Global Text Mining and Development of Pharmacogenomic Knowledge Resource for Precision Medicine

Understanding patients’ genomic variations and their effect in protecting or predisposing them to drug response phenotypes is important for providing personalized healthcare. Several studies have manually curated such genotype–phenotype relationships into organized databases from clinical trial data or published literature. However, there are no text mining tools available to extract high-accuracy information from such existing knowledge. In this work, we used a semiautomated text mining approach to retrieve a complete pharmacogenomic (PGx) resource integrating disease–drug–gene-polymorphism relationships to derive a global perspective for ease in therapeutic approaches. We used an R package, pubmed.mineR, to automatically retrieve PGx-related literature. We identified 1,753 disease types, and 666 drugs, associated with 4,132 genes and 33,942 polymorphisms collated from 180,088 publications. With further manual curation, we obtained a total of 2,304 PGx relationships. We evaluated our approach by performance (precision = 0.806) with benchmark datasets like Pharmacogenomic Knowledgebase (PharmGKB) (0.904), Online Mendelian Inheritance in Man (OMIM) (0.600), and The Comparative Toxicogenomics Database (CTD) (0.729). We validated our study by comparing our results with 362 commercially used the US- Food and drug administration (FDA)-approved drug labeling biomarkers. Of the 2,304 PGx relationships identified, 127 belonged to the FDA list of 362 approved pharmacogenomic markers, indicating that our semiautomated text mining approach may reveal significant PGx information with markers for drug response prediction. In addition, it is a scalable and state-of-art approach in curation for PGx clinical utility.