Compound‐protein interaction prediction with end‐to‐end learning of neural networks for graphs and sequences

By Masashi Tsubaki, Kentaro Tomii, Jun Sese. 2018

630 citations recorded by the source corpus.

Motivation: In bioinformatics, machine learning‐based methods that predict the compound‐protein interactions (CPIs) play an important role in the virtual screening for drug discovery. Recently, end‐to‐end representation learning for discrete symbolic data (e.g. words in natural language processing) using deep neural networks has demonstrated excellent performance on various difficult problems. For the CPI problem, data are provided as discrete symbolic data, i.e. compounds are represented as graphs where the vertices are atoms, the edges are chemical bonds, and proteins are sequences in which the characters are amino acids. In this study, we investigate the use of end‐to‐end representation learning for compounds and proteins, integrate the representations, and develop a new CPI prediction approach by combining a graph neural network (GNN) for compounds and a convolutional neural network (CNN) for proteins. Results: Our experiments using three CPI datasets demonstrated that the proposed end‐to‐end approach achieves competitive or higher performance as compared to various existing CPI prediction methods. In addition, the proposed approach significantly outperformed existing methods on an unbalanced dataset. This suggests that data‐driven representations of compounds and proteins obtained by end‐to‐end GNNs and CNNs are more robust than traditional chemical and biological features obtained from databases. Although analyzing deep learning models is difficult due to their black‐box nature, we address this issue using a neural attention mechanism, which allows us to consider which subsequences in a protein are more important for a drug compound when predicting its interaction. The neural attention mechanism also provides effective visualization, which makes it easier to analyze a model even when modeling is performed using real‐valued representations instead of discrete features. Availability and implementation: https://github.com/masashitsubaki Supplementary information: Supplementary data are available at Bioinformatics online.

Subfields: Computational Theory and Mathematics, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Molecular Biology

Citations in the corpus

TANKBind: Trigonometry-Aware Neural NetworKs for Drug-Protein Binding Structure Prediction (2022, methodology): “…works either use complex-free models to predict the binding affinity directly from protein-ligand pairs Wang and Dokholyan [2021], Li et al. [2020], Tsubaki et al. [2019], Gao et al. [2018], Karimi et al. [2019], Zheng et al. [2020] or make predictions through complex structure that has been…”
Interpretable bilinear attention network with domain adaptation improves drug–target prediction (2022, neutral): “The one-side attention is equivalent to the neural attention mechanism introduced by Tsubaki et al. (2019) 14 , which is used to capture the joint representation between a drug vector representation and a protein subsequence matrix representation.”
Intrinsic-Extrinsic Convolution and Pooling for Learning on 3D Protein Structures (2021, methodology): “…neural networks (CNN) to learn protein representations directly from an amino acid sequence, for tasks such as protein function prediction (Kulmanov et al., 2017; Kulmanov & Hoehndorf, 2019), protein-compound interaction (Tsubaki et al., 2018), or protein fold classiﬁcation (Hou et al., 2018).”
Graph Convolutional Neural Networks for Predicting Drug-Target Interactions (2018, methodology): “Tsubaki et al.18 apply graph convolution networks and 1D-CNN to learn features from 2D molecular graphs and protein sequences, respectively.”
Artificial intelligence in oncology (2020, background): “Although we do not dive into detail here, various novel architectures, such as graphical convolution 18,19 and capsuleNet, are continually being proposed and applied in biomedicine.”
Predicting drug–protein interaction using quasi-visual question answering system (2019, methodology): “In addition, for Human dataset, we report the Precision and Recall value following [Tsubaki et al., 2018].”