The abstract is read at the publisher; the summary is JClub's.
Phenoconversion in pharmacogenomics is linked to major gaps between genotype-predicted and observed drug-metabolizing capacity, undermining clinical utility of PGx testing.
- Why it matters: Genotype-based predictions often miss non-genetic influences on enzyme activity, and phenoconversion is hard to identify because key determinants are scattered across medication, labs, diagnoses, and unstructured EHR notes.
- What they did: This review discusses how large language models could retrieve and contextualize heterogeneous clinical and pharmacogenomic data to support dynamic phenotype assessment, including modifier identification beyond static genotype categories.
- The result: LLM-enabled dynamic phenotype models may better connect genetic predisposition to real-world drug response and enable more precise, context-aware pharmacotherapy.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.