Predicting Locations of Cryptic Pockets from Single Protein Structures Using the PocketMiner Graph Neural Network

Overview

Journal Nat Commun

Specialty Biology

Date 2023 Mar 1

PMID 36859488

Authors

Artur Meller

Michael Ward

Jonathan Borowsky

Meghana Kshirsagar

Jeffrey M Lotthammer

Felipe Oviedo

Juan Lavista Ferres

Gregory R Bowman

Affiliations

Soon will be listed here.

Abstract

Cryptic pockets expand the scope of drug discovery by enabling targeting of proteins currently considered undruggable because they lack pockets in their ground state structures. However, identifying cryptic pockets is labor-intensive and slow. The ability to accurately and rapidly predict if and where cryptic pockets are likely to form from a structure would greatly accelerate the search for druggable pockets. Here, we present PocketMiner, a graph neural network trained to predict where pockets are likely to open in molecular dynamics simulations. Applying PocketMiner to single structures from a newly curated dataset of 39 experimentally confirmed cryptic pockets demonstrates that it accurately identifies cryptic pockets (ROC-AUC: 0.87) >1,000-fold faster than existing methods. We apply PocketMiner across the human proteome and show that predicted pockets open in simulations, suggesting that over half of proteins thought to lack pockets based on available structures likely contain cryptic pockets, vastly expanding the potentially druggable proteome.

Citing Articles

Revisiting the druggable genome using predicted structures and data mining.

Godinez-Macias K, Chen D, Wallis J, Siegel M, Adam A, Bopp S NPJ Drug Discov. 2025; 2(1):3.

PMID: 40066064 PMC: 11892419. DOI: 10.1038/s44386-025-00006-5.

Decoding allosteric landscapes: computational methodologies for enzyme modulation and drug discovery.

Zhu R, Wu C, Zha J, Lu S, Zhang J RSC Chem Biol. 2025; .

PMID: 39981029 PMC: 11836628. DOI: 10.1039/d4cb00282b.

Scaling Structure Aware Virtual Screening to Billions of Molecules with SPRINT.

McNutt A, Adduri A, Ellington C, Dayao M, Xing E, Mohimani H ArXiv. 2025; .

PMID: 39975427 PMC: 11838698.

Enhanced identification of small molecules binding to hnRNPA1 via cryptic pockets mapping coupled with X-Ray fragment screening.

Dunnett L, Das S, Venditti V, Prischi F bioRxiv. 2025; .

PMID: 39763864 PMC: 11702612. DOI: 10.1101/2024.12.17.628909.

CryptoBench: cryptic protein-ligand binding sites dataset and benchmark.

Skrhak V, Novotny M, Feidakis C, Krivak R, Hoksza D Bioinformatics. 2024; 41(1).

PMID: 39693053 PMC: 11725321. DOI: 10.1093/bioinformatics/btae745.

References

Porter J, Zimmerman M, Bowman G . Enspara: Modeling molecular ensembles with scalable data structures and parallel computing. J Chem Phys. 2019; 150(4):044108. PMC: 6910589. DOI: 10.1063/1.5063794. View

Jin R, Gouaux E . Probing the function, conformational plasticity, and dimer-dimer contacts of the GluR2 ligand-binding core: studies of 5-substituted willardiines and GluR2 S1S2 in the crystal. Biochemistry. 2003; 42(18):5201-13. DOI: 10.1021/bi020632t. View

Vithani N, Ward M, Zimmerman M, Novak B, Borowsky J, Singh S . SARS-CoV-2 Nsp16 activation mechanism and a cryptic pocket with pan-coronavirus antiviral potential. Biophys J. 2021; 120(14):2880-2889. PMC: 8007187. DOI: 10.1016/j.bpj.2021.03.024. View

Sun Z, Wakefield A, Kolossvary I, Beglov D, Vajda S . Structure-Based Analysis of Cryptic-Site Opening. Structure. 2019; 28(2):223-235.e2. PMC: 7004864. DOI: 10.1016/j.str.2019.11.007. View

Pande V, Beauchamp K, Bowman G . Everything you wanted to know about Markov State Models but were afraid to ask. Methods. 2010; 52(1):99-105. PMC: 2933958. DOI: 10.1016/j.ymeth.2010.06.002. View

Lakomek N, Fares C, Becker S, Carlomagno T, Meiler J, Griesinger C . Side-chain orientation and hydrogen-bonding imprint supra-Tau(c) motion on the protein backbone of ubiquitin. Angew Chem Int Ed Engl. 2005; 44(47):7776-8. DOI: 10.1002/anie.200502573. View

Torng W, Altman R . High precision protein functional site detection using 3D convolutional neural networks. Bioinformatics. 2019; 35(9):1503-1512. PMC: 6499237. DOI: 10.1093/bioinformatics/bty813. View

Feenstra K, Hess B, Berendsen H . Improving efficiency of large time-scale molecular dynamics simulations of hydrogen-rich systems. J Comput Chem. 2022; 20(8):786-798. DOI: 10.1002/(SICI)1096-987X(199906)20:8<786::AID-JCC5>3.0.CO;2-B. View

Huang P, Feldmeier K, Parmeggiani F, Fernandez Velasco D, Hocker B, Baker D . De novo design of a four-fold symmetric TIM-barrel protein with atomic-level accuracy. Nat Chem Biol. 2015; 12(1):29-34. PMC: 4684731. DOI: 10.1038/nchembio.1966. View

10.

Schames J, Henchman R, Siegel J, Sotriffer C, Ni H, McCammon J . Discovery of a novel binding trench in HIV integrase. J Med Chem. 2004; 47(8):1879-81. DOI: 10.1021/jm0341913. View

11.

Cock P, Antao T, Chang J, Chapman B, Cox C, Dalke A . Biopython: freely available Python tools for computational molecular biology and bioinformatics. Bioinformatics. 2009; 25(11):1422-3. PMC: 2682512. DOI: 10.1093/bioinformatics/btp163. View

12.

Clore G, Schwieters C . Amplitudes of protein backbone dynamics and correlated motions in a small alpha/beta protein: correspondence of dipolar coupling and heteronuclear relaxation measurements. Biochemistry. 2004; 43(33):10678-91. DOI: 10.1021/bi049357w. View

13.

Torng W, Altman R . 3D deep convolutional neural networks for amino acid environment similarity analysis. BMC Bioinformatics. 2017; 18(1):302. PMC: 5472009. DOI: 10.1186/s12859-017-1702-0. View

14.

Sztain T, Amaro R, McCammon J . Elucidation of Cryptic and Allosteric Pockets within the SARS-CoV-2 Main Protease. J Chem Inf Model. 2021; 61(7):3495-3501. PMC: 8117783. DOI: 10.1021/acs.jcim.1c00140. View

15.

Chen K, Mizianty M, Gao J, Kurgan L . A critical comparative assessment of predictions of protein-binding sites for biologically relevant organic compounds. Structure. 2011; 19(5):613-21. DOI: 10.1016/j.str.2011.02.015. View

16.

Lang J, Vigouroux A, Planamente S, El Sahili A, Blin P, Aumont-Nicaise M . Agrobacterium uses a unique ligand-binding mode for trapping opines and acquiring a competitive advantage in the niche construction on plant host. PLoS Pathog. 2014; 10(10):e1004444. PMC: 4192606. DOI: 10.1371/journal.ppat.1004444. View

17.

Wenthur C, Gentry P, Mathews T, Lindsley C . Drugs for allosteric sites on receptors. Annu Rev Pharmacol Toxicol. 2013; 54:165-84. PMC: 4063350. DOI: 10.1146/annurev-pharmtox-010611-134525. View

18.

Baek M, DiMaio F, Anishchenko I, Dauparas J, Ovchinnikov S, Lee G . Accurate prediction of protein structures and interactions using a three-track neural network. Science. 2021; 373(6557):871-876. PMC: 7612213. DOI: 10.1126/science.abj8754. View

19.

Mirdita M, Schutze K, Moriwaki Y, Heo L, Ovchinnikov S, Steinegger M . ColabFold: making protein folding accessible to all. Nat Methods. 2022; 19(6):679-682. PMC: 9184281. DOI: 10.1038/s41592-022-01488-1. View

20.

Cimermancic P, Weinkam P, Rettenmaier T, Bichmann L, Keedy D, Woldeyes R . CryptoSite: Expanding the Druggable Proteome by Characterization and Prediction of Cryptic Binding Sites. J Mol Biol. 2016; 428(4):709-719. PMC: 4794384. DOI: 10.1016/j.jmb.2016.01.029. View