{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,16]],"date-time":"2026-11-16T22:01:49Z","timestamp":1794866509377,"version":"4.9.1"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T00:00:00Z","timestamp":1791763200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T00:00:00Z","timestamp":1791763200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Drug Discov."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    In modern peptide drug discovery, the incorporation of noncanonical amino acids (ncAAs) has become a powerful strategy to improve potency and key developability properties, including stability, solubility, and oral bioavailability. This shift has expanded peptide chemical diversity and design spaces well beyond natural residues, creating fundamental challenges for predictive methods (e.g., quantitative structure-activity relationship modeling) used in lead optimization: limited transferability from natural residues to novel ncAAs, limited interpretability, and poor scalability to ultralarge peptide spaces (&gt;10\n                    <jats:sup>50<\/jats:sup>\n                    ). We present PepOpt, an interpretable machine learning framework that unifies molecule-based and sequence-based peptide representations in linear models and exploits dynamic programming to efficiently explore ultralarge peptide spaces. PepOpt achieves high predictive accuracy and interpretability, supports training and inference across diverse ncAAs, including ncAAs absent from the training set whose constituent substructures are represented in the training data. Its linear structure decomposes predictions into residue-specific contributions, enabling systematic optimization without exhaustive sequence enumeration. Notably, PepOpt is inherently capable of multi-parameter optimization without specialized modifications. Together, these capabilities position PepOpt as a valuable platform for prediction, interpretation, ideation, and rapid exploration in ncAA-rich ultralarge peptide chemical spaces, accelerating the rational design of novel peptide therapeutics.\n                  <\/jats:p>","DOI":"10.1038\/s44386-026-00069-y","type":"journal-article","created":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T13:02:55Z","timestamp":1791810175000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Interpretable machine learning framework for peptide lead optimization in ultralarge design spaces"],"prefix":"10.1038","volume":"3","author":[{"given":"Yixiang","family":"Mao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruibo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Sheridan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Sindhikara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dipannita","family":"Kalyani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amy B.","family":"McCracken","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bryant","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shasha","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianxiong","family":"Mi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher W.","family":"Plummer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jennifer M.","family":"Johnston","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liying","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,10,12]]},"reference":[{"key":"69_CR1","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.3390\/ijms25031798","volume":"25","author":"M Vincenzi","year":"2024","unstructured":"Vincenzi, M., Mercurio, F. A. & Leone, M. Virtual screening of peptide libraries: the search for peptide-based therapeutics using computational tools. Int. J. Mol. Sci. 25, 1798 (2024).","journal-title":"Int. J. Mol. Sci."},{"key":"69_CR2","doi-asserted-by":"publisher","first-page":"4167","DOI":"10.1021\/jacs.8b13178","volume":"141","author":"AA Vinogradov","year":"2019","unstructured":"Vinogradov, A. A., Yin, Y. & Suga, H. Macrocyclic peptides as drug candidates: recent progress and remaining challenges. J. Am. Chem. Soc. 141, 4167\u20134181 (2019).","journal-title":"J. Am. Chem. Soc."},{"key":"69_CR3","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1021\/acsmedchemlett.3c00037","volume":"14","author":"JL Hickey","year":"2023","unstructured":"Hickey, J. L., Sindhikara, D., Zultanski, S. L. & Schultz, D. M. Beyond 20 in the 21st century: prospects and challenges of non-canonical amino acids in peptide drug discovery. ACS Med. Chem. Lett. 14, 557\u2013565 (2023).","journal-title":"ACS Med. Chem. Lett."},{"key":"69_CR4","doi-asserted-by":"publisher","first-page":"FDD75","DOI":"10.4155\/fdd-2022-0005","volume":"4","author":"C Lamers","year":"2022","unstructured":"Lamers, C. Overcoming the shortcomings of peptide-based therapeutics. Future Drug Discov. 4, FDD75 (2022).","journal-title":"Future Drug Discov."},{"key":"69_CR5","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1016\/j.drudis.2013.10.011","volume":"19","author":"K Josephson","year":"2014","unstructured":"Josephson, K., Ricardo, A. & Szostak, J. W. mRNA display: from basic principles to macrocycle drug discovery. Drug Discov. Today 19, 388\u2013399 (2014).","journal-title":"Drug Discov. Today"},{"key":"69_CR6","doi-asserted-by":"publisher","first-page":"16770","DOI":"10.1021\/acs.jmedchem.1c01599","volume":"64","author":"TJ Tucker","year":"2021","unstructured":"Tucker, T. J. et al. A series of novel, highly potent, and orally bioavailable next-generation tricyclic peptide PCSK9 inhibitors. J. Med. Chem. 64, 16770\u201316800 (2021).","journal-title":"J. Med. Chem."},{"key":"69_CR7","doi-asserted-by":"publisher","first-page":"1784","DOI":"10.1056\/NEJMoa2504187","volume":"393","author":"R Bissonnette","year":"2025","unstructured":"Bissonnette, R. et al. Oral icotrokinra for plaque psoriasis in adults and adolescents. N. Engl. J. Med. 393, 1784\u20131795 (2025).","journal-title":"N. Engl. J. Med."},{"key":"69_CR8","first-page":"1","volume":"1","author":"JC Dearden","year":"2016","unstructured":"Dearden, J. C. The history and development of quantitative structure-activity relationships (QSARs). Int. J. Quant. Struct. Prop. Relatsh. 1, 1\u201344 (2016).","journal-title":"Int. J. Quant. Struct. Prop. Relatsh."},{"key":"69_CR9","doi-asserted-by":"publisher","first-page":"3275","DOI":"10.1021\/acs.jcim.2c00699","volume":"62","author":"RP Sheridan","year":"2022","unstructured":"Sheridan, R. P., Culberson, J. C., Joshi, E., Tudor, M. & Karnachi, P. Prediction accuracy of production ADMET models as a function of version: activity Cliffs rule. J. Chem. Inf. Model. 62, 3275\u20133280 (2022).","journal-title":"J. Chem. Inf. Model."},{"key":"69_CR10","doi-asserted-by":"publisher","first-page":"1279","DOI":"10.1007\/s00204-022-03252-y","volume":"96","author":"P De","year":"2022","unstructured":"De, P., Kar, S., Ambure, P. & Roy, K. Prediction reliability of QSAR models: an overview of various validation tools. Arch. Toxicol. 96, 1279\u20131295 (2022).","journal-title":"Arch. Toxicol."},{"key":"69_CR11","doi-asserted-by":"publisher","first-page":"bbac128","DOI":"10.1093\/bib\/bbac128","volume":"23","author":"R Zhang","year":"2022","unstructured":"Zhang, R., Ghosh, S. & Pal, R. Predicting binding affinities of emerging variants of SARS-CoV-2 using spike protein sequencing data: observations, caveats and recommendations. Brief. Bioinform. 23, bbac128 (2022).","journal-title":"Brief. Bioinform."},{"key":"69_CR12","doi-asserted-by":"publisher","first-page":"10037","DOI":"10.3390\/ijms262010037","volume":"26","author":"Q Wang","year":"2025","unstructured":"Wang, Q. et al. Progress of AI-driven drug-target interaction prediction and lead optimization. Int. J. Mol. Sci. 26, 10037 (2025).","journal-title":"Int. J. Mol. Sci."},{"key":"69_CR13","doi-asserted-by":"publisher","first-page":"1126","DOI":"10.1021\/jm00390a003","volume":"30","author":"S Hellberg","year":"1987","unstructured":"Hellberg, S., Sjoestroem, M., Skagerberg, B. & Wold, S. Peptide quantitative structure-activity relationships, a multivariate approach. J. Med. Chem. 30, 1126\u20131135 (1987).","journal-title":"J. Med. Chem."},{"key":"69_CR14","doi-asserted-by":"publisher","first-page":"25760","DOI":"10.1021\/acsomega.2c03062","volume":"7","author":"Z Du","year":"2022","unstructured":"Du, Z., Wang, D. & Li, Y. Comprehensive evaluation and comparison of machine learning methods in QSAR modeling of antioxidant tripeptides. ACS Omega 7, 25760\u201325771 (2022).","journal-title":"ACS Omega"},{"key":"69_CR15","doi-asserted-by":"publisher","first-page":"882","DOI":"10.1016\/j.omtn.2020.05.006","volume":"20","author":"J Yan","year":"2020","unstructured":"Yan, J. et al. Deep-AmPEP30: improve short antimicrobial peptides prediction with deep learning. Mol. Ther. Nucleic Acids 20, 882\u2013894 (2020).","journal-title":"Mol. Ther. Nucleic Acids"},{"key":"69_CR16","doi-asserted-by":"publisher","first-page":"797","DOI":"10.1038\/s41551-022-00991-2","volume":"7","author":"J Huang","year":"2023","unstructured":"Huang, J. et al. Identification of potent antimicrobial peptides via a machine-learning pipeline that mines the entire space of peptide sequences. Nat. Biomed. Eng. 7, 797\u2013810 (2023).","journal-title":"Nat. Biomed. Eng."},{"key":"69_CR17","doi-asserted-by":"publisher","first-page":"1888","DOI":"10.1021\/acs.jmedchem.3c01611","volume":"67","author":"L Cao","year":"2024","unstructured":"Cao, L. et al. Multi_CycGT: a deep learning-based multimodal model for predicting the membrane permeability of cyclic peptides. J. Med. Chem. 67, 1888\u20131899 (2024).","journal-title":"J. Med. Chem."},{"key":"69_CR18","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1039\/D4ME00172A","volume":"10","author":"DG Otero","year":"2024","unstructured":"Otero, D. G., Akbari, O. & Bilodeau, C. PepMNet: a hybrid deep learning model for predicting peptide properties using hierarchical graph representations. Mol. Syst. Des. Eng. 10, 205\u2013218 (2024).","journal-title":"Mol. Syst. Des. Eng."},{"key":"69_CR19","doi-asserted-by":"publisher","first-page":"4116","DOI":"10.1021\/acs.molpharmaceut.4c00478","volume":"21","author":"X Tan","year":"2024","unstructured":"Tan, X. et al. Predicting peptide permeability across diverse barriers: a systematic investigation. Mol. Pharm. 21, 4116\u20134127 (2024).","journal-title":"Mol. Pharm."},{"key":"69_CR20","doi-asserted-by":"publisher","first-page":"bbaf367","DOI":"10.1093\/bib\/bbaf367","volume":"26","author":"R Zhang","year":"2025","unstructured":"Zhang, R. et al. Pepland: a large-scale pre-trained peptide representation model for a comprehensive landscape of both canonical and non-canonical amino acids. Brief. Bioinform. 26, bbaf367 (2025).","journal-title":"Brief. Bioinform."},{"key":"69_CR21","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1021\/acs.jcim.4c01441","volume":"65","author":"AL Feller","year":"2025","unstructured":"Feller, A. L. & Wilke, C. O. Peptide-aware chemical language model successfully predicts membrane diffusion of cyclic peptides. J. Chem. Inf. Model. 65, 571\u2013579 (2025).","journal-title":"J. Chem. Inf. Model."},{"key":"69_CR22","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1021\/jm00334a001","volume":"7","author":"SM Free","year":"1964","unstructured":"Free, S. M. & Wilson, J. W. A mathematical contribution to structure-activity studies. J. Med. Chem. 7, 395\u2013399 (1964).","journal-title":"J. Med. Chem."},{"key":"69_CR23","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1021\/pr015513z","volume":"1","author":"IA Doytchinova","year":"2002","unstructured":"Doytchinova, I. A., Blythe, M. J. & Flower, D. R. Additive method for the prediction of protein-peptide binding affinity. Application to the MHC class I molecule HLA-A*0201. J. Proteome Res. 1, 263\u2013272 (2002).","journal-title":"J. Proteome Res."},{"key":"69_CR24","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1021\/jm9700575","volume":"41","author":"M Sandberg","year":"1998","unstructured":"Sandberg, M., Eriksson, L., Jonsson, J., Sj\u00f6str\u00f6m, M. & Wold, S. New chemical descriptors relevant for the design of biologically active peptides. A multivariate characterization of 87 amino acids. J. Med. Chem. 41, 2481\u20132491 (1998).","journal-title":"J. Med. Chem."},{"key":"69_CR25","doi-asserted-by":"publisher","first-page":"2021","DOI":"10.1021\/acs.jcim.2c00224","volume":"62","author":"WA Warr","year":"2022","unstructured":"Warr, W. A., Nicklaus, M. C., Nicolaou, C. A. & Rarey, M. Exploration of ultralarge compound collections for drug discovery. J. Chem. Inf. Model. 62, 2021\u20132034 (2022).","journal-title":"J. Chem. Inf. Model."},{"key":"69_CR26","doi-asserted-by":"publisher","first-page":"1158","DOI":"10.1021\/acs.jcim.3c01790","volume":"64","author":"K Klarich","year":"2024","unstructured":"Klarich, K., Goldman, B., Kramer, T., Riley, P. & Walters, W. P. Thompson sampling-an efficient method for searching ultralarge synthesis on demand databases. J. Chem. Inf. Model. 64, 1158\u20131171 (2024).","journal-title":"J. Chem. Inf. Model."},{"key":"69_CR27","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1021\/acs.jcim.9b01014","volume":"60","author":"A Capecchi","year":"2020","unstructured":"Capecchi, A., Zhang, A. & Reymond, J.-L. Populating chemical space with peptides using a genetic algorithm. J. Chem. Inf. Model. 60, 121\u2013132 (2020).","journal-title":"J. Chem. Inf. Model."},{"key":"69_CR28","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1038\/s42004-025-01758-x","volume":"8","author":"P Eisenhuth","year":"2025","unstructured":"Eisenhuth, P., Liessmann, F., Moretti, R. & Meiler, J. Ultra-large library screening with an evolutionary algorithm in Rosetta (REvoLd). Commun. Chem. 8, 335 (2025).","journal-title":"Commun. Chem."},{"key":"69_CR29","doi-asserted-by":"publisher","first-page":"e202400186","DOI":"10.1002\/minf.202400186","volume":"44","author":"M Orsi","year":"2025","unstructured":"Orsi, M. & Reymond, J. Navigating a 1E+60 chemical space of peptide\/peptoid oligomers. Mol. Inform. 44, e202400186 (2025).","journal-title":"Mol. Inform."},{"key":"69_CR30","doi-asserted-by":"publisher","first-page":"1560","DOI":"10.1021\/acs.jcim.4c00049","volume":"64","author":"GA Landrum","year":"2024","unstructured":"Landrum, G. A. & Riniker, S. Combining IC50 or k i values from different sources is a source of significant noise. J. Chem. Inf. Model. 64, 1560\u20131567 (2024).","journal-title":"J. Chem. Inf. Model."},{"key":"69_CR31","doi-asserted-by":"publisher","first-page":"9398","DOI":"10.1021\/acs.jcim.5c01609","volume":"65","author":"JR Ash","year":"2025","unstructured":"Ash, J. R. et al. Practically significant method comparison protocols for machine learning in small molecule drug discovery. J. Chem. Inf. Model. 65, 9398\u20139411 (2025).","journal-title":"J. Chem. Inf. Model."},{"key":"69_CR32","doi-asserted-by":"publisher","first-page":"99","DOI":"10.2307\/3001913","volume":"5","author":"JW TUKEY","year":"1949","unstructured":"TUKEY, J. W. Comparing individual means in the analysis of variance. Biometrics 5, 99\u2013114 (1949).","journal-title":"Biometrics"},{"key":"69_CR33","doi-asserted-by":"publisher","first-page":"e0130140","DOI":"10.1371\/journal.pone.0130140","volume":"10","author":"S Bach","year":"2015","unstructured":"Bach, S. et al. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE 10, e0130140 (2015).","journal-title":"PLoS ONE"},{"key":"69_CR34","unstructured":"Lundberg, S. M. & Lee, S.-I. A unified approach to interpreting model predictions. Advances in neural information processing systems 30 (2017)."},{"key":"69_CR35","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1021\/acs.jcim.7b00026","volume":"58","author":"V Yordanov","year":"2018","unstructured":"Yordanov, V., Dimitrov, I. & Doytchinova, I. Proteochemometrics-based prediction of peptide binding to HLA-DP proteins. J. Chem. Inf. Model. 58, 297\u2013304 (2018).","journal-title":"J. Chem. Inf. Model."},{"key":"69_CR36","doi-asserted-by":"publisher","first-page":"2024","DOI":"10.1016\/j.str.2016.09.006","volume":"24","author":"SM Ivanov","year":"2016","unstructured":"Ivanov, S. M., Huber, R. G., Warwicker, J. & Bond, P. J. Energetics and dynamics across the Bcl-2-regulated apoptotic pathway reveal distinct evolutionary determinants of specificity and affinity. Structure 24, 2024\u20132033 (2016).","journal-title":"Structure"},{"key":"69_CR37","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1021\/acs.jcim.8b00765","volume":"59","author":"SM Ivanov","year":"2018","unstructured":"Ivanov, S. M., Huber, R. G., Alibay, I., Warwicker, J. & Bond, P. J. Energetic fingerprinting of ligand binding to paralogous proteins: the case of the apoptotic pathway. J. Chem. Inf. Model. 59, 245\u2013261 (2018).","journal-title":"J. Chem. Inf. Model."},{"key":"69_CR38","doi-asserted-by":"crossref","unstructured":"Ivanov, S. In silico isomerization produces apt negative data for VHTS validation. J. Chem. Inf. Model. (2026).","DOI":"10.26434\/chemrxiv-2026-bgc3j\/v4"},{"key":"69_CR39","doi-asserted-by":"publisher","first-page":"734","DOI":"10.1093\/bib\/bbt056","volume":"15","author":"H Ding","year":"2014","unstructured":"Ding, H., Takigawa, I., Mamitsuka, H. & Zhu, S. Similarity-based machine learning methods for predicting drug-target interactions: a brief review. Brief. Bioinform. 15, 734\u2013747 (2014).","journal-title":"Brief. Bioinform."},{"key":"69_CR40","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-49372-0","volume":"15","author":"R Zhang","year":"2024","unstructured":"Zhang, R., Nolte, D., Sanchez-Villalobos, C., Ghosh, S. & Pal, R. Topological regression as an interpretable and efficient tool for quantitative structure-activity relationship modeling. Nat. Commun. 15, 5072 (2024).","journal-title":"Nat. Commun."},{"key":"69_CR41","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-025-01071-8","volume":"17","author":"Y Mao","year":"2025","unstructured":"Mao, Y., Ghosh, S. & Pal, R. AdapTor: adaptive topological regression for quantitative structure-activity relationship modeling. J. Cheminform. 17, 128 (2025).","journal-title":"J. Cheminform."},{"key":"69_CR42","doi-asserted-by":"publisher","first-page":"1259","DOI":"10.1021\/acs.jcim.1c01360","volume":"62","author":"JL Baylon","year":"2022","unstructured":"Baylon, J. L. et al. PepSeA: peptide sequence alignment and visualization tools to enable lead optimization. J. Chem. Inf. Model. 62, 1259\u20131267 (2022).","journal-title":"J. Chem. Inf. Model."},{"key":"69_CR43","doi-asserted-by":"publisher","first-page":"3059","DOI":"10.1093\/nar\/gkf436","volume":"30","author":"K Katoh","year":"2002","unstructured":"Katoh, K., Misawa, K., Kuma, K. & Miyata, T. MAFFT: a novel method for rapid multiple sequence alignment based on fast Fourier transform. Nucleic Acids Res. 30, 3059\u20133066 (2002).","journal-title":"Nucleic Acids Res."},{"key":"69_CR44","doi-asserted-by":"publisher","first-page":"1969","DOI":"10.1021\/acs.jcim.9b01067","volume":"60","author":"RP Sheridan","year":"2020","unstructured":"Sheridan, R. P. et al. Experimental error, kurtosis, activity cliffs, and methodology: what limits the predictivity of quantitative structure-activity relationship models? J. Chem. Inf. Model. 60, 1969\u20131982 (2020).","journal-title":"J. Chem. Inf. Model."},{"key":"69_CR45","unstructured":"RDKit: Open-source cheminformatics. http:\/\/www.rdkit.org. Accessed: 2025-11-14."},{"key":"69_CR46","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-018-0258-y","volume":"10","author":"H Moriwaki","year":"2018","unstructured":"Moriwaki, H., Tian, Y.-S., Kawashita, N. & Takagi, T. Mordred: a molecular descriptor calculator. J. Cheminform. 10, 4 (2018).","journal-title":"J. Cheminform."},{"key":"69_CR47","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1080\/00401706.1970.10488635","volume":"12","author":"AE Hoerl","year":"1970","unstructured":"Hoerl, A. E. & Kennard, R. W. Ridge regression: applications to nonorthogonal problems. Technometrics 12, 69\u201382 (1970).","journal-title":"Technometrics"},{"key":"69_CR48","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","volume":"58","author":"R Tibshirani","year":"1996","unstructured":"Tibshirani, R. Regression shrinkage and selection via the Lasso. J. R. Stat. Soc. Ser. B 58, 267\u2013288 (1996).","journal-title":"J. R. Stat. Soc. Ser. B"},{"key":"69_CR49","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","volume":"67","author":"H Zou","year":"2005","unstructured":"Zou, H. & Hastie, T. Regularization and variable selection via the elastic net. J. R. Stat. Soc. Ser. B 67, 301\u2013320 (2005).","journal-title":"J. R. Stat. Soc. Ser. B"},{"key":"69_CR50","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1162\/neco.1992.4.3.415","volume":"4","author":"DJC MacKay","year":"1992","unstructured":"MacKay, D. J. C. Bayesian interpolation. Neural Comput. 4, 415\u2013447 (1992).","journal-title":"Neural Comput."},{"key":"69_CR51","unstructured":"Bishop, C. M. & Nasrabadi, N. M. Pattern Recognition and Machine Learning, vol. 4 (Springer, 2006)."},{"key":"69_CR52","first-page":"52","volume":"407","author":"J Cha","year":"1994","unstructured":"Cha, J. Partial least squares. Adv. Methods Mark. Res. 407, 52\u201378 (1994).","journal-title":"Adv. Methods Mark. Res."},{"key":"69_CR53","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1207\/s15328031us0304_4","volume":"3","author":"M Haenlein","year":"2004","unstructured":"Haenlein, M. & Kaplan, A. M. A beginner\u2019s guide to partial least squares analysis. Underst. Stat. 3, 283\u2013297 (2004).","journal-title":"Underst. Stat."},{"key":"69_CR54","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1021\/acs.jcim.3c01250","volume":"64","author":"E Heid","year":"2024","unstructured":"Heid, E. et al. Chemprop: a machine learning package for chemical property prediction. J. Chem. Inf. Model. 64, 9\u201317 (2024).","journal-title":"J. Chem. Inf. Model."},{"key":"69_CR55","doi-asserted-by":"crossref","unstructured":"Burns, Jackson W. et al. Deep Learning Foundation Models for Low-Data Regimes from Classical Molecular Descriptors. J. Chem. Inf. Model. (2026).","DOI":"10.1021\/acs.jcim.6c01546"},{"key":"69_CR56","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, 2623\u20132631 (ACM, 2019).","DOI":"10.1145\/3292500.3330701"}],"container-title":["npj Drug Discovery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s44386-026-00069-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s44386-026-00069-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s44386-026-00069-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T17:26:52Z","timestamp":1791826012000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s44386-026-00069-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,12]]},"references-count":56,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["69"],"URL":"https:\/\/doi.org\/10.1038\/s44386-026-00069-y","relation":{},"ISSN":["3005-1452"],"issn-type":[{"value":"3005-1452","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,12]]},"assertion":[{"value":"27 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 August 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 October 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":"Declarations"}}],"article-number":"45"}}