Geometric Graph Learning with Extended Atom-Types Features for Protein-Ligand Binding Affinity Prediction

TL;DR

This paper introduces enhanced graph-based machine learning models incorporating extensive atom types for improved protein-ligand binding affinity prediction, achieving state-of-the-art results on standard benchmarks.

Contribution

The work extends graph-based learning by integrating detailed atom types and features into multiscale graphs, paired with gradient boosting, to improve binding affinity prediction accuracy.

Findings

The models outperform existing methods on CASF benchmarks.

The SYBYL atom-type model achieves the best performance.

Both models demonstrate state-of-the-art predictive accuracy.

Abstract

Understanding and accurately predicting protein-ligand binding affinity are essential in the drug design and discovery process. At present, machine learning-based methodologies are gaining popularity as a means of predicting binding affinity due to their efficiency and accuracy, as well as the increasing availability of structural and binding affinity data for protein-ligand complexes. In biomolecular studies, graph theory has been widely applied since graphs can be used to model molecules or molecular complexes in a natural manner. In the present work, we upgrade the graph-based learners for the study of protein-ligand interactions by integrating extensive atom types such as SYBYL and extended connectivity interactive features (ECIF) into multiscale weighted colored graphs (MWCG). By pairing with the gradient boosting decision tree (GBDT) machine learning algorithm, our approach results in two different methods, namely $^\text{sybyl}\text{GGL}$-Score and $^\text{ecif}\text{GGL}$-Score. Both of our models are extensively validated in their scoring power using three commonly used benchmark datasets in the drug design area, namely CASF-2007, CASF-2013, and CASF-2016. The performance of our best model $^\text{sybyl}\text{GGL}$-Score is compared with other state-of-the-art models in the binding affinity prediction for each benchmark. While both of our models achieve state-of-the-art results, the SYBYL atom-type model $^\text{sybyl}\text{GGL}$-Score outperforms other methods by a wide margin in all benchmarks.