PLA-SGCN: Protein-Ligand Binding Affinity Prediction by Integrating Similar Pairs and Semi-supervised Graph Convolutional Network

TL;DR

This paper introduces PLA-SGCN, a semi-supervised graph convolutional network that integrates similar hard protein-ligand pairs for improved binding affinity prediction, demonstrating superior performance on multiple datasets.

Contribution

It proposes an end-to-end framework that retrieves hard similar pairs, learns graph topology, and predicts binding affinity using semi-supervised GCN, advancing PLA prediction methods.

Findings

Significantly outperforms existing methods on PDBbind, Davis, KIBA, and BindingDB datasets.

Effectively retrieves and utilizes hard similar pairs for better prediction accuracy.

Demonstrates the benefit of integrating sample similarity and graph learning in PLA prediction.

Abstract

The protein-ligand binding affinity (PLA) prediction goal is to predict whether or not the ligand could bind to a protein sequence. Recently, in PLA prediction, deep learning has received much attention. Two steps are involved in deep learning-based approaches: feature extraction and task prediction step. Many deep learning-based approaches concentrate on introducing new feature extraction networks or integrating auxiliary knowledge like protein-protein interaction networks or gene ontology knowledge. Then, a task prediction network is designed simply using some fully connected layers. This paper aims to integrate retrieved similar hard protein-ligand pairs in PLA prediction (i.e., task prediction step) using a semi-supervised graph convolutional network (GCN). Hard protein-ligand pairs are retrieved for each input query sample based on the manifold smoothness constraint. Then, a graph is learned automatically in which each node is a protein-ligand pair, and each edge represents the similarity between pairs. In other words, an end-to-end framework is proposed that simultaneously retrieves hard similar samples, learns protein-ligand descriptor, learns the graph topology of the input sample with retrieved similar hard samples (learn adjacency matrix), and learns a semi-supervised GCN to predict the binding affinity (as task predictor). The training step adjusts the parameter values, and in the inference step, the learned model is fine-tuned for each input sample. To evaluate the proposed approach, it is applied to the four well-known PDBbind, Davis, KIBA, and BindingDB datasets. The results show that the proposed method significantly performs better than the comparable approaches.