Molecular free energy optimization on a computational graph

Free energy is arguably the most important property of molecular systems. Despite great progress in both its efficient estimation by scoring functions/potentials and more rigorous computation based on extensive sampling, we remain far from accurately predicting and manipulating biomolecular structur...

Full description

Saved in:
Bibliographic Details
Published in:RSC advances Vol. 11; no. 21; pp. 12929 - 12937
Main Authors: Cao, Xiaoyong, Tian, Pu
Format: Journal Article
Language:English
Published: England Royal Society of Chemistry 06.04.2021
The Royal Society of Chemistry
Subjects:
Artificial intelligence
Chemistry
Energy theory
Free energy
Gibbs free energy
infrastructure
Iterative methods
Optimization
protein structure
Sampling
Solvation
solvation energy
ISSN:2046-2069, 2046-2069
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Free energy is arguably the most important property of molecular systems. Despite great progress in both its efficient estimation by scoring functions/potentials and more rigorous computation based on extensive sampling, we remain far from accurately predicting and manipulating biomolecular structures and their interactions. There are fundamental limitations, including accuracy of interaction description and difficulty of sampling in high dimensional space, to be tackled. Computational graph underlies major artificial intelligence platforms and is proven to facilitate training, optimization and learning. Combining autodifferentiation, coordinates transformation and generalized solvation free energy theory, we construct a computational graph infrastructure to realize seamless integration of fully trainable local free energy landscape with end to end differentiable iterative free energy optimization. This new framework drastically improves efficiency by replacing local sampling with differentiation. Its specific implementation in protein structure refinement achieves superb efficiency and competitive accuracy when compared with state of the art all-atom mainstream methods. GSFE-refinement is a super efficient protein refinement method that integrates the GSFE theory, coordinates transformation, neural network and auto differentiation, and maps molecular free energy optimization onto a computational graph.
Bibliography:Electronic supplementary information (ESI) available. See DOI
10.1039/d1ra01455b
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2046-2069
2046-2069
DOI:10.1039/d1ra01455b