GraphDTI: A robust deep learning predictor of drug-target interactions from multiple heterogeneous data

Journal of Cheminformatics

Limeng Pu¹  Manali Singha²  Michal Brylinski³  Joseph Feinstein⁴  Hsiao-Chun Wu⁵  Guannan Liu⁵  Prasanga Neupane⁵  J. Ramanujam⁶ 

[1] Center for Computation and Technology, Louisiana State University, 70803, Baton Rouge, LA, USA;Department of Biological Sciences, Louisiana State University, 70803, Baton Rouge, LA, USA;Department of Biological Sciences, Louisiana State University, 70803, Baton Rouge, LA, USA;Center for Computation and Technology, Louisiana State University, 70803, Baton Rouge, LA, USA;Department of Computer Science, Brown University, 02902, Providence, RI, USA;Division of Electrical and Computer Engineering, Louisiana State University, 70803, Baton Rouge, LA, USA;Division of Electrical and Computer Engineering, Louisiana State University, 70803, Baton Rouge, LA, USA;Center for Computation and Technology, Louisiana State University, 70803, Baton Rouge, LA, USA;

关键词: Drug–target interactions;    Protein–protein interaction network;    Drug perturbed gene expression;    Feature selection;    Multi-layer perceptron;    Machine learning;    Deep learning;    GraphDTI;   

DOI  :  10.1186/s13321-021-00540-0

来源: Springer

【 摘 要 】

Traditional techniques to identify macromolecular targets for drugs utilize solely the information on a query drug and a putative target. Nonetheless, the mechanisms of action of many drugs depend not only on their binding affinity toward a single protein, but also on the signal transduction through cascades of molecular interactions leading to certain phenotypes. Although using protein-protein interaction networks and drug-perturbed gene expression profiles can facilitate system-level investigations of drug-target interactions, utilizing such large and heterogeneous data poses notable challenges. To improve the state-of-the-art in drug target identification, we developed GraphDTI, a robust machine learning framework integrating the molecular-level information on drugs, proteins, and binding sites with the system-level information on gene expression and protein-protein interactions. In order to properly evaluate the performance of GraphDTI, we compiled a high-quality benchmarking dataset and devised a new cluster-based cross-validation protocol. Encouragingly, GraphDTI not only yields an AUC of 0.996 against the validation dataset, but it also generalizes well to unseen data with an AUC of 0.939, significantly outperforming other predictors. Finally, selected examples of identified drugtarget interactions are validated against the biomedical literature. Numerous applications of GraphDTI include the investigation of drug polypharmacological effects, side effects through offtarget binding, and repositioning opportunities.

【 授权许可】

CC BY