Pharmacogenomics (PGx)
Automated pharmacogenomic analysis across 88+ drug-metabolizing genes. From sequencing data to star allele calls, metabolizer phenotypes, and prescriber-ready reports with CPIC guideline mapping.
PGx Analysis Is Fragmented and Manual
Pharmacogenomic testing requires a chain of specialized steps: calling star alleles from sequencing data, detecting structural variants in complex genes like CYP2D6, assigning metabolizer phenotypes, and mapping results to clinical guidelines. Most labs cobble together separate tools for each step, with manual review at every handoff.
The complexity multiplies for genes with structural variation — deletions, duplications, and hybrid rearrangements that standard variant callers miss entirely. Without automated SV detection, labs either send these genes out or report incomplete results, leaving prescribers without critical drug-gene information.
How AIVA Automates PGx Analysis
Purpose-built capabilities for pharmacogenomics (pgx)
88+ Pharmacogene Coverage
Automated star allele calling across 88+ drug-metabolizing genes including CYP2D6, CYP2C19, CYP2C9, CYP2B6, CYP3A4, CYP3A5, DPYD, TPMT, NUDT15, UGT1A1, VKORC1, SLCO1B1, and more. Covers drug transporters, phase II enzymes, and drug targets following PharmVar nomenclature.
ML-Powered Structural Variant Detection
Detects gene deletions, duplications, and hybrid rearrangements in complex pharmacogenes that standard variant callers miss. Critical for accurate CYP2D6 genotyping where structural variants directly impact metabolizer status and drug dosing recommendations.
CPIC & DPWG Guideline Mapping
Automatically maps star allele diplotypes to clinical phenotypes (Poor, Intermediate, Normal, Rapid, Ultrarapid Metabolizer) using activity score-based classification following CPIC and DPWG clinical guidelines. Each result includes the evidence chain from variant to dosing recommendation.
Prescriber-Ready PGx Reports
Generates clinical PGx reports with diplotype genotypes, predicted metabolizer phenotypes, activity scores, affected medications, and alternative drug recommendations. Leverages the 4M+ AIVA-KG connections for comprehensive drug-gene-pathway interaction data.
Star allele calling across drug-metabolizing genes, transporters, and drug targets
Gene-disease-drug-pathway knowledge graph powering PGx interpretation
Patient data is not stored or used for model training
Start PGx Analysis
See how AIVA transforms pharmacogenomics (pgx) for your lab. Request a demo or try AIVA live today.