Drug target assessments: Classifying target modulation and associated health effects using multi-level BERT-based classification models

Abstract

Motivation: Drug target selection determines the success of the drug development pipeline. Therefore, novel drug targets need to be assessed for their therapeutic benefits/risks at the earliest stage possible. Where manual risk/benefit analyses are often user-biased and time-consuming, Large Language Models can offer a systematic and efficient approach to curating and analysing literature. Currently, publicly available Large Language Models are lacking for this task, while public platforms for target assessments are limited to co-occurrences. Results: BERT-models for multi-level classification of drug target-health effect relationships described in PubMed were developed. Relationships were classified based on (i) causality; (ii) direction of target modulation; (iii) direction of the associated health effect. The models showed competitive performances with F1 scores between 0.86 and 0.92 and their applicability was demonstrated using ADAM33 and OSM as case study. The developed classification pipeline is the first to allow detailed classification of drug target-health effect relationships. The models provide mechanistic insight into how target modulation affects health and disease, both from an efficacy and safety perspective. The models, deployed on the whole of PubMed and available through the TargetTri platform, are expected to offer a significant advancement in artificial intelligence-assisted target identification and evaluation.