MCN-CPI: Multiscale Convolutional Network for Compound–Protein Interaction Prediction

Wang, Shuang; Jiang, Mingjian; Zhang, Shugang; Wang, Xiaofeng; Yuan, Qing; Wei, Zhiqiang; Li, Zhen

doi:10.3390/biom11081119

Cited by 29 publications

(14 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3D convolutional neural networks (3D-CNNs), widely used for a vast number of computer vision applications with 3D volumetric data, have been successfully applied to the prediction of protein–ligand binding affinity. 1 , 14 , 18 , 19 , 22 , 23 , 35 , 45 We herein propose to use 3D-CNNs as a binary pose classifier to learn representation for 3D atomic structures of compound poses. Our 3D-CNN is composed of three convolutional layers and three fully connected layers, followed by a sigmoid activation.…”

Section: D-cnnmentioning

confidence: 99%

Pose Classification Using Three-Dimensional Atomic Structure-Based Neural Networks Applied to Ion Channel–Ligand Docking

Shim

Kim

Allen

et al. 2022

J. Chem. Inf. Model.

View full text Add to dashboard Cite

The identification of promising lead compounds showing pharmacological activities toward a biological target is essential in early stage drug discovery. With the recent increase in available small-molecule databases, virtual high-throughput screening using physics-based molecular docking has emerged as an essential tool in assisting fast and cost-efficient lead discovery and optimization. However, the best scored docking poses are often suboptimal, resulting in incorrect screening and chemical property calculation. We address the pose classification problem by leveraging data-driven machine learning approaches to identify correct docking poses from AutoDock Vina and Glide screens. To enable effective classification of docking poses, we present two convolutional neural network approaches: a three-dimensional convolutional neural network (3D-CNN) and an attention-based point cloud network (PCN) trained on the PDBbind refined set. We demonstrate the effectiveness of our proposed classifiers on multiple evaluation data sets including the standard PDBbind CASF-2016 benchmark data set and various compound libraries with structurally different protein targets including an ion channel data set extracted from Protein Data Bank (PDB) and an in-house KCa3.1 inhibitor data set. Our experiments show that excluding false positive docking poses using the proposed classifiers improves virtual high-throughput screening to identify novel molecules against each target protein compared to the initial screen based on the docking scores.

show abstract

Section: D-cnnmentioning

confidence: 99%

Pose Classification Using Three-Dimensional Atomic Structure-Based Neural Networks Applied to Ion Channel–Ligand Docking

Shim

Kim

Allen

et al. 2022

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…where δ x and δ y are the larger and smaller affinity values, respectively, and b x and b y are the corresponding prediction values of the model. Z is a normalization constant, and h(x) is the step function that takes the form of the following Equation [11]:…”

Section: Metricsmentioning

confidence: 99%

“…With the rapid advancements in deep learning in the last decade, various data-driven methods were proposed for the description of drugs and target proteins [7][8][9][10][11]. These deep learning approaches differ from hand-crafted features, and features can be extracted automatically through deep learning methods and are proved to be more effective.…”

Section: Introductionmentioning

confidence: 99%

SAG-DTA: Prediction of Drug–Target Affinity Using Self-Attention Graph Network

Zhang

Jiang

Wang

et al. 2021

IJMS

Self Cite

View full text Add to dashboard Cite

The prediction of drug–target affinity (DTA) is a crucial step for drug screening and discovery. In this study, a new graph-based prediction model named SAG-DTA (self-attention graph drug–target affinity) was implemented. Unlike previous graph-based methods, the proposed model utilized self-attention mechanisms on the drug molecular graph to obtain effective representations of drugs for DTA prediction. Features of each atom node in the molecular graph were weighted using an attention score before being aggregated as molecule representation. Various self-attention scoring methods were compared in this study. In addition, two pooing architectures, namely, global and hierarchical architectures, were presented and evaluated on benchmark datasets. Results of comparative experiments on both regression and binary classification tasks showed that SAG-DTA was superior to previous sequence-based or other graph-based methods and exhibited good generalization ability.

show abstract

“…For example, Tsubaki et al [21] develops a novel CPI prediction method by combining graph neural network (GNN) and convolution neural network (CNN) for compounds and proteins representation respectively. GraphDTA [22], MCN-CPI [23] and PADME [24] also construct graphs to describe molecules and apply GNN for the feature extraction in DTA prediction. The achievements of these methods demonstrate that the GNN could effectively characterize the small molecule.…”

Section: Introductionmentioning

confidence: 99%

Sequence-based drug-target affinity prediction using weighted graph neural networks

et al. 2022

Self Cite

View full text Add to dashboard Cite

Background Affinity prediction between molecule and protein is an important step of virtual screening, which is usually called drug-target affinity (DTA) prediction. Its accuracy directly influences the progress of drug development. Sequence-based drug-target affinity prediction can predict the affinity according to protein sequence, which is fast and can be applied to large datasets. However, due to the lack of protein structure information, the accuracy needs to be improved. Results The proposed model which is called WGNN-DTA can be competent in drug-target affinity (DTA) and compound-protein interaction (CPI) prediction tasks. Various experiments are designed to verify the performance of the proposed method in different scenarios, which proves that WGNN-DTA has the advantages of simplicity and high accuracy. Moreover, because it does not need complex steps such as multiple sequence alignment (MSA), it has fast execution speed, and can be suitable for the screening of large databases. Conclusion We construct protein and molecular graphs through sequence and SMILES that can effectively reflect their structures. To utilize the detail contact information of protein, graph neural network is used to extract features and predict the binding affinity based on the graphs, which is called weighted graph neural networks drug-target affinity predictor (WGNN-DTA). The proposed method has the advantages of simplicity and high accuracy.

show abstract

MCN-CPI: Multiscale Convolutional Network for Compound–Protein Interaction Prediction

Cited by 29 publications

References 26 publications

Pose Classification Using Three-Dimensional Atomic Structure-Based Neural Networks Applied to Ion Channel–Ligand Docking

Pose Classification Using Three-Dimensional Atomic Structure-Based Neural Networks Applied to Ion Channel–Ligand Docking

SAG-DTA: Prediction of Drug–Target Affinity Using Self-Attention Graph Network

Sequence-based drug-target affinity prediction using weighted graph neural networks

Contact Info

Product

Resources

About