Molecular Free Energy Optimization on a Computational Graph

Overview

Journal RSC Adv

Publisher Royal Society of Chemistry

Specialty Chemistry

Date 2022 Apr 15

PMID 35423805

Authors

Xiaoyong Cao

Pu Tian

Affiliations

Soon will be listed here.

Abstract

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.

Citing Articles

"Dividing and Conquering" and "Caching" in Molecular Modeling.

Cao X, Tian P Int J Mol Sci. 2021; 22(9).

PMID: 34068835 PMC: 8126232. DOI: 10.3390/ijms22095053.

DeepRefiner: high-accuracy protein structure refinement by deep network calibration.

Shuvo M, Gulfam M, Bhattacharya D Nucleic Acids Res. 2021; 49(W1):W147-W152.

PMID: 33999209 PMC: 8262753. DOI: 10.1093/nar/gkab361.

References

Bhattacharya D . refineD: improved protein structure refinement using machine learning based restrained relaxation. Bioinformatics. 2019; 35(18):3320-3328. DOI: 10.1093/bioinformatics/btz101. View

Cao X, Tian P . "Dividing and Conquering" and "Caching" in Molecular Modeling. Int J Mol Sci. 2021; 22(9). PMC: 8126232. DOI: 10.3390/ijms22095053. View

Qian B, Raman S, Das R, Bradley P, McCoy A, Read R . High-resolution structure prediction and the crystallographic phase problem. Nature. 2007; 450(7167):259-64. PMC: 2504711. DOI: 10.1038/nature06249. View

Deng H, Jia Y, Zhang Y . 3DRobot: automated generation of diverse and well-packed protein structure decoys. Bioinformatics. 2015; 32(3):378-87. PMC: 5006309. DOI: 10.1093/bioinformatics/btv601. View

Davis I, Arendall 3rd W, Richardson D, Richardson J . The backrub motion: how protein backbone shrugs when a sidechain dances. Structure. 2006; 14(2):265-74. DOI: 10.1016/j.str.2005.10.007. View

Zhang J, Zhang Y . A novel side-chain orientation dependent potential derived from random-walk reference state for protein fold selection and structure prediction. PLoS One. 2010; 5(10):e15386. PMC: 2965178. DOI: 10.1371/journal.pone.0015386. View

Adiyaman R, McGuffin L . Methods for the Refinement of Protein Structure 3D Models. Int J Mol Sci. 2019; 20(9). PMC: 6539982. DOI: 10.3390/ijms20092301. View

Feig M . Computational protein structure refinement: Almost there, yet still so far to go. Wiley Interdiscip Rev Comput Mol Sci. 2019; 7(3). PMC: 6319934. DOI: 10.1002/wcms.1307. View

Leman J, Weitzner B, Lewis S, Adolf-Bryfogle J, Alam N, Alford R . Macromolecular modeling and design in Rosetta: recent methods and frameworks. Nat Methods. 2020; 17(7):665-680. PMC: 7603796. DOI: 10.1038/s41592-020-0848-2. View

10.

Uziela K, Menendez Hurtado D, Shu N, Wallner B, Elofsson A . ProQ3D: improved model quality assessments using deep learning. Bioinformatics. 2017; 33(10):1578-1580. DOI: 10.1093/bioinformatics/btw819. View

11.

Vanommeslaeghe K, Hatcher E, Acharya C, Kundu S, Zhong S, Shim J . CHARMM general force field: A force field for drug-like molecules compatible with the CHARMM all-atom additive biological force fields. J Comput Chem. 2009; 31(4):671-90. PMC: 2888302. DOI: 10.1002/jcc.21367. View

12.

Nymeyer H, Garcia A, Onuchic J . Folding funnels and frustration in off-lattice minimalist protein landscapes. Proc Natl Acad Sci U S A. 1998; 95(11):5921-8. PMC: 34496. DOI: 10.1073/pnas.95.11.5921. View

13.

Long S, Tian P . A simple neural network implementation of generalized solvation free energy for assessment of protein structural models. RSC Adv. 2022; 9(62):36227-36233. PMC: 9074945. DOI: 10.1039/c9ra05168f. View

14.

Roy A, Kucukural A, Zhang Y . I-TASSER: a unified platform for automated protein structure and function prediction. Nat Protoc. 2010; 5(4):725-38. PMC: 2849174. DOI: 10.1038/nprot.2010.5. View

15.

Khatib F, Cooper S, Tyka M, Xu K, Makedon I, Popovic Z . Algorithm discovery by protein folding game players. Proc Natl Acad Sci U S A. 2011; 108(47):18949-53. PMC: 3223433. DOI: 10.1073/pnas.1115898108. View

16.

Zemla A . LGA: A method for finding 3D similarities in protein structures. Nucleic Acids Res. 2003; 31(13):3370-4. PMC: 168977. DOI: 10.1093/nar/gkg571. View

17.

Shaw D, Maragakis P, Lindorff-Larsen K, Piana S, Dror R, Eastwood M . Atomic-level characterization of the structural dynamics of proteins. Science. 2010; 330(6002):341-6. DOI: 10.1126/science.1187409. View

18.

Gkeka P, Stoltz G, Barati Farimani A, Belkacemi Z, Ceriotti M, Chodera J . Machine Learning Force Fields and Coarse-Grained Variables in Molecular Dynamics: Application to Materials and Biological Systems. J Chem Theory Comput. 2020; 16(8):4757-4775. PMC: 8312194. DOI: 10.1021/acs.jctc.0c00355. View

19.

Nugent T, Cozzetto D, Jones D . Evaluation of predictions in the CASP10 model refinement category. Proteins. 2013; 82 Suppl 2:98-111. PMC: 4282348. DOI: 10.1002/prot.24377. View

20.

Alford R, Leaver-Fay A, Jeliazkov J, OMeara M, DiMaio F, Park H . The Rosetta All-Atom Energy Function for Macromolecular Modeling and Design. J Chem Theory Comput. 2017; 13(6):3031-3048. PMC: 5717763. DOI: 10.1021/acs.jctc.7b00125. View