Forman persistent Ricci curvature (FPRC)-based machine learning models for protein–ligand binding affinity prediction

Abstract

Artificial intelligence (AI) techniques have already been gradually applied to the entire drug design process, from target discovery, lead discovery, lead optimization and preclinical development to the final three phases of clinical trials. Currently, one of the central challenges for AI-based drug design is molecular featurization, which is to identify or design appropriate molecular descriptors or fingerprints. Efficient and transferable molecular descriptors are key to the success of all AI-based drug design models. Here we propose Forman persistent Ricci curvature (FPRC)-based molecular featurization and feature engineering, for the first time. Molecular structures and interactions are modeled as simplicial complexes, which are generalization of graphs to their higher dimensional counterparts. Further, a multiscale representation is achieved through a filtration process, during which a series of nested simplicial complexes at different scales are generated. Forman Ricci curvatures (FRCs) are calculated on the series of simplicial complexes, and the persistence and variation of FRCs during the filtration process is defined as FPRC. Moreover, persistent attributes, which are FPRC-based functions and properties, are employed as molecular descriptors, and combined with machine learning models, in particular, gradient boosting tree (GBT). Our FPRC-GBT models are extensively trained and tested on three most commonly-used datasets, including PDBbind-2007, PDBbind-2013 and PDBbind-2016. It has been found that our results are better than the ones from machine learning models with traditional molecular descriptors.

Dowker complex based machine learning (DCML) models for protein-ligand binding affinity prediction

“…Mathematically, a bipartite graph G ( V 1 , V 2 , E ) has two vertex sets V 1 and V 2 , and all its edges are formed only between the two vertex sets. Recently, bipartite-graph based interactive matrixes have been used for machine learning models in drug design and achieved great success [ 20 , 30 – 34 , 40 ]. Mathematically, these interactive matrixes, which are based on atomic distances and electrostatic interactions, can be transformed into a weighted biadjacency matrixes between protein and ligand atoms.…”

Prediction of Binding Free Energy of Protein–Ligand Complexes with a Hybrid Molecular Mechanics/Generalized Born Surface Area and Machine Learning Method

“…The R p values of GXLE in six systems are higher than those of X-score, while the R s values in seven targets are higher than those of X-score. In addition, we also compared our GXLE model against the recently developed geometric and topological invariant-based ML models, which have shown superior performance in benchmark studies. − To this end, we have retrained the open-sourced PSH-ML using the same training set as ours (including 3511 complexes). Then, we have tested it on the same extended test set, as shown Table .…”

Novel Solubility Prediction Models: Molecular Fingerprints and Physicochemical Features vs Graph Convolutional Neural Networks

“…There are several methods to represent molecules. For example, creating features using transformer 22 and using mathematical features 23 are also reasonable methods, but our study sought to use the most fundamental, simple, and clear method above all else. In addition, this study used a molecular fingerprint that best reflects structural simplicity since the purpose is to predict solubility.…”