{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T04:52:10Z","timestamp":1791953530026,"version":"4.3.4"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1014805","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:00:00Z","timestamp":1791158400000}}],"reference-count":95,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Norwegian Cancer Society","award":["215817"],"award-info":[{"award-number":["215817"]}],"id":[{"id":"https:\/\/ror.org\/01925vb10","id-type":"ROR","asserted-by":"crossref"}]},{"name":"LifeScience Convergence Environment Immunolingo"},{"name":"Research Council of Norway projects","award":["300740"],"award-info":[{"award-number":["300740"]}],"id":[{"id":"https:\/\/ror.org\/00epmv149","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Research Council of Norway projects","award":["331890"],"award-info":[{"award-number":["331890"]}],"id":[{"id":"https:\/\/ror.org\/00epmv149","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Research Council of Norway","award":["311341"],"award-info":[{"award-number":["311341"]}]},{"DOI":"10.13039\/100007793","name":"Stiftelsen Kristian Gerhard Jebsen","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007793","id-type":"DOI","asserted-by":"publisher"}]},{"name":"European Union","award":["101125630"],"award-info":[{"award-number":["101125630"]}],"id":[{"id":"https:\/\/ror.org\/019w4f821","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Generative machine learning models offer a powerful framework for therapeutic design, by efficiently exploring large spaces of biological sequences enriched for desirable properties. Unlike supervised learning methods, which require both positive and negative labeled data, generative models such as LSTMs can be trained solely on positively labeled sequences, for example, high-affinity antibodies. This is particularly advantageous in biological settings where negative data are scarce, unreliable, or biologically ill-defined. However, the lack of attribution methods for generative models has hindered the ability to extract interpretable biological insights from such models. To address this gap, we developed Generative Attribution Metric Analysis (GAMA), an attribution method for autoregressive generative models based on Integrated Gradients. We assessed GAMA using synthetic datasets with known ground truths to characterize its statistical behavior and validate its ability to recover biologically relevant features. We further demonstrated the utility of GAMA by applying it to experimental antibody-antigen binding data. GAMA enables model interpretability and the validation of generative sequence design strategies without the need for negative training data.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1014805","type":"journal-article","created":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T17:37:34Z","timestamp":1790617054000},"page":"e1014805","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["Attribution assignment for deep-generative sequence models enables interpretability analysis using positive-only data"],"prefix":"10.1371","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9097-7963","authenticated-orcid":true,"given":"Robert","family":"Frank","sequence":"first","affiliation":[{"name":"University of Oslo","place":["Oslo, Norway"],"department":["Department of Immunology and Oslo University Hospital"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Widrich","sequence":"additional","affiliation":[{"name":"Institute for Machine Learning, Johannes Kepler University Linz","place":["Linz, Austria"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rahmad","family":"Akbar","sequence":"additional","affiliation":[{"name":"University of Oslo","place":["Oslo, Norway"],"department":["Department of Immunology and Oslo University Hospital"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"G\u00fcnter","family":"Klambauer","sequence":"additional","affiliation":[{"name":"Institute for Machine Learning, Johannes Kepler University Linz","place":["Linz, Austria"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Geir Kjetil","family":"Sandve","sequence":"additional","affiliation":[{"name":"University of Oslo","place":["Oslo, Norway"],"department":["Department of Informatics"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philippe A.","family":"Robert","sequence":"additional","affiliation":[{"name":"University of Oslo","place":["Oslo, Norway"],"department":["Department of Immunology and Oslo University Hospital"]},{"name":"Department of Biomedicine, University of Basel","place":["Basel, Switzerland"],"department":["Translational Immunology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2622-5032","authenticated-orcid":true,"given":"Victor","family":"Greiff","sequence":"additional","affiliation":[{"name":"University of Oslo","place":["Oslo, Norway"],"department":["Department of Immunology and Oslo University Hospital"]},{"name":"Imprint Labs, LLC","place":["New York, New York, United States of America"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,28]]},"reference":[{"key":"pcbi.1014805.ref001","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-term Memory","volume":"9","author":"S Hochreiter","year":"1997","journal-title":"Neural computation"},{"key":"pcbi.1014805.ref002","author":"A Gu","year":"2024"},{"key":"pcbi.1014805.ref003","article-title":"Generative Adversarial Nets.","volume-title":"Ghahramani Z, Welling M, Cortes C, Lawrence N, Weinberger KQ, editors. Advances in Neural Information Processing Systems","author":"IJ Goodfellow","year":"2014"},{"key":"pcbi.1014805.ref004","article-title":"Auto-encoding variational bayes.","volume-title":"Bengio Y, LeCun Y, editors. 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings","author":"DP Kingma","year":"2014"},{"key":"pcbi.1014805.ref005","first-page":"2256","volume-title":"Deep unsupervised learning using nonequilibrium thermodynamics. In: Proceedings of the 32nd International Conference on Machine Learning. PMLR","author":"J Sohl-Dickstein","year":"2015"},{"key":"pcbi.1014805.ref006","author":"A Vaswani","year":"2017"},{"issue":"13","key":"pcbi.1014805.ref007","doi-asserted-by":"crossref","first-page":"3454","DOI":"10.1093\/bioinformatics\/btac353","article-title":"Conditional generative modeling for de novo protein design with hierarchical functions","volume":"38","author":"T Kucera","year":"2022","journal-title":"Bioinformatics"},{"key":"pcbi.1014805.ref008","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.cbpa.2021.04.004","article-title":"Protein sequence design with deep generative models","volume":"65","author":"Z Wu","year":"2021","journal-title":"Curr Opin Chem Biol"},{"issue":"1","key":"pcbi.1014805.ref009","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1186\/s13321-023-00702-2","article-title":"Deep generative model for drug design from protein target sequence","volume":"15","author":"Y Chen","year":"2023","journal-title":"J Cheminform"},{"issue":"1","key":"pcbi.1014805.ref010","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-021-25756-4","article-title":"Efficient generative modeling of protein sequences using simple autoregressive models","volume":"12","author":"J Trinquier","year":"2021","journal-title":"Nat Commun"},{"issue":"8","key":"pcbi.1014805.ref011","doi-asserted-by":"crossref","first-page":"1099","DOI":"10.1038\/s41587-022-01618-2","article-title":"Large language models generate functional protein sequences across diverse families","volume":"41","author":"A Madani","year":"2023","journal-title":"Nat Biotechnol"},{"issue":"2","key":"pcbi.1014805.ref012","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1038\/s41587-024-02127-0","article-title":"Machine learning for functional protein design","volume":"42","author":"P Notin","year":"2024","journal-title":"Nat Biotechnol"},{"issue":"2","key":"pcbi.1014805.ref013","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1038\/s41587-023-02115-w","article-title":"Generative models for protein structures and sequences","volume":"42","author":"C Hsu","year":"2024","journal-title":"Nat Biotechnol"},{"issue":"7972","key":"pcbi.1014805.ref014","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1038\/s41586-023-06221-2","article-title":"Scientific discovery in the age of artificial intelligence","volume":"620","author":"H Wang","year":"2023","journal-title":"Nature"},{"issue":"1","key":"pcbi.1014805.ref015","doi-asserted-by":"crossref","first-page":"1059","DOI":"10.1038\/s41467-024-45051-2","article-title":"Protein structure generation via folding diffusion","volume":"15","author":"KE Wu","year":"2024","journal-title":"Nat Commun"},{"issue":"7976","key":"pcbi.1014805.ref016","doi-asserted-by":"crossref","first-page":"1089","DOI":"10.1038\/s41586-023-06415-8","article-title":"De novo design of protein structure and function with RFdiffusion","volume":"620","author":"JL Watson","year":"2023","journal-title":"Nature"},{"issue":"7","key":"pcbi.1014805.ref017","doi-asserted-by":"crossref","first-page":"1828","DOI":"10.1016\/j.chempr.2023.03.020","article-title":"Generative design of de novo proteins based on secondary structure constraints using an attention-based diffusion model","volume":"9","author":"B Ni","year":"2023","journal-title":"Chem"},{"key":"pcbi.1014805.ref018","doi-asserted-by":"crossref","unstructured":"Davidsen K, Olson BJ, DeWitt WS, Feng J, Harkins E, Bradley P, et al. Deep generative models for T cell receptor protein sequences. eLife. 2019 Sep 5;8:e46935. doi:10.7554\/eLife.46935","DOI":"10.7554\/eLife.46935"},{"key":"pcbi.1014805.ref019","unstructured":"Anand N, Huang P. Generative modeling for protein structures."},{"issue":"1","key":"pcbi.1014805.ref020","doi-asserted-by":"crossref","first-page":"5099","DOI":"10.1038\/s41467-022-32818-8","article-title":"Controlling gene expression with deep generative design of regulatory DNA","volume":"13","author":"J Zrimec","year":"2022","journal-title":"Nat Commun"},{"key":"pcbi.1014805.ref021","author":"N Killoran","year":"2017"},{"issue":"13","key":"pcbi.1014805.ref022","doi-asserted-by":"crossref","first-page":"7071","DOI":"10.1093\/nar\/gkad451","article-title":"Design of synthetic promoters for cyanobacteria with generative deep-learning model","volume":"51","author":"E Seo","year":"2023","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"pcbi.1014805.ref023","doi-asserted-by":"crossref","first-page":"4155","DOI":"10.1038\/s41467-025-59389-8","article-title":"Generative and predictive neural networks for the design of functional RNA molecules","volume":"16","author":"AT Riley","year":"2025","journal-title":"Nat Commun"},{"issue":"1","key":"pcbi.1014805.ref024","doi-asserted-by":"crossref","first-page":"5852","DOI":"10.1038\/s41598-021-85274-7","article-title":"Antibody design using LSTM based deep generative model from phage display library for affinity maturation","volume":"11","author":"K Saka","year":"2021","journal-title":"Sci Rep"},{"issue":"1","key":"pcbi.1014805.ref025","doi-asserted-by":"crossref","first-page":"2031482","DOI":"10.1080\/19420862.2022.2031482","article-title":"In silico proof of principle of machine learning-based antibody design at unconstrained scale","volume":"14","author":"R Akbar","year":"2022","journal-title":"MAbs"},{"key":"pcbi.1014805.ref026","doi-asserted-by":"crossref","unstructured":"Amimeur T, Shaver JM, Ketchem RR, Taylor JA, Clark RH, Smith J, et al. Designing feature-controlled humanoid antibody discovery libraries using generative adversarial networks. Immunology. 2020.","DOI":"10.1101\/2020.04.12.024844"},{"issue":"1","key":"pcbi.1014805.ref027","doi-asserted-by":"crossref","first-page":"2403","DOI":"10.1038\/s41467-021-22732-w","article-title":"Protein design and variant prediction using autoregressive generative models","volume":"12","author":"J-E Shin","year":"2021","journal-title":"Nat Commun"},{"issue":"1","key":"pcbi.1014805.ref028","doi-asserted-by":"crossref","first-page":"2069075","DOI":"10.1080\/19420862.2022.2069075","article-title":"Predicting antibody binders and generating synthetic antibodies using deep learning","volume":"14","author":"YW Lim","year":"2022","journal-title":"MAbs"},{"key":"pcbi.1014805.ref029","author":"X Kong","year":"2023"},{"issue":"2","key":"pcbi.1014805.ref030","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1038\/s41587-023-01763-2","article-title":"Efficient evolution of human antibodies from general protein language models","volume":"42","author":"BL Hie","year":"2024","journal-title":"Nat Biotechnol"},{"key":"pcbi.1014805.ref031","author":"C Molnar","year":"2018"},{"key":"pcbi.1014805.ref032","volume-title":"Inferring the Effects of Protein Variants on Protein\u2013protein Interactions with Interpretable Transformer Representations. Research","author":"Z Liu","year":"2023"},{"key":"pcbi.1014805.ref033","doi-asserted-by":"crossref","unstructured":"Carter B, Krog J, Birnbaum ME, Gifford DK. Machine learning model interpretations explain T cell receptor binding. Immunology. 2023.","DOI":"10.1101\/2023.08.15.553228"},{"key":"pcbi.1014805.ref034","author":"GSW Goh","year":"2021"},{"key":"pcbi.1014805.ref035","first-page":"3319","volume-title":"Axiomatic attribution for deep networks. In: Proceedings of the 34th International Conference on Machine Learning.","author":"M Sundararajan","year":"2017"},{"issue":"2","key":"pcbi.1014805.ref036","doi-asserted-by":"crossref","first-page":"100406","DOI":"10.1016\/j.patter.2021.100406","article-title":"Antibody structure prediction using interpretable deep learning","volume":"3","author":"JA Ruffolo","year":"2021","journal-title":"Patterns (N Y)"},{"issue":"7792","key":"pcbi.1014805.ref037","doi-asserted-by":"crossref","first-page":"706","DOI":"10.1038\/s41586-019-1923-7","article-title":"Improved protein structure prediction using potentials from deep learning","volume":"577","author":"AW Senior","year":"2020","journal-title":"Nature"},{"key":"pcbi.1014805.ref038","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1007\/978-3-030-28954-6_18","article-title":"Interpretable Deep Learning in Drug Discovery.","volume-title":"Samek W, Montavon G, Vedaldi A, Hansen LK, M\u00fcller KR, editors. Explainable AI: Interpreting, Explaining and Visualizing Deep Learning","author":"K Preuer","year":"2019"},{"issue":"12","key":"pcbi.1014805.ref039","doi-asserted-by":"crossref","first-page":"5026","DOI":"10.1021\/acs.jcim.9b00538","article-title":"Prediction and interpretable visualization of retrosynthetic reactions using graph convolutional networks","volume":"59","author":"S Ishida","year":"2019","journal-title":"J Chem Inf Model"},{"key":"pcbi.1014805.ref040","doi-asserted-by":"crossref","unstructured":"Nearing GS, Sampson AK, Kratzert F, Frame J. Post-processing a conceptual rainfall-runoff model with an LSTM. 2020.","DOI":"10.31223\/OSF.IO\/53TE4"},{"key":"pcbi.1014805.ref041","doi-asserted-by":"crossref","unstructured":"De la Fuente LA, Ehsani MR, Gupta HV, Condon LE. Towards Interpretable LSTM-based modelling of hydrological systems. EGUsphere. 2023;1\u201329.","DOI":"10.5194\/hess-2023-252"},{"key":"pcbi.1014805.ref042","author":"V Agarwal","year":"2019"},{"issue":"16","key":"pcbi.1014805.ref043","doi-asserted-by":"crossref","first-page":"2308","DOI":"10.1093\/bioinformatics\/btab127","article-title":"lncLocator 2.0: a cell-line-specific subcellular localization predictor for long non-coding RNAs with interpretable deep learning","volume":"37","author":"Y Lin","year":"2021","journal-title":"Bioinform"},{"issue":"12","key":"pcbi.1014805.ref044","doi-asserted-by":"crossref","first-page":"845","DOI":"10.1038\/s43588-022-00372-4","article-title":"Unconstrained generation of synthetic antibody-antigen structures to guide machine learning methodology for antibody specificity prediction","volume":"2","author":"PA Robert","year":"2022","journal-title":"Nat Comput Sci"},{"key":"pcbi.1014805.ref045","doi-asserted-by":"crossref","unstructured":"Ursu E, Minnegalieva A, Rawat P, Chernigovskaya M, Tacutu R, Sandve GK, et al. Training data composition determines machine learning generalization and biological rule discovery. 2024","DOI":"10.1101\/2024.06.17.599333"},{"key":"pcbi.1014805.ref046","first-page":"18832","volume-title":"Modern hopfield networks and attention for immune repertoire classification. In: Proceedings of the 34th International Conference on Neural Information Processing Systems.","author":"M Widrich","year":"2020"},{"key":"pcbi.1014805.ref047","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/978-3-030-28954-6_11","article-title":"Explaining and Interpreting LSTMs.","volume-title":"Samek W, Montavon G, Vedaldi A, Hansen LK, M\u00fcller KR, editors. Explainable AI: interpreting, explaining and visualizing deep learning","author":"L Arras","year":"2019"},{"key":"pcbi.1014805.ref048","author":"A Karpathy","year":"2015"},{"key":"pcbi.1014805.ref049","first-page":"7555","article-title":"Sequential Integrated Gradients: a simple but effective method for explaining language models.","author":"J Enguehard","year":"2023","journal-title":"Rogers A, Boyd-Graber J, Okazaki N, editors. Findings of the association for computational linguistics: ACL 2023"},{"key":"pcbi.1014805.ref050","doi-asserted-by":"crossref","first-page":"120046","DOI":"10.1016\/j.eswa.2023.120046","article-title":"Conditional generative positive and unlabeled learning","volume":"224","author":"A Papi\u010d","year":"2023","journal-title":"Expert Systems with Applications"},{"key":"pcbi.1014805.ref051","unstructured":"Pramanik V, Maliha M, Jha SK. Enhancing integrated gradients using emphasis factors and attention for effective explainability of large language models. 2024."},{"key":"pcbi.1014805.ref052","author":"Z Zhao","year":"2024"},{"key":"pcbi.1014805.ref053","doi-asserted-by":"crossref","unstructured":"Zhou W, Adel H, Schuff H, Vu NT. Explaining pre-trained language models with attribution scores: an analysis in low-resource settings. In: Proceedings of the language resources and evaluation conference. 2024. 6867\u201375. https:\/\/doi.org\/10.63317\/28zzvopwxasg","DOI":"10.63317\/28zzvopwxasg"},{"key":"pcbi.1014805.ref054","author":"LM Paes","year":"2024"},{"issue":"9","key":"pcbi.1014805.ref055","doi-asserted-by":"crossref","first-page":"1481","DOI":"10.1007\/s00439-021-02417-6","article-title":"Interpretable generative deep learning: an illustration with single cell gene expression data","volume":"141","author":"M Treppner","year":"2022","journal-title":"Hum Genet"},{"key":"pcbi.1014805.ref056","unstructured":"Ismail AA, Adebayo J, Bravo HC, Ra S, Cho K. Concept bottleneck generative models."},{"key":"pcbi.1014805.ref057","doi-asserted-by":"crossref","unstructured":"Liu W, Li R, Zheng M, Karanam S, Wu Z, Bhanu B, et al. Towards visually explaining variational autoencoders. In: 2020 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), 2020. 8639\u201348. https:\/\/doi.org\/10.1109\/cvpr42600.2020.00867","DOI":"10.1109\/CVPR42600.2020.00867"},{"key":"pcbi.1014805.ref058","doi-asserted-by":"crossref","unstructured":"Ross A, Chen N, Hang EZ, Glassman EL, Doshi-Velez F. Evaluating the interpretability of generative models by interactive reconstruction. In: Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, 2021. 1\u201315.","DOI":"10.1145\/3411764.3445296"},{"key":"pcbi.1014805.ref059","doi-asserted-by":"crossref","first-page":"1099521","DOI":"10.3389\/frai.2023.1099521","article-title":"Feature relevance XAI in anomaly detection: Reviewing approaches and challenges","volume":"6","author":"J Tritscher","year":"2023","journal-title":"Front Artif Intell"},{"issue":"5","key":"pcbi.1014805.ref060","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbac343","article-title":"Benchmarks in antimicrobial peptide prediction are biased due to the selection of negative data","volume":"23","author":"K Sidorczuk","year":"2022","journal-title":"Brief Bioinform"},{"key":"pcbi.1014805.ref061","doi-asserted-by":"crossref","first-page":"1055151","DOI":"10.3389\/fimmu.2022.1055151","article-title":"NetTCR-2.1: lessons and guidance on how to develop models for TCR specificity predictions","volume":"13","author":"A Montemurro","year":"2022","journal-title":"Front Immunol"},{"issue":"5","key":"pcbi.1014805.ref062","doi-asserted-by":"crossref","first-page":"977","DOI":"10.1039\/D3DD00218G","article-title":"Learning peptide properties with positive examples only","volume":"3","author":"M Ansari","year":"2024","journal-title":"Digit Discov"},{"issue":"11","key":"pcbi.1014805.ref063","doi-asserted-by":"crossref","first-page":"108856","DOI":"10.1016\/j.celrep.2021.108856","article-title":"A compact vocabulary of paratope-epitope interactions enables predictability of antibody-antigen binding","volume":"34","author":"R Akbar","year":"2021","journal-title":"Cell Rep"},{"issue":"3","key":"pcbi.1014805.ref064","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/j.tips.2020.12.004","article-title":"Machine learning for biologics: opportunities for protein engineering, developability, and formulation","author":"H Narayanan","year":"2021","journal-title":"Trends in Pharmacol Sci"},{"key":"pcbi.1014805.ref065","first-page":"260","volume-title":"Statistical inference in autoregressive models: estimation of autoregressive models. Illustrated edition. S.l","author":"B Ramanjineyulu","year":"2013"},{"key":"pcbi.1014805.ref066","article-title":"Professor forcing: a new algorithm for training recurrent networks.","volume-title":"Lee D, Sugiyama M, Luxburg U, Guyon I, Garnett R, editors. Advances in Neural Information Processing Systems [Internet]","author":"AM Lamb","year":"2016"},{"issue":"12","key":"pcbi.1014805.ref067","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1016\/j.tibtech.2021.03.003","article-title":"Animal immunization, in vitro display technologies, and machine learning for antibody discovery","volume":"39","author":"AH Laustsen","year":"2021","journal-title":"Trends Biotechnol"},{"key":"pcbi.1014805.ref068","author":"I Torjesen","year":"2015","journal-title":"The pharmaceutical journal"},{"issue":"6","key":"pcbi.1014805.ref069","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1038\/s43588-024-00642-3","article-title":"Linguistics-based formalization of the antibody language as a basis for antibody language models","volume":"4","author":"MH Vu","year":"2024","journal-title":"Nat Comput Sci"},{"issue":"5","key":"pcbi.1014805.ref070","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbad236","article-title":"Explainable AI for bioinformatics: methods, tools and applications","volume":"24","author":"MR Karim","year":"2023","journal-title":"Briefings in Bioinformatics"},{"issue":"6","key":"pcbi.1014805.ref071","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbae537","article-title":"Predictability of antigen binding based on short motifs in the antibody CDRH3","volume":"25","author":"L Scheffer","year":"2024","journal-title":"Brief Bioinform"},{"issue":"6","key":"pcbi.1014805.ref072","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1038\/s41551-021-00699-9","article-title":"Optimization of therapeutic antibodies by predicting antigen specificity from antibody sequence via deep learning","volume":"5","author":"DM Mason","year":"2021","journal-title":"Nat Biomed Eng"},{"key":"pcbi.1014805.ref073","doi-asserted-by":"crossref","first-page":"627813","DOI":"10.3389\/fimmu.2021.627813","article-title":"Machine learning analysis of na\u00efve b-cell receptor repertoires stratifies celiac disease patients and controls","volume":"12","author":"O Shemesh","year":"2021","journal-title":"Front Immunol"},{"issue":"8","key":"pcbi.1014805.ref074","doi-asserted-by":"crossref","first-page":"452","DOI":"10.1186\/s13059-014-0452-9","article-title":"Cancer genomics: one cell at a time","volume":"15","author":"NE Navin","year":"2014","journal-title":"Genome Biol"},{"key":"pcbi.1014805.ref075","first-page":"413","volume-title":"Isolation forest. In: 2008 Eighth IEEE International Conference on Data Mining","author":"FT Liu","year":"2008"},{"key":"pcbi.1014805.ref076","unstructured":"Bengio Y, Frasconi P, Schmidhuber J. Gradient flow in recurrent nets: the difficulty of learning long-term dependencies. a field guide to dynamical recurrent neural networks. 2003."},{"issue":"4","key":"pcbi.1014805.ref077","doi-asserted-by":"crossref","first-page":"719","DOI":"10.1007\/s10994-020-05877-5","article-title":"Learning from positive and unlabeled data: a survey","volume":"109","author":"J Bekker","year":"2020","journal-title":"Mach Learn"},{"key":"pcbi.1014805.ref078","doi-asserted-by":"crossref","unstructured":"Zhang D, Lee WS. Learning classifiers without negative examples: A reduction approach. In: 2008 Third International Conference on Digital Information Management, 2008. 638\u201343. https:\/\/doi.org\/10.1109\/icdim.2008.4746761","DOI":"10.1109\/ICDIM.2008.4746761"},{"key":"pcbi.1014805.ref079","author":"F Mordelet","year":"2010"},{"key":"pcbi.1014805.ref080","author":"X Tang","year":"2024"},{"key":"pcbi.1014805.ref081","author":"J Schneider","year":"2024"},{"issue":"7","key":"pcbi.1014805.ref082","doi-asserted-by":"crossref","first-page":"100513","DOI":"10.1016\/j.patter.2022.100513","article-title":"Deciphering the language of antibodies using self-supervised learning","volume":"3","author":"J Leem","year":"2022","journal-title":"Patterns (N Y)"},{"key":"pcbi.1014805.ref083","author":"A Dounas","year":"2024"},{"key":"pcbi.1014805.ref084","author":"M Beck","year":"2024"},{"issue":"4","key":"pcbi.1014805.ref085","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbac267","article-title":"Machine-designed biotherapeutics: opportunities, feasibility and advantages of deep learning in computational antibody discovery","volume":"23","author":"W Wilman","year":"2022","journal-title":"Brief Bioinform"},{"issue":"1","key":"pcbi.1014805.ref086","doi-asserted-by":"crossref","first-page":"2008790","DOI":"10.1080\/19420862.2021.2008790","article-title":"Progress and challenges for the machine learning-based design of fit-for-purpose monoclonal antibodies","volume":"14","author":"R Akbar","year":"2022","journal-title":"MAbs"},{"issue":"1","key":"pcbi.1014805.ref087","article-title":"Epistasis in a fitness landscape defined by antibody-antigen binding free energy","volume":"8","author":"RM Adams","year":"2019","journal-title":"Cell Syst"},{"issue":"1","key":"pcbi.1014805.ref088","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1111\/imr.12654","article-title":"TCR repertoire evolution during maintenance of CMV-specific T-cell populations","volume":"283","author":"K Schober","year":"2018","journal-title":"Immunol Rev"},{"key":"pcbi.1014805.ref089","article-title":"Adam: A Method for Stochastic Optimization.","volume-title":"Bengio Y, LeCun Y, editors. 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings","author":"DP Kingma","year":"2015"},{"key":"pcbi.1014805.ref090","first-page":"635029","author":"A Tareen","year":"2019"},{"issue":"60","key":"pcbi.1014805.ref091","doi-asserted-by":"crossref","first-page":"3021","DOI":"10.21105\/joss.03021","article-title":"seaborn: statistical data visualization","volume":"6","author":"M Waskom","year":"2021","journal-title":"JOSS"},{"key":"pcbi.1014805.ref092","author":"A Paszke","year":"2019"},{"issue":"7825","key":"pcbi.1014805.ref093","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with NumPy","volume":"585","author":"CR Harris","year":"2020","journal-title":"Nature"},{"key":"pcbi.1014805.ref094","doi-asserted-by":"crossref","unstructured":"McKinney W. Data structures for statistical computing in python. In: Proceedings of the Python in science conference. 2010. 56\u201361. https:\/\/doi.org\/10.25080\/majora-92bf1922-00a","DOI":"10.25080\/Majora-92bf1922-00a"},{"issue":"3","key":"pcbi.1014805.ref095","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: fundamental algorithms for scientific computing in Python","volume":"17","author":"P Virtanen","year":"2020","journal-title":"Nat Methods"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1014805","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:00:00Z","timestamp":1791158400000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014805","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T18:03:44Z","timestamp":1791223424000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014805"}},"subtitle":[],"editor":[{"given":"Pingzhao","family":"Hu","sequence":"first","affiliation":[{"name":"Western University","place":["CANADA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,28]]},"references-count":95,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,28]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1014805","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,28]]}}}