Mayer-homology learning prediction of protein-ligand binding affinities

TL;DR

This paper introduces a novel topological feature extraction method based on Mayer homology for predicting protein-ligand binding affinities, showing improved accuracy over existing models.

Contribution

It develops persistent Mayer homology theory with a generalized differential, enabling richer topological features for molecular data analysis.

Findings

Superior prediction performance on PDBbind datasets

Effective multiscale topological vectorization for molecules

Enhanced molecular feature representation for machine learning

Abstract

Artificial intelligence-assisted drug design is revolutionizing the pharmaceutical industry. Effective molecular features are crucial for accurate machine learning predictions, and advanced mathematics plays a key role in designing these features. Persistent homology theory, which equips topological invariants with persistence, provides valuable insights into molecular structures. The calculation of Betti numbers is based on differential that typically satisfy \(d^2 = 0\). Our recent work has extended this concept by employing Mayer homology with a generalized differential that satisfies \(d^N = 0\) for \(N \geq 2\), leading to the development of persistent Mayer homology (PMH) theory and richer topological information across various scales. In this study, we utilize PMH to create a novel multiscale topological vectorization for molecular representation, offering valuable tools for descriptive and predictive analysis in molecular data and machine learning prediction. Specifically, benchmark tests on established protein-ligand datasets, including PDBbind-2007, PDBbind-2013, and PDBbind-2016, demonstrate the superior performance of our Mayer homology models in predicting protein-ligand binding affinities.