Calculation of Protein-Ligand Binding Free Energy Using a Physics-Guided Neural Network

Cain, Sahar; Risheh, Ali; Forouzesh, Negin

doi:10.1109/bibm52615.2021.9669867

Cited by 3 publications

(1 citation statement)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With that, the second component is designed based on Graph Convolutional Network, which has demonstrated remarkable performance in extracting spatial and structural features in different domains, including computational structural biology [ 44 ]. The proposed Physics-Guided Neural Network was first introduced in [ 45 ]. Here, we analyze and test it on a PDBbind (refined) set of a comprehensive collection of protein–ligand complexes and small host–guest systems.…”

Section: Introductionmentioning

confidence: 99%

A Physics-Guided Neural Network for Predicting Protein–Ligand Binding Free Energy: From Host–Guest Systems to the PDBbind Database

2022

Self Cite

View full text Add to dashboard Cite

Calculation of protein–ligand binding affinity is a cornerstone of drug discovery. Classic implicit solvent models, which have been widely used to accomplish this task, lack accuracy compared to experimental references. Emerging data-driven models, on the other hand, are often accurate yet not fully interpretable and also likely to be overfitted. In this research, we explore the application of Theory-Guided Data Science in studying protein–ligand binding. A hybrid model is introduced by integrating Graph Convolutional Network (data-driven model) with the GBNSR6 implicit solvent (physics-based model). The proposed physics-data model is tested on a dataset of 368 complexes from the PDBbind refined set and 72 host–guest systems. Results demonstrate that the proposed Physics-Guided Neural Network can successfully improve the “accuracy” of the pure data-driven model. In addition, the “interpretability” and “transferability” of our model have boosted compared to the purely data-driven model. Further analyses include evaluating model robustness and understanding relationships between the physical features.

show abstract

Section: Introductionmentioning

confidence: 99%