Drug-Target-Interaction Prediction with Contrastive and Siamese Transformers

Abstract

As machine learning (ML) becomes increasingly integrated into the drug development process, accurately predicting Drug-Target Interactions (DTI) becomes a necessity for pharmaceutical research. This prediction plays a crucial role in various aspects of drug development, including virtual screening, repurposing of drugs, and proactively identifying potential side effects. While Deep Learning has made significant progress in enhancing DTI prediction, challenges related to interpretability and consistent performance persist in the field. This study introduces two innovative methodologies that combine Generative Pretraining and Contrastive Learning to specialize Transformers for bio-chemical modeling. These systems are designed to best incorporate cross-attention, which enables a nuanced alignment of multi-representation embeddings. Our empirical evaluation will showcase the effectiveness and interpretability of this proposed framework. Through a series of experiments, we provide compelling evidence of its superior predictive accuracy and enhanced interpretability. The primary objective of this research is not only to contribute to the advancement of novel DTI prediction methods but also to promote greater transparency and reliability within the drug discovery pipeline.