{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T06:20:41Z","timestamp":1773382841844,"version":"3.50.1"},"reference-count":137,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T00:00:00Z","timestamp":1718323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T00:00:00Z","timestamp":1718323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100009566","name":"University of Oslo | Livsvitenskap, Universitetet i Oslo","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009566","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005416","name":"Norges Forskningsr\u00e5d","doi-asserted-by":"publisher","award":["311341"],"award-info":[{"award-number":["311341"]}],"id":[{"id":"10.13039\/501100005416","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005416","name":"Norges Forskningsr\u00e5d","doi-asserted-by":"publisher","award":["300740"],"award-info":[{"award-number":["300740"]}],"id":[{"id":"10.13039\/501100005416","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005416","name":"Norges Forskningsr\u00e5d","doi-asserted-by":"publisher","award":["331890"],"award-info":[{"award-number":["331890"]}],"id":[{"id":"10.13039\/501100005416","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005416","name":"Norges Forskningsr\u00e5d","doi-asserted-by":"publisher","award":["311341"],"award-info":[{"award-number":["311341"]}],"id":[{"id":"10.13039\/501100005416","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007793","name":"Stiftelsen Kristian Gerhard Jebsen","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007793","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007028","name":"Leona M. and Harry B. Helmsley Charitable Trust","doi-asserted-by":"publisher","award":["2019PG-T1D011"],"award-info":[{"award-number":["2019PG-T1D011"]}],"id":[{"id":"10.13039\/100007028","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010661","name":"EC | Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["825821"],"award-info":[{"award-number":["825821"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008730","name":"Kreftforeningen","doi-asserted-by":"publisher","award":["215817"],"award-info":[{"award-number":["215817"]}],"id":[{"id":"10.13039\/100008730","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Comput Sci"],"DOI":"10.1038\/s43588-024-00642-3","type":"journal-article","created":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T10:04:10Z","timestamp":1718359450000},"page":"412-422","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Linguistics-based formalization of the antibody language as a basis for antibody language models"],"prefix":"10.1038","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9702-226X","authenticated-orcid":false,"given":"Mai Ha","family":"Vu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1345-5015","authenticated-orcid":false,"given":"Philippe A.","family":"Robert","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6692-0876","authenticated-orcid":false,"given":"Rahmad","family":"Akbar","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6767-3064","authenticated-orcid":false,"given":"Bartlomiej","family":"Swiatczak","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4959-1409","authenticated-orcid":false,"given":"Geir Kjetil","family":"Sandve","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5275-8073","authenticated-orcid":false,"given":"Dag Trygve Truslew","family":"Haug","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2622-5032","authenticated-orcid":false,"given":"Victor","family":"Greiff","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,6,14]]},"reference":[{"key":"642_CR1","doi-asserted-by":"publisher","unstructured":"Burnet, M. Auto-Immunity and Auto-Immune Disease (Springer, 1972); https:\/\/doi.org\/10.1007\/978-94-011-8095-5","DOI":"10.1007\/978-94-011-8095-5"},{"key":"642_CR2","doi-asserted-by":"publisher","first-page":"1057","DOI":"10.1126\/science.4035345","volume":"229","author":"NK Jerne","year":"1985","unstructured":"Jerne, N. K. The generative grammar of the immune system. Science 229, 1057\u20131059 (1985).","journal-title":"Science"},{"key":"642_CR3","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1038\/302575a0","volume":"302","author":"S Tonegawa","year":"1983","unstructured":"Tonegawa, S. Somatic generation of antibody diversity. Nature 302, 575\u2013581 (1983).","journal-title":"Nature"},{"key":"642_CR4","unstructured":"Landsteiner, K. The Specificity of Serological Reactions (Harvard Univ. Press, 1945)."},{"key":"642_CR5","doi-asserted-by":"publisher","first-page":"108856","DOI":"10.1016\/j.celrep.2021.108856","volume":"34","author":"R Akbar","year":"2021","unstructured":"Akbar, R. et al. A compact vocabulary of paratope\u2013epitope interactions enables predictability of antibody\u2013antigen binding. Cell Rep. 34, 108856 (2021).","journal-title":"Cell Rep."},{"key":"642_CR6","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1016\/j.str.2021.01.005","volume":"29","author":"JD Guest","year":"2021","unstructured":"Guest, J. D. et al. An expanded benchmark for antibody-antigen docking and affinity prediction reveals insights into antibody recognition determinants. Structure 29, 606\u2013621.e5 (2021).","journal-title":"Structure"},{"key":"642_CR7","doi-asserted-by":"publisher","first-page":"311","DOI":"10.4049\/jimmunol.2300136","volume":"211","author":"CG Rappazzo","year":"2023","unstructured":"Rappazzo, C. G. et al. Defining and studying B cell receptor and TCR interactions. J. Immunol. 211, 311\u2013322 (2023).","journal-title":"J. Immunol."},{"key":"642_CR8","doi-asserted-by":"publisher","first-page":"1643","DOI":"10.1126\/science.129.3364.1643","volume":"129","author":"DW Talmage","year":"1959","unstructured":"Talmage, D. W. Immunological specificity. Science 129, 1643\u20131648 (1959).","journal-title":"Science"},{"key":"642_CR9","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1038\/s43588-022-00372-4","volume":"2","author":"PA Robert","year":"2022","unstructured":"Robert, P. A. et al. Unconstrained generation of synthetic antibody\u2013antigen structures to guide machine learning methodology for antibody specificity prediction. Nat. Comput. Sci. 2, 845\u2013865 (2022).","journal-title":"Nat. Comput. Sci."},{"key":"642_CR10","doi-asserted-by":"publisher","unstructured":"Mason, D. M. et al. Optimization of therapeutic antibodies by predicting antigen specificity from antibody sequence via deep learning. Nat. Biomed. Eng. https:\/\/doi.org\/10.1038\/s41551-021-00699-9 (2021).","DOI":"10.1038\/s41551-021-00699-9"},{"key":"642_CR11","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.copbio.2018.01.006","volume":"51","author":"PA Robert","year":"2018","unstructured":"Robert, P. A., Marschall, A. L. & Meyer-Hermann, M. Induction of broadly neutralizing antibodies in germinal centre simulations. Curr. Opin. Biotechnol. 51, 137\u2013145 (2018).","journal-title":"Curr. Opin. Biotechnol."},{"key":"642_CR12","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.coisb.2020.10.010","volume":"24","author":"V Greiff","year":"2020","unstructured":"Greiff, V., Yaari, G. & Cowell, L. G. Mining adaptive immune receptor repertoires for biological and clinical information using machine learning. Curr. Opin. Syst. Biol. 24, 109\u2013119 (2020).","journal-title":"Curr. Opin. Syst. Biol."},{"key":"642_CR13","unstructured":"Burbach, S. M. & Briney, B. Improving antibody language models with native pairing. Preprint at https:\/\/arxiv.org\/abs\/2308.14300 (2023)."},{"key":"642_CR14","doi-asserted-by":"publisher","unstructured":"Singh, R. et al. Learning the language of antibody hypervariability. Preprint at bioRxiv https:\/\/doi.org\/10.1101\/2023.04.26.538476 (2023).","DOI":"10.1101\/2023.04.26.538476"},{"key":"642_CR15","doi-asserted-by":"publisher","first-page":"100036","DOI":"10.1016\/j.immuno.2024.100036","volume":"14","author":"N Deutchmann","year":"2024","unstructured":"Deutchmann, N. et al. Do domain-specific protein language models outperform general models on immunology-related tasks? ImmunoInformatics 14, 100036 (2024).","journal-title":"ImmunoInformatics"},{"key":"642_CR16","doi-asserted-by":"publisher","first-page":"1467","DOI":"10.1016\/j.celrep.2017.04.054","volume":"19","author":"V Greiff","year":"2017","unstructured":"Greiff, V. et al. Systems analysis reveals high genetic and antigen-driven predetermination of antibody repertoires throughout B cell development. Cell Rep. 19, 1467\u20131478 (2017).","journal-title":"Cell Rep."},{"key":"642_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3605943","volume":"56","author":"B Min","year":"2023","unstructured":"Min, B. et al. Recent advances in natural language processing via large pre-trained language models: a survey. ACM Comput. Surv. 56, 1\u201340 (2023).","journal-title":"ACM Comput. Surv."},{"key":"642_CR18","doi-asserted-by":"publisher","DOI":"10.1145\/3649449","author":"J Li","year":"2024","unstructured":"Li, J., Tang, T., Zhao, W. X., Nie, J.-Y. & Wen, J.-R. Pre-trained language models for text generation: a survey. ACM Comput. Surv. https:\/\/doi.org\/10.1145\/3649449 (2024).","journal-title":"ACM Comput. Surv."},{"key":"642_CR19","doi-asserted-by":"publisher","first-page":"e99","DOI":"10.1353\/lan.2019.0015","volume":"95","author":"T Linzen","year":"2019","unstructured":"Linzen, T. What can linguistics and deep learning contribute to each other? Response to pater. Language 95, e99\u2013e108 (2019).","journal-title":"Language"},{"key":"642_CR20","doi-asserted-by":"publisher","DOI":"10.1080\/19420862.2021.2008790","volume":"14","author":"R Akbar","year":"2022","unstructured":"Akbar, R. et al. Progress and challenges for the machine learning-based design of fit-for-purpose monoclonal antibodies. mAbs 14, 2008790 (2022).","journal-title":"mAbs"},{"key":"642_CR21","doi-asserted-by":"crossref","unstructured":"Mhanna, V. et al. Adaptive immune receptor repertoire analysis. Nat. Rev. Methods Primer 4, 6 (2024).","DOI":"10.1038\/s43586-023-00284-1"},{"key":"642_CR22","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. BERT: pre-training of deep bidirectional transformers for language understanding. In Proc. 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) 4171\u20134186 (Association for Computational Linguistics, 2019); https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"642_CR23","unstructured":"Brown, T. et al. Language models are few-shot learners. Adv. Neural Inf. Process. Syst. 33, 1877\u20131901 (2020)."},{"key":"642_CR24","doi-asserted-by":"publisher","unstructured":"Vu, M. H. et al. Linguistically inspired roadmap for building biologically reliable protein language models. Nat. Mach. Intell. https:\/\/doi.org\/10.1038\/s42256-023-00637-1 (2023).","DOI":"10.1038\/s42256-023-00637-1"},{"key":"642_CR25","doi-asserted-by":"publisher","first-page":"100513","DOI":"10.1016\/j.patter.2022.100513","volume":"3","author":"J Leem","year":"2022","unstructured":"Leem, J., Mitchell, L. S., Farmery, J. H. R., Barton, J. & Galson, J. D. Deciphering the language of antibodies using self-supervised learning. Patterns 3, 100513 (2022).","journal-title":"Patterns"},{"key":"642_CR26","doi-asserted-by":"publisher","first-page":"vbac046","DOI":"10.1093\/bioadv\/vbac046","volume":"2","author":"TH Olsen","year":"2022","unstructured":"Olsen, T. H., Moal, I. H. & Deane, C. M. AbLang: an antibody language model for completing antibody sequences. Bioinform. Adv. 2, vbac046 (2022).","journal-title":"Bioinform. Adv."},{"key":"642_CR27","unstructured":"Ruffolo, J. A., Gray, J. J. & Sulam, J. Deciphering antibody affinity maturation with language models and weakly supervised learning. Machine Learning for Structural Biology Workshop (NeurIPS, 2021)."},{"key":"642_CR28","doi-asserted-by":"publisher","first-page":"979","DOI":"10.1016\/j.cels.2023.10.001","volume":"14","author":"RW Shuai","year":"2023","unstructured":"Shuai, R. W., Ruffolo, J. A. & Gray, J. J. IgLM: infilling language modeling for antibody sequence design. Cell Syst. 14, 979\u2013989.e4 (2023).","journal-title":"Cell Syst."},{"key":"642_CR29","doi-asserted-by":"publisher","first-page":"100406","DOI":"10.1016\/j.patter.2021.100406","volume":"3","author":"JA Ruffolo","year":"2022","unstructured":"Ruffolo, J. A., Sulam, J. & Gray, J. J. Antibody structure prediction using interpretable deep learning. Patterns 3, 100406 (2022).","journal-title":"Patterns"},{"key":"642_CR30","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":"642_CR31","doi-asserted-by":"publisher","first-page":"680687","DOI":"10.3389\/fimmu.2021.680687","volume":"12","author":"M Ostrovsky-Berman","year":"2021","unstructured":"Ostrovsky-Berman, M., Frankel, B., Polak, P. & Yaari, G. Immune2vec: embedding B\/T cell receptor sequences in \u211dN using natural language processing. Front. Immunol. 12, 680687 (2021).","journal-title":"Front. Immunol."},{"key":"642_CR32","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.82819","volume":"12","author":"A Chandra","year":"2023","unstructured":"Chandra, A., T\u00fcnnermann, L., L\u00f6fstedt, T. & Gratz, R. Transformer-based deep learning for predicting protein properties in the life sciences. eLife 12, e82819 (2023).","journal-title":"eLife"},{"key":"642_CR33","doi-asserted-by":"publisher","first-page":"a041462","DOI":"10.1101\/cshperspect.a041462","volume":"16","author":"J Barton","year":"2024","unstructured":"Barton, J., Gaspariunas, A., Galson, J. D. & Leem, J. Building representation learning models for antibody comprehension. Cold Spring Harb. Perspect. Biol. 16, a041462 (2024).","journal-title":"Cold Spring Harb. Perspect. Biol."},{"key":"642_CR34","unstructured":"Dounas, A., Cotet, T.-S. & Yermanos, A. Learning immune receptor representations with protein language models. Preprint at https:\/\/arxiv.org\/abs\/2402.03823 (2024)."},{"key":"642_CR35","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1038\/s41587-023-01763-2","volume":"42","author":"BL Hie","year":"2024","unstructured":"Hie, B. L. et al. Efficient evolution of human antibodies from general protein language models. Nat. Biotechnol. 42, 275\u2013283 (2024).","journal-title":"Nat. Biotechnol."},{"key":"642_CR36","doi-asserted-by":"publisher","unstructured":"Zhao, Y. et al. SC-AIR-BERT: a pre-trained single-cell model for predicting the antigen-binding specificity of the adaptive immune receptor. Brief. Bioinform. https:\/\/doi.org\/10.1093\/bib\/bbad191 (2023).","DOI":"10.1093\/bib\/bbad191"},{"key":"642_CR37","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.bpj.2023.11.3334","volume":"123","author":"Y Wang","year":"2024","unstructured":"Wang, Y. et al. An explainable language model for antibody specificity prediction using curated influenza hemagglutinin antibodies. Biophys. J. 123, 3 (2024).","journal-title":"Biophys. J."},{"key":"642_CR38","doi-asserted-by":"crossref","unstructured":"Barton, J., Galson, J. D. & Leem, J. Enhancing antibody language models with structural information. In Machine Learning for Structural Biology Workshop (NeurIPS, 2023).","DOI":"10.1101\/2023.12.12.569610"},{"key":"642_CR39","unstructured":"Teney, D., Oh, S. J. & Abbasnejad, E. ID and OOD performance are sometimes inversely correlated on real-world datasets. In 37th Conference on Neural Information Processing Systems (NeurIPS, 2023)."},{"key":"642_CR40","unstructured":"Chomsky, N. in The Structure of Language: Readings in the Philosophy of Language (eds Fodor, J. A. & Katz, J. J.) 50\u2013118 (Prentice-Hall, 1964)."},{"key":"642_CR41","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1038\/s42256-019-0048-x","volume":"1","author":"C Rudin","year":"2019","unstructured":"Rudin, C. Stop explaining black box machine learning models for high stakes decisions and use interpretable models instead. Nat. Mach. Intell. 1, 206\u2013215 (2019).","journal-title":"Nat. Mach. Intell."},{"key":"642_CR42","doi-asserted-by":"crossref","unstructured":"Chen, V. et al. Best practices for interpretable machine learning in computational biology. Preprint at bioRxiv 10.1101\/2022.10.28.513978 (2022).","DOI":"10.1101\/2022.10.28.513978"},{"key":"642_CR43","doi-asserted-by":"publisher","unstructured":"Sundermeyer, M., Schl\u00fcter, R. & Ney, H. LSTM neural networks for language modeling. In Proc. Interspeech 2012 194\u2013197 (ISCA, 2012); https:\/\/doi.org\/10.21437\/Interspeech.2012-65","DOI":"10.21437\/Interspeech.2012-65"},{"key":"642_CR44","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T. et al. Language models are few-shot learners. Adv. Neural Inf. Process. Syst 33, 1877\u20131901 (2020).","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"642_CR45","doi-asserted-by":"publisher","first-page":"625341","DOI":"10.3389\/frai.2021.625341","volume":"4","author":"K Church","year":"2021","unstructured":"Church, K. & Liberman, M. The future of computational linguistics: on beyond alchemy. Front. Artif. Intell. 4, 625341 (2021).","journal-title":"Front. Artif. Intell."},{"key":"642_CR46","unstructured":"Mielke, S. J. et al. Between words and characters: a brief history of open-vocabulary modeling and tokenization in NLP. Preprint at https:\/\/arxiv.org\/abs\/2112.10508 (2021)."},{"key":"642_CR47","unstructured":"Kutuzov, A. & Kuzmenko, E. To Lemmatize or not to lemmatize: how word normalisation affects ELMo performance in word sense disambiguation. In Proc. First NLPL Workshop on Deep Learning for Natural Language Processing 22\u201328 (Link\u00f6ping Univ. Electronic Press, 2019)."},{"key":"642_CR48","doi-asserted-by":"publisher","unstructured":"Peters, M. E. et al. Deep contextualized word representations. In Proc. 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) 2227\u20132237 (Association for Computational Linguistics, 2018); https:\/\/doi.org\/10.18653\/v1\/N18-1202","DOI":"10.18653\/v1\/N18-1202"},{"key":"642_CR49","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1002\/pro.4205","volume":"31","author":"TH Olsen","year":"2022","unstructured":"Olsen, T. H., Boyles, F. & Deane, C. M. Observed antibody space: a diverse database of cleaned, annotated, and translated unpaired and paired antibody sequences. Protein Sci. 31, 141\u2013146 (2022).","journal-title":"Protein Sci."},{"key":"642_CR50","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1111\/imr.12666","volume":"284","author":"BD Corrie","year":"2018","unstructured":"Corrie, B. D. et al. iReceptor: a platform for querying and analyzing antibody\/B-cell and T-cell receptor repertoire data across federated repositories. Immunol. Rev. 284, 24\u201341 (2018).","journal-title":"Immunol. Rev."},{"key":"642_CR51","doi-asserted-by":"publisher","first-page":"20140243","DOI":"10.1098\/rstb.2014.0243","volume":"370","author":"Y Elhanati","year":"2015","unstructured":"Elhanati, Y. et al. Inferring processes underlying B-cell repertoire diversity. Phil. Trans. R. Soc. B 370, 20140243 (2015).","journal-title":"Phil. Trans. R. Soc. B"},{"key":"642_CR52","doi-asserted-by":"publisher","first-page":"bay040","DOI":"10.1093\/database\/bay040","volume":"2018","author":"S Ferdous","year":"2018","unstructured":"Ferdous, S. & Martin, A. C. R. AbDb: antibody structure database\u2014a database of PDB-derived antibody structures. Database 2018, bay040 (2018).","journal-title":"Database"},{"key":"642_CR53","unstructured":"Pan, Y., Li, X., Yang, Y. & Dong, R. Morphological Word Segmentation on Agglutinative Languages for Neural Machine Translation. Preprint at http:\/\/arxiv.org\/abs\/2001.01589 (2020)."},{"key":"642_CR54","unstructured":"Schwartz, L. et al. Neural polysynthetic language modelling. Preprint at https:\/\/arxiv.org\/abs\/2005.05477 (2019)."},{"key":"642_CR55","doi-asserted-by":"publisher","unstructured":"Adams, O., Makarucha, A., Neubig, G., Bird, S. & Cohn, T. Cross-lingual word embeddings for low-resource language modeling. In Proc. 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers. 937\u2013947 (Association for Computational Linguistics, 2017); https:\/\/doi.org\/10.18653\/v1\/E17-1088","DOI":"10.18653\/v1\/E17-1088"},{"key":"642_CR56","doi-asserted-by":"publisher","unstructured":"Agi\u0107, \u017d., Hovy, D. & S\u00f8gaard, A. If all you have is a bit of the Bible: learning POS taggers for truly low-resource languages. In Proc. 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. (Volume 2: Short Papers) 268\u2013272 (Association for Computational Linguistics, 2015); https:\/\/doi.org\/10.3115\/v1\/P15-2044","DOI":"10.3115\/v1\/P15-2044"},{"key":"642_CR57","doi-asserted-by":"publisher","unstructured":"Fang, M. & Cohn, T. Model transfer for tagging low-resource languages using a bilingual dictionary. In Proc. 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) (eds Barzilay, R. & Kan, M.-Y.) 587\u2013593 (Association for Computational Linguistics, 2017); https:\/\/doi.org\/10.18653\/v1\/P17-2093","DOI":"10.18653\/v1\/P17-2093"},{"key":"642_CR58","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-02832-w","volume":"9","author":"Q Marcou","year":"2018","unstructured":"Marcou, Q., Mora, T. & Walczak, A. M. High-throughput immune repertoire analysis with IGoR. Nat. Commun. 9, 561 (2018).","journal-title":"Nat. Commun."},{"key":"642_CR59","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1038\/s41586-022-05412-7","volume":"612","author":"Y Dong","year":"2022","unstructured":"Dong, Y. et al. Structural principles of B cell antigen receptor assembly. Nature 612, 156\u2013161 (2022).","journal-title":"Nature"},{"key":"642_CR60","doi-asserted-by":"publisher","DOI":"10.1080\/19420862.2021.1873478","volume":"13","author":"WK Wong","year":"2021","unstructured":"Wong, W. K. et al. Ab-Ligity: identifying sequence-dissimilar antibodies that bind to the same epitope. mAbs 13, 1873478 (2021).","journal-title":"mAbs"},{"key":"642_CR61","doi-asserted-by":"publisher","first-page":"eabk2039","DOI":"10.1126\/sciadv.abk2039","volume":"8","author":"A Antanasijevic","year":"2022","unstructured":"Antanasijevic, A. et al. From structure to sequence: antibody discovery using cryoEM. Sci. Adv. 8, eabk2039 (2022).","journal-title":"Sci. Adv."},{"key":"642_CR62","doi-asserted-by":"publisher","unstructured":"Abu-Shmais, A. A. et al. Convergent sequence features of antiviral B cells. Preprint at bioRxiv https:\/\/doi.org\/10.1101\/2023.09.06.556442 (2023).","DOI":"10.1101\/2023.09.06.556442"},{"key":"642_CR63","doi-asserted-by":"publisher","first-page":"1693","DOI":"10.1016\/j.immuni.2022.07.006","volume":"55","author":"M Sangesland","year":"2022","unstructured":"Sangesland, M. et al. Allelic polymorphism controls autoreactivity and vaccine elicitation of human broadly neutralizing antibodies against influenza virus. Immunity 55, 1693\u20131709.e8 (2022).","journal-title":"Immunity"},{"key":"642_CR64","doi-asserted-by":"publisher","first-page":"1569","DOI":"10.1126\/science.298.5598.1569","volume":"298","author":"MD Hauser","year":"2002","unstructured":"Hauser, M. D., Chomsky, N. & Fitch, W. T. The faculty of language: what is it, who has it, and how did it evolve? Science 298, 1569\u20131579 (2002).","journal-title":"Science"},{"key":"642_CR65","doi-asserted-by":"publisher","DOI":"10.1038\/srep30312","volume":"6","author":"RJ Pantazes","year":"2016","unstructured":"Pantazes, R. J. et al. Identification of disease-specific motifs in the antibody specificity repertoire via next-generation sequencing. Sci. Rep. 6, 30312 (2016).","journal-title":"Sci. Rep."},{"key":"642_CR66","doi-asserted-by":"publisher","DOI":"10.1126\/science.adc9498","volume":"380","author":"EL Shrock","year":"2023","unstructured":"Shrock, E. L. et al. Germline-encoded amino acid\u2013binding motifs drive immunodominant public antibody responses. Science 380, eadc9498 (2023).","journal-title":"Science"},{"key":"642_CR67","doi-asserted-by":"publisher","first-page":"eabp9540","DOI":"10.1126\/sciadv.abp9540","volume":"8","author":"M Aguilar Rangel","year":"2022","unstructured":"Aguilar Rangel, M. et al. Fragment-based computational design of antibodies targeting structured epitopes. Sci. Adv. 8, eabp9540 (2022).","journal-title":"Sci. Adv."},{"key":"642_CR68","doi-asserted-by":"publisher","first-page":"1059","DOI":"10.1073\/pnas.1908723117","volume":"117","author":"J Zhou","year":"2020","unstructured":"Zhou, J., Panaitiu, A. E. & Grigoryan, G. A general-purpose protein design framework based on mining sequence\u2013structure relationships in known protein structures. Proc. Natl Acad. Sci. USA 117, 1059\u20131068 (2020).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"642_CR69","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1109\/TIT.1956.1056813","volume":"2","author":"N Chomsky","year":"1956","unstructured":"Chomsky, N. Three models for the description of language. IRE Trans. Inf. Theory 2, 113\u2013124 (1956).","journal-title":"IRE Trans. Inf. Theory"},{"key":"642_CR70","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1146\/annurev.bi.50.070181.002433","volume":"50","author":"MG Rossmann","year":"1981","unstructured":"Rossmann, M. G. & Argos, P. Protein folding. Annu. Rev. Biochem. 50, 497\u2013532 (1981).","journal-title":"Annu. Rev. Biochem."},{"key":"642_CR71","doi-asserted-by":"publisher","unstructured":"Qing, R. et al. Protein design: from the aspect of water solubility and stability. Chem. Rev. https:\/\/doi.org\/10.1021\/acs.chemrev.1c00757 (2022).","DOI":"10.1021\/acs.chemrev.1c00757"},{"key":"642_CR72","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1002\/bip.22101","volume":"99","author":"DB Searls","year":"2013","unstructured":"Searls, D. B. A primer in macromolecular linguistics. Biopolymers 99, 203\u2013217 (2013).","journal-title":"Biopolymers"},{"key":"642_CR73","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1002\/prot.21195","volume":"66","author":"J Hockenmaier","year":"2006","unstructured":"Hockenmaier, J., Joshi, A. K. & Dill, K. A. Routes are trees: the parsing perspective on protein folding. Proteins Struct. Funct. Bioinform. 66, 1\u201315 (2006).","journal-title":"Proteins Struct. Funct. Bioinform."},{"key":"642_CR74","doi-asserted-by":"publisher","unstructured":"Hockenmaier, J., Joshi, A. K. & Dill, K. A. Protein folding and chart parsing. In Proc. 2006 Conference on Empirical Methods in Natural Language Processing, EMNLP \u201906 293\u2013300 (Association for Computational Linguistics, 2006); https:\/\/doi.org\/10.3115\/1610075.1610117","DOI":"10.3115\/1610075.1610117"},{"key":"642_CR75","doi-asserted-by":"publisher","first-page":"4289","DOI":"10.1016\/j.polymer.2007.05.018","volume":"48","author":"KA Dill","year":"2007","unstructured":"Dill, K. A. et al. Computational linguistics: a new tool for exploring biopolymer structures and statistical mechanics. Polymer 48, 4289\u20134300 (2007).","journal-title":"Polymer"},{"key":"642_CR76","unstructured":"Thellmann, K.-D., Stadler, B., Usbeck, R. & Lehmann, J. Transformer with tree-order encoding for neural program generation. Preprint at https:\/\/arxiv.org\/abs\/2206.13354 (2022)."},{"key":"642_CR77","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1016\/j.cels.2019.03.006","volume":"8","author":"M AlQuraishi","year":"2019","unstructured":"AlQuraishi, M. End-to-end differentiable learning of protein structure. Cell Syst. 8, 292\u2013301.e3 (2019).","journal-title":"Cell Syst."},{"key":"642_CR78","doi-asserted-by":"publisher","unstructured":"Zhang, L. et al. AnglesRefine: refinement of 3D protein structures using Transformer based on torsion angles. Preprint at bioRxiv https:\/\/doi.org\/10.1101\/2023.07.25.550599 (2023).","DOI":"10.1101\/2023.07.25.550599"},{"key":"642_CR79","doi-asserted-by":"publisher","first-page":"4486","DOI":"10.1021\/acs.jcim.9b00215","volume":"59","author":"TE Malliavin","year":"2019","unstructured":"Malliavin, T. E., Mucherino, A., Lavor, C. & Liberti, L. Systematic exploration of protein conformational space using a distance geometry approach. J. Chem. Inf. Model. 59, 4486\u20134503 (2019).","journal-title":"J. Chem. Inf. Model."},{"key":"642_CR80","doi-asserted-by":"publisher","first-page":"302","DOI":"10.3389\/fimmu.2013.00302","volume":"4","author":"I Sela-Culang","year":"2013","unstructured":"Sela-Culang, I., Kunik, V. & Ofran, Y. The structural basis of antibody\u2013antigen recognition. Front. Immunol. 4, 302 (2013).","journal-title":"Front. Immunol."},{"key":"642_CR81","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.61393","volume":"9","author":"CT Boughter","year":"2020","unstructured":"Boughter, C. T. et al. Biochemical patterns of antibody polyreactivity revealed through a bioinformatics-based analysis of CDR loops. eLife 9, e61393 (2020).","journal-title":"eLife"},{"key":"642_CR82","doi-asserted-by":"publisher","DOI":"10.1126\/science.aan6619","volume":"358","author":"JJ Bunker","year":"2017","unstructured":"Bunker, J. J. et al. Natural polyreactive IgA antibodies coat the intestinal microbiota. Science 358, eaan6619 (2017).","journal-title":"Science"},{"key":"642_CR83","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1016\/j.molimm.2019.06.012","volume":"112","author":"M Lecerf","year":"2019","unstructured":"Lecerf, M., Kanyavuz, A., Lacroix-Desmazes, S. & Dimitrov, J. D. Sequence features of variable region determining physicochemical properties and polyreactivity of therapeutic antibodies. Mol. Immunol. 112, 338\u2013346 (2019).","journal-title":"Mol. Immunol."},{"key":"642_CR84","first-page":"569","volume":"23","author":"J Guo","year":"1997","unstructured":"Guo, J. Critical tokenization and its properties. Comput. Linguist. 23, 569\u2013596 (1997).","journal-title":"Comput. Linguist."},{"key":"642_CR85","first-page":"103","volume":"19","author":"D Hindle","year":"1993","unstructured":"Hindle, D. & Rooth, M. Structural ambiguity and lexical relations. Comput. Linguist. 19, 103\u2013120 (1993).","journal-title":"Comput. Linguist."},{"key":"642_CR86","doi-asserted-by":"publisher","first-page":"1999195","DOI":"10.1080\/19420862.2021.1999195","volume":"13","author":"O Cunningham","year":"2021","unstructured":"Cunningham, O., Scott, M., Zhou, Z. S. & Finlay, W. J. J. Polyreactivity and polyspecificity in therapeutic antibody development: risk factors for failure in preclinical and clinical development campaigns. mAbs 13, 1999195 (2021).","journal-title":"mAbs"},{"key":"642_CR87","doi-asserted-by":"publisher","first-page":"3065","DOI":"10.3389\/fimmu.2018.03065","volume":"9","author":"ML Fern\u00e1ndez-Quintero","year":"2019","unstructured":"Fern\u00e1ndez-Quintero, M. L. et al. Characterizing the diversity of the CDR-H3 loop conformational ensembles in relationship to antibody binding properties. Front. Immunol. 9, 3065 (2019).","journal-title":"Front. Immunol."},{"key":"642_CR88","doi-asserted-by":"publisher","unstructured":"Bachas, S. et al. Antibody optimization enabled by artificial intelligence predictions of binding affinity and naturalness. Preprint at bioRxiv https:\/\/doi.org\/10.1101\/2022.08.16.504181 (2022).","DOI":"10.1101\/2022.08.16.504181"},{"key":"642_CR89","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-31457-3","volume":"13","author":"EK Makowski","year":"2022","unstructured":"Makowski, E. K. et al. Co-optimization of therapeutic antibody affinity and specificity using machine learning models that generalize to novel mutational space. Nat. Commun. 13, 3788 (2022).","journal-title":"Nat. Commun."},{"key":"642_CR90","doi-asserted-by":"publisher","first-page":"3996","DOI":"10.1093\/bioinformatics\/btaa263","volume":"36","author":"S Pittala","year":"2020","unstructured":"Pittala, S. & Bailey-Kellogg, C. Learning context-aware structural representations to predict antigen and antibody binding interfaces. Bioinformatics 36, 3996\u20134003 (2020).","journal-title":"Bioinformatics"},{"key":"642_CR91","doi-asserted-by":"publisher","first-page":"298","DOI":"10.3389\/fimmu.2019.00298","volume":"10","author":"MC Jespersen","year":"2019","unstructured":"Jespersen, M. C., Mahajan, S., Peters, B., Nielsen, M. & Marcatili, P. Antibody specific B-cell epitope predictions: leveraging information from antibody\u2013antigen protein complexes. Front. Immunol. 10, 298 (2019).","journal-title":"Front. Immunol."},{"key":"642_CR92","unstructured":"Del Vecchio, A., Deac, A., Li\u00f2, P. & Veli\u010dkovi\u0107, P. Neural message passing for joint paratope-epitope prediction. In 2021 ICML Workshop on Computational Biology (2021)."},{"key":"642_CR93","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1039\/C9ME00071B","volume":"4","author":"AJ Brown","year":"2019","unstructured":"Brown, A. J. et al. Augmenting adaptive immunity: progress and challenges in the quantitative engineering and analysis of adaptive immune receptor repertoires. Mol. Syst. Des. Eng. 4, 701\u2013736 (2019).","journal-title":"Mol. Syst. Des. Eng."},{"key":"642_CR94","unstructured":"de Saussure, F. Course in General Linguistics (Open Court, 1986)."},{"key":"642_CR95","doi-asserted-by":"publisher","first-page":"3628","DOI":"10.1073\/pnas.73.10.3628","volume":"73","author":"N Hozumi","year":"1976","unstructured":"Hozumi, N. & Tonegawa, S. Evidence for somatic rearrangement of immunoglobulin genes coding for variable and constant regions. Proc. Natl Acad. Sci. USA 73, 3628\u20133632 (1976).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"642_CR96","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1016\/j.cels.2018.12.004","volume":"8","author":"RM Adams","year":"2019","unstructured":"Adams, R. M., Kinney, J. B., Walczak, A. M. & Mora, T. Epistasis in a fitness landscape defined by antibody\u2013antigen binding free energy. Cell Syst. 8, 86\u201393.e3 (2019).","journal-title":"Cell Syst."},{"key":"642_CR97","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1162\/tacl_a_00115","volume":"4","author":"T Linzen","year":"2016","unstructured":"Linzen, T., Dupoux, E. & Goldberg, Y. Assessing the ability of LSTMs to learn syntax-sensitive dependencies. Trans. Assoc. Comput. Linguist. 4, 521\u2013535 (2016).","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"642_CR98","unstructured":"Goldberg, Y. Assessing BERT\u2019s syntactic abilities. Preprint at https:\/\/arxiv.org\/abs\/1901.05287 (2019)."},{"key":"642_CR99","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1146\/annurev-linguistics-031120-015515","volume":"8","author":"K Erk","year":"2022","unstructured":"Erk, K. The probabilistic turn in semantics and pragmatics. Annu. Rev. Linguist. 8, 101\u2013121 (2022).","journal-title":"Annu. Rev. Linguist."},{"key":"642_CR100","doi-asserted-by":"publisher","unstructured":"Sutton, P. R. Towards a probabilistic semantics for vague adjectives. In Bayesian Natural Language Semantics and Pragmatics (eds Zeevat, H. & Schmitz, H.-C.) 221\u2013246 (Springer, 2015); https:\/\/doi.org\/10.1007\/978-3-319-17064-0_10","DOI":"10.1007\/978-3-319-17064-0_10"},{"key":"642_CR101","unstructured":"Baroni, M. & Zamparelli, R. Nouns are vectors, adjectives are matrices: representing adjective-noun constructions in semantic space. In Proc. 2010 Conference on Empirical Methods in Natural Language Processing 1183\u20131193 (Association for Computational Linguistics, 2010)."},{"key":"642_CR102","unstructured":"Clark, S., Coecke, B. & Sadrzadeh, M. A compositional distributional model of meaning. in Proceedings of the Second Symposium on Quantum Interaction (eds Bruza, P. et al.) 133\u2013140 (Oxford, 2008)."},{"key":"642_CR103","unstructured":"Sadrzadeh, M. & Kartsaklis, D. Compositional distributional models of meaning. In Proc. COLING 2016 26th International Conference on Computational Linguistics: Tutorial Abstracts (eds Matsumoto, Y. & Prasad, R) 1\u20134 (2016)."},{"key":"642_CR104","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1162\/tacl_a_00304","volume":"8","author":"RT McCoy","year":"2020","unstructured":"McCoy, R. T., Frank, R. & Linzen, T. Does syntax need to grow on trees? Sources of hierarchical inductive bias in sequence-to-sequence networks. Trans. Assoc. Comput. Linguist. 8, 125\u2013140 (2020).","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"642_CR105","unstructured":"Harer, J., Reale, C. & Chin, P. Tree-Transformer: a transformer-based method for correction of tree-structured data. Preprint at https:\/\/arxiv.org\/abs\/1908.00449 (2019)."},{"key":"642_CR106","doi-asserted-by":"publisher","DOI":"10.1080\/19420862.2022.2031482","volume":"14","author":"R Akbar","year":"2022","unstructured":"Akbar, R. et al. In silico proof of principle of machine learning-based antibody design at unconstrained scale. mAbs 14, 2031482 (2022).","journal-title":"mAbs"},{"key":"642_CR107","doi-asserted-by":"crossref","unstructured":"Su, J. et al. SaProt: protein language modeling with structure-aware vocabulary. in The Twelfth International Conference on Learning Representations (2024).","DOI":"10.1101\/2023.10.01.560349"},{"key":"642_CR108","doi-asserted-by":"publisher","first-page":"D439","DOI":"10.1093\/nar\/gkab1061","volume":"50","author":"M Varadi","year":"2022","unstructured":"Varadi, M. et al. AlphaFold protein structure database: massively expanding the structural coverage of protein-sequence space with high-accuracy models. Nucleic Acids Res. 50, D439\u2013D444 (2022).","journal-title":"Nucleic Acids Res."},{"key":"642_CR109","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":"642_CR110","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1038\/s42003-023-04927-7","volume":"6","author":"B Abanades","year":"2023","unstructured":"Abanades, B. et al. ImmuneBuilder: deep-learning models for predicting the structures of immune proteins. Commun. Biol. 6, 575 (2023).","journal-title":"Commun. Biol."},{"key":"642_CR111","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-38063-x","volume":"14","author":"JA Ruffolo","year":"2023","unstructured":"Ruffolo, J. A., Chu, L.-S., Mahajan, S. P. & Gray, J. J. Fast, accurate antibody structure prediction from deep learning on massive set of natural antibodies. Nat. Commun. 14, 2389 (2023).","journal-title":"Nat. Commun."},{"key":"642_CR112","doi-asserted-by":"publisher","unstructured":"Fang, X. et al. A method for multiple-sequence-alignment-free protein structure prediction using a protein language model. Nat. Mach. Intell. https:\/\/doi.org\/10.1038\/s42256-023-00721-6 (2023).","DOI":"10.1038\/s42256-023-00721-6"},{"key":"642_CR113","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.str.2019.10.011","volume":"28","author":"F Ambrosetti","year":"2020","unstructured":"Ambrosetti, F., Jim\u00e9nez-Garc\u00eda, B., Roel-Touris, J. & Bonvin, A. M. J. J. Modeling antibody\u2013antigen complexes by information-driven docking. Structure 28, 119\u2013129.e2 (2020).","journal-title":"Structure"},{"key":"642_CR114","doi-asserted-by":"publisher","unstructured":"Sandve, G. K. & Greiff, V. Access to ground truth at unconstrained size makes simulated data as indispensable as experimental data for bioinformatics methods development and benchmarking. Bioinformatics https:\/\/doi.org\/10.1093\/bioinformatics\/btac612 (2022).","DOI":"10.1093\/bioinformatics\/btac612"},{"key":"642_CR115","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/19420862.2023.2175319","volume":"15","author":"ML Fern\u00e1ndez-Quintero","year":"2023","unstructured":"Fern\u00e1ndez-Quintero, M. L. et al. Challenges in antibody structure prediction. mAbs 15, 1 (2023).","journal-title":"mAbs"},{"key":"642_CR116","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1146\/annurev-physchem-042018-052331","volume":"71","author":"F No\u00e9","year":"2020","unstructured":"No\u00e9, F., Tkatchenko, A., M\u00fcller, K.-R. & Clementi, C. Machine learning for molecular simulation. Annu. Rev. Phys. Chem. 71, 361\u2013390 (2020).","journal-title":"Annu. Rev. Phys. Chem."},{"key":"642_CR117","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/j.sbi.2019.12.016","volume":"61","author":"Y Wang","year":"2020","unstructured":"Wang, Y., Lamim Ribeiro, J. M. & Tiwary, P. Machine learning approaches for analyzing and enhancing molecular dynamics simulations. Curr. Opin. Struct. Biol. 61, 139\u2013145 (2020).","journal-title":"Curr. Opin. Struct. Biol."},{"key":"642_CR118","doi-asserted-by":"publisher","first-page":"2355","DOI":"10.1021\/acs.jctc.0c01343","volume":"17","author":"S Doerr","year":"2021","unstructured":"Doerr, S. et al. TorchMD: a deep learning framework for molecular simulations. J. Chem. Theory Comput. 17, 2355\u20132363 (2021).","journal-title":"J. Chem. Theory Comput."},{"key":"642_CR119","doi-asserted-by":"publisher","first-page":"4335","DOI":"10.1021\/acs.jctc.3c00735","volume":"19","author":"NE Jackson","year":"2023","unstructured":"Jackson, N. E., Savoie, B. M., Statt, A. & Webb, M. A. Introduction to machine learning for molecular simulation. J. Chem. Theory Comput. 19, 4335\u20134337 (2023).","journal-title":"J. Chem. Theory Comput."},{"key":"642_CR120","doi-asserted-by":"publisher","first-page":"070902","DOI":"10.1063\/1.5109531","volume":"151","author":"YI Yang","year":"2019","unstructured":"Yang, Y. I., Shao, Q., Zhang, J., Yang, L. & Gao, Y. Q. Enhanced sampling in molecular dynamics. J. Chem. Phys. 151, 070902 (2019).","journal-title":"J. Chem. Phys."},{"key":"642_CR121","doi-asserted-by":"publisher","first-page":"044130","DOI":"10.1063\/5.0014475","volume":"153","author":"JC Phillips","year":"2020","unstructured":"Phillips, J. C. et al. Scalable molecular dynamics on CPU and GPU architectures with NAMD. J. Chem. Phys. 153, 044130 (2020).","journal-title":"J. Chem. Phys."},{"key":"642_CR122","unstructured":"Heinz, J. in The Oxford Handbook of Developmental Linguistics Vol. 1 (eds Lidz, J. L. et al.) 633\u2013663 (Oxford Univ. Press, 2016)."},{"key":"642_CR123","doi-asserted-by":"publisher","first-page":"1377","DOI":"10.1162\/tacl_a_00608","volume":"11","author":"M Wilson","year":"2023","unstructured":"Wilson, M., Petty, J. & Frank, R. How abstract is linguistic generalization in large language models? Experiments with argument structure. Trans. Assoc. Comput. Linguist. 11, 1377\u20131395 (2023).","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"642_CR124","unstructured":"Del\u00e9tang, G. et al. Neural networks and the Chomsky hierarchy. In 11th International Conference on Learning Representations, ICLR 2023 (2023)."},{"key":"642_CR125","doi-asserted-by":"publisher","unstructured":"Bhattamishra, S., Ahuja, K. & Goyal, N. On the ability and limitations of transformers to recognize formal languages. In Proc. 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) 7096\u20137116 (Association for Computational Linguistics, 2020); https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.576","DOI":"10.18653\/v1\/2020.emnlp-main.576"},{"key":"642_CR126","unstructured":"Ho, J., Jain, A. & Abbeel, P. Denoising diffusion probabilistic models. Adv. Neural Inf. Process. Syst. 33, 6840\u20136851 (2020)."},{"key":"642_CR127","first-page":"9754","volume":"35","author":"S Luo","year":"2022","unstructured":"Luo, S. et al. Antigen-specific antibody design and optimization with diffusion-based generative models for protein structures. Adv. Neural Inf. Process. Syst. 35, 9754\u20139767 (2022).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"642_CR128","doi-asserted-by":"publisher","unstructured":"Keidar, D., Opedal, A., Jin, Z. & Sachan, M. Slangvolution: a causal analysis of semantic change and frequency dynamics in slang. In Proc. 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (eds Muresan, S. et al.) 1422\u20131442 (Association for Computational Linguistics, 2022); https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.101","DOI":"10.18653\/v1\/2022.acl-long.101"},{"key":"642_CR129","unstructured":"Kutuzov, A., \u00d8vrelid, L., Szymanski, T. & Velldal, E. Diachronic word embeddings and semantic shifts: a survey. In Proc. 27th International Conference on Computational Linguistics. (eds Bender, E. M. et al.) 1384\u20131397 (Association for Computational Linguistics, 2018)."},{"key":"642_CR130","doi-asserted-by":"publisher","first-page":"22252","DOI":"10.1073\/pnas.1909504116","volume":"116","author":"SH Krovi","year":"2019","unstructured":"Krovi, S. H., Kappler, J. W., Marrack, P. & Gapin, L. Inherent reactivity of unselected TCR repertoires to peptide-MHC molecules. Proc. Natl Acad. Sci. USA 116, 22252\u201322261 (2019).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"642_CR131","doi-asserted-by":"crossref","unstructured":"Chomsky, N. Cartesian Linguistics: A Chapter in the History of Rationalist Thought (Cambridge Univ. Press, 2009).","DOI":"10.1017\/CBO9780511803116"},{"key":"642_CR132","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1111\/j.1600-065X.1989.tb00025.x","volume":"110","author":"AS Perelson","year":"1989","unstructured":"Perelson, A. S. Immune network theory. Immunol. Rev. 110, 5 (1989).","journal-title":"Immunol. Rev."},{"key":"642_CR133","first-page":"235","volume":"131D","author":"A Coutinho","year":"1980","unstructured":"Coutinho, A. The self-nonself discrimination and the nature and acquisition of the antibody repertoire. Ann. Immunol. 131D, 235\u2013253 (1980).","journal-title":"Ann. Immunol."},{"key":"642_CR134","unstructured":"Piattelli-Palmarini, M. The rise of selective theories: A case study and some lessons from immunology. In Language Learning and Concept Acquisition (ed. Demopoulos, W.) Ch. 5 (Ablex, 1986)."},{"key":"642_CR135","doi-asserted-by":"crossref","unstructured":"Piattelli-Palmarini, M. & Uriagereka, J. The immune syntax: The evolution of the language virus. In Variation and universals in biolinguistics (ed. Jenkins, L.) 341\u2013377 (Brill, 2004).","DOI":"10.1163\/9780080474748_017"},{"key":"642_CR136","doi-asserted-by":"publisher","unstructured":"The Semiotics of Cellular Communication in the Immune System (Springer, 1988); https:\/\/doi.org\/10.1007\/978-3-642-73145-7","DOI":"10.1007\/978-3-642-73145-7"},{"key":"642_CR137","doi-asserted-by":"publisher","first-page":"711","DOI":"10.1093\/intimm\/10.6.711","volume":"10","author":"H Atlan","year":"1998","unstructured":"Atlan, H. & Cohen, I. R. Immune information, self-organization and meaning. Int. Immunol. 10, 711\u2013717 (1998).","journal-title":"Int. Immunol."}],"container-title":["Nature Computational Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s43588-024-00642-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43588-024-00642-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43588-024-00642-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,26]],"date-time":"2024-06-26T16:14:05Z","timestamp":1719418445000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s43588-024-00642-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,14]]},"references-count":137,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,6]]}},"alternative-id":["642"],"URL":"https:\/\/doi.org\/10.1038\/s43588-024-00642-3","relation":{},"ISSN":["2662-8457"],"issn-type":[{"value":"2662-8457","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,14]]},"assertion":[{"value":"29 September 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 June 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"V.G. declares advisory board positions in aiNET GmbH, Enpicom B.V, Specifica Inc, Adaptyv Biosystems, EVQLV, Omniscope, Diagonal Therapeutics and Absci. V.G. is a consultant for Roche\/Genentech, immunai, Proteinea and LabGenius.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}