3D-RISM-AI: A Machine Learning Approach to Predict Protein–Ligand Binding Affinity Using 3D-RISM

Abstract

Hydration free energy (HFE) is a key factor in improving protein–ligand binding free energy (BFE) prediction accuracy. The HFE itself can be calculated using the three-dimensional reference interaction model (3D-RISM); however, the BFE predictions solely evaluated using 3D-RISM are not correlated to the experimental BFE for abundant protein–ligand pairs. In this study, to predict the BFE for multiple sets of protein–ligand pairs, we propose a machine learning approach incorporating the HFEs obtained using 3D-RISM, termed 3D-RISM-AI. In the learning process, structural metrics, intra-/intermolecular energies, and HFEs obtained via 3D-RISM of ∼4000 complexes in the PDBbind database (ver. 2018) were used. The BFEs predicted using 3D-RISM-AI were well correlated to the experimental data (Pearson’s correlation coefficient of 0.80 and root-mean-square error of 1.91 kcal/mol). As important factors for the prediction, the difference in the solvent accessible surface area between the bound and unbound structures and the hydration properties of the ligands were detected during the learning process.

HAC-Net: A Hybrid Attention-Based Convolutional Neural Network for Highly Accurate Protein–Ligand Binding Affinity Prediction

“…There has been continuous progress in applying ML to predict protein–ligand binding affinity, gaining significant popularity in 2010 with NNScore, an ensemble of 10 multi-layer perceptrons (MLPs), and RF-Score, a random forest-based model. Many groups have subsequently utilized random forest-based approaches − or related methods such as gradient-boosted trees − to predict binding affinity, and most other architectures contain one or multiple MLPs as subcomponents. Convolutional neural networks (CNNs) have become increasingly popular for binding affinity prediction due to their success on image detection tasks .…”

Multiscale simulation of fluids: coupling molecular and continuum

“…In combining the equations of O'Connell and Thompson, 31 to get the constraint of eqn (18), this changes the form of constraint to a differential control algorithm. Differential control aims to ensure the time evolution of both systems is the same.…”

“…F i is not essential to the functioning of eqn (19). Despite this, Yen et al 152 proposed that the sum of the force terms in eqn (18) be averaged over M iterations to improve signal to noise, applied together with the time averaged MD velocity instead of the instantaneous values in eqn (20),…”

Applications of Free-Energy Calculations to Biomolecular Processes. A Collection

“…13 ■ MACHINE LEARNING AND FREE-ENERGY CALCULATIONS On the machine learning front, a data-driven approach incorporating the hydration free energies obtained using 3D-RISM, termed 3D-RISM-AI, was developed by Osaki et al, leveraging several physicochemical descriptors. 14 In another study by Gusev et al, it was demonstrated that the combination of active learning with automated machine learning and free-energy calculations yields at least 20-fold speedup relative to nai ̈ve brute force approaches. 15 Finally, a new strategy from Akkus et al to estimate binding free energies using end-state molecular dynamics simulation based on LIE and ANI-2x neural network potentials predicts the single-point interaction energies between ligand−protein and ligand− solvent pairs at the accuracy of the wb97x/6-31G* level.…”