PGX Pipeline

An end-to-end pharmacogenomics platform for whole-exome cohorts: raw reads to annotated SNV, indel and CNV calls, pharmacogenomic database enrichment, cohort analytics, and an interactive variant browser researchers can actually use.

Built solo by Bruno Young de Castro · M1 GENIOMHE (AI & Bioinformatics), Université Paris-Saclay / Université Évry

Showcase site. Everything below runs on synthetic data — no patient data appears anywhere. The full pipeline source is private; selected excerpts and full documentation are in the GitHub repository.

Try the live output

Real, unmodified pipeline output from a synthetic 128-sample cohort. Both are self-contained single-page apps — no server, works offline.

MegaVCF Explorer

Every variant from every sample in one browser. Search CYP2D6 and click a variant: ACMG criteria with a live evidence editor, CPIC/DPWG/PharmGKB drug guidance, star alleles, population frequencies, caller support, per-sample genotypes.

Open the explorer →

Analytics Dashboard

Click a point above the Bonferroni line on the Manhattan plot — a detail card opens with that variant's evidence. Then open PGx + Medications and click clopidogrel to work backwards from a drug.

Open the dashboard →

Figure set

The publication-ready matplotlib output — Manhattan, QQ, forest, gene signal, sample QC, metabolizer and PGx-readiness heatmaps, ML ROC and precision-recall — with methods and interpretation notes per section.

Browse figures →

Validation

F1 on GIAB HG002, whole-exome. Every standalone caller run on the same data with the same reference.

CallerF1
GATK HaplotypeCaller0.902
Strelka20.909
DeepVariant0.911
PGX ensemble (PASS tier only)0.907
PGX ensemble + ML triage0.929

Synthetic cohort against a known truth set — zero false positives in both validations, which was the design goal rather than a coincidence.

SNV / indelCNV
Truth variants25924
True positives25723
False positives00
False negatives21
F10.9960.978

Read the detail

Documentation and runnable source excerpts on GitHub.

Architecture

Run model, the 19-stage graph, the four entry points, the five-caller CNV ensemble design, and the module layout.

ARCHITECTURE.md →

Methods

Why pharmacogenomics needs its own pipeline, star alleles, ACMG/AMP, calling metrics, the triage model, and the cohort analytics suite.

METHODS.md →

Results

Validation design, full numbers, what they mean, and an honest limitations section.

RESULTS.md →

Code excerpts

The calibrated gradient-boosted triage model, verbatim, and the CNV consensus voting algorithm. Both self-contained and runnable with --demo.

code-excerpts/ →
Research use only. No clinical validation has been performed. This is not a diagnostic device, and every output requires expert review and orthogonal validation before it informs anything. Full limitations are documented in RESULTS.md.