{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T23:39:59Z","timestamp":1792712399713,"version":"4.5.0"},"reference-count":81,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T00:00:00Z","timestamp":1789171200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T00:00:00Z","timestamp":1791936000000},"content-version":"vor","delay-in-days":32,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/100000057","name":"U.S. Department of Health & Human Services | NIH | National Institute of General Medical Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Commun"],"DOI":"10.1038\/s41467-026-77557-2","type":"journal-article","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T04:35:03Z","timestamp":1789187703000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Functional alignment of protein language models via reinforcement learning"],"prefix":"10.1038","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7993-7936","authenticated-orcid":false,"given":"Nathaniel","family":"Blalock","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Srinath","family":"Seshadri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kensuke","family":"Nakamura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Agrim","family":"Babbar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarah A.","family":"Fahlberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ameya","family":"Kulkarni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2586-7263","authenticated-orcid":false,"given":"Philip A.","family":"Romero","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"77557_CR1","doi-asserted-by":"publisher","first-page":"eads0018","DOI":"10.1126\/science.ads0018","volume":"387","author":"T Hayes","year":"2025","unstructured":"Hayes, T. et al. Simulating 500 million years of evolution with a language model. Science 387, eads0018 (2025).","journal-title":"Science"},{"key":"77557_CR2","doi-asserted-by":"crossref","unstructured":"Bhatnagar, A. et al. Scaling unlocks broader generation and deeper functional understanding of proteins. In Advancaes in Neural Information Processing Systems, Vol. 38, 46109\u201346145 (2025).","DOI":"10.52202\/085713-1536"},{"key":"77557_CR3","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1126\/science.ade2574","volume":"379","author":"Z Lin","year":"2023","unstructured":"Lin, Z. et al. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science 379, 1123\u20131130 (2023).","journal-title":"Science"},{"key":"77557_CR4","doi-asserted-by":"publisher","first-page":"1617","DOI":"10.1038\/s41587-022-01432-w","volume":"40","author":"R Chowdhury","year":"2022","unstructured":"Chowdhury, R. et al. Single-sequence protein structure prediction using a language model and deep learning. Nat. Biotechnol. 40, 1617\u20131623 (2022).","journal-title":"Nat. Biotechnol."},{"key":"77557_CR5","doi-asserted-by":"publisher","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","volume":"44","author":"A Elnaggar","year":"2022","unstructured":"Elnaggar, A. et al. ProtTrans: toward understanding the language of life through self-supervised learning. IEEE Trans. Pattern Anal. Mach. Intell. 44, 7112\u20137127 (2022).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"77557_CR6","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1038\/s42256-022-00457-9","volume":"4","author":"S Unsal","year":"2022","unstructured":"Unsal, S. et al. Learning functional properties of proteins with language models. Nat. Mach. Intell. 4, 227\u2013245 (2022).","journal-title":"Nat. Mach. Intell."},{"key":"77557_CR7","doi-asserted-by":"crossref","unstructured":"Meier, J. et al. Language models enable zero-shot prediction of the effects of mutations on protein function https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/hash\/f51338d736f95dd42427296047067694-Abstract.html (2021).","DOI":"10.1101\/2021.07.09.450648"},{"key":"77557_CR8","doi-asserted-by":"crossref","unstructured":"Su, J. et al. SaProt: protein language modeling with structure-aware vocabulary. In International Conference on Learning Representations, 6987\u20137009 (2024).","DOI":"10.1101\/2023.10.01.560349"},{"key":"77557_CR9","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.1038\/s41592-019-0598-1","volume":"16","author":"EC Alley","year":"2019","unstructured":"Alley, E. C., Khimulya, G., Biswas, S., AlQuraishi, M. & Church, G. M. Unified rational protein engineering with sequence-based deep representation learning. Nat. Methods 16, 1315\u20131322 (2019).","journal-title":"Nat. Methods"},{"key":"77557_CR10","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1016\/j.cels.2022.01.003","volume":"13","author":"BL Hie","year":"2022","unstructured":"Hie, B. L., Yang, K. K. & Kim, P. S. Evolutionary velocity with protein language models predicts evolutionary dynamics of diverse proteins. Cell Syst. 13, 274\u2013285 (2022).","journal-title":"Cell Syst."},{"key":"77557_CR11","doi-asserted-by":"publisher","first-page":"1868","DOI":"10.1038\/s41592-025-02776-2","volume":"22","author":"S Gelman","year":"2025","unstructured":"Gelman, S. et al. Biophysics-based protein language models for protein engineering. Nat. Methods 22, 1868\u20131879 (2025).","journal-title":"Nat. Methods"},{"key":"77557_CR12","doi-asserted-by":"publisher","first-page":"1099","DOI":"10.1038\/s41587-022-01618-2","volume":"41","author":"A Madani","year":"2023","unstructured":"Madani, A. et al. Large language models generate functional protein sequences across diverse families. Nat. Biotechnol. 41, 1099\u20131106 (2023).","journal-title":"Nat. Biotechnol."},{"key":"77557_CR13","doi-asserted-by":"publisher","unstructured":"Munsamy, G. et al. Conditional language models enable the efficient design of proficient enzymes. Preprint at https:\/\/doi.org\/10.1101\/2024.05.03.592223 (2024).","DOI":"10.1101\/2024.05.03.592223"},{"key":"77557_CR14","doi-asserted-by":"publisher","unstructured":"Romero-Romero, S. et al. De novo design of triosephosphate isomerases using generative language models. Preprint at https:\/\/doi.org\/10.1101\/2024.11.10.622869 (2024).","DOI":"10.1101\/2024.11.10.622869"},{"key":"77557_CR15","doi-asserted-by":"publisher","unstructured":"Chen, L. T. et al. Target sequence-conditioned design of peptide binders using masked language modeling. Nat. Biotechnol. 1\u20139 https:\/\/doi.org\/10.1038\/s41587-025-02761-2 (2025).","DOI":"10.1038\/s41587-025-02761-2"},{"key":"77557_CR16","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adr8638","volume":"11","author":"S Bhat","year":"2025","unstructured":"Bhat, S. et al. De novo design of peptide binders to conformationally diverse targets with contrastive language modeling. Sci. Adv. 11, eadr8638 (2025).","journal-title":"Sci. Adv."},{"key":"77557_CR17","doi-asserted-by":"crossref","unstructured":"Truong Jr, T. & Bepler, T. PoET: a generative model of protein families as sequences-of-sequences. In Advances in Neural Information Processing Systems, Vol. 36, 77379\u201377415 (2023).","DOI":"10.52202\/075280-3384"},{"key":"77557_CR18","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-32007-7","volume":"13","author":"N Ferruz","year":"2022","unstructured":"Ferruz, N., Schmidt, S. & H\u00f6cker, B. ProtGPT2 is a deep unsupervised language model for protein design. Nat. Commun. 13, 4348 (2022).","journal-title":"Nat. Commun."},{"key":"77557_CR19","doi-asserted-by":"publisher","unstructured":"Hesslow, D., Zanichelli, N., Notin, P., Poli, I. & Marks, D. RITA: a study on scaling up generative protein sequence models. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2205.05789 (2022).","DOI":"10.48550\/arXiv.2205.05789"},{"key":"77557_CR20","doi-asserted-by":"crossref","unstructured":"Chen, B. et al. xTrimoPGLM: unified 100-billion-parameter pretrained transformer for deciphering the language of proteins. Nat. Methods 22, 1028\u20131039 (2025).","DOI":"10.1038\/s41592-025-02636-z"},{"key":"77557_CR21","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1016\/j.cels.2024.01.008","volume":"15","author":"KK Yang","year":"2024","unstructured":"Yang, K. K., Fusi, N. & Lu, A. X. Convolutions are competitive with transformers for protein sequence pretraining. Cell Syst. 15, 286\u2013294 (2024).","journal-title":"Cell Syst."},{"key":"77557_CR22","doi-asserted-by":"crossref","unstructured":"Peng, F. Z. et al. PTM-Mamba: a PTM-aware protein language model with bidirectional gated Mamba blocks. Nat. Methods 22, 945\u2013949 (2025).","DOI":"10.1038\/s41592-025-02656-9"},{"key":"77557_CR23","doi-asserted-by":"crossref","unstructured":"Ouyang, L. et al. Training language models to follow instructions with human feedback. In Advances in Neural Information Processing Systems, Vol. 35, 27730\u201327744 (2022).","DOI":"10.52202\/068431-2011"},{"key":"77557_CR24","doi-asserted-by":"publisher","unstructured":"Bai, Y. et al. Constitutional AI: harmlessness from AI feedback. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2212.08073 (2022).","DOI":"10.48550\/arXiv.2212.08073"},{"key":"77557_CR25","unstructured":"Stiennon, N. et al. Learning to summarize with human feedback. In Proc. Advances in Neural Information Processing Systems, Vol. 33, 3008\u20133021 (Curran Associates, Inc., 2020)."},{"key":"77557_CR26","doi-asserted-by":"publisher","unstructured":"Touvron, H. et al. Llama 2: open foundation and fine-tuned chat models. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2307.09288 (2023).","DOI":"10.48550\/arXiv.2307.09288"},{"key":"77557_CR27","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2104878118","volume":"118","author":"S Gelman","year":"2021","unstructured":"Gelman, S., Fahlberg, S. A., Heinzelman, P., Romero, P. A. & Gitter, A. Neural networks to learn protein sequence\u2013function relationships from deep mutational scanning data. Proc. Natl. Acad. Sci. USA 118, e2104878118 (2021).","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"77557_CR28","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-50712-3","volume":"15","author":"CR Freschlin","year":"2024","unstructured":"Freschlin, C. R., Fahlberg, S. A., Heinzelman, P. & Romero, P. A. Neural network extrapolation to distant regions of the protein fitness landscape. Nat. Commun. 15, 6405 (2024).","journal-title":"Nat. Commun."},{"key":"77557_CR29","doi-asserted-by":"publisher","first-page":"1114","DOI":"10.1038\/s41587-021-01146-5","volume":"40","author":"C Hsu","year":"2022","unstructured":"Hsu, C., Nisonoff, H., Fannjiang, C. & Listgarten, J. Learning protein fitness models from evolutionary and assay-labeled data. Nat. Biotechnol. 40, 1114\u20131122 (2022).","journal-title":"Nat. Biotechnol."},{"key":"77557_CR30","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1008736","volume":"17","author":"A Hawkins-Hooker","year":"2021","unstructured":"Hawkins-Hooker, A. et al. Generating functional protein variants with variational autoencoders. PLoS Comput. Biol. 17, e1008736 (2021).","journal-title":"PLoS Comput. Biol."},{"key":"77557_CR31","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1126\/science.add2187","volume":"378","author":"J Dauparas","year":"2022","unstructured":"Dauparas, J. et al. Robust deep learning\u2013based protein sequence design using ProteinMPNN. Science 378, 49\u201356 (2022).","journal-title":"Science"},{"key":"77557_CR32","doi-asserted-by":"publisher","unstructured":"Alamdari, S. et al. Protein generation with evolutionary diffusion: sequence is all you need. Preprint at https:\/\/doi.org\/10.1101\/2023.09.11.556673 (2024).","DOI":"10.1101\/2023.09.11.556673"},{"key":"77557_CR33","doi-asserted-by":"crossref","unstructured":"Nijkamp, E., Ruffolo, J. A., Weinstein, E. N., Naik, N. & Madani, A. ProGen2: exploring the boundaries of protein language models. Cell Syst. 14, 968\u2013978.e3 (2023).","DOI":"10.1016\/j.cels.2023.10.002"},{"key":"77557_CR34","doi-asserted-by":"publisher","first-page":"1461","DOI":"10.1021\/acssynbio.2c00662","volume":"12","author":"Y Chen","year":"2023","unstructured":"Chen, Y. et al. Deep mutational scanning of an oxygen-independent fluorescent protein CreiLOV for comprehensive profiling of mutational and epistatic effects. ACS Synth. Biol. 12, 1461\u20131473 (2023).","journal-title":"ACS Synth. Biol."},{"key":"77557_CR35","doi-asserted-by":"publisher","first-page":"1537","DOI":"10.1261\/rna.040709.113","volume":"19","author":"D Melamed","year":"2013","unstructured":"Melamed, D., Young, D. L., Gamble, C. E., Miller, C. R. & Fields, S. Deep mutational scanning of an RRM domain of the Saccharomyces cerevisiae poly(A)-binding protein. RNA 19, 1537\u20131551 (2013).","journal-title":"RNA"},{"key":"77557_CR36","doi-asserted-by":"publisher","first-page":"7159","DOI":"10.1073\/pnas.1422285112","volume":"112","author":"PA Romero","year":"2015","unstructured":"Romero, P. A., Tran, T. M. & Abate, A. R. Dissecting enzyme function with microfluidic-based deep mutational scanning. Proc. Natl. Acad. Sci. USA 112, 7159\u20137164 (2015).","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"77557_CR37","doi-asserted-by":"publisher","first-page":"E1263","DOI":"10.1073\/pnas.1303309110","volume":"110","author":"LM Starita","year":"2013","unstructured":"Starita, L. M. et al. Activity-enhancing mutations in an E3 ubiquitin ligase identified by high-throughput mutagenesis. Proc. Natl. Acad. Sci. USA 110, E1263\u2013E1272 (2013).","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"77557_CR38","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1038\/nature17995","volume":"533","author":"KS Sarkisyan","year":"2016","unstructured":"Sarkisyan, K. S. et al. Local fitness landscape of the green fluorescent protein. Nature 533, 397\u2013401 (2016).","journal-title":"Nature"},{"key":"77557_CR39","doi-asserted-by":"publisher","first-page":"2643","DOI":"10.1016\/j.cub.2014.09.072","volume":"24","author":"CA Olson","year":"2014","unstructured":"Olson, C. A., Wu, N. C. & Sun, R. A comprehensive biophysical description of pairwise epistasis throughout an entire protein domain. Curr. Biol. 24, 2643\u20132651 (2014).","journal-title":"Curr. Biol."},{"key":"77557_CR40","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1021\/sb500237x","volume":"4","author":"A Mukherjee","year":"2015","unstructured":"Mukherjee, A. et al. Engineering and characterization of new LOV-based fluorescent proteins from Chlamydomonas reinhardtii and Vaucheria frigida. ACS Synth. Biol. 4, 371\u2013377 (2015).","journal-title":"ACS Synth. Biol."},{"key":"77557_CR41","doi-asserted-by":"publisher","first-page":"e64753","DOI":"10.1371\/journal.pone.0064753","volume":"8","author":"A Mukherjee","year":"2013","unstructured":"Mukherjee, A., Walker, J., Weyant, K. B. & Schroeder, C. M. Characterization of flavin-based fluorescent proteins: an emerging class of fluorescent reporters. PLoS ONE 8, e64753 (2013).","journal-title":"PLoS ONE"},{"key":"77557_CR42","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1021\/acs.bioconjchem.9b00688","volume":"31","author":"HF Ozbakir","year":"2020","unstructured":"Ozbakir, H. F., Anderson, N. T., Fan, K.-C. & Mukherjee, A. Beyond the green fluorescent protein: biomolecular reporters for anaerobic and deep-tissue imaging. Bioconjugate Chem. 31, 293\u2013302 (2020).","journal-title":"Bioconjugate Chem."},{"key":"77557_CR43","doi-asserted-by":"publisher","first-page":"36493","DOI":"10.1074\/jbc.M103114200","volume":"276","author":"TE Swartz","year":"2001","unstructured":"Swartz, T. E. et al. The photocycle of a flavin-binding domain of the blue light photoreceptor phototropin*. J. Biol. Chem. 276, 36493\u201336500 (2001).","journal-title":"J. Biol. Chem."},{"key":"77557_CR44","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1038\/s41592-018-0138-4","volume":"15","author":"AJ Riesselman","year":"2018","unstructured":"Riesselman, A. J., Ingraham, J. B. & Marks, D. S. Deep generative models of genetic variation capture the effects of mutations. Nat. Methods 15, 816\u2013822 (2018).","journal-title":"Nat. Methods"},{"key":"77557_CR45","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1038\/nbt.3769","volume":"35","author":"TA Hopf","year":"2017","unstructured":"Hopf, T. A. et al. Mutation effects predicted from sequence co-variation. Nat. Biotechnol. 35, 128\u2013135 (2017).","journal-title":"Nat. Biotechnol."},{"key":"77557_CR46","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1003776","volume":"10","author":"JK Mann","year":"2014","unstructured":"Mann, J. K. et al. The fitness landscape of HIV-1 Gag: advanced modeling approaches and validation of model predictions by in vitro testing. PLoS Comput. Biol. 10, e1003776 (2014).","journal-title":"PLoS Comput. Biol."},{"key":"77557_CR47","doi-asserted-by":"crossref","unstructured":"Rohl, C. A., Strauss, C. E. M., Misura, K. M. S. & Baker, D. Protein structure prediction using Rosetta. in Methods in Enzymology, Vol. 383, 66\u201393 (Academic Press, 2004).","DOI":"10.1016\/S0076-6879(04)83004-0"},{"key":"77557_CR48","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1002\/prot.21086","volume":"65","author":"J Meiler","year":"2006","unstructured":"Meiler, J. & Baker, D. ROSETTALIGAND: protein\u2013small molecule docking with full side-chain flexibility. Proteins Struct. Funct. Bioinform. 65, 538\u2013548 (2006).","journal-title":"Proteins Struct. Funct. Bioinform."},{"key":"77557_CR49","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1038\/s41586-024-07601-y","volume":"631","author":"CA Goverde","year":"2024","unstructured":"Goverde, C. A. et al. Computational design of soluble and functional membrane protein analogues. Nature 631, 449\u2013458 (2024).","journal-title":"Nature"},{"key":"77557_CR50","doi-asserted-by":"publisher","first-page":"4041","DOI":"10.1093\/bioinformatics\/btab434","volume":"37","author":"C Marks","year":"2021","unstructured":"Marks, C., Hummer, A. M., Chin, M. & Deane, C. M. Humanization of antibodies using a machine learning approach on large-scale repertoire data. Bioinformatics 37, 4041\u20134047 (2021).","journal-title":"Bioinformatics"},{"key":"77557_CR51","doi-asserted-by":"publisher","first-page":"2020203","DOI":"10.1080\/19420862.2021.2020203","volume":"14","author":"D Prihoda","year":"2022","unstructured":"Prihoda, D. et al. BioPhi: a platform for antibody design, humanization, and humanness evaluation based on natural antibody repertoires and deep learning. mAbs 14, 2020203 (2022).","journal-title":"mAbs"},{"key":"77557_CR52","unstructured":"Chu, T. et al. SFT memorizes, RL generalizes: a comparative study of foundation model post-training. In Proc. of the 42nd International Conference on Machine Learning, PMLR 267, 10818\u201310838 (2025)."},{"key":"77557_CR53","doi-asserted-by":"crossref","unstructured":"Rafailov, R. et al. Direct preference optimization: your language model is secretly a reward model. In Advances in Neural Information Processing Systems, Vol. 36, 53728\u201353741 (2023).","DOI":"10.52202\/075280-2338"},{"key":"77557_CR54","unstructured":"Xu, S. et al. Is DPO superior to PPO for LLM alignment? A comprehensive study. In Proc. of the 41st International Conference on Machine Learning, PMLR 235, 54983\u201354998 (2024)."},{"key":"77557_CR55","doi-asserted-by":"crossref","unstructured":"Ivison, H. et al. Unpacking DPO and PPO: disentangling best practices for learning from preference feedback. In Advances in Neural Information Processing Systems, Vol. 37, 36602\u201336633 (2024).","DOI":"10.52202\/079017-1154"},{"key":"77557_CR56","doi-asserted-by":"crossref","unstructured":"Widatalla, T. et al. Aligning protein-generative models to experimental fitness with ProteinDPO. Nat. Methods 23, 1805\u20131813 (2026).","DOI":"10.1038\/s41592-026-03137-3"},{"key":"77557_CR57","doi-asserted-by":"publisher","unstructured":"Stocco, F. et al. Guiding generative protein language models with reinforcement learning. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2412.12979 (2024).","DOI":"10.48550\/arXiv.2412.12979"},{"key":"77557_CR58","doi-asserted-by":"publisher","unstructured":"Mistani, P. & Mysore, V. Preference optimization of protein language models as a multi-objective binder design paradigm. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2403.04187 (2024).","DOI":"10.48550\/arXiv.2403.04187"},{"key":"77557_CR59","doi-asserted-by":"crossref","unstructured":"Hsu, C. et al. Learning inverse folding from millions of predicted structures. In Proc. of the 39th International Conference on Machine Learning, PMLR 162, 8946\u20138970 (2022).","DOI":"10.1101\/2022.04.10.487779"},{"key":"77557_CR60","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.1016\/j.gpb.2023.03.004","volume":"21","author":"X Xu","year":"2023","unstructured":"Xu, X. et al. AB-Gen: antibody library design with generative pre-trained transformer and deep reinforcement learning. Genom. Proteom. Bioinform. 21, 1043\u20131053 (2023).","journal-title":"Genom. Proteom. Bioinform."},{"key":"77557_CR61","unstructured":"Sternke, M. C. & Karpiak, J. D. ProteinRL: reinforcement learning with generative protein language models for property-directed sequence design. In NeurIPS 2023 Generative AI and Biology Workshop (2023)."},{"key":"77557_CR62","unstructured":"Angermueller, C. et al. Model-based reinforcement learning for biological sequence design. In International Conference on Learning Representations (2020)."},{"key":"77557_CR63","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1038\/s44286-023-00002-4","volume":"1","author":"JT Rapp","year":"2024","unstructured":"Rapp, J. T., Bremer, B. J. & Romero, P. A. Self-driving laboratories to autonomously navigate the protein fitness landscape. Nat. Chem. Eng. 1, 97\u2013107 (2024).","journal-title":"Nat. Chem. Eng."},{"key":"77557_CR64","doi-asserted-by":"crossref","unstructured":"Singh, N. et al. A generalized platform for artificial intelligence-powered autonomous enzyme engineering. Nat. Commun. 16, 5648 (2025).","DOI":"10.1038\/s41467-025-61209-y"},{"key":"77557_CR65","unstructured":"The UniProt Consortium. UniProt: the Universal Protein Knowledgebase in 2023. Nucleic Acids Res. 51, D523\u2013D531 (2023)."},{"key":"77557_CR66","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-11-431","volume":"11","author":"LS Johnson","year":"2010","unstructured":"Johnson, L. S., Eddy, S. R. & Portugaly, E. Hidden Markov model speed heuristic and iterative HMM search procedure. BMC Bioinform. 11, 431 (2010).","journal-title":"BMC Bioinform."},{"key":"77557_CR67","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-29443-w","volume":"13","author":"NS Detlefsen","year":"2022","unstructured":"Detlefsen, N. S., Hauberg, S. & Boomsma, W. Learning meaningful representations of protein sequences. Nat. Commun. 13, 1914 (2022).","journal-title":"Nat. Commun."},{"key":"77557_CR68","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-13633-0","volume":"10","author":"X Ding","year":"2019","unstructured":"Ding, X., Zou, Z. & Brooks, C. L. III Deciphering protein evolution and fitness landscapes with latent space models. Nat. Commun. 10, 5644 (2019).","journal-title":"Nat. Commun."},{"key":"77557_CR69","doi-asserted-by":"publisher","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 & Data Mining, 2623\u20132631 https:\/\/doi.org\/10.1145\/3292500.3330701 (Association for Computing Machinery, 2019).","DOI":"10.1145\/3292500.3330701"},{"key":"77557_CR70","doi-asserted-by":"publisher","unstructured":"Shao, Z. et al. DeepSeekMath: pushing the limits of mathematical reasoning in open language models. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2402.03300 (2024).","DOI":"10.48550\/arXiv.2402.03300"},{"key":"77557_CR71","doi-asserted-by":"crossref","unstructured":"Guo, D. et al. DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning. Nature 645, 633\u2013638 (2025).","DOI":"10.1038\/s41586-025-09422-z"},{"key":"77557_CR72","unstructured":"Schulman, J., Moritz, P., Levine, S., Jordan, M. & Abbeel, P. High-dimensional continuous control using generalized advantage estimation. In International Conference on Learning Representations https:\/\/arxiv.org\/abs\/1506.02438 (2016)."},{"key":"77557_CR73","unstructured":"Kumar, A., Raghunathan, A., Jones, R., Ma, T. & Liang, P. Fine-tuning can distort pretrained features and underperform out-of-distribution. In International Conference on Learning Representations (2022)."},{"key":"77557_CR74","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1038\/s41586-021-04043-8","volume":"599","author":"J Frazer","year":"2021","unstructured":"Frazer, J. et al. Disease variant prediction with deep generative models of evolutionary data. Nature 599, 91\u201395 (2021).","journal-title":"Nature"},{"key":"77557_CR75","doi-asserted-by":"publisher","first-page":"1582","DOI":"10.1093\/bioinformatics\/bty862","volume":"35","author":"TA Hopf","year":"2019","unstructured":"Hopf, T. A. et al. The EVcouplings Python framework for coevolutionary sequence analysis. Bioinformatics 35, 1582\u20131584 (2019).","journal-title":"Bioinformatics"},{"key":"77557_CR76","doi-asserted-by":"publisher","first-page":"e28766","DOI":"10.1371\/journal.pone.0028766","volume":"6","author":"DS Marks","year":"2011","unstructured":"Marks, D. S. et al. Protein 3D structure computed from evolutionary sequence variation. PLoS ONE 6, e28766 (2011).","journal-title":"PLoS ONE"},{"key":"77557_CR77","doi-asserted-by":"publisher","unstructured":"Notin, P. et al. TranceptEVE: combining family-specific and family-agnostic models of protein sequences for improved fitness prediction. Preprint at https:\/\/doi.org\/10.1101\/2022.12.07.519495 (2022).","DOI":"10.1101\/2022.12.07.519495"},{"key":"77557_CR78","doi-asserted-by":"crossref","unstructured":"Notin, P. et al. ProteinGym: large-scale benchmarks for protein fitness prediction and design. In Advances in Neural Information Processing Systems, Vol. 36, 64331\u201364379 (2023).","DOI":"10.52202\/075280-2810"},{"key":"77557_CR79","unstructured":"Notin, P. et al. Tranception: protein fitness prediction with autoregressive transformers and inference-time retrieval. In Proceedings of the 39th International Conference on Machine Learning, PMLR 162, 16990\u201317017 (2022)."},{"key":"77557_CR80","doi-asserted-by":"publisher","unstructured":"Salazar, J., Liang, D., Nguyen, T. Q. & Kirchhoff, K. Masked language model scoring. In Proc. 58th Annual Meeting of the Association for Computational Linguistics, 2699\u20132712 https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.240 (2020).","DOI":"10.18653\/v1\/2020.acl-main.240"},{"key":"77557_CR81","doi-asserted-by":"publisher","unstructured":"Abramson, J. et al. Accurate structure prediction of biomolecular interactions with AlphaFold 3. Nature 1\u20133 https:\/\/doi.org\/10.1038\/s41586-024-07487-w (2024).","DOI":"10.1038\/s41586-024-07487-w"}],"container-title":["Nature Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-77557-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-77557-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-77557-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T11:03:01Z","timestamp":1791975781000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-77557-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,12]]},"references-count":81,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["77557"],"URL":"https:\/\/doi.org\/10.1038\/s41467-026-77557-2","relation":{},"ISSN":["2041-1723"],"issn-type":[{"value":"2041-1723","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,12]]},"assertion":[{"value":"15 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 August 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 September 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":"10751"}}