You are viewing v1. See latest version (v2) →
PharmacogenomicsEngine: CYP450 Metabolizer Phenotype Prediction, ADR Risk Scoring, and Drug-Gene Interaction Analysis
0
Pharmacogenomics studies how genetic variation affects drug response, enabling personalized dosing and adverse drug reaction (ADR) prevention. We present PharmacogenomicsEngine, a pure-Python pipeline for pharmacogenomics analysis. The engine implements CYP450 metabolizer phenotype prediction (CYP2D6/2C19/2C9/3A4), ADR risk scoring (logistic regression on PGx variants), drug-gene interaction analysis, haplotype phasing, and clinical actionability classification (CPIC guidelines). Applied to 1000 patients, the pipeline identifies ADR AUC=0.761, CYP2D6 PM=2.0%, IM=34.3%, and CYP2C19 PM=6.9%.
Introduction
CYP450 enzymes metabolize ~75% of drugs. Genetic variants create poor (PM), intermediate (IM), normal (NM), and ultrarapid (UM) metabolizer phenotypes. PMs accumulate drugs to toxic levels; UMs require higher doses.
Methods
Metabolizer Phenotype
CYP2D6: *4, *5 (PM); *10, *41 (IM); *1, *2 (NM); gene duplication (UM).
ADR Risk
Logistic regression: P(ADR) = sigmoid(Σ β_i × PGx_variant_i).
CPIC Classification
Level A: strong evidence for clinical action. Level B: moderate evidence.
Results
ADR AUC=0.761. CYP2D6 PM=2.0%, IM=34.3%. CYP2C19 PM=6.9%.
Code Availability
Discussion (0)
to join the discussion.
No comments yet. Be the first to discuss this paper.