{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T16:00:28Z","timestamp":1794326428017,"version":"4.9.0"},"reference-count":71,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T00:00:00Z","timestamp":1756166400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T00:00:00Z","timestamp":1756166400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000266","name":"RCUK | Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/X034712\/1"],"award-info":[{"award-number":["EP\/X034712\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Commun"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>The efficient separation of chiral molecules is a fundamental challenge in the manufacture of pharmaceuticals and light-polarising materials. We developed an approach that combines machine learning with a physics-based representation to predict resolving agents for chiral molecules, using a transformer-based neural network. In retrospective tests, our approach reaches a four to six-fold improvement over the historical - trial and error based - hit rate. We further validate the model in a prospective experiment, where we use the model to design a resolution screen for six unseen racemates. We successfully resolved three of the six mixtures in a single round of experiments and obtained an overall 8-to-1 true positive to false negative ratio. Together with this study, we release a previously proprietary dataset of over 6000 resolution experiments, the largest diastereomeric salt crystallisation dataset to date. More broadly, our approach and open crystallisation data lay the foundation for accelerating and reducing the costs of chiral resolutions.<\/jats:p>","DOI":"10.1038\/s41467-025-62825-4","type":"journal-article","created":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T20:29:12Z","timestamp":1756240152000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Predictive design of crystallographic chiral separation"],"prefix":"10.1038","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6397-0002","authenticated-orcid":false,"given":"Rokas","family":"Elijo\u0161ius","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2999-0955","authenticated-orcid":false,"given":"Emma","family":"King-Smith","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix A.","family":"Faber","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Louise","family":"Bernier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5572-6771","authenticated-orcid":false,"given":"Simon","family":"Berritt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3341-9831","authenticated-orcid":false,"given":"William P.","family":"Farrell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3473-8455","authenticated-orcid":false,"given":"Xinjun","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacquelyn L.","family":"Klug-McLeod","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8683-0691","authenticated-orcid":false,"given":"Jason","family":"Mustakis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9966-7459","authenticated-orcid":false,"given":"Neal W.","family":"Sach","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5269-0494","authenticated-orcid":false,"given":"Qingyi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5884-4896","authenticated-orcid":false,"given":"Roger M.","family":"Howard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9616-3108","authenticated-orcid":false,"given":"Alpha A.","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,26]]},"reference":[{"key":"62825_CR1","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1038\/nphoton.2013.176","volume":"7","author":"Y Yang","year":"2013","unstructured":"Yang, Y., da Costa, R. C., Fuchter, M. J. & Campbell, A. J. Circularly polarized light detection by a chiral organic semiconductor transistor. Nat. Photon. 7, 634\u2013638 (2013).","journal-title":"Nat. Photon."},{"key":"62825_CR2","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms9379","volume":"6","author":"W Li","year":"2015","unstructured":"Li, W. et al. Circularly polarized light detection with hot electrons in chiral plasmonic metamaterials. Nat. Commun. 6, 8379 (2015).","journal-title":"Nat. Commun."},{"key":"62825_CR3","doi-asserted-by":"publisher","first-page":"1900684","DOI":"10.1002\/adfm.201900684","volume":"29","author":"M Schulz","year":"2019","unstructured":"Schulz, M. et al. Chiral excitonic organic photodiodes for direct detection of circular polarized light. Adv. Funct. Mater. 29, 1900684 (2019).","journal-title":"Adv. Funct. Mater."},{"key":"62825_CR4","doi-asserted-by":"publisher","first-page":"2624","DOI":"10.1002\/adma.201204961","volume":"25","author":"Y Yang","year":"2013","unstructured":"Yang, Y., da Costa, R. C., Smilgies, D.-M., Campbell, A. J. & Fuchter, M. J. Induction of circularly polarized electroluminescence from an achiral light-emitting polymer via a chiral small-molecule dopant. Adv. Mater. 25, 2624\u20132628 (2013).","journal-title":"Adv. Mater."},{"key":"62825_CR5","doi-asserted-by":"publisher","first-page":"1900524","DOI":"10.1002\/adma.201900524","volume":"31","author":"Z-G Wu","year":"2019","unstructured":"Wu, Z.-G. et al. Chiral octahydro-binaphthol compound-based thermally activated delayed fluorescence materials for circularly polarized electroluminescence with superior EQE of 32.6% and extremely low efficiency roll-off. Adv. Mater. 31, 1900524 (2019).","journal-title":"Adv. Mater."},{"key":"62825_CR6","doi-asserted-by":"publisher","first-page":"4928","DOI":"10.1021\/acsnano.9b01876","volume":"13","author":"JM Abendroth","year":"2019","unstructured":"Abendroth, J. M. et al. Spin selectivity in photoinduced charge-transfer mediated by chiral molecules. ACS Nano 13, 4928\u20134946 (2019).","journal-title":"ACS Nano"},{"key":"62825_CR7","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1038\/s41570-019-0087-1","volume":"3","author":"R Naaman","year":"2019","unstructured":"Naaman, R., Paltiel, Y. & Waldeck, D. H. Chiral molecules and the electron spin. Nat. Rev. Chem. 3, 250\u2013260 (2019).","journal-title":"Nat. Rev. Chem."},{"key":"62825_CR8","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/0021-9673(94)00812-N","volume":"694","author":"J Caldwell","year":"1995","unstructured":"Caldwell, J. Stereochemical determinants of the nature and consequences of drug metabolism. J. Chromatogr. A 694, 39\u201348 (1995).","journal-title":"J. Chromatogr. A"},{"key":"62825_CR9","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/BF03342662","volume":"20","author":"AM Evans","year":"2001","unstructured":"Evans, A. M. Comparative pharmacology of S(+)-ibuprofen and (RS)-ibuprofen. Clin. Rheumatol. 20, 9\u201314 (2001).","journal-title":"Clin. Rheumatol."},{"key":"62825_CR10","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1046\/j.1365-2125.1998.00775.x","volume":"46","author":"H Bardsley","year":"1998","unstructured":"Bardsley, H., Gristwood, R., Baker, H., Watson, N. & Nimmo, W. A comparison of the cardiovascular effects of levobupivacaine and rac-bupivacaine following intravenous administration to healthy volunteers. Br. J. Clin. Pharmacol. 46, 245\u2013249 (1998).","journal-title":"Br. J. Clin. Pharmacol."},{"key":"62825_CR11","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.jpba.2017.07.008","volume":"147","author":"A Calcaterra","year":"2018","unstructured":"Calcaterra, A. & D\u2019Acquarica, I. The market of chiral drugs: chiral switches versus de novo enantiomerically pure compounds. J. Pharm. Biomed. Anal. 147, 323\u2013340 (2018).","journal-title":"J. Pharm. Biomed. Anal."},{"key":"62825_CR12","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.drudis.2006.11.004","volume":"12","author":"MJ Gaunt","year":"2007","unstructured":"Gaunt, M. J., Johansson, C. C., McNally, A. & Vo, N. T. Enantioselective organocatalysis. Drug Discov. Today 12, 8\u201327 (2007).","journal-title":"Drug Discov. Today"},{"key":"62825_CR13","doi-asserted-by":"crossref","unstructured":"Hassan, A. & Krische, M. J. Unlocking hydrogenation for C\u2013C bond formation: a brief overview of enantioselective methods. https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/op200195m (2011).","DOI":"10.1021\/op200195m"},{"key":"62825_CR14","doi-asserted-by":"publisher","first-page":"8942","DOI":"10.1002\/anie.201612462","volume":"56","author":"M H\u00f6nig","year":"2017","unstructured":"H\u00f6nig, M., Sondermann, P., Turner, N. J. & Carreira, E. M. Enantioselective chemo- and biocatalysis: partners in retrosynthesis. Angew. Chem. Int. Ed. 56, 8942\u20138973 (2017).","journal-title":"Angew. Chem. Int. Ed."},{"key":"62825_CR15","doi-asserted-by":"crossref","unstructured":"Stout, C. N. & Renata, H. Reinvigorating the chiral pool: chemoenzymatic approaches to complex peptides and terpenoids. Acc. Chem. Res. 54, 1143\u20131156 (2021).","DOI":"10.1021\/acs.accounts.0c00823"},{"key":"62825_CR16","doi-asserted-by":"publisher","first-page":"1094","DOI":"10.1002\/chir.23453","volume":"34","author":"Y Teng","year":"2022","unstructured":"Teng, Y. et al. Advances and applications of chiral resolution in pharmaceutical field. Chirality 34, 1094\u20131119 (2022).","journal-title":"Chirality"},{"key":"62825_CR17","doi-asserted-by":"publisher","first-page":"1337","DOI":"10.1016\/j.tetasy.2006.04.036","volume":"17","author":"FC Ferreira","year":"2006","unstructured":"Ferreira, F. C., Ghazali, N. F., Cocchini, U. & Livingston, A. G. Rational approach to the selection of conditions for diastereomeric resolution of chiral amines by diacid resolving agents. Tetrahedron. Asymmetry 17, 1337\u20131348 (2006).","journal-title":"Tetrahedron. Asymmetry"},{"key":"62825_CR18","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1002\/chir.22564","volume":"28","author":"Z Szeleczky","year":"2016","unstructured":"Szeleczky, Z. et al. Selecting resolving agents with respect to their eutectic compositions. Chirality 28, 230\u2013234 (2016).","journal-title":"Chirality"},{"key":"62825_CR19","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1038\/s41557-023-01393-w","volume":"16","author":"E King-Smith","year":"2024","unstructured":"King-Smith, E. et al. Probing the chemical \u201cReactome\" with high throughput experimentation data. Nat. Chem. 16, 633\u2013643 (2024).","journal-title":"Nat. Chem."},{"key":"62825_CR20","doi-asserted-by":"publisher","first-page":"4017","DOI":"10.1016\/S0957-4166(00)00373-6","volume":"11","author":"M Pallavicini","year":"2000","unstructured":"Pallavicini, M., Valoti, E., Villa, L. & Piccolo, O. Resolution of \u03b2-unsaturated amines with isopropylidene glycerol hydrogen phthalate. Tetrahedron. Asymmetry 11, 4017\u20134025 (2000).","journal-title":"Tetrahedron. Asymmetry"},{"key":"62825_CR21","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1002\/chir.20695","volume":"22","author":"Q He","year":"2010","unstructured":"He, Q., Peng, Y.-F. & Rohani, S. Diastereomeric resolution of p-chloromandelic acid with (R)-phenylethylamine. Chirality 22, 16\u201323 (2010).","journal-title":"Chirality"},{"key":"62825_CR22","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1109\/TNNLS.2013.2292894","volume":"25","author":"B Frenay","year":"2014","unstructured":"Frenay, B. & Verleysen, M. Classification in the presence of label noise: a survey. IEEE Trans. Neural Netw. Learn. Syst. 25, 845\u2013869 (2014).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"62825_CR23","doi-asserted-by":"publisher","unstructured":"Sukhbaatar, S., Bruna, J., Paluri, M., Bourdev, L. & Fergus, R. Training convolutional networks with noisy labels. https:\/\/doi.org\/10.48550\/arXiv.1406.2080 (2015).","DOI":"10.48550\/arXiv.1406.2080"},{"key":"62825_CR24","doi-asserted-by":"publisher","first-page":"2406","DOI":"10.1021\/acs.cgd.2c01376","volume":"23","author":"MH Bosits","year":"2023","unstructured":"Bosits, M. H. et al. Population balance modeling of diastereomeric salt resolution. Cryst. Growth Des. 23, 2406\u20132416 (2023).","journal-title":"Cryst. Growth Des."},{"key":"62825_CR25","doi-asserted-by":"publisher","first-page":"5326","DOI":"10.1021\/jp068530q","volume":"111","author":"PG Karamertzanis","year":"2007","unstructured":"Karamertzanis, P. G. et al. Toward the computational design of diastereomeric resolving agents: an experimental and computational study of 1-Phenylethylammonium-2-phenylacetate derivatives. J. Phys. Chem. B 111, 5326\u20135336 (2007).","journal-title":"J. Phys. Chem. B"},{"key":"62825_CR26","doi-asserted-by":"publisher","first-page":"184115","DOI":"10.1103\/PhysRevB.87.184115","volume":"87","author":"AP Bart\u00f3k","year":"2013","unstructured":"Bart\u00f3k, A. P., Kondor, R. & Cs\u00e1nyi, G. On representing chemical environments. Phys. Rev. B 87, 184115 (2013).","journal-title":"Phys. Rev. B"},{"key":"62825_CR27","doi-asserted-by":"publisher","first-page":"1153","DOI":"10.1137\/15M1054183","volume":"14","author":"AV Shapeev","year":"2016","unstructured":"Shapeev, A. V. Moment tensor potentials: a class of systematically improvable interatomic potentials. Multiscale Model. Simul. 14, 1153\u20131173 (2016).","journal-title":"Multiscale Model. Simul."},{"key":"62825_CR28","doi-asserted-by":"publisher","first-page":"014104","DOI":"10.1103\/PhysRevB.99.014104","volume":"99","author":"R Drautz","year":"2019","unstructured":"Drautz, R. Atomic cluster expansion for accurate and transferable interatomic potentials. Phys. Rev. B 99, 014104 (2019).","journal-title":"Phys. Rev. B"},{"key":"62825_CR29","first-page":"5255","volume":"13","author":"FA Faber","year":"2017","unstructured":"Faber, F. A. et al. Prediction errors of molecular machine learning models lower than hybrid DFT error. JCTC 13, 5255\u20135264 (2017).","journal-title":"JCTC"},{"key":"62825_CR30","doi-asserted-by":"publisher","first-page":"6924","DOI":"10.1039\/C7SC02267K","volume":"8","author":"M Gastegger","year":"2017","unstructured":"Gastegger, M., Behler, J. & Marquetand, P. Machine learning molecular dynamics for the simulation of infrared spectra. Chem. Sci. 8, 6924\u20136935 (2017).","journal-title":"Chem. Sci."},{"key":"62825_CR31","doi-asserted-by":"publisher","first-page":"241717","DOI":"10.1063\/1.5020710","volume":"148","author":"FA Faber","year":"2018","unstructured":"Faber, F. A., Christensen, A. S., Huang, B. & Von Lilienfeld, O. A. Alchemical and structural distribution based representation for universal quantum machine learning. J. Chem. Phys. 148, 241717 (2018).","journal-title":"J. Chem. Phys."},{"key":"62825_CR32","doi-asserted-by":"publisher","first-page":"105001","DOI":"10.1088\/1367-2630\/ab4509","volume":"21","author":"N Raimbault","year":"2019","unstructured":"Raimbault, N., Grisafi, A., Ceriotti, M. & Rossi, M. Using Gaussian process regression to simulate the vibrational Raman spectra of molecular crystals. N. J. Phys. 21, 105001 (2019).","journal-title":"N. J. Phys."},{"key":"62825_CR33","doi-asserted-by":"publisher","first-page":"3401","DOI":"10.1073\/pnas.1816132116","volume":"116","author":"DM Wilkins","year":"2019","unstructured":"Wilkins, D. M. et al. Accurate molecular polarizabilities with coupled cluster theory and machine learning. Proc. Natl. Acad. Sci. 116, 3401\u20133406 (2019).","journal-title":"Proc. Natl. Acad. Sci."},{"key":"62825_CR34","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":"62825_CR35","doi-asserted-by":"publisher","first-page":"014106","DOI":"10.1063\/1.4973380","volume":"146","author":"K Yao","year":"2017","unstructured":"Yao, K., Herr, J. E. & Parkhill, J. The many-body expansion combined with neural networks. J. Chem. Phys. 146, 014106 (2017).","journal-title":"J. Chem. Phys."},{"key":"62825_CR36","doi-asserted-by":"publisher","first-page":"10073","DOI":"10.1021\/acs.chemrev.1c00022","volume":"121","author":"VL Deringer","year":"2021","unstructured":"Deringer, V. L. et al. Gaussian process regression for materials and molecules. Chem. Rev. 121, 10073\u201310141 (2021).","journal-title":"Chem. Rev."},{"key":"62825_CR37","doi-asserted-by":"publisher","unstructured":"Batatia, I., Kov\u00e1cs, D. P., Simm, G. N. C., Ortner, C. & Cs\u00e1nyi, G. MACE: higher order equivariant message passing neural networks for fast and accurate force fields. https:\/\/doi.org\/10.48550\/arXiv.2206.07697 (2022).","DOI":"10.48550\/arXiv.2206.07697"},{"key":"62825_CR38","doi-asserted-by":"publisher","unstructured":"Bahdanau, D., Cho, K. & Bengio, Y. Neural machine translation by jointly learning to align and translate. https:\/\/doi.org\/10.48550\/arXiv.1409.0473 (2016).","DOI":"10.48550\/arXiv.1409.0473"},{"key":"62825_CR39","doi-asserted-by":"publisher","unstructured":"Vaswani, A. et al. Attention is all you need. https:\/\/doi.org\/10.48550\/arXiv.1706.03762 (2017).","DOI":"10.48550\/arXiv.1706.03762"},{"key":"62825_CR40","doi-asserted-by":"publisher","unstructured":"Brown, T. B. et al. Language models are few-shot learners. https:\/\/doi.org\/10.48550\/arXiv.2005.14165 (2020).","DOI":"10.48550\/arXiv.2005.14165"},{"key":"62825_CR41","doi-asserted-by":"publisher","unstructured":"Rae, J. W. et al. Scaling language models: methods, analysis & insights from training Gopher. https:\/\/doi.org\/10.48550\/arXiv.2112.11446 (2022).","DOI":"10.48550\/arXiv.2112.11446"},{"key":"62825_CR42","doi-asserted-by":"publisher","unstructured":"Lewkowycz, A. et al. Solving quantitative reasoning problems with language models. https:\/\/doi.org\/10.48550\/arXiv.2206.14858 (2022).","DOI":"10.48550\/arXiv.2206.14858"},{"key":"62825_CR43","doi-asserted-by":"publisher","unstructured":"Achiam, J. et al. Gpt-4 technical report. https:\/\/doi.org\/10.48550\/arXiv.2303.08774 (2023).","DOI":"10.48550\/arXiv.2303.08774"},{"key":"62825_CR44","doi-asserted-by":"publisher","unstructured":"Touvron, H. et al. LLaMA: open and efficient foundation language models. https:\/\/doi.org\/10.48550\/arXiv.2302.13971 (2023).","DOI":"10.48550\/arXiv.2302.13971"},{"key":"62825_CR45","doi-asserted-by":"publisher","first-page":"1572","DOI":"10.1021\/acscentsci.9b00576","volume":"5","author":"P Schwaller","year":"2019","unstructured":"Schwaller, P. et al. Molecular transformer: a model for uncertainty-calibrated chemical reaction prediction. ACS Cent. Sci. 5, 1572\u20131583 (2019).","journal-title":"ACS Cent. Sci."},{"key":"62825_CR46","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","volume":"596","author":"J Jumper","year":"2021","unstructured":"Jumper, J. et al. Highly accurate protein structure prediction with AlphaFold. Nature 596, 583\u2013589 (2021).","journal-title":"Nature"},{"key":"62825_CR47","doi-asserted-by":"publisher","unstructured":"Kreuzer, D., Beaini, D., Hamilton, W. L., L\u00e9tourneau, V. & Tossou, P. Rethinking Graph Transformers with Spectral Attention. https:\/\/doi.org\/10.48550\/arXiv.2106.03893 (2021).","DOI":"10.48550\/arXiv.2106.03893"},{"key":"62825_CR48","doi-asserted-by":"crossref","unstructured":"Bran, A. M. et al. Augmenting large language models with chemistry tools. Nat. Mach. Intell. 6, 525\u2013535 (2024).","DOI":"10.1038\/s42256-024-00832-8"},{"key":"62825_CR49","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-39868-6","volume":"14","author":"C Kuenneth","year":"2023","unstructured":"Kuenneth, C. & Ramprasad, R. polyBERT: a chemical language model to enable fully machine-driven ultrafast polymer informatics. Nat. Commun. 14, 4099 (2023).","journal-title":"Nat. Commun."},{"key":"62825_CR50","doi-asserted-by":"publisher","unstructured":"Zhang, D. et al. ChemLLM: a chemical large language model. https:\/\/doi.org\/10.48550\/arXiv.2402.06852 (2024).","DOI":"10.48550\/arXiv.2402.06852"},{"key":"62825_CR51","doi-asserted-by":"publisher","first-page":"2351","DOI":"10.1021\/acs.analchem.3c04028","volume":"96","author":"Y Hong","year":"2024","unstructured":"Hong, Y., Welch, C. J., Piras, P. & Tang, H. Enhanced structure-based prediction of chiral stationary phases for chromatographic enantioseparation from 3D molecular conformations. Anal. Chem. 96, 2351\u20132359 (2024).","journal-title":"Anal. Chem."},{"key":"62825_CR52","doi-asserted-by":"publisher","first-page":"1297","DOI":"10.1038\/s42256-023-00740-3","volume":"5","author":"NC Frey","year":"2023","unstructured":"Frey, N. C. et al. Neural scaling of deep chemical models. Nat. Mach. Intell. 5, 1297\u20131305 (2023).","journal-title":"Nat. Mach. Intell."},{"key":"62825_CR53","doi-asserted-by":"publisher","first-page":"eabe4166","DOI":"10.1126\/sciadv.abe4166","volume":"7","author":"P Schwaller","year":"2021","unstructured":"Schwaller, P., Hoover, B., Reymond, J.-L., Strobelt, H. & Laino, T. Extraction of organic chemistry grammar from unsupervised learning of chemical reactions. Sci. Adv. 7, eabe4166 (2021).","journal-title":"Sci. Adv."},{"key":"62825_CR54","unstructured":"Jain, S. & Wallace, B. C. Attention is not explanation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (eds Burstein, J., Doran, C. & Solorio, T.) Vol. 1 (Long and Short Papers), 3543\u20133556, (Association for Computational Linguistics, 2019)."},{"key":"62825_CR55","doi-asserted-by":"publisher","unstructured":"Wiegreffe, S. & Pinter, Y. Attention is not not explanation. https:\/\/doi.org\/10.48550\/arXiv.1908.04626 (2019).","DOI":"10.48550\/arXiv.1908.04626"},{"key":"62825_CR56","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":"62825_CR57","doi-asserted-by":"publisher","unstructured":"Wagner, J. et al. Openforcefield\/openff-forcefields: Version 2.0.0 \u201cSage\u201d. Zenodo https:\/\/doi.org\/10.5281\/zenodo.5214478 (2021).","DOI":"10.5281\/zenodo.5214478"},{"key":"62825_CR58","doi-asserted-by":"publisher","unstructured":"Zills, F., Sch\u00e4fer, M., Tovey, S., K\u00e4stner, J. & Holm, C. ZnTrack\u2014Data as code. https:\/\/doi.org\/10.48550\/arXiv.2401.10603 (2024).","DOI":"10.48550\/arXiv.2401.10603"},{"key":"62825_CR59","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00894-012-1667-x","volume":"19","author":"JJP Stewart","year":"2013","unstructured":"Stewart, J. J. P. Optimization of parameters for semiempirical methods VI: more modifications to the NDDO approximations and re-optimization of parameters. J. Mol. Model 19, 1\u201332 (2013).","journal-title":"J. Mol. Model"},{"key":"62825_CR60","unstructured":"Stewart, J. J. P. Mopac2016 http:\/\/OpenMOPAC.net (Stewart Computational Chemistry, 2016)."},{"key":"62825_CR61","unstructured":"COSMOlogic GmbH & Co. KG. COSMOtherm, Release 19. http:\/\/cosmologic.de."},{"key":"62825_CR62","doi-asserted-by":"publisher","first-page":"2224","DOI":"10.1021\/j100007a062","volume":"99","author":"A Klamt","year":"1995","unstructured":"Klamt, A. Conductor-like screening model for real solvents: a new approach to the quantitative calculation of solvation phenomena. J. Phys. Chem. 99, 2224\u20132235 (1995).","journal-title":"J. Phys. Chem."},{"key":"62825_CR63","doi-asserted-by":"publisher","first-page":"5074","DOI":"10.1021\/jp980017s","volume":"102","author":"A Klamt","year":"1998","unstructured":"Klamt, A., Jonas, V., B\u00fcrger, T. & Lohrenz, J. C. W. Refinement and parametrization of COSMO-RS. J. Phys. Chem. A 102, 5074\u20135085 (1998).","journal-title":"J. Phys. Chem. A"},{"key":"62825_CR64","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1002\/aic.690480220","volume":"48","author":"F Eckert","year":"2002","unstructured":"Eckert, F. & Klamt, A. Fast solvent screening via quantum chemistry: COSMO-RS approach. AIChE J. 48, 369\u2013385 (2002).","journal-title":"AIChE J."},{"key":"62825_CR65","doi-asserted-by":"publisher","first-page":"6697","DOI":"10.1039\/C9SC01844A","volume":"10","author":"Y Amar","year":"2019","unstructured":"Amar, Y., Schweidtmann, A. M., Deutsch, P., Cao, L. & Lapkin, A. Machine learning and molecular descriptors enable rational solvent selection in asymmetric catalysis. Chem. Sci. 10, 6697\u20136706 (2019).","journal-title":"Chem. Sci."},{"key":"62825_CR66","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1016\/j.ijggc.2016.03.022","volume":"49","author":"G Gonfa","year":"2016","unstructured":"Gonfa, G., Bustam, M. A. & Shariff, A. M. Quantum-chemical-based quantitative structure-activity relationships for estimation of CO2 absorption\/desorption capacities of amine-based absorbents. Int. J. Greenh. Gas. Control 49, 372\u2013378 (2016).","journal-title":"Int. J. Greenh. Gas. Control"},{"key":"62825_CR67","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1002\/aic.14630","volume":"61","author":"T Zhou","year":"2015","unstructured":"Zhou, T., McBride, K., Zhang, X., Qi, Z. & Sundmacher, K. Integrated solvent and process design exemplified for a Diels\u2013Alder reaction. AIChE J. 61, 147\u2013158 (2015).","journal-title":"AIChE J."},{"key":"62825_CR68","doi-asserted-by":"crossref","unstructured":"Akiba, T., Sano, S., Yanase, T., Ohta, T. & Koyama, M. Optuna: A next-generation hyperparameter optimization framework. In Proc. 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (ACM, 2019).","DOI":"10.1145\/3292500.3330701"},{"key":"62825_CR69","doi-asserted-by":"publisher","unstructured":"Elijo\u0161ius, R. et al. Supporting data: predictive design of crystallographic chiral separation. https:\/\/doi.org\/10.5061\/dryad.d2547d89c (2025).","DOI":"10.5061\/dryad.d2547d89c"},{"key":"62825_CR70","doi-asserted-by":"publisher","unstructured":"Elijo\u0161ius, R. RokasEl\/DiastereomericResolutions: predictive design of crystallographic chiral Separation. https:\/\/doi.org\/10.5281\/zenodo.15783253 (2025).","DOI":"10.5281\/zenodo.15783253"},{"key":"62825_CR71","doi-asserted-by":"publisher","unstructured":"Elijo\u0161ius, R. RokasEl\/3dmolcsp-diastereomeric-resolutions: predictive design of crystallographic chiral Separation. https:\/\/doi.org\/10.5281\/zenodo.15783255 (2025).","DOI":"10.5281\/zenodo.15783255"}],"container-title":["Nature Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41467-025-62825-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-025-62825-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-025-62825-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T18:20:31Z","timestamp":1757442031000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41467-025-62825-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,26]]},"references-count":71,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["62825"],"URL":"https:\/\/doi.org\/10.1038\/s41467-025-62825-4","relation":{},"ISSN":["2041-1723"],"issn-type":[{"value":"2041-1723","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,26]]},"assertion":[{"value":"22 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 August 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A.A.L. is a co-founder and owns equity in PostEra Inc. and Byterat Ltd. L.B., S.B., X.H., J.L.K.M., J.M., N.W.S., Q.Y., and R.M.H. are employed by Pfizer Inc. WPF is employed by Virscidian Inc. and formerly at Pfizer. F.A.F. is employed by AstraZeneca at the time of publication; however, none of the work presented in this manuscript was conducted at or influenced by this affiliation. The remaining authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"7977"}}