Self-Attention Based Molecule Representation for Predicting Drug-Target Interaction

TL;DR

This paper introduces a novel self-attention based molecule representation for drug-target interaction prediction, significantly improving accuracy and effectively identifying drugs targeting specific biomarkers, which could accelerate drug discovery and personalized medicine.

Contribution

The paper proposes a new self-attention based molecule representation and a DTI model that outperforms existing methods in accuracy and biomarker targeting.

Findings

Outperforms state-of-the-art by up to 4.9% in precision-recall AUC

Effectively lists known drugs targeting cancer biomarkers in top-30 candidates

Enhances drug discovery efficiency and personalized medicine

Abstract

Predicting drug-target interactions (DTI) is an essential part of the drug discovery process, which is an expensive process in terms of time and cost. Therefore, reducing DTI cost could lead to reduced healthcare costs for a patient. In addition, a precisely learned molecule representation in a DTI model could contribute to developing personalized medicine, which will help many patient cohorts. In this paper, we propose a new molecule representation based on the self-attention mechanism, and a new DTI model using our molecule representation. The experiments show that our DTI model outperforms the state of the art by up to 4.9% points in terms of area under the precision-recall curve. Moreover, a study using the DrugBank database proves that our model effectively lists all known drugs targeting a specific cancer biomarker in the top-30 candidate list.