Deep learning-enabled natural language processing to identify directional pharmacokinetic drug-drug interactions

Joel Zirkle; Xiaomei Han; Rebecca Racz; Mohammadreza Samieegohar; Anik Chaturbedi; John Mann; Shilpa Chakravartula; Zhihua Li

doi:10.1186/s12859-023-05520-9

Deep learning-enabled natural language processing to identify directional pharmacokinetic drug-drug interactions

BMC Bioinformatics. 2023 Nov 1;24(1):413. doi: 10.1186/s12859-023-05520-9.

Authors

Joel Zirkle¹, Xiaomei Han¹, Rebecca Racz¹, Mohammadreza Samieegohar¹, Anik Chaturbedi¹, John Mann¹, Shilpa Chakravartula¹, Zhihua Li²

Affiliations

¹ Division of Applied Regulatory Science, Office of Clinical Pharmacology, Office of Translational Sciences, Center for Drug Evaluation and Research, Food and Drug Administration, WO Bldg 64 Rm 2078, 10903 New Hampshire Ave, Silver Spring, MD, 20993, USA.
² Division of Applied Regulatory Science, Office of Clinical Pharmacology, Office of Translational Sciences, Center for Drug Evaluation and Research, Food and Drug Administration, WO Bldg 64 Rm 2078, 10903 New Hampshire Ave, Silver Spring, MD, 20993, USA. Zhihua.li@fda.hhs.gov.

Abstract

Background: During drug development, it is essential to gather information about the change of clinical exposure of a drug (object) due to the pharmacokinetic (PK) drug-drug interactions (DDIs) with another drug (precipitant). While many natural language processing (NLP) methods for DDI have been published, most were designed to evaluate if (and what kind of) DDI relationships exist in the text, without identifying the direction of DDI (object vs. precipitant drug). Here we present a method for the automatic identification of the directionality of a PK DDI from literature or drug labels.

Methods: We reannotated the Text Analysis Conference (TAC) DDI track 2019 corpus for identifying the direction of a PK DDI and evaluated the performance of a fine-tuned BioBERT model on this task by following the training and validation steps prespecified by TAC.

Results: This initial attempt showed the model achieved an F-score of 0.82 in identifying sentences as containing PK DDI and an F-score of 0.97 in identifying object versus precipitant drugs in those sentences.

Discussion and conclusion: Despite a growing list of NLP methods for DDI extraction, most of them use a common set of corpora to perform general purpose tasks (e.g., classifying a sentence into one of several fixed DDI categories). There is a lack of coordination between the drug development and biomedical informatics method development community to develop corpora and methods to perform specific tasks (e.g., extract clinical exposure changes due to PK DDI). We hope that our effort can encourage such a coordination so that more "fit for purpose" NLP methods could be developed and used to facilitate the drug development process.

Keywords: Directionality; Drug-drug interactions; Natural language processing; Pharmacokinetic; Transformer language model.

MeSH terms

Data Mining / methods
Deep Learning*
Drug Interactions
Language
Natural Language Processing*