A Cascade Graph Convolutional Network for Predicting Protein–Ligand Binding Affinity

Abstract

Accurate prediction of binding affinity between protein and ligand is a very important step in the field of drug discovery. Although there are many methods based on different assumptions and rules do exist, prediction performance of protein–ligand binding affinity is not satisfactory so far. This paper proposes a new cascade graph-based convolutional neural network architecture by dealing with non-Euclidean irregular data. We represent the molecule as a graph, and use a simple linear transformation to deal with the sparsity problem of the one-hot encoding of original data. The first stage adopts ARMA graph convolutional neural network to learn the characteristics of atomic space in the protein–ligand complex. In the second stage, one variant of the MPNN graph convolutional neural network is introduced with chemical bond information and interactive atomic features. Finally, the architecture passes through the global add pool and the fully connected layer, and outputs a constant value as the predicted binding affinity. Experiments on the PDBbind v2016 data set showed that our method is better than most of the current methods. Our method is also comparable to the state-of-the-art method on the data set, and is more intuitive and simple.

On the Frustration to Predict Binding Affinities from Protein–Ligand Structures with Deep Neural Networks

“…For example, drug discovery would immediately benefit from key advances in this topic, by better triaging potentially interesting molecules among virtual screening hits , and proposing viable analogues in emerging ultra-large chemical spaces for hit to lead optimization. With the ever increasing amount of high-resolution experimentally determined protein–ligand structures, binding affinity prediction algorithms have switched from physics-based to empirical scoring functions, and in the last few years to machine learning and deep learning methods. , The latter category of descriptor-based scoring functions has notably led to numerous protein–ligand affinity models − (see a nonexhaustive list Table S1) notably because deep learning does not require explicit descriptor engineering and is ideally suited to find hidden nonlinear relationships between 3D protein–ligand structures and binding affinity. The first deep neural networks (DNNs) to predict binding affinities were convolutional neural networks (CNNs) reading a protein–ligand complex as an ensemble of grid-based voxels with multiple channels corresponding to pharmacophoric properties. ,, The CNN architecture is relatively inefficient from a computational point of view because most of the voxels do not carry any relevant information.…”

“…Despite several warnings on the composition and completeness of the PDBbind archive, it remains the largest resource to train machine learning models for structure-based prediction of binding affinities. Many graph neural networks (GNNs), used as end-to-end standalone architecture, ,,,, in cascade or in combination with CNNs, have been described recently. None of them significantly outperforms first-generation CNNs, most models presenting rather similar accuracies (Pearson correlation coefficient in the 0.80–0.85 range; root-mean square error (RMSE) around 1.2–1.3 pK unit) in predicting affinities for the PDBbind core set (Table S1) but significantly lower accuracies for true external test sets. ,, …”

Accurate Protein-Ligand Complex Structure Prediction using Geometric Deep Learning

“…A.2.4 for details). The comparisons of LigPose affnity with several recent structure-based deep learning methods [37,39,35,36,41,38,40] Pearson R of 0.835. Compared to the methods that use native structures, LigPose affnity is also comparable or better than the best performing method PointTransformer (MAE: 0.91, RMSE: 1.19, Pearson R: 0.852), indicating its strong ability to learn native-like atom interactions.…”

A novel graph convolutional neural network for predicting interaction sites on protein kinase inhibitors in phosphorylation

“…Bioinformatics is a versatile tool to research complicated biological processes, and machine learning continues to gain popularity for the development of tools to analyze biological data. A graph convolutional neural (GCN) network is a recently developed neural network to directly operate and analyze graphic structures and has been widely applied for analysis of protein-ligand complexes, structure-embedded graph representation 29 , structure-based virtual screening 30 , prediction of binding affinity 31 , 32 , and prediction of binding residues 34 . Moreover, many novel algorithms have been proposed for solving specific biological issues in recent years 33 .…”