MDL-CPI: multi-view deep learning model for compound-protein interaction prediction.

Researchers

Journal

Modalities

Models

Abstract

Elucidating the mechanisms of Compound-Protein Interactions (CPIs) plays an essential role in drug discovery and development. Many computational efforts have been done to accelerate the field development. However, current predictive performance is still not satisfactory, and existing methods consider only protein and compound features, ignoring their interactive information. In this study, we propose a multi-view deep learning method named MDL-CPI for CPI prediction. To sufficiently extract discriminative information, we introduce a hybrid architecture that leverages BERT (Bidirectional Encoder Representations from Transformers) and CNN (Convolutional Neural Network) to extract protein features from a sequential perspective, uses the GNN (Graph Neural Networks) to extract compound features from a structural perspective, and generates a unified feature space using AE2 network to learn the interactive information between BERT-CNN and Graph embeddings. Comparative results on benchmark datasets show that our proposed method exhibits better performance compared to existing CPI prediction methods, demonstrating strong predictive ability of our model. Importantly, we demonstrate that the learned interactive information between compounds and proteins is critical to improving predictive performance. To facilitate the use of our method, we release our source code and dataset at: https://github.com/Longwt123/MDL-CPI.Copyright © 2022 Elsevier Inc. All rights reserved.