A Novel Text-Mining Approach for Retrieving Pharmacogenomics Associations From the Literature

Abstract

Text mining in biomedical literature is an emerging field which has already been shown to have a variety of implementations in many research areas, including genetics, personalized medicine, and pharmacogenomics. In this study, we describe a novel text-mining approach for the extraction of pharmacogenomics associations. The code that was used toward this end was implemented using R programming language, either through custom scripts, where needed, or through utilizing functions from existing libraries. Articles (abstracts or full texts) that correspond to a specified query were extracted from PubMed, while concept annotations were derived by PubTator Central. Terms that denote a Mutation or a Gene as well as Chemical compound terms corresponding to drug compounds were normalized and the sentences containing the aforementioned terms were filtered and preprocessed to create appropriate training sets. Finally, after training and adequate hyperparameter tuning, four text classifiers were created and evaluated (FastText, Linear kernel SVMs, XGBoost, Lasso, and Elastic-Net Regularized Generalized Linear Models) with regard to their performance in identifying pharmacogenomics associations. Although further improvements are essential toward proper implementation of this text-mining approach in the clinical practice, our study stands as a comprehensive, simplified, and up-to-date approach for the identification and assessment of research articles enriched in clinically relevant pharmacogenomics relationships. Furthermore, this work highlights a series of challenges concerning the effective application of text mining in biomedical literature, whose resolution could substantially contribute to the further development of this field.

Keywords: FastText, biomedical text classification, supervised learning; Pubmed; Pubtator; natural language processing; pharmacogenomics associations; text mining.

FIGURE 1

Flowchart of the proposed automated text-mining approach and the validation steps for the retrieved literature relationships. PMIDs, PubMed identifiers; PMCIDs, PubMed Central identifiers (attributed to full-text articles only).

FIGURE 2

Presentation of the performance metrics, as calculated after using 10-fold Cross Validation with the training data, for all four models trained with sentences discussing one pair of Variant-Chemical (1-pair sentences).

FIGURE 3

Performance metrics, as calculated after using 10-fold Cross Validation with the training data, for all four models trained with sentences discussing multiple Variant-Chemical pairs (n-pair sentences). The resulting metrics are presented by model and by class, since this is a multiclass classification task, while finally, the by-class metrics for each model separately are weighted with the corresponding class prevalence and summed up to calculate the overall performance metrics.