{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T01:29:46Z","timestamp":1786411786301,"version":"build-2736575974"},"reference-count":95,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T00:00:00Z","timestamp":1786406400000},"content-version":"vor","delay-in-days":42,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Commun"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Accurate descriptions of interactions between atoms are essential for molecular simulations used to study biology and support drug discovery. Existing force fields often face a trade-off between physical reliability, computational efficiency, and accuracy across unfamiliar molecules. Here we show that Residual Learning Force Field, a hybrid machine learning force field, can reduce this trade-off by combining simple physics-based descriptions of bonded interactions with learned corrections for remaining energetic effects. The two components are trained together through a three-step strategy so that each contributes complementary information. In tests covering drug-like molecules, molecular dimers, torsional energy profiles, energy-minimum structures, and biomolecular simulations, Residual Learning Force Field gives accurate and stable predictions across diverse systems. These results suggest that combining physical constraints with data-driven corrections can provide a practical route toward more reliable and efficient molecular simulation for biological research and drug discovery.<\/jats:p>","DOI":"10.1038\/s41467-026-74983-0","type":"journal-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T22:37:32Z","timestamp":1782859052000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep residual learning for molecular force fields"],"prefix":"10.1038","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1262-9947","authenticated-orcid":false,"given":"Xinyu","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8559-3671","authenticated-orcid":false,"given":"Mingan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanlong","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Duanhua","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runze","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zunyun","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhehuan","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiacheng","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9547-0643","authenticated-orcid":false,"given":"Xutong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0426-3417","authenticated-orcid":false,"given":"Xiaomin","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Teng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3323-3092","authenticated-orcid":false,"given":"Mingyue","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,30]]},"reference":[{"key":"74983_CR1","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1038\/253694a0","volume":"253","author":"M Levitt","year":"1975","unstructured":"Levitt, M. & Warshel, A. Computer simulation of protein folding. Nature 253, 694\u2013698 (1975).","journal-title":"Nature"},{"key":"74983_CR2","doi-asserted-by":"publisher","first-page":"10142","DOI":"10.1021\/acs.chemrev.0c01111","volume":"121","author":"OT Unke","year":"2021","unstructured":"Unke, O. T. et al. Machine Learning Force Fields. Chem. Rev. 121, 10142\u201310186 (2021).","journal-title":"Chem. Rev."},{"key":"74983_CR3","doi-asserted-by":"publisher","first-page":"1019","DOI":"10.1038\/s41586-024-08127-z","volume":"635","author":"T Wang","year":"2024","unstructured":"Wang, T. et al. Ab initio characterization of protein molecular dynamics with AI2BMD. Nature 635, 1019\u20131027 (2024).","journal-title":"Nature"},{"key":"74983_CR4","doi-asserted-by":"publisher","first-page":"6262","DOI":"10.1021\/acs.jctc.1c00571","volume":"17","author":"Y Qiu","year":"2021","unstructured":"Qiu, Y. et al. Development and Benchmarking of Open Force Field v1.0.0\u2014the Parsley Small-Molecule Force Field. J. Chem. Theory Comput. 17, 6262\u20136280 (2021).","journal-title":"J. Chem. Theory Comput."},{"key":"74983_CR5","doi-asserted-by":"publisher","first-page":"3251","DOI":"10.1021\/acs.jctc.3c00039","volume":"19","author":"S Boothroyd","year":"2023","unstructured":"Boothroyd, S. et al. Development and Benchmarking of Open Force Field 2.0.0: The Sage Small Molecule Force Field. J. Chem. Theory Comput. 19, 3251\u20133275 (2023).","journal-title":"J. Chem. Theory Comput."},{"key":"74983_CR6","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/j.jmgm.2005.12.005","volume":"25","author":"J Wang","year":"2006","unstructured":"Wang, J., Wang, W., Kollman, P. A. & Case, D. A. Automatic atom type and bond type perception in molecular mechanical calculations. J. Mol. Graph. Model. 25, 247\u2013260 (2006).","journal-title":"J. Mol. Graph. Model."},{"key":"74983_CR7","doi-asserted-by":"publisher","first-page":"490","DOI":"10.1002\/(SICI)1096-987X(199604)17:5\/6<490::AID-JCC1>3.0.CO;2-P","volume":"17","author":"TA Halgren","year":"1996","unstructured":"Halgren, T. A. Merck molecular force field. I. Basis, form, scope, parameterization, and performance of MMFF94. J. Comput. Chem. 17, 490\u2013519 (1996).","journal-title":"J. Comput. Chem."},{"key":"74983_CR8","doi-asserted-by":"publisher","first-page":"3696","DOI":"10.1021\/acs.jctc.5b00255","volume":"11","author":"JA Maier","year":"2015","unstructured":"Maier, J. A. et al. ff14SB: Improving the Accuracy of Protein Side Chain and Backbone Parameters from ff99SB. J. Chem. Theory Comput. 11, 3696\u20133713 (2015).","journal-title":"J. Chem. Theory Comput."},{"key":"74983_CR9","doi-asserted-by":"publisher","first-page":"6183","DOI":"10.1021\/acs.jcim.3c01153","volume":"63","author":"DA Case","year":"2023","unstructured":"Case, D. A. et al. AmberTools. J. Chem. Inf. Model. 63, 6183\u20136191 (2023).","journal-title":"J. Chem. Inf. Model."},{"key":"74983_CR10","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1002\/jcc.21367","volume":"31","author":"K Vanommeslaeghe","year":"2010","unstructured":"Vanommeslaeghe, K. et al. CHARMM general force field: A force field for drug-like molecules compatible with the CHARMM all-atom additive biological force fields. J. Comput. Chem. 31, 671\u2013690 (2010).","journal-title":"J. Comput. Chem."},{"key":"74983_CR11","doi-asserted-by":"crossref","unstructured":"Ermer, O. Calculation of molecular properties using force fields. Applications in organic chemistry. in Bonding Forces. (1976).","DOI":"10.1007\/3-540-07671-9_3"},{"key":"74983_CR12","doi-asserted-by":"publisher","first-page":"031104","DOI":"10.1063\/1.5020808","volume":"5","author":"JA Harrison","year":"2018","unstructured":"Harrison, J. A. et al. Review of force fields and intermolecular potentials used in atomistic computational materials research. Appl. Phys. Rev. 5, 031104 (2018).","journal-title":"Appl. Phys. Rev."},{"key":"74983_CR13","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1016\/j.sbi.2021.11.011","volume":"72","author":"X He","year":"2022","unstructured":"He, X., Walker, B., Man, V. H., Ren, P. & Wang, J. Recent progress in general force fields of small molecules. Curr. Opin. Struct. Biol. 72, 187\u2013193 (2022).","journal-title":"Curr. Opin. Struct. Biol."},{"key":"74983_CR14","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436\u2013444 (2015).","journal-title":"Nature"},{"key":"74983_CR15","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1038\/s41557-021-00716-z","volume":"13","author":"N Artrith","year":"2021","unstructured":"Artrith, N. et al. Best practices in machine learning for chemistry. Nat. Chem. 13, 505\u2013508 (2021).","journal-title":"Nat. Chem."},{"key":"74983_CR16","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms13890","volume":"8","author":"KT Sch\u00fctt","year":"2017","unstructured":"Sch\u00fctt, K. T., Arbabzadah, F., Chmiela, S., M\u00fcller, K. R. & Tkatchenko, A. Quantum-chemical insights from deep tensor neural networks. Nat. Commun. 8, 13890 (2017).","journal-title":"Nat. Commun."},{"key":"74983_CR17","doi-asserted-by":"publisher","first-page":"e1603015","DOI":"10.1126\/sciadv.1603015","volume":"3","author":"S Chmiela","year":"2017","unstructured":"Chmiela, S. et al. Machine learning of accurate energy-conserving molecular force fields. Sci. Adv. 3, e1603015 (2017).","journal-title":"Sci. Adv."},{"key":"74983_CR18","doi-asserted-by":"publisher","first-page":"eadf0873","DOI":"10.1126\/sciadv.adf0873","volume":"9","author":"S Chmiela","year":"2023","unstructured":"Chmiela, S. et al. Accurate global machine learning force fields for molecules with hundreds of atoms. Sci. Adv. 9, eadf0873 (2023).","journal-title":"Sci. Adv."},{"key":"74983_CR19","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2014.22","volume":"1","author":"R Ramakrishnan","year":"2014","unstructured":"Ramakrishnan, R., Dral, P. O., Rupp, M. & von Lilienfeld, O. A. Quantum chemistry structures and properties of 134 kilo molecules. Sci. Data 1, 140022 (2014).","journal-title":"Sci. Data"},{"key":"74983_CR20","unstructured":"Hu, W. et al. OGB-LSC: A large-scale challenge for machine learning on graphs. In Advances in Neural Information Processing Systems (2021)."},{"key":"74983_CR21","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01882-6","volume":"10","author":"P Eastman","year":"2023","unstructured":"Eastman, P. et al. SPICE, A dataset of drug-like molecules and peptides for training machine learning potentials. Sci. Data 10, 11 (2023).","journal-title":"Sci. Data"},{"key":"74983_CR22","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1002\/med.22008","volume":"44","author":"M Chen","year":"2024","unstructured":"Chen, M. et al. The emergence of machine learning force fields in drug design. Med. Res. Rev. 44, 1147\u20131182 (2024).","journal-title":"Med. Res. Rev."},{"key":"74983_CR23","doi-asserted-by":"publisher","first-page":"3192","DOI":"10.1039\/C6SC05720A","volume":"8","author":"JS Smith","year":"2017","unstructured":"Smith, J. S., Isayev, O. & Roitberg, A. E. ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost. Chem. Sci. 8, 3192\u20133203 (2017).","journal-title":"Chem. Sci."},{"key":"74983_CR24","doi-asserted-by":"publisher","first-page":"4192","DOI":"10.1021\/acs.jctc.0c00121","volume":"16","author":"C Devereux","year":"2020","unstructured":"Devereux, C. et al. Extending the applicability of the ANI deep learning molecular potential to sulfur and halogens. J. Chem. Theory Comput. 16, 4192\u20134202 (2020).","journal-title":"J. Chem. Theory Comput."},{"key":"74983_CR25","unstructured":"Sch\u00fctt, K. T. et al. SchNet: a continuous-filter convolutional neural network for modeling quantum interactions. In Proceedings of the 31st International Conference on Neural Information Processing Systems. (2017)."},{"key":"74983_CR26","doi-asserted-by":"publisher","first-page":"143001","DOI":"10.1103\/PhysRevLett.120.143001","volume":"120","author":"L Zhang","year":"2018","unstructured":"Zhang, L., Han, J., Wang, H., Car, R. & E, W. Deep Potential molecular dynamics: A Scalable Model with the Accuracy of Quantum Mechanics. Phys. Rev. Lett. 120, 143001 (2018).","journal-title":"Phys. Rev. Lett."},{"key":"74983_CR27","unstructured":"Sch\u00fctt, K., Unke, O. & Gastegger, M. Equivariant message passing for the prediction of tensorial properties and molecular spectra. In Proceedings of the 38th International Conference on Machine Learning 139, 9377\u20139388 (PMLR, 2021)."},{"key":"74983_CR28","doi-asserted-by":"publisher","first-page":"eaav6490","DOI":"10.1126\/sciadv.aav6490","volume":"5","author":"R Zubatyuk","year":"2019","unstructured":"Zubatyuk, R., Smith, J. S., Leszczynski, J. & Isayev, O. Accurate and transferable multitask prediction of chemical properties with an atoms-in-molecules neural network. Sci. Adv. 5, eaav6490 (2019).","journal-title":"Sci. Adv."},{"key":"74983_CR29","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-27921-1","volume":"13","author":"S Batzner","year":"2022","unstructured":"Batzner, S. et al. E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials. Nat. Commun. 13, 245 (2022).","journal-title":"Nat. Commun."},{"key":"74983_CR30","unstructured":"Th\u00f6lke, P. & Fabritiis, G. D. Equivariant transformers for neural network based molecular potentials. In International Conference on Learning Representations (2022)."},{"key":"74983_CR31","doi-asserted-by":"publisher","first-page":"4076","DOI":"10.1021\/acs.jctc.4c00253","volume":"20","author":"RP Pelaez","year":"2024","unstructured":"Pelaez, R. P. et al. TorchMD-Net 2.0: Fast Neural Network Potentials for Molecular Simulations. J. Chem. Theory Comput. 20, 4076\u20134087 (2024).","journal-title":"J. Chem. Theory Comput."},{"key":"74983_CR32","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-43720-2","volume":"15","author":"Y Wang","year":"2024","unstructured":"Wang, Y. et al. Enhancing geometric representations for molecules with equivariant vector-scalar interactive message passing. Nat. Commun. 15, 313 (2024).","journal-title":"Nat. Commun."},{"key":"74983_CR33","doi-asserted-by":"crossref","unstructured":"Batatia, I., Kov\u00e1cs, D. P., Simm, G. N. C., Ortner, C. & Csanyi, G. MACE: Higher order equivariant message passing neural networks for fast and accurate force fields. In Advances in Neural Information Processing Systems (eds Oh, A. H., Agarwal, A., Belgrave, D. & Cho, K.) (2022).","DOI":"10.52202\/068431-0830"},{"key":"74983_CR34","doi-asserted-by":"publisher","first-page":"17598","DOI":"10.1021\/jacs.4c07099","volume":"147","author":"DP Kov\u00e1cs","year":"2025","unstructured":"Kov\u00e1cs, D. P. et al. MACE-OFF: Short-range transferable machine learning force fields for organic molecules. J. Am. Chem. Soc. 147, 17598\u201317611 (2025).","journal-title":"J. Am. Chem. Soc."},{"key":"74983_CR35","doi-asserted-by":"publisher","first-page":"021304","DOI":"10.1063\/5.0237876","volume":"12","author":"Y Wang","year":"2025","unstructured":"Wang, Y. et al. On the design space between molecular mechanics and machine learning force fields. Appl. Phys. Rev. 12, 021304 (2025).","journal-title":"Appl. Phys. Rev."},{"key":"74983_CR36","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1016\/j.sbi.2009.03.004","volume":"19","author":"JL Klepeis","year":"2009","unstructured":"Klepeis, J. L., Lindorff-Larsen, K., Dror, R. O. & Shaw, D. E. Long-timescale molecular dynamics simulations of protein structure and function. Curr. Opin. Struct. Biol. 19, 120\u2013127 (2009).","journal-title":"Curr. Opin. Struct. Biol."},{"key":"74983_CR37","doi-asserted-by":"publisher","first-page":"2798","DOI":"10.1021\/ct900292r","volume":"5","author":"R Schulz","year":"2009","unstructured":"Schulz, R., Lindner, B., Petridis, L. & Smith, J. C. Scaling of multimillion-atom biological molecular dynamics simulation on a petascale supercomputer. J. Chem. Theory Comput. 5, 2798\u20132808 (2009).","journal-title":"J. Chem. Theory Comput."},{"key":"74983_CR38","doi-asserted-by":"publisher","first-page":"3036","DOI":"10.1021\/acs.jmedchem.8b01925","volume":"62","author":"MR Bauer","year":"2019","unstructured":"Bauer, M. R. & Mackey, M. D. Electrostatic complementarity as a fast and effective tool to optimize binding and selectivity of protein\u2013ligand complexes. J. Med. Chem. 62, 3036\u20133050 (2019).","journal-title":"J. Med. Chem."},{"key":"74983_CR39","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1021\/acs.jcim.2c01127","volume":"63","author":"K K\u0159\u00ed\u017e","year":"2023","unstructured":"K\u0159\u00ed\u017e, K., Schmidt, L., Andersson, A. T., Walz, M.-M. & van der Spoel, D. An imbalance in the force: The need for standardized benchmarks for molecular simulation. J. Chem. Inf. Model. 63, 412\u2013431 (2023).","journal-title":"J. Chem. Inf. Model."},{"key":"74983_CR40","doi-asserted-by":"crossref","unstructured":"Ponder, J. W. & Case, D. A. Force fields for protein simulations. Adv. Protein Chem. 66, 27\u201385 (Academic Press, 2003).","DOI":"10.1016\/S0065-3233(03)66002-X"},{"key":"74983_CR41","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1146\/annurev-biophys-070317-033349","volume":"48","author":"Z Jing","year":"2019","unstructured":"Jing, Z. et al. Polarizable force fields for biomolecular simulations: recent advances and applications. Annu. Rev. Biophys. 48, 371\u2013394 (2019).","journal-title":"Annu. Rev. Biophys."},{"key":"74983_CR42","doi-asserted-by":"publisher","first-page":"7751","DOI":"10.1021\/acs.jctc.2c00930","volume":"18","author":"G Nawrocki","year":"2022","unstructured":"Nawrocki, G. et al. Protein\u2013ligand binding free-energy calculations with ARROW\u2500A purely first-principles parameterized polarizable force field. J. Chem. Theory Comput. 18, 7751\u20137763 (2022).","journal-title":"J. Chem. Theory Comput."},{"key":"74983_CR43","doi-asserted-by":"publisher","first-page":"035101","DOI":"10.1063\/5.0147023","volume":"159","author":"Z Wang","year":"2023","unstructured":"Wang, Z. et al. Improving machine learning force fields for molecular dynamics simulations with fine-grained force metrics. J. Chem. Phys. 159, 035101 (2023).","journal-title":"J. Chem. Phys."},{"key":"74983_CR44","unstructured":"Fu, X. et al. Forces are not enough: Benchmark and critical evaluation for machine learning force fields with molecular simulations. Trans. Mach. Learn. Res. https:\/\/openreview.net\/forum?id=A8pqQipwkt (2023)."},{"key":"74983_CR45","doi-asserted-by":"publisher","first-page":"121501","DOI":"10.1063\/5.0139611","volume":"158","author":"JD Morrow","year":"2023","unstructured":"Morrow, J. D., Gardner, J. L. A. & Deringer, V. L. How to validate machine-learned interatomic potentials. J. Chem. Phys. 158, 121501 (2023).","journal-title":"J. Chem. Phys."},{"key":"74983_CR46","doi-asserted-by":"publisher","first-page":"2362","DOI":"10.1039\/C9SC06017K","volume":"11","author":"S-LJ Lahey","year":"2020","unstructured":"Lahey, S.-L. J. & Rowley, C. N. Simulating protein\u2013ligand binding with neural network potentials. Chem. Sci. 11, 2362\u20132368 (2020).","journal-title":"Chem. Sci."},{"key":"74983_CR47","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1021\/acs.jpcb.3c06662","volume":"128","author":"P Eastman","year":"2024","unstructured":"Eastman, P. et al. OpenMM 8: Molecular dynamics simulation with machine learning potentials. J. Phys. Chem. B 128, 109\u2013116 (2024).","journal-title":"J. Phys. Chem. B"},{"key":"74983_CR48","doi-asserted-by":"publisher","first-page":"12016","DOI":"10.1039\/D2SC02739A","volume":"13","author":"Y Wang","year":"2022","unstructured":"Wang, Y. et al. End-to-end differentiable construction of molecular mechanics force fields. Chem. Sci. 13, 12016\u201312033 (2022).","journal-title":"Chem. Sci."},{"key":"74983_CR49","doi-asserted-by":"publisher","first-page":"12861","DOI":"10.1039\/D4SC00690A","volume":"15","author":"K Takaba","year":"2024","unstructured":"Takaba, K. et al. Machine-learned molecular mechanics force fields from large-scale quantum chemical data. Chem. Sci. 15, 12861\u201312878 (2024).","journal-title":"Chem. Sci."},{"key":"74983_CR50","doi-asserted-by":"publisher","first-page":"5558","DOI":"10.1021\/acs.jctc.3c01421","volume":"20","author":"G Chen","year":"2024","unstructured":"Chen, G. et al. Advancing force fields parameterization: a directed graph attention networks approach. J. Chem. Theory Comput. 20, 5558\u20135569 (2024).","journal-title":"J. Chem. Theory Comput."},{"key":"74983_CR51","doi-asserted-by":"publisher","first-page":"2730","DOI":"10.1039\/D4SC06640E","volume":"16","author":"T Zheng","year":"2025","unstructured":"Zheng, T. et al. Data-driven parametrization of molecular mechanics force fields for expansive chemical space coverage. Chem. Sci. 16, 2730\u20132740 (2025).","journal-title":"Chem. Sci."},{"key":"74983_CR52","doi-asserted-by":"publisher","first-page":"12554","DOI":"10.1039\/D3SC02581K","volume":"14","author":"T Pl\u00e9","year":"2023","unstructured":"Pl\u00e9, T., Lagard\u00e8re, L. & Piquemal, J.-P. Force-field-enhanced neural network interactions: from local equivariant embedding to atom-in-molecule properties and long-range effects. Chem. Sci. 14, 12554\u201312569 (2023).","journal-title":"Chem. Sci."},{"key":"74983_CR53","doi-asserted-by":"publisher","first-page":"12661","DOI":"10.1039\/D3SC04317G","volume":"14","author":"M Th\u00fcrlemann","year":"2023","unstructured":"Th\u00fcrlemann, M. & Riniker, S. Hybrid classical\/machine-learning force fields for the accurate description of molecular condensed-phase systems. Chem. Sci. 14, 12661\u201312675 (2023).","journal-title":"Chem. Sci."},{"key":"74983_CR54","doi-asserted-by":"publisher","first-page":"33723","DOI":"10.1021\/jacs.5c09558","volume":"147","author":"A Kabylda","year":"2025","unstructured":"Kabylda, A. et al. Molecular simulations with a pretrained neural network and universal pairwise force fields. J. Am. Chem. Soc. 147, 33723\u201333734 (2025).","journal-title":"J. Am. Chem. Soc."},{"key":"74983_CR55","doi-asserted-by":"publisher","first-page":"23620","DOI":"10.1021\/jacs.3c07628","volume":"145","author":"A Illarionov","year":"2023","unstructured":"Illarionov, A. et al. Combining force fields and neural networks for an accurate representation of chemically diverse molecular interactions. J. Am. Chem. Soc. 145, 23620\u201323629 (2023).","journal-title":"J. Am. Chem. Soc."},{"key":"74983_CR56","doi-asserted-by":"publisher","first-page":"8878","DOI":"10.1073\/pnas.1806064115","volume":"115","author":"L Pereyaslavets","year":"2018","unstructured":"Pereyaslavets, L. et al. On the importance of accounting for nuclear quantum effects in ab initio calibrated force fields in biological simulations. Proc. Natl. Acad. Sci. USA 115, 8878\u20138882 (2018).","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"74983_CR57","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-28041-0","volume":"13","author":"L Pereyaslavets","year":"2022","unstructured":"Pereyaslavets, L. et al. Accurate determination of solvation free energies of neutral organic compounds from first principles. Nat. Commun. 13, 414 (2022).","journal-title":"Nat. Commun."},{"key":"74983_CR58","doi-asserted-by":"publisher","first-page":"1481","DOI":"10.1021\/ct501050s","volume":"11","author":"J Witte","year":"2015","unstructured":"Witte, J., Goldey, M., Neaton, J. B. & Head-Gordon, M. Beyond energies: geometries of nonbonded molecular complexes as metrics for assessing electronic structure approaches. J. Chem. Theory Comput. 11, 1481\u20131492 (2015).","journal-title":"J. Chem. Theory Comput."},{"key":"74983_CR59","doi-asserted-by":"publisher","first-page":"5776","DOI":"10.1021\/acs.chemrev.4c00893","volume":"125","author":"S Tretiakov","year":"2025","unstructured":"Tretiakov, S., Nigam, A. & Pollice, R. Studying noncovalent interactions in molecular systems with machine learning. Chem. Rev. 125, 5776\u20135829 (2025).","journal-title":"Chem. Rev."},{"key":"74983_CR60","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1021\/ct300826t","volume":"9","author":"L-P Wang","year":"2013","unstructured":"Wang, L.-P., Chen, J. & Van Voorhis, T. Systematic parametrization of polarizable force fields from quantum chemistry data. J. Chem. Theory Comput. 9, 452\u2013460 (2013).","journal-title":"J. Chem. Theory Comput."},{"key":"74983_CR61","doi-asserted-by":"publisher","first-page":"3712","DOI":"10.1021\/acs.jpclett.2c00121","volume":"13","author":"MP Bernhardt","year":"2022","unstructured":"Bernhardt, M. P., Nagata, Y. & van der Vegt, N. F. A. Where Lennard-Jones potentials fail: iterative optimization of ion\u2013water pair potentials based on Ab initio molecular dynamics data. J. Phys. Chem. Lett. 13, 3712\u20133717 (2022).","journal-title":"J. Phys. Chem. Lett."},{"key":"74983_CR62","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep Residual Learning for Image Recognition. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 770\u2013778 (IEEE, 2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"74983_CR63","doi-asserted-by":"publisher","first-page":"e1491","DOI":"10.1002\/wcms.1491","volume":"11","author":"DGA Smith","year":"2021","unstructured":"Smith, D. G. A. et al. The MolSSI QCArchive project: An open-source platform to compute, organize, and share quantum chemistry data. WIREs Comput. Mol. Sci. 11, e1491 (2021).","journal-title":"WIREs Comput. Mol. Sci."},{"key":"74983_CR64","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-021-00833-x","volume":"8","author":"AG Donchev","year":"2021","unstructured":"Donchev, A. G. et al. Quantum chemical benchmark databases of gold-standard dimer interaction energies. Sci. Data 8, 55 (2021).","journal-title":"Sci. Data"},{"key":"74983_CR65","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1021\/acs.jcim.1c01346","volume":"62","author":"BK Rai","year":"2022","unstructured":"Rai, B. K. et al. TorsionNet: A deep neural network to rapidly predict small-molecule torsional energy profiles with the accuracy of quantum mechanics. J. Chem. Inf. Model. 62, 785\u2013800 (2022).","journal-title":"J. Chem. Inf. Model."},{"key":"74983_CR66","doi-asserted-by":"publisher","first-page":"1265","DOI":"10.1021\/acs.jcim.6b00614","volume":"57","author":"BD Sellers","year":"2017","unstructured":"Sellers, B. D., James, N. C. & Gobbi, A. A comparison of quantum and molecular mechanical methods to estimate strain energy in druglike fragments. J. Chem. Inf. Model. 57, 1265\u20131275 (2017).","journal-title":"J. Chem. Inf. Model."},{"key":"74983_CR67","doi-asserted-by":"publisher","first-page":"2427","DOI":"10.1021\/ct2002946","volume":"7","author":"J \u0158ez\u00e1\u010d","year":"2011","unstructured":"\u0158ez\u00e1\u010d, J., Riley, K. E. & Hobza, P. S66: A Well-balanced database of Benchmark interaction energies relevant to biomolecular structures. J. Chem. Theory Comput. 7, 2427\u20132438 (2011).","journal-title":"J. Chem. Theory Comput."},{"key":"74983_CR68","doi-asserted-by":"publisher","first-page":"6094","DOI":"10.1021\/acs.jcim.2c01185","volume":"62","author":"L D\u2019Amore","year":"2022","unstructured":"D\u2019Amore, L. et al. Collaborative assessment of molecular geometries and energies from the open force field. J. Chem. Inf. Model. 62, 6094\u20136104 (2022).","journal-title":"J. Chem. Inf. Model."},{"key":"74983_CR69","doi-asserted-by":"publisher","first-page":"6258","DOI":"10.1021\/acs.jcim.0c00904","volume":"60","author":"S-LJ Lahey","year":"2020","unstructured":"Lahey, S.-L. J., Thien Phuc, T. N. & Rowley, C. N. Benchmarking force field and the ANI neural network potentials for the torsional potential energy surface of biaryl drug fragments. J. Chem. Inf. Model. 60, 6258\u20136268 (2020).","journal-title":"J. Chem. Inf. Model."},{"key":"74983_CR70","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1007\/s10822-011-9538-6","volume":"26","author":"J Liebeschuetz","year":"2012","unstructured":"Liebeschuetz, J., Hennemann, J., Olsson, T. & Groom, C. R. The good, the bad and the twisted: a survey of ligand geometry in protein crystal structures. J. Comput. Aided Mol. Des. 26, 169\u2013183 (2012).","journal-title":"J. Comput. Aided Mol. Des."},{"key":"74983_CR71","doi-asserted-by":"publisher","first-page":"2798","DOI":"10.1529\/biophysj.106.084301","volume":"91","author":"J Wang","year":"2006","unstructured":"Wang, J., Deng, Y. & Roux, B. Absolute binding free energy calculations using molecular dynamics simulations with restraining potentials. Biophys. J. 91, 2798\u20132814 (2006).","journal-title":"Biophys. J."},{"key":"74983_CR72","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.1021\/ci2002318","volume":"52","author":"T Schulz-Gasch","year":"2012","unstructured":"Schulz-Gasch, T., Sch\u00e4rfer, C., Guba, W. & Rarey, M. TFD: Torsion fingerprints as a new measure to compare small molecule conformations. J. Chem. Inf. Model. 52, 1499\u20131512 (2012).","journal-title":"J. Chem. Inf. Model."},{"key":"74983_CR73","doi-asserted-by":"publisher","first-page":"045010","DOI":"10.1088\/2632-2153\/ac9955","volume":"3","author":"S Stocker","year":"2022","unstructured":"Stocker, S., Gasteiger, J., Becker, F., G\u00fcnnemann, S. & Margraf, J. T. How robust are modern graph neural network potentials in long and hot molecular dynamics simulations? Mach. Learn. Sci. Technol. 3, 045010 (2022).","journal-title":"Mach. Learn. Sci. Technol."},{"key":"74983_CR74","doi-asserted-by":"publisher","first-page":"5701","DOI":"10.1021\/acs.jcim.3c00773","volume":"63","author":"R Galvelis","year":"2023","unstructured":"Galvelis, R. et al. NNP\/MM: Accelerating molecular dynamics simulations with machine learning potentials and molecular mechanics. J. Chem. Inf. Model. 63, 5701\u20135708 (2023).","journal-title":"J. Chem. Inf. Model."},{"key":"74983_CR75","doi-asserted-by":"publisher","first-page":"1481","DOI":"10.1021\/acs.jcim.3c02031","volume":"64","author":"F Saban\u00e9s Zariquiey","year":"2024","unstructured":"Saban\u00e9s Zariquiey, F. et al. Enhancing protein\u2013ligand binding affinity predictions using neural network potentials. J. Chem. Inf. Model. 64, 1481\u20131485 (2024).","journal-title":"J. Chem. Inf. Model."},{"key":"74983_CR76","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1021\/ja9058052","volume":"132","author":"A Hagarman","year":"2010","unstructured":"Hagarman, A., Measey, T. J., Mathieu, D., Schwalbe, H. & Schweitzer-Stenner, R. Intrinsic propensities of amino acid residues in GxG peptides inferred from amide I\u2032 band profiles and NMR scalar coupling constants. J. Am. Chem. Soc. 132, 540\u2013551 (2010).","journal-title":"J. Am. Chem. Soc."},{"key":"74983_CR77","doi-asserted-by":"publisher","first-page":"3598","DOI":"10.1021\/acs.jpcb.0c10401","volume":"125","author":"D Rosenberger","year":"2021","unstructured":"Rosenberger, D., Smith, J. S. & Garcia, A. E. Modeling of peptides with classical and novel machine learning force fields: a comparison. J. Phys. Chem. B 125, 3598\u20133612 (2021).","journal-title":"J. Phys. Chem. B"},{"key":"74983_CR78","doi-asserted-by":"publisher","first-page":"3526","DOI":"10.1021\/ja00246a005","volume":"109","author":"AM Sapse","year":"1987","unstructured":"Sapse, A. M., Mallah-Levy, L., Daniels, S. B. & Erickson, B. W. The.gamma. turn: ab initio calculations on proline and N-acetylproline amide. J. Am. Chem. Soc. 109, 3526\u20133529 (1987).","journal-title":"J. Am. Chem. Soc."},{"key":"74983_CR79","doi-asserted-by":"publisher","first-page":"7784","DOI":"10.1021\/jp0001743","volume":"104","author":"C Park","year":"2000","unstructured":"Park, C. & Goddard, W. A. Stabilization of \u03b1-helices by dipole\u2212dipole interactions within \u03b1-helices. J. Phys. Chem. B 104, 7784\u20137789 (2000).","journal-title":"J. Phys. Chem. B"},{"key":"74983_CR80","doi-asserted-by":"crossref","unstructured":"Unke, O. T. et al. Biomolecular dynamics with machine-learned quantum-mechanical force fields trained on diverse chemical fragments. Sci. Adv. 10, eadn4397 (2024).","DOI":"10.1126\/sciadv.adn4397"},{"key":"74983_CR81","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1021\/ja982919c","volume":"121","author":"M Takano","year":"1999","unstructured":"Takano, M., Yamato, T., Higo, J., Suyama, A. & Nagayama, K. Molecular dynamics of a 15-residue poly(l-alanine) in water:\u2009 helix formation and energetics. J. Am. Chem. Soc. 121, 605\u2013612 (1999).","journal-title":"J. Am. Chem. Soc."},{"key":"74983_CR82","doi-asserted-by":"publisher","first-page":"2292","DOI":"10.1021\/acs.chemrev.0c01087","volume":"121","author":"J Damjanovic","year":"2021","unstructured":"Damjanovic, J., Miao, J., Huang, H. & Lin, Y.-S. Elucidating solution structures of cyclic peptides using molecular dynamics simulations. Chem. Rev. 121, 2292\u20132324 (2021).","journal-title":"Chem. Rev."},{"key":"74983_CR83","doi-asserted-by":"publisher","first-page":"13936","DOI":"10.1021\/acs.chemrev.0c01291","volume":"121","author":"Q Song","year":"2021","unstructured":"Song, Q. et al. Molecular self-assembly and supramolecular chemistry of cyclic peptides. Chem. Rev. 121, 13936\u201313995 (2021).","journal-title":"Chem. Rev."},{"key":"74983_CR84","doi-asserted-by":"publisher","first-page":"9151","DOI":"10.1021\/ja00141a005","volume":"117","author":"M Engels","year":"1995","unstructured":"Engels, M., Bashford, D. & Ghadiri, M. R. Structure and dynamics of self-assembling peptide nanotubes and the channel-mediated water organization and self-diffusion. A molecular dynamics study. J. Am. Chem. Soc. 117, 9151\u20139158 (1995).","journal-title":"J. Am. Chem. Soc."},{"key":"74983_CR85","doi-asserted-by":"publisher","first-page":"3158","DOI":"10.3390\/ijms23063158","volume":"23","author":"D Conde","year":"2022","unstructured":"Conde, D., Garrido, P. F., Calvelo, M., Pi\u00f1eiro, \u00c1 & Garcia-Fandino, R. Molecular dynamics simulations of transmembrane cyclic peptide nanotubes using classical force fields, hydrogen mass repartitioning, and hydrogen isotope exchange methods: a critical comparison. Int. J. Mol. Sci. 23, 3158 (2022).","journal-title":"Int. J. Mol. Sci."},{"key":"74983_CR86","doi-asserted-by":"publisher","first-page":"6613","DOI":"10.1039\/C7CC00846E","volume":"53","author":"MR Silk","year":"2017","unstructured":"Silk, M. R. et al. Parallel and antiparallel cyclic d\/l peptide nanotubes. Chem. Commun. 53, 6613\u20136616 (2017).","journal-title":"Chem. Commun."},{"key":"74983_CR87","doi-asserted-by":"publisher","unstructured":"Rufa, D. A. et al. Towards chemical accuracy for alchemical free energy calculations with hybrid physics-based machine learning \/ molecular mechanics potentials. Preprint at: bioRxiv https:\/\/doi.org\/10.1101\/2020.07.29.227959 (2020).","DOI":"10.1101\/2020.07.29.227959"},{"key":"74983_CR88","first-page":"273002","volume":"29","author":"HL Ask","year":"2017","unstructured":"Ask, H. L. et al. The atomic simulation environment\u2014a Python library for working with atoms. J. Phys.: Condens. Matter 29, 273002 (2017).","journal-title":"J. Phys.: Condens. Matter"},{"key":"74983_CR89","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1109\/5992.998641","volume":"4","author":"SR Bahn","year":"2002","unstructured":"Bahn, S. R. & Jacobsen, K. W. An object-oriented scripting interface to a legacy electronic structure code. Comput. Sci. Eng. 4, 56\u201366 (2002).","journal-title":"Comput. Sci. Eng."},{"key":"74983_CR90","doi-asserted-by":"publisher","first-page":"108171","DOI":"10.1016\/j.cpc.2021.108171","volume":"271","author":"AP Thompson","year":"2022","unstructured":"Thompson, A. P. et al. LAMMPS - a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales. Comput. Phys. Commun. 271, 108171 (2022).","journal-title":"Comput. Phys. Commun."},{"key":"74983_CR91","unstructured":"Hamilton, W. L., Ying, Z. & Leskovec, J. Inductive representation learning on large graphs. In Proceedings of the 31st International Conference on Neural Information Processing Systems 1025\u20131035 (Curran Associates Inc., 2017)."},{"key":"74983_CR92","first-page":"1263","volume":"70","author":"J Gilmer","year":"2017","unstructured":"Gilmer, J., Schoenholz, S. S., Riley, P. F., Vinyals, O. & Dahl, G. E. Neural message passing for quantum chemistry. Int. Conf. Mach. Learn. 70, 1263\u20131272 (2017).","journal-title":"Int. Conf. Mach. Learn."},{"key":"74983_CR93","unstructured":"Murphy, R. L., Srinivasan, B., Rao, V. A. & Ribeiro, B. Relational pooling for graph representations. In Proceedings of the 36th Intenational Conference on Machine Learning 97, 4663\u20134673 (PMLR, 2019)."},{"key":"74983_CR94","doi-asserted-by":"publisher","first-page":"184108","DOI":"10.1063\/5.0006002","volume":"152","author":"DGA Smith","year":"2020","unstructured":"Smith, D. G. A. et al. PSI4 1.4: Open-source software for high-throughput quantum chemistry. J. Chem. Phys. 152, 184108 (2020).","journal-title":"J. Chem. Phys."},{"key":"74983_CR95","doi-asserted-by":"publisher","unstructured":"Jiang, X. Code for paper \u2018deep residual learning for molecular force fields\u2019 (v1.0.0). Zenodo https:\/\/doi.org\/10.5281\/zenodo.20484065 (2026).","DOI":"10.5281\/zenodo.20484065"}],"container-title":["Nature Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-74983-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-74983-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-74983-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T01:02:42Z","timestamp":1786410162000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-74983-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":95,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["74983"],"URL":"https:\/\/doi.org\/10.1038\/s41467-026-74983-0","relation":{"has-preprint":[{"id-type":"doi","id":"10.26434\/chemrxiv-2025-003lg\/v5","asserted-by":"object"},{"id-type":"doi","id":"10.26434\/chemrxiv-2025-003lg-v2","asserted-by":"object"},{"id-type":"doi","id":"10.26434\/chemrxiv-2025-003lg-v3","asserted-by":"object"},{"id-type":"doi","id":"10.26434\/chemrxiv-2025-003lg-v4","asserted-by":"object"},{"id-type":"doi","id":"10.26434\/chemrxiv-2025-003lg","asserted-by":"object"}]},"ISSN":["2041-1723"],"issn-type":[{"value":"2041-1723","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,30]]},"assertion":[{"value":"28 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}}],"article-number":"8160"}}