NeoDTI: neural integration of neighbor information from a heterogeneous network for discovering new drug–target interactions

TLDR

Accurate in silico prediction of drug–target interactions can accelerate drug discovery, and systems‑biology approaches model drugs and targets by their functional roles in biological networks. The authors aim to develop NeoDTI, a nonlinear end‑to‑end neural model that integrates heterogeneous network data to learn topology‑preserving representations for DTI prediction. NeoDTI employs graph‑convolution‑based information passing and aggregation to fuse diverse network information, is robust to hyperparameter choices, and can incorporate additional data such as compound–protein binding affinities. NeoDTI outperforms state‑of‑the‑art DTI predictors and identifies novel interactions supported by prior evidence, demonstrating its utility for drug development and repositioning. Source code and data are available at https://github.com/FangpingWan/NeoDTI, with supplementary materials hosted on Bioinformatics online.

Abstract

Abstract Motivation Accurately predicting drug–target interactions (DTIs) in silico can guide the drug discovery process and thus facilitate drug development. Computational approaches for DTI prediction that adopt the systems biology perspective generally exploit the rationale that the properties of drugs and targets can be characterized by their functional roles in biological networks. Results Inspired by recent advance of information passing and aggregation techniques that generalize the convolution neural networks to mine large-scale graph data and greatly improve the performance of many network-related prediction tasks, we develop a new nonlinear end-to-end learning model, called NeoDTI, that integrates diverse information from heterogeneous network data and automatically learns topology-preserving representations of drugs and targets to facilitate DTI prediction. The substantial prediction performance improvement over other state-of-the-art DTI prediction methods as well as several novel predicted DTIs with evidence supports from previous studies have demonstrated the superior predictive power of NeoDTI. In addition, NeoDTI is robust against a wide range of choices of hyperparameters and is ready to integrate more drug and target related information (e.g. compound–protein binding affinity data). All these results suggest that NeoDTI can offer a powerful and robust tool for drug development and drug repositioning. Availability and implementation The source code and data used in NeoDTI are available at: https://github.com/FangpingWan/NeoDTI. Supplementary information Supplementary data are available at Bioinformatics online.