{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T09:04:23Z","timestamp":1778058263544,"version":"3.51.4"},"reference-count":51,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2021,5,20]],"date-time":"2021-05-20T00:00:00Z","timestamp":1621468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100005319","name":"Academy of Natural Sciences","doi-asserted-by":"publisher","award":["KJ2019A0502"],"award-info":[{"award-number":["KJ2019A0502"]}],"id":[{"id":"10.13039\/100005319","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100005319","name":"Academy of Natural Sciences","doi-asserted-by":"publisher","award":["KJ2018ZD034"],"award-info":[{"award-number":["KJ2018ZD034"]}],"id":[{"id":"10.13039\/100005319","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018526","name":"Key Research and Development Program of Wuhu","doi-asserted-by":"publisher","award":["2019YF07"],"award-info":[{"award-number":["2019YF07"]}],"id":[{"id":"10.13039\/501100018526","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["18030901093"],"award-info":[{"award-number":["18030901093"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004921","name":"Shanghai Jiao Tong University","doi-asserted-by":"publisher","award":["2020 SJTU-HUJI"],"award-info":[{"award-number":["2020 SJTU-HUJI"]}],"id":[{"id":"10.13039\/501100004921","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["21901157"],"award-info":[{"award-number":["21901157"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,11,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Full-quantum mechanics (QM) calculations are extraordinarily precise but difficult to apply to large systems, such as biomolecules. Motivated by the massive demand for efficient calculations for large systems at the full-QM level and by the significant advances in machine learning, we have designed a neural network-based two-body molecular fractionation with conjugate caps (NN-TMFCC) approach to accelerate the energy and atomic force calculations of proteins. The results show very high precision for the proposed NN potential energy surface models of residue-based fragments, with energy root-mean-squared errors (RMSEs) less than 1.0\u00a0kcal\/mol and force RMSEs less than 1.3\u00a0kcal\/mol\/\u00c5 for both training and testing sets. The proposed NN-TMFCC method calculates the energies and atomic forces of 15 representative proteins with full-QM precision in 10\u2013100\u00a0s, which is thousands of times faster than the full-QM calculations. The computational complexity of the NN-TMFCC method is independent of the protein size and only depends on the number of residue species, which makes this method particularly suitable for rapid prediction of large systems with tens of thousands or even hundreds of thousands of times acceleration. This highly precise and efficient NN-TMFCC approach exhibits considerable potential for performing energy and force calculations, structure predictions and molecular dynamics simulations of proteins with full-QM precision.<\/jats:p>","DOI":"10.1093\/bib\/bbab158","type":"journal-article","created":{"date-parts":[[2021,4,5]],"date-time":"2021-04-05T11:08:18Z","timestamp":1617620898000},"source":"Crossref","is-referenced-by-count":19,"title":["Machine learning builds full-QM precision protein force fields in seconds"],"prefix":"10.1093","volume":"22","author":[{"given":"Yanqiang","family":"Han","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhilong","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyun","family":"Wei","sequence":"additional","affiliation":[{"name":"Shanghai First Maternity and Infant Hospital, Tongji University School of Medicine, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinyun","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Functional Molecular Solids of Ministry of Education, Anhui Normal University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinjin","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory for Thin Film and Microfabrication of Ministry of Education, Department of Micro\/Nano Electronics, Shanghai Jiao Tong University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2021,5,20]]},"reference":[{"key":"2021110814303430900_ref1","volume-title":"Modern Quantum Chemistry: Introduction to Advanced Electronic Structure Theory","author":"Szabo","year":"2012"},{"issue":"1","key":"2021110814303430900_ref2","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1038\/s41535-019-0149-0","article-title":"Predicting the phase diagram of solid carbon dioxide at high pressure from first principles","volume":"4","author":"Han","year":"2019","journal-title":"Npj Quantum Mater"},{"issue":"23","key":"2021110814303430900_ref3","doi-asserted-by":"crossref","first-page":"e26397","DOI":"10.1002\/qua.26397","article-title":"Molecular structure determination of solid carbon dioxide phase IV at high pressures and temperatures based on M\u00f8ller-Plesset perturbation theory","volume":"120","author":"Han","year":"2020","journal-title":"Int J Quantum Chem"},{"issue":"1","key":"2021110814303430900_ref4","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1021\/acs.jpclett.0c03101","article-title":"Neural networks accelerate the ab initio prediction of solid\u2013solid phase transitions at high pressures","volume":"12","author":"Han","year":"2021","journal-title":"J Phys Chem Lett"},{"issue":"1","key":"2021110814303430900_ref5","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1038\/ncomms3647","article-title":"A solid-solid phase transition in carbon dioxide at high pressures and intermediate temperatures","volume":"4","author":"Li","year":"2013","journal-title":"Nat Commun"},{"issue":"9","key":"2021110814303430900_ref6","doi-asserted-by":"crossref","first-page":"5520","DOI":"10.1021\/acs.chemrev.5b00630","article-title":"Ligand-binding affinity estimates supported by quantum-mechanical methods","volume":"116","author":"Ryde","year":"2016","journal-title":"Chem Rev"},{"issue":"7","key":"2021110814303430900_ref7","doi-asserted-by":"crossref","first-page":"3601","DOI":"10.1021\/cr400388t","article-title":"Quantum chemical studies of mechanisms for metalloenzymes","volume":"114","author":"Blomberg","year":"2014","journal-title":"Chem Rev"},{"issue":"7","key":"2021110814303430900_ref8","doi-asserted-by":"crossref","first-page":"1198","DOI":"10.1002\/anie.200802019","article-title":"MM methods for biomolecular systems","volume":"48","author":"Senn","year":"2009","journal-title":"Angew Chem-Int Ed"},{"issue":"13","key":"2021110814303430900_ref9","doi-asserted-by":"crossref","first-page":"138302","DOI":"10.1103\/PhysRevLett.94.138302","article-title":"Quantum mechanical free energy barrier for an enzymatic reaction","volume":"94","author":"Rod","year":"2005","journal-title":"Phys Rev Lett"},{"issue":"13","key":"2021110814303430900_ref10","doi-asserted-by":"crossref","first-page":"7501","DOI":"10.1021\/acs.chemrev.5b00644","article-title":"Modeling molecular interactions in water: from pairwise to many body potential energy functions","volume":"116","author":"Cisneros","year":"2016","journal-title":"Chem Rev"},{"issue":"9","key":"2021110814303430900_ref11","doi-asserted-by":"crossref","first-page":"2748","DOI":"10.1021\/ar500077t","article-title":"Fragment quantum mechanical calculation of proteins and its applications","volume":"47","author":"He","year":"2014","journal-title":"Acc Chem Res"},{"issue":"42","key":"2021110814303430900_ref12","doi-asserted-by":"crossref","first-page":"10405","DOI":"10.1021\/ja000921+","article-title":"Evidence for intramolecular N-H Center dot center dot center dot O resonance-assisted hydrogen bonding in beta-enaminones and related heterodienes. A combined crystal-structural, IR and NMR spectroscopic, and quantum-mechanical investigation","volume":"122","author":"Gilli","year":"2000","journal-title":"J Am Chem Soc"},{"issue":"19","key":"2021110814303430900_ref13","doi-asserted-by":"crossref","first-page":"2898","DOI":"10.1103\/PhysRevLett.68.2898","article-title":"Fragment formation studied with antisymmetrized version of molecular-dynamics with 2-nucleon collisions","volume":"68","author":"Ono","year":"1992","journal-title":"Phys Rev Lett"},{"issue":"3","key":"2021110814303430900_ref14","doi-asserted-by":"crossref","first-page":"1381","DOI":"10.1021\/ct300845q","article-title":"Electrostatically embedded molecular tailoring approach and validation for peptides","volume":"9","author":"Isegawa","year":"2013","journal-title":"J Chem Theory Comput"},{"issue":"39","key":"2021110814303430900_ref15","doi-asserted-by":"crossref","first-page":"22190","DOI":"10.1039\/D0CP04432F","article-title":"Molecular tailoring approach\u2014a new guide to quantify the energy of push-pull effects: a case study on (E)-3-(1H-pyrrol-2-Yl)prop-2-enones","volume":"22","author":"Afonin","year":"2020","journal-title":"Phys Chem Chem Phys"},{"issue":"10","key":"2021110814303430900_ref16","doi-asserted-by":"crossref","first-page":"104104","DOI":"10.1063\/1.2347710","article-title":"Accuracy and efficiency of electronic energies from systematic molecular fragmentation","volume":"125","author":"Collins","year":"2006","journal-title":"J Chem Phys"},{"issue":"1","key":"2021110814303430900_ref17","doi-asserted-by":"crossref","first-page":"632","DOI":"10.1021\/cr200093j","article-title":"Fragmentation methods: a route to accurate calculations on large systems","volume":"112","author":"Gordon","year":"2012","journal-title":"Chem Rev"},{"issue":"1","key":"2021110814303430900_ref18","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1021\/acs.accounts.0c00580","article-title":"Structures and spectroscopic properties of large molecules and condensed-phase systems predicted by generalized energy-based fragmentation approach","volume":"54","author":"Li","year":"2021","journal-title":"Acc Chem Res"},{"issue":"9","key":"2021110814303430900_ref19","doi-asserted-by":"crossref","first-page":"2712","DOI":"10.1021\/ar500038z","article-title":"Generalized energy-based fragmentation approach and its applications to macromolecules and molecular aggregates","volume":"47","author":"Li","year":"2014","journal-title":"Acc Chem Res"},{"issue":"6","key":"2021110814303430900_ref20","doi-asserted-by":"crossref","first-page":"1890","DOI":"10.1021\/ct700167b","article-title":"Design of a next generation force field: the X-POL potential","volume":"3","author":"Xie","year":"2007","journal-title":"J Chem Theory Comput"},{"issue":"14","key":"2021110814303430900_ref21","doi-asserted-by":"crossref","first-page":"5137","DOI":"10.1021\/ja909575j","article-title":"Electrostatic polarization makes a substantial contribution to the free energy of avidin-biotin binding","volume":"132","author":"Tong","year":"2010","journal-title":"J Am Chem Soc"},{"issue":"36","key":"2021110814303430900_ref22","doi-asserted-by":"crossref","first-page":"12690","DOI":"10.1073\/pnas.0506378102","article-title":"Kernel energy method: application to insulin","volume":"102","author":"Huang","year":"2005","journal-title":"Proc Natl Acad Sci"},{"issue":"2","key":"2021110814303430900_ref23","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1021\/ct200783n","article-title":"Combined fragmentation method: a simple method for fragmentation of large molecules","volume":"8","author":"Le","year":"2012","journal-title":"J Chem Theory Comput"},{"issue":"7","key":"2021110814303430900_ref24","doi-asserted-by":"crossref","first-page":"3599","DOI":"10.1063\/1.1591727","article-title":"Molecular fractionation with conjugate caps for full quantum mechanical calculation of protein\u2013molecule interaction energy","volume":"119","author":"Zhang","year":"2003","journal-title":"J Chem Phys"},{"issue":"19","key":"2021110814303430900_ref25","doi-asserted-by":"crossref","first-page":"7215","DOI":"10.1021\/ja0427247","article-title":"An efficient fragment-based approach for predicting the ground-state energies and structures of large molecules","volume":"127","author":"Li","year":"2005","journal-title":"J Am Chem Soc"},{"issue":"1","key":"2021110814303430900_ref26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1021\/ct700223r","article-title":"Electrostatically embedded many-body expansion for simulations","volume":"4","author":"Dahlke","year":"2008","journal-title":"J Chem Theory Comput"},{"issue":"30","key":"2021110814303430900_ref27","doi-asserted-by":"crossref","first-page":"6904","DOI":"10.1021\/jp0716740","article-title":"Extending the power of quantum chemistry to large systems with the fragment molecular orbital method","volume":"111","author":"Fedorov","year":"2007","journal-title":"J Phys Chem A"},{"issue":"28","key":"2021110814303430900_ref28","doi-asserted-by":"crossref","first-page":"11550","DOI":"10.1002\/anie.202003326","article-title":"Quantitative prediction of aggregation-induced emission: a full quantum mechanical approach to the optical spectra","volume":"59","author":"Zhang","year":"2020","journal-title":"Angew Chem Int Ed"},{"issue":"3","key":"2021110814303430900_ref29","doi-asserted-by":"crossref","first-page":"1864","DOI":"10.1039\/C5CP05693D","article-title":"Fragment quantum chemical approach to geometry optimization and vibrational spectrum calculation of proteins","volume":"18","author":"Liu","year":"2016","journal-title":"Phys Chem Chem Phys"},{"issue":"7715","key":"2021110814303430900_ref30","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1038\/s41586-018-0337-2","article-title":"Machine learning for molecular and materials science","volume":"559","author":"Butler","year":"2018","journal-title":"Nature"},{"issue":"7","key":"2021110814303430900_ref31","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1016\/j.chempr.2020.05.014","article-title":"Learning to make chemical predictions: the interplay of feature representation, data, and machine learning methods","volume":"6","author":"Haghighatlari","year":"2020","journal-title":"Chem"},{"issue":"32","key":"2021110814303430900_ref32","doi-asserted-by":"crossref","first-page":"10158","DOI":"10.1021\/jacs.8b03913","article-title":"Crystal structure prediction via deep learning","volume":"140","author":"Ryan","year":"2018","journal-title":"J Am Chem Soc"},{"issue":"7","key":"2021110814303430900_ref33","doi-asserted-by":"crossref","first-page":"1521","DOI":"10.1021\/jm9507035","article-title":"Evolutionary optimization in quantitative structure\u2212 activity relationship: an application of genetic neural networks","volume":"39","author":"So","year":"1996","journal-title":"J Med Chem"},{"issue":"10","key":"2021110814303430900_ref34","doi-asserted-by":"crossref","first-page":"4129","DOI":"10.1063\/1.469597","article-title":"Neural network models of potential energy surfaces","volume":"103","author":"Blank","year":"1995","journal-title":"J Chem Phys"},{"issue":"14","key":"2021110814303430900_ref35","doi-asserted-by":"crossref","first-page":"146401","DOI":"10.1103\/PhysRevLett.98.146401","article-title":"Generalized neural-network representation of high-dimensional potential-energy surfaces","volume":"98","author":"Behler","year":"2007","journal-title":"Phys Rev Lett"},{"issue":"4","key":"2021110814303430900_ref36","doi-asserted-by":"crossref","first-page":"3192","DOI":"10.1039\/C6SC05720A","article-title":"ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost","volume":"8","author":"Smith","year":"2017","journal-title":"Chem Sci"},{"issue":"1","key":"2021110814303430900_ref37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-019-10827-4","article-title":"Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning","volume":"10","author":"Smith","year":"2019","journal-title":"Nat Commun"},{"issue":"8","key":"2021110814303430900_ref38","doi-asserted-by":"crossref","first-page":"2261","DOI":"10.1039\/C7SC04934J","article-title":"The TensorMol-0.1 model chemistry: a neural network augmented with long-range physics","volume":"9","author":"Yao","year":"2018","journal-title":"Chem Sci"},{"issue":"13","key":"2021110814303430900_ref39","doi-asserted-by":"crossref","first-page":"136403","DOI":"10.1103\/PhysRevLett.104.136403","article-title":"Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons","volume":"104","author":"Bart\u00f3k","year":"2010","journal-title":"Phys Rev Lett"},{"issue":"12","key":"2021110814303430900_ref40","doi-asserted-by":"crossref","first-page":"2326","DOI":"10.1021\/acs.jpclett.5b00831","article-title":"Machine learning predictions of molecular properties: accurate many-body potentials and nonlocality in chemical space","volume":"6","author":"Hansen","year":"2015","journal-title":"J Phys Chem Lett"},{"issue":"16","key":"2021110814303430900_ref41","doi-asserted-by":"crossref","first-page":"1084","DOI":"10.1002\/qua.24912","article-title":"Fourier series of atomic radial distribution functions: a molecular fingerprint for machine learning models of quantum chemical properties","volume":"115","author":"Von Lilienfeld","year":"2015","journal-title":"Int J Quantum Chem"},{"key":"2021110814303430900_ref42","first-page":"071101","article-title":"Fitting potential energy surfaces with fundamental invariant neural network","volume-title":"J Chem Phys","author":"Shao","year":"2016"},{"issue":"2","key":"2021110814303430900_ref43","doi-asserted-by":"crossref","first-page":"145","DOI":"10.3866\/PKU.WHXB201803281","article-title":"Highly accurately fitted potential energy surfaces for polyatomic reactive systems","volume":"35","author":"Bina","year":"2019","journal-title":"Acta Phys-Chim Sin"},{"issue":"1","key":"2021110814303430900_ref44","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"},{"issue":"D1","key":"2021110814303430900_ref45","doi-asserted-by":"crossref","first-page":"D437","DOI":"10.1093\/nar\/gkaa1038","article-title":"RCSB Protein Data Bank: powerful new tools for exploring 3D structures of biological macromolecules for basic and applied research and education in fundamental biology, biomedicine, biotechnology, bioengineering and energy sciences","volume":"49","author":"Burley","year":"2021","journal-title":"Nucleic Acids Res"},{"issue":"2","key":"2021110814303430900_ref46","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1002\/wcms.1121","article-title":"An overview of the amber biomolecular simulation package","volume":"3","author":"Salomon-Ferrer","year":"2013","journal-title":"Wiley Interdiscip Rev Comput Mol Sci"},{"issue":"16","key":"2021110814303430900_ref47","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":"2021110814303430900_ref48","author":"Cerutti","year":"2016","journal-title":"Univ Calif San Franc"},{"issue":"8","key":"2021110814303430900_ref49","doi-asserted-by":"crossref","first-page":"3696","DOI":"10.1021\/acs.jctc.5b00255","article-title":"Ff14SB: improving the accuracy of protein side chain and backbone parameters from Ff99SB","volume":"11","author":"Maier","year":"2015","journal-title":"J Chem Theory Comput"},{"issue":"1\u20132","key":"2021110814303430900_ref50","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/S0009-2614(99)01123-9","article-title":"Replica-exchange molecular dynamics method for protein folding","volume":"314","author":"Sugita","year":"1999","journal-title":"Chem Phys Lett"},{"key":"2021110814303430900_ref51","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1016\/j.cpc.2018.03.016","article-title":"DeePMD-kit: a deep learning package for many-body potential energy representation and molecular dynamics","volume":"228","author":"Wang","year":"2018","journal-title":"Comput Phys Commun"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/22\/6\/bbab158\/41089104\/bbab158.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/22\/6\/bbab158\/41089104\/bbab158.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,8]],"date-time":"2021-11-08T14:35:55Z","timestamp":1636382155000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbab158\/6279287"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,20]]},"references-count":51,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,11,5]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbab158","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,11]]},"published":{"date-parts":[[2021,5,20]]},"article-number":"bbab158"}}