG)

required: false

description: Left institutional logo for cover and header

- name: Logo right

format: image (JPG/PNG)

required: false

description: Right institutional logo for cover and header

outputs:

- name: Clinical PDF report

format: PDF (A4)

description: Professional clinical report with interpretation, tables, and disclaimer

metadata:

openclaw:

requires:

bins:

- python3

env: []

config: []

always: false

emoji: "🧬"

homepage: https://github.com/ClawBio/ClawBio

os: [darwin, linux]

min_python: "3.9"

dependencies:

- reportlab

- pandas

private: true

install: []

trigger_keywords:

- WES clinical report

- exome PDF report english

- clinical report english

- Novogene report english

- WES report PDF

Skill for generating professional clinical PDF reports in English from

whole exome sequencing (WES) data. Designed for Novogene WES data

(GATK + ANNOVAR pipeline) but adaptable to any WES pipeline with

equivalent annotations.

**Fire this skill when the user says any of:**

- "generate WES clinical report in English"

- "English exome PDF report"

- "WES report PDF"

- "clinical report from exome data"

- "Novogene report English"

- "exome clinical PDF"

**Do NOT fire when:**

- User asks for a Spanish report (use `wes-clinical-report-es`)

- User asks for variant annotation only (use `variant-annotation`)

- User asks for ACMG classification only (use `clinical-variant-reporter`)

One skill, one task: convert WES markdown reports into professional

English-language clinical PDFs with interpretation.

1. Parse WES markdown report (structured sections 1-7)

2. Extract KPI metrics from Exome Summary

3. Extract pathogenic variants, PGx alerts, rare damaging variants

4. Build interpretive summary paragraph

5. Render all sections as styled PDF with clinical tables

6. Add ancestry estimation (section 8) if data available

7. Add limitations section (section 9)

8. Add disclaimer and report metadata

9. Output PDF to specified directory

1. **Clinical interpretation summary**: key findings, high-risk PGx alerts,

prioritised rare variants, clinical follow-up recommendations.

2. **Clinically significant variants**: ClinVar P/LP, ACMG SF v3.2,

cancer predisposition panel, conflicting variants.

3. **Pharmacogenomics**: CPIC star alleles, clinical effects, affected

medications with contextualised high-risk alerts.

4. **Fitness and nutrition traits**: genotypes with evidence grades

(Corpas et al. 2021).

5. **Rare damaging variant prioritisation**: REVEL, CADD, gnomAD AF.

6. **Disease and pathway context**: OMIM, GWAS, COSMIC, KEGG.

7. **Institutional logos**: configurable left/right logos on cover and header.

python skills/wes-clinical-report-en/wes_clinical_report_en.py \

--report-dir /path/to/REPORTS/ \

--output-dir /path/to/PDF-EN/ \

--logo-left /path/to/logo_left.jpg \

--logo-right /path/to/logo_right.jpg

python skills/wes-clinical-report-en/wes_clinical_report_en.py \

--report-dir /path/to/REPORTS/ \

--output-dir /path/to/PDF-EN/ \

--samples Sample3

python skills/wes-clinical-report-en/wes_clinical_report_en.py --demo

The skill consumes WES reports in markdown format generated by the

analysis pipeline (scripts 02-12 in `ANALYSIS/SCRIPTS/`). Each markdown

report must follow this structure:

1. **Logo paths must exist**: if logo files are missing, the report still

generates but without institutional branding. The script silently skips

missing logos.

2. **Table truncation**: tables with more than 20 rows are truncated in

the PDF with a note to consult TSV files. Do not assume all data is

visible in the PDF.

3. **Ancestry data is optional**: section 8 requires

`ancestry_results.json` in the ancestry output directory. If absent,

the section shows "No ancestry data available."

4. **ClinVar classifications are time-sensitive**: the report reflects

ClinVar state at annotation time. Do not treat classifications as

permanent.

5. **PGx star alleles from SNVs only**: CYP2D6 CNV analysis is not

included. Do not claim complete metaboliser phenotyping.

ClawBio is a research and educational tool. It is not a medical device

and does not provide clinical diagnoses. Consult a healthcare professional

before making any medical decisions.

The agent dispatches and explains; the skill executes. The agent should

not modify PDF generation logic inline. All report customisation goes

through CLI flags.

- `variant-annotation`: upstream VCF annotation feeding markdown reports

- `clinical-variant-reporter`: ACMG classification for deeper analysis

- `wes-clinical-report-es`: Spanish language version of the same report

- Review cadence: quarterly (aligned with ClinVar release cycle)

- Staleness signals: ClinVar version drift, CPIC guideline updates

- Deprecation: if WES is superseded by WGS-only clinical pipelines

- Python 3.9+

- reportlab >= 4.0

- WES markdown reports (see input format above)

- Institutional logos in JPG/PNG (optional)

This skill is **private** and not included in the ClawBio public catalog.

It contains institutional report templates that should not be distributed

publicly.

- Corpas et al. (2021) "Whole Genome Interpretation for a Family of Five"

*Frontiers in Genetics* 12:535123

- CPIC guidelines for pharmacogenomics

- ClinVar / gnomAD / OMIM / COSMIC / KEGG for variant annotation

| Metric | Count |

|--------|-------|

| Total SNP variants | 25,432 |

| Missense | 11,234 |

| Synonymous | 12,100 |

| Stopgain | 85 |

| Frameshift | 42 |

| Splicing | 120 |

| Loss-of-function (stopgain + frameshift) | 127 |

| Rare coding (gnomAD < 1%) | 3,210 |

| Rare + computationally damaging | 245 |

| ClinVar Pathogenic / Likely Pathogenic | 8 |

The homozygosity to heterozygosity ratio is **2.35**, which is above the expected ~1.5 for outbred populations.

Sample1 carries 8 variant(s) classified as Pathogenic or Likely Pathogenic in ClinVar:

| Gene | Variant | Zygosity | Classification | Consequence | Associated Condition |

|------|---------|----------|----------------|-------------|---------------------|

| BRCA2 | c.5946delT | Het | Pathogenic | frameshift deletion | Hereditary breast/ovarian cancer |

| MUTYH | c.536A>G | Het | Pathogenic | missense SNV | MUTYH-associated polyposis |

| GJB2 | c.35delG | Hom | Pathogenic | frameshift deletion | Deafness, autosomal recessive 1A |

| SERPINA1 | c.1096G>A | Het | Pathogenic | missense SNV | Alpha-1-antitrypsin deficiency |

| HFE | c.845G>A | Het | Pathogenic | missense SNV | Hereditary hemochromatosis |

| DPYD | c.1905+1G>A | Het | Pathogenic/LP | splicing | Dihydropyrimidine dehydrogenase deficiency |

| MEFV | c.2080A>G | Het | Likely Pathogenic | missense SNV | Familial Mediterranean fever |

| GAA | c.525delT | Het | Pathogenic | frameshift deletion | Pompe disease |

An additional 12 variant(s) have conflicting or uncertain classifications.

The most clinically relevant are listed below (coding variants in disease-associated genes):

ACMG SF v3.2 actionable genes: 156 coding variants identified across 73 medically actionable genes, of which 2 have ClinVar P/LP classification.

Cancer predisposition panel: 3 with P/LP classification across 95 cancer predisposition genes.

The following pharmacogenomic markers were identified from CPIC-defined star-allele positions. Variants are reported where the genotype differs from the reference allele.

| Gene | Variant | Allele | Zygosity | Clinical Effect | Affected Medications |

|------|---------|--------|----------|-----------------|---------------------|

| CYP2D6 | rs3892097 | *4 | Het | Slow metaboliser | codeine, tramadol, tamoxifen |

| NAT2 | rs1801280 | *5 | Hom | Slow acetylator | isoniazid, hydralazine |

| CYP2C19 | rs4244285 | *2 | Het | Slow metaboliser | clopidogrel, omeprazole |

| SLCO1B1 | rs4149056 | *5 | Het | Decreased transport | simvastatin, atorvastatin |

| VKORC1 | rs9923231 | - | Het | Low-dose warfarin | warfarin |

| CYP1A2 | rs762551 | *1F | Hom | Ultra-rapid (inducible) | caffeine, clozapine |

Genotypes at positions associated with fitness and nutrition traits (Corpas et al. 2021, Tables 3-5). Only markers captured by the WES panel and with non-reference genotypes are shown.

Evidence grades: A = strong replication, B = moderate, C = preliminary.

| Gene | Variant | Trait | Interpretation | Ev. |

|------|---------|-------|----------------|-----|

| ACTN3 | rs1815739 | Muscle fibre type (power vs endurance) | XX - endurance phenotype | A |

| Gene | Variant | Trait | Interpretation | Ev. |

|------|---------|-------|----------------|-----|

| MTHFR | rs1801133 | Folate metabolism (C677T) | CT - 35% reduced | A |

| GC | rs2282679 | Vitamin D binding protein | Lower vitamin D | A |

| FADS1 | rs174547 | Omega-3 conversion | Poor converter | B |

| TCF7L2 | rs7903146 | Type 2 diabetes risk | Moderate | A |

| ADH1B | rs1229984 | Alcohol metabolism speed | Ultra-rapid | A |

| TAS2R38 | rs713598 | Bitter taste perception | Medium taster | B |

245 variants pass all filters: coding, rare (gnomAD AF < 0.01), and computationally predicted damaging (CADD > 20 or REVEL > 0.5). Top 15 ranked by pathogenicity prediction score:

| Gene | Variant | Consequence | Zygosity | REVEL | CADD | gnomAD AF | OMIM Disease |

|------|---------|-------------|----------|-------|------|-----------|-------------|

| ABCA4 | c.5882G>A | missense SNV | Het | 0.92 | 33.0 | 0.0012 | Stargardt disease |

| GJB2 | c.35delG | frameshift deletion | Hom | - | 35.0 | 0.0089 | Deafness, autosomal recessive 1A |

| USH2A | c.2299delG | frameshift deletion | Het | - | 34.0 | 0.0034 | Usher syndrome type 2A |

| CFTR | c.1521_1523delCTT | frameshift deletion | Het | - | 32.0 | 0.0078 | Cystic fibrosis |

| ATP7B | c.3207C>A | missense SNV | Het | 0.88 | 29.5 | 0.0015 | Wilson disease |

Across the full variant set: 1,245 variants map to OMIM disease entries, 456 overlap GWAS Catalog associations, and 89 have COSMIC somatic mutation records.

KEGG pathways enriched in rare coding variants:

- hsa04010: MAPK signalling pathway (12 variants)

- hsa04151: PI3K-Akt signalling pathway (9 variants)

- hsa04110: Cell cycle (7 variants)

- hsa04310: Wnt signalling pathway (5 variants)

Whole exome sequencing was performed on an Illumina NovaSeq 6000 platform using 150 bp paired-end reads with the Xplus capture kit (60.5 Mb target region). Reads were aligned to the GRCh38/hg38 reference genome using BWA-MEM. Variant calling was performed with GATK HaplotypeCaller v4.3.0 following GATK Best Practices. Functional annotation was performed with ANNOVAR, incorporating ClinVar (2024), gnomAD v3.1.2 (9 population groups), COSMIC, OMIM, SIFT, PolyPhen-2, CADD, REVEL, and 15 additional databases. Pharmacogenomic analysis used CPIC star-allele definitions with evidence enrichment from the ClinPGx API (PharmGKB). Fitness and nutrition trait interpretation followed the evidence framework of Corpas et al. (2021) Frontiers in Genetics 12:535123. Variant prioritisation applied sequential filters: coding consequence, population frequency (gnomAD AF < 0.01), computational pathogenicity (CADD > 20 or REVEL > 0.5).

*Report prepared by ClawBio WES Analysis Pipeline on 2026-04-05*