Translational Knowledge Discovery Between Drug Interactions and Pharmacogenetics

Abstract

Clinical translation of drug-drug interaction (DDI) studies is limited, and knowledge gaps across different types of DDI evidence make it difficult to consolidate and link them to clinical consequences. Consequently, we developed information retrieval (IR) models to retrieve DDI and drug-gene interaction (DGI) evidence from 25 million PubMed abstracts and distinguish DDI evidence into in vitro pharmacokinetic (PK), clinical PK, and clinical pharmacodynamic (PD) studies for US Food and Drug Administration (FDA) approved and withdrawn drugs. Additionally, information extraction models were developed to extract DDI-pairs and DGI-pairs from the IR-retrieved abstracts. An overlapping analysis identified 986 unique DDI-pairs between all 3 types of evidence. Another 2,157 and 13,012 DDI-pairs and 3,173 DGI-pairs were identified from known clinical PK/PD DDI, clinical PD DDI, and DGI evidence, respectively. By integrating DDI and DGI evidence, we discovered 119 and 18 new pharmacogenetic hypotheses associated with CYP3A and CYP2D6, respectively. Some of these DGI evidence can also aid us in understanding DDI mechanisms.

Figure 1

Text mining pipeline for the information retrieval and information extraction tasks

Figure 2. Hypotheses generation

a) Translate drug-drug interaction (DDI) signals to predict genetic effects related to Adverse Drug Events (ADEs) and b) Translate drug-gene interaction (DGI) signals to predict molecular mechanisms of DDI

Figure 3

Results from the information retrieval and information extraction stages accompanied by a Venn diagram illustrating the overlap between the different DDI studies