Deep-Learning-Based Drug–Target Interaction Prediction

TLDR

Drug–target interaction prediction is a key challenge in drug repositioning, and in silico methods can accelerate discovery and reveal potential drug–drug interactions, but performance depends heavily on the descriptors used. This study develops DeepDTIs, a deep‑learning framework that predicts novel drug–target interactions for approved drugs without classifying targets. DeepDTIs first learns representations from raw descriptors via unsupervised pretraining, then trains a classification model on known interaction pairs. DeepDTIs matches or surpasses state‑of‑the‑art methods and can predict new drug–target associations for existing drugs and targets.

Abstract

Identifying interactions between known drugs and targets is a major challenge in drug repositioning. In silico prediction of drug-target interaction (DTI) can speed up the expensive and time-consuming experimental work by providing the most potent DTIs. In silico prediction of DTI can also provide insights about the potential drug-drug interaction and promote the exploration of drug side effects. Traditionally, the performance of DTI prediction depends heavily on the descriptors used to represent the drugs and the target proteins. In this paper, to accurately predict new DTIs between approved drugs and targets without separating the targets into different classes, we developed a deep-learning-based algorithmic framework named DeepDTIs. It first abstracts representations from raw input descriptors using unsupervised pretraining and then applies known label pairs of interaction to build a classification model. Compared with other methods, it is found that DeepDTIs reaches or outperforms other state-of-the-art methods. The DeepDTIs can be further used to predict whether a new drug targets to some existing targets or whether a new target interacts with some existing drugs.