{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T01:39:48Z","timestamp":1777426788734,"version":"3.51.4"},"reference-count":49,"publisher":"Oxford University Press (OUP)","issue":"17","license":[{"start":{"date-parts":[[2016,11,10]],"date-time":"2016-11-10T00:00:00Z","timestamp":1478736000000},"content-version":"vor","delay-in-days":73,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-11-MONU-006"],"award-info":[{"award-number":["ANR-11-MONU-006"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Motivation<\/jats:title><jats:p>Docking prediction algorithms aim to find the native conformation of a complex of proteins from knowledge of their unbound structures. They rely on a combination of sampling and scoring methods, adapted to different scales. Polynomial Expansion of Protein Structures and Interactions for Docking (PEPSI-Dock) improves the accuracy of the first stage of the docking pipeline, which will sharpen up the final predictions. Indeed, PEPSI-Dock benefits from the precision of a very detailed data-driven model of the binding free energy used with a global and exhaustive rigid-body search space. As well as being accurate, our computations are among the fastest by virtue of the sparse representation of the pre-computed potentials and FFT-accelerated sampling techniques. Overall, this is the first demonstration of a FFT-accelerated docking method coupled with an arbitrary-shaped distance-dependent interaction potential.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>First, we present a novel learning process to compute data-driven distant-dependent pairwise potentials, adapted from our previous method used for rescoring of putative protein\u2013protein binding poses. The potential coefficients are learned by combining machine-learning techniques with physically interpretable descriptors. Then, we describe the integration of the deduced potentials into a FFT-accelerated spherical sampling provided by the Hex library. Overall, on a training set of 163 heterodimers, PEPSI-Dock achieves a success rate of 91% mid-quality predictions in the top-10 solutions. On a subset of the protein docking benchmark v5, it achieves 44.4% mid-quality predictions in the top-10 solutions when starting from bound structures and 20.5% when starting from unbound structures. The method runs in 5\u201315\u2009min on a modern laptop and can easily be extended to other types of interactions.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availability and Implementation<\/jats:title><jats:p>https:\/\/team.inria.fr\/nano-d\/software\/PEPSI-Dock.<\/jats:p><\/jats:sec><jats:sec><jats:title>Contact<\/jats:title><jats:p>sergei.grudinin@inria.fr<\/jats:p><\/jats:sec>","DOI":"10.1093\/bioinformatics\/btw443","type":"journal-article","created":{"date-parts":[[2016,9,1]],"date-time":"2016-09-01T07:53:39Z","timestamp":1472716419000},"page":"i693-i701","source":"Crossref","is-referenced-by-count":17,"title":["PEPSI-Dock: a detailed data-driven protein\u2013protein interaction potential accelerated by polar Fourier correlation"],"prefix":"10.1093","volume":"32","author":[{"given":"Emilie","family":"Neveu","sequence":"first","affiliation":[{"name":"Inria\/University Grenoble Alpes\/LJK-CNRS, F-38000 Grenoble, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David W","family":"Ritchie","sequence":"additional","affiliation":[{"name":"Inria Nancy \u2013 Grand Est, 54600 Villers-les-Nancy, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Petr","family":"Popov","sequence":"additional","affiliation":[{"name":"Inria\/University Grenoble Alpes\/LJK-CNRS, F-38000 Grenoble, France"},{"name":"Moscow Institute of Physics and Technology, Dolgoprudniy, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergei","family":"Grudinin","sequence":"additional","affiliation":[{"name":"Inria\/University Grenoble Alpes\/LJK-CNRS, F-38000 Grenoble, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2016,8,29]]},"reference":[{"key":"2023020113324964500_btw443-B1","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1093\/nar\/28.1.235","article-title":"The protein data bank","volume":"28","author":"Berman","year":"2000","journal-title":"Nucleic Acids Res"},{"key":"2023020113324964500_btw443-B2","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1007\/BF00126743","article-title":"The development of a simple empirical scoring function to estimate the binding constant for a protein-ligand complex of known three-dimensional structure","volume":"8","author":"B\u00f6hm","year":"1994","journal-title":"J. Comput. Aided Mol. Des"},{"key":"2023020113324964500_btw443-B3","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1016\/j.sbi.2006.02.002","article-title":"Flexible protein\u2013protein docking","volume":"16","author":"Bonvin","year":"2006","journal-title":"Curr. Opin. Struct. Biol"},{"key":"2023020113324964500_btw443-B4","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511804441","volume-title":"Convex Optimization","author":"Boyd","year":"2004"},{"key":"2023020113324964500_btw443-B5","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1002\/jcc.540040211","article-title":"Charmm: A program for macromolecular energy, minimization, and dynamics calculations","volume":"4","author":"Brooks","year":"1983","journal-title":"J. Comput. Chem"},{"key":"2023020113324964500_btw443-B6","doi-asserted-by":"crossref","first-page":"1668","DOI":"10.1002\/jcc.20290","article-title":"The amber biomolecular simulation programs","volume":"26","author":"Case","year":"2005","journal-title":"J. Comput. Chem"},{"key":"2023020113324964500_btw443-B7","doi-asserted-by":"crossref","first-page":"1026","DOI":"10.1002\/prot.22626","article-title":"Predicting protein complex geometries with a neural network","volume":"78","author":"Chae","year":"2010","journal-title":"Proteins Struct. Funct. Bioinf"},{"key":"2023020113324964500_btw443-B8","doi-asserted-by":"crossref","first-page":"3137","DOI":"10.1021\/ci5004152","article-title":"Toward on-the-fly quantum mechanical\/molecular mechanical (qm\/mm) docking: Development and benchmark of a scoring function","volume":"54","author":"Chaskar","year":"2014","journal-title":"J. Chem. Inf. Model"},{"key":"2023020113324964500_btw443-B9","doi-asserted-by":"crossref","first-page":"4217","DOI":"10.1529\/biophysj.108.135814","article-title":"Dars (decoys as the reference state) potentials for protein\u2013protein docking","volume":"95","author":"Chuang","year":"2008","journal-title":"Biophys. J"},{"key":"2023020113324964500_btw443-B10","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1023\/A:1007996124545","article-title":"Empirical scoring functions: I. the development of a fast empirical scoring function to estimate the binding affinity of ligands in receptor complexes","volume":"11","author":"Eldridge","year":"1997","journal-title":"J. Comput. Aided Mol. Des"},{"key":"2023020113324964500_btw443-B11","doi-asserted-by":"crossref","first-page":"1739","DOI":"10.1021\/jm0306430","article-title":"Glide: a new approach for rapid, accurate docking and scoring. 1. Method and assessment of docking accuracy","volume":"47","author":"Friesner","year":"2004","journal-title":"J. Med. Chem"},{"key":"2023020113324964500_btw443-B12","doi-asserted-by":"crossref","first-page":"2807","DOI":"10.1021\/ci500406k","article-title":"Beware of machine learning-based scoring functions\u2014on the danger of developing black boxes","volume":"54","author":"Gabel","year":"2014","journal-title":"J. Chem. Inf. Model"},{"key":"2023020113324964500_btw443-B13","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1006\/jmbi.1999.3371","article-title":"Knowledge-based scoring function to predict protein-ligand interactions","volume":"295","author":"Gohlke","year":"2000","journal-title":"J. Mol. Biol"},{"key":"2023020113324964500_btw443-B14","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1016\/S0022-2836(03)00670-3","article-title":"Protein\u2013protein docking with simultaneous optimization of rigid-body displacement and side-chain conformations","volume":"331","author":"Gray","year":"2003","journal-title":"J. Mol. Biol"},{"key":"2023020113324964500_btw443-B15","article-title":"Predicting binding poses and affinities in the CSAR 2013-2014 docking exercises using the knowledge-based Convex-PL potential","author":"Grudinin","year":"2015","journal-title":"J. Chem. Inf. Model"},{"key":"2023020113324964500_btw443-B16","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1021\/ct700301q","article-title":"Gromacs 4: algorithms for highly efficient, load-balanced, and scalable molecular simulation","volume":"4","author":"Hess","year":"2008","journal-title":"J. Chem. Theory Comput"},{"key":"2023020113324964500_btw443-B17","year":"2012"},{"key":"2023020113324964500_btw443-B18","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1002\/prot.21949","article-title":"An iterative knowledge-based scoring function for protein\u2013protein recognition","volume":"72","author":"Huang","year":"2008","journal-title":"Proteins Struct. Funct. Bioinf"},{"key":"2023020113324964500_btw443-B19","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1021\/ci9002987","article-title":"Inclusion of solvation and entropy in the knowledge\u2013based scoring function for protein\u2013ligand interactions","volume":"50","author":"Huang","year":"2010","journal-title":"J. Chem. Inf. Model"},{"key":"2023020113324964500_btw443-B20","doi-asserted-by":"crossref","first-page":"2097","DOI":"10.1021\/ci2000727","article-title":"Scoring and lessons learned with the CSAR benchmark using an improved iterative knowledge-based scoring function","volume":"51","author":"Huang","year":"2011","journal-title":"J. Chem. Inf. Model"},{"key":"2023020113324964500_btw443-B21","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1110\/ps.041081905","article-title":"Assessing predictions of protein\u2013protein interaction: the CAPRI experiment","volume":"14","author":"Janin","year":"2005","journal-title":"Protein Sci"},{"key":"2023020113324964500_btw443-B22","doi-asserted-by":"crossref","first-page":"2195","DOI":"10.1073\/pnas.89.6.2195","article-title":"Molecular surface recognition: determination of geometric fit between proteins and their ligands by correlation techniques","volume":"89","author":"Katchalski-Katzir","year":"1992","journal-title":"Proc. Natl. Acad. Sci. U. S. A"},{"key":"2023020113324964500_btw443-B23","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1021\/ci100369f","article-title":"A machine learning-based method to improve docking scoring functions and its application to drug repurposing","volume":"51","author":"Kinnings","year":"2011","journal-title":"J. Chem. Inf. Model"},{"key":"2023020113324964500_btw443-B24","first-page":"247","article-title":"Knowledge-based potentials \u2013 back to the roots","volume":"63","author":"Koppensteiner","year":"1998","journal-title":"Biochemistry"},{"key":"2023020113324964500_btw443-B25","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1021\/ci800298z","article-title":"Empirical scoring functions for advanced protein\u2013ligand docking with plants","volume":"49","author":"Korb","year":"2009","journal-title":"J. Chem. Inf. Model"},{"key":"2023020113324964500_btw443-B26","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1002\/prot.21117","article-title":"Piper: an FFT-based protein docking program with pairwise potentials","volume":"65","author":"Kozakov","year":"2006","journal-title":"Proteins Struct. Funct. Bioinf"},{"key":"2023020113324964500_btw443-B27","doi-asserted-by":"crossref","first-page":"4040","DOI":"10.1021\/jm049081q","article-title":"Validation and use of the MM-PBSA approach for drug discovery","volume":"48","author":"Kuhn","year":"2005","journal-title":"J. Med. Chem"},{"key":"2023020113324964500_btw443-B28","doi-asserted-by":"crossref","DOI":"10.1002\/prot.25007","article-title":"Prediction of homo- and hetero-protein complexes by ab-initio and template-based docking: a CASP-CAPRI experiment","author":"Lensink","year":"2016","journal-title":"Proteins Struct. Funct. Bioinf"},{"key":"2023020113324964500_btw443-B29","doi-asserted-by":"crossref","first-page":"592","DOI":"10.1021\/ci300493w","article-title":"ID-Score: a new empirical scoring function based on a comprehensive set of descriptors related to protein\u2013ligand interactions","volume":"53","author":"Li","year":"2013","journal-title":"J. Chem. Inf. Model"},{"key":"2023020113324964500_btw443-B30","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1021\/ci500731a","article-title":"Classification of current scoring functions","volume":"55","author":"Liu","year":"2015","journal-title":"J. Chem. Inf. Model"},{"key":"2023020113324964500_btw443-B31","doi-asserted-by":"crossref","first-page":"876","DOI":"10.1016\/0022-2836(92)90228-C","article-title":"Contact potential that recognizes the correct folding of globular proteins","volume":"227","author":"Maiorov","year":"1992","journal-title":"J. Mol. Biol"},{"key":"2023020113324964500_btw443-B32","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1002\/prot.10393","article-title":"Assessment of blind predictions of protein\u2013protein interactions: current status of docking methods","volume":"52","author":"M\u00e9ndez","year":"2003","journal-title":"Proteins Struct. Funct. Genet"},{"key":"2023020113324964500_btw443-B33","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1002\/prot.20588","article-title":"General and targeted statistical potentials for protein\u2013ligand interactions","volume":"61","author":"Mooij","year":"2005","journal-title":"Proteins Struct. Funct. Bioinf"},{"key":"2023020113324964500_btw443-B34","doi-asserted-by":"crossref","first-page":"791","DOI":"10.1021\/jm980536j","article-title":"A general and fast scoring function for protein\u2013ligand interactions: a simplified potential approach","volume":"42","author":"Muegge","year":"1999","journal-title":"J. Med. Chem"},{"key":"2023020113324964500_btw443-B35","volume-title":"Numerical Optimization. Springer Series in Operations Research and Financial Engineering","author":"Nocedal","year":"2000"},{"key":"2023020113324964500_btw443-B36","doi-asserted-by":"crossref","first-page":"950","DOI":"10.1002\/jcc.23569","article-title":"Rapid determination of RMSDs corresponding to macromolecular rigid body motions","volume":"35","author":"Popov","year":"2014","journal-title":"J. Comput. Chem"},{"key":"2023020113324964500_btw443-B37","doi-asserted-by":"crossref","first-page":"2242","DOI":"10.1021\/acs.jcim.5b00372","article-title":"Knowledge of native protein\u2013protein interfaces is sufficient to construct predictive models for the selection of binding candidates","volume":"55","author":"Popov","year":"2015","journal-title":"J. Chem. Inf. Model"},{"key":"2023020113324964500_btw443-B38","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1002\/prot.20585","article-title":"Atomically detailed potentials to recognize native and approximate protein structures","volume":"61","author":"Qiu","year":"2005","journal-title":"Proteins Struct. Funct. Bioinf"},{"key":"2023020113324964500_btw443-B39","doi-asserted-by":"crossref","first-page":"808","DOI":"10.1107\/S002188980502474X","article-title":"High-order analytic translation matrix elements for real-space six-dimensional polar Fourier correlations","volume":"38","author":"Ritchie","year":"2005","journal-title":"J. Appl. Crystallogr"},{"key":"2023020113324964500_btw443-B40","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1002\/(SICI)1097-0134(20000501)39:2<178::AID-PROT8>3.0.CO;2-6","article-title":"Protein docking using spherical polar Fourier correlations","volume":"39","author":"Ritchie","year":"2000","journal-title":"Proteins Struct. Funct. Genet"},{"key":"2023020113324964500_btw443-B41","doi-asserted-by":"crossref","first-page":"2398","DOI":"10.1093\/bioinformatics\/btq444","article-title":"Ultra-fast FFT protein docking on graphics processors","volume":"26","author":"Ritchie","year":"2010","journal-title":"Bioinformatics"},{"key":"2023020113324964500_btw443-B42","doi-asserted-by":"crossref","first-page":"1865","DOI":"10.1093\/bioinformatics\/btn334","article-title":"Accelerating and focusing protein\u2013protein docking correlations using multi-dimensional rotational FFT generating functions","volume":"24","author":"Ritchie","year":"2008","journal-title":"Bioinformatics"},{"key":"2023020113324964500_btw443-B43","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/4175.001.0001","volume-title":"Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond","author":"Scholkopf","year":"2001"},{"key":"2023020113324964500_btw443-B44","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1002\/prot.20859","article-title":"Optimal design of protein docking potentials: efficiency and limitations","volume":"62","author":"Tobi","year":"2006","journal-title":"Proteins Struct. Funct. Bioinf"},{"key":"2023020113324964500_btw443-B45","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1093\/bioinformatics\/btt038","article-title":"Swarmdock: a server for flexible protein\u2013protein docking","volume":"29","author":"Torchala","year":"2013","journal-title":"Bioinformatics"},{"key":"2023020113324964500_btw443-B46","doi-asserted-by":"crossref","first-page":"3031","DOI":"10.1016\/j.jmb.2015.07.016","article-title":"Updates to the integrated protein\u2013protein interaction benchmarks: Docking benchmark version 5 and affinity benchmark version 2","volume":"427","author":"Vreven","year":"2015","journal-title":"Journal of molecular biology"},{"key":"2023020113324964500_btw443-B47","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1023\/A:1016357811882","article-title":"Further development and validation of empirical scoring functions for structure-based binding affinity prediction","volume":"16","author":"Wang","year":"2002","journal-title":"J. Comput. Aided Mol. Des"},{"key":"2023020113324964500_btw443-B48","doi-asserted-by":"crossref","first-page":"2043","DOI":"10.1016\/j.bpj.2011.09.012","article-title":"Goap: a generalized orientation-dependent, all-atom statistical potential for protein structure prediction","volume":"101","author":"Zhou","year":"2011","journal-title":"Biophys. J"},{"key":"2023020113324964500_btw443-B49","doi-asserted-by":"crossref","first-page":"1923","DOI":"10.1021\/ci400120b","article-title":"SFCscoreRF: a random forest-based scoring function for improved affinity prediction of protein\u2013ligand complexes","volume":"53","author":"Zilian","year":"2013","journal-title":"J. Chem. Inf. Model"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/32\/17\/i693\/49024276\/bioinformatics_32_17_i693.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/32\/17\/i693\/49024276\/bioinformatics_32_17_i693.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T15:55:53Z","timestamp":1749570953000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/32\/17\/i693\/2450773"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,8,29]]},"references-count":49,"journal-issue":{"issue":"17","published-print":{"date-parts":[[2016,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btw443","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2016,9,1]]},"published":{"date-parts":[[2016,8,29]]}}}