{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T07:56:50Z","timestamp":1778227010198,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T00:00:00Z","timestamp":1691107200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,6]]},"DOI":"10.1145\/3580305.3599468","type":"proceedings-article","created":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T18:10:58Z","timestamp":1691172658000},"page":"506-517","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Pre-training Antibody Language Models for Antigen-Specific Computational Antibody Design"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8862-8320","authenticated-orcid":false,"given":"Kaiyuan","family":"Gao","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3530-590X","authenticated-orcid":false,"given":"Lijun","family":"Wu","sequence":"additional","affiliation":[{"name":"Microsoft Research AI4Science, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2157-9077","authenticated-orcid":false,"given":"Jinhua","family":"Zhu","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of GIPAS, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7240-9326","authenticated-orcid":false,"given":"Tianbo","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Life Sciences and Biomedical Pioneering Innovation Center, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9823-9033","authenticated-orcid":false,"given":"Yingce","family":"Xia","sequence":"additional","affiliation":[{"name":"Microsoft Research AI4Science, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6394-8531","authenticated-orcid":false,"given":"Liang","family":"He","sequence":"additional","affiliation":[{"name":"Microsoft Research AI4Science, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7126-0139","authenticated-orcid":false,"given":"Shufang","family":"Xie","sequence":"additional","affiliation":[{"name":"Microsoft Research AI4Science, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7126-0139","authenticated-orcid":false,"given":"Tao","family":"Qin","sequence":"additional","affiliation":[{"name":"Microsoft Research AI4Science, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7324-6632","authenticated-orcid":false,"given":"Haiguang","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Research AI4Science, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7627-4604","authenticated-orcid":false,"given":"Kun","family":"He","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0476-8020","authenticated-orcid":false,"given":"Tie-Yan","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Research AI4Science, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,8,4]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"A general framework for computational anti-body design. PLoS computational biology 14, 4","author":"Adolf-Bryfogle Jared","year":"2018","unstructured":"Jared Adolf-Bryfogle , Oleks Kalyuzhniy , Michael Kubitz , Brian D Weitzner , Xiaozhen Hu , Yumiko Adachi , William R Schief , and Roland L Dunbrack Jr . 2018. Rosetta AntibodyDesign (RAbD) : A general framework for computational anti-body design. PLoS computational biology 14, 4 ( 2018 ), e1006112. Jared Adolf-Bryfogle, Oleks Kalyuzhniy, Michael Kubitz, Brian D Weitzner, Xiaozhen Hu, Yumiko Adachi, William R Schief, and Roland L Dunbrack Jr. 2018. RosettaAntibodyDesign (RAbD): A general framework for computational anti-body design. PLoS computational biology 14, 4 (2018), e1006112."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1080\/19420862.2022.2031482"},{"key":"e_1_3_2_2_3_1","volume-title":"Unified rational protein engineering with sequence-based deep representation learning. Nature methods 16, 12","author":"Alley Ethan C","year":"2019","unstructured":"Ethan C Alley , Grigory Khimulya , Surojit Biswas , Mohammed AlQuraishi , and George M Church . 2019. Unified rational protein engineering with sequence-based deep representation learning. Nature methods 16, 12 ( 2019 ), 1315--1322. Ethan C Alley, Grigory Khimulya, Surojit Biswas, Mohammed AlQuraishi, and George M Church. 2019. Unified rational protein engineering with sequence-based deep representation learning. Nature methods 16, 12 (2019), 1315--1322."},{"key":"e_1_3_2_2_4_1","volume-title":"Antibody optimization enabled by artificial intelligence predictions of binding affinity and naturalness. bioRxiv","author":"Bachas Sharrol","year":"2022","unstructured":"Sharrol Bachas , Goran Rakocevic , David Spencer , Anand V. Sastry , Robel Haile , John M. Sutton , George Kasun , Andrew Stachyra , Jahir M. Gutierrez , Edriss Yassine , Borka Medjo , Vincent Blay , Christa Kohnert , Jennifer T. Stanton , Alexander Brown , Nebojsa Tijanic , Cailen McCloskey , Rebecca Viazzo , Rebecca Consbruck , Hayley Carter , Simon Levine , Shaheed Abdulhaqq , Jacob Shaul , Abigail B. Ventura , Randal S. Olson , Engin Yapici , Joshua Meier , Sean McClain , Matthew Weinstock , Gregory Hannum , Ariel Schwartz , Miles Gander , and Roberto Spreafico . 2022. Antibody optimization enabled by artificial intelligence predictions of binding affinity and naturalness. bioRxiv ( 2022 ). Sharrol Bachas, Goran Rakocevic, David Spencer, Anand V. Sastry, Robel Haile, John M. Sutton, George Kasun, Andrew Stachyra, Jahir M. Gutierrez, Edriss Yassine, Borka Medjo, Vincent Blay, Christa Kohnert, Jennifer T. Stanton, Alexander Brown, Nebojsa Tijanic, Cailen McCloskey, Rebecca Viazzo, Rebecca Consbruck, Hayley Carter, Simon Levine, Shaheed Abdulhaqq, Jacob Shaul, Abigail B. Ventura, Randal S. Olson, Engin Yapici, Joshua Meier, Sean McClain, Matthew Weinstock, Gregory Hannum, Ariel Schwartz, Miles Gander, and Roberto Spreafico. 2022. Antibody optimization enabled by artificial intelligence predictions of binding affinity and naturalness. bioRxiv (2022)."},{"key":"e_1_3_2_2_5_1","volume-title":"International Conference on Machine Learning. PMLR, 1261--1271","author":"Cao Yue","year":"2021","unstructured":"Yue Cao , Payel Das , Vijil Chenthamarakshan , Pin-Yu Chen , Igor Melnyk , and Yang Shen . 2021 . Fold2seq: A joint sequence (1d)-fold (3d) embedding-based generative model for protein design . In International Conference on Machine Learning. PMLR, 1261--1271 . Yue Cao, Payel Das, Vijil Chenthamarakshan, Pin-Yu Chen, Igor Melnyk, and Yang Shen. 2021. Fold2seq: A joint sequence (1d)-fold (3d) embedding-based generative model for protein design. In International Conference on Machine Learning. PMLR, 1261--1271."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.3390\/antib7030023"},{"key":"e_1_3_2_2_7_1","unstructured":"Ratul Chowdhury Nazim Bouatta Surojit Biswas Christina Floristean Anant Kharkare Koushik Roye Charlotte Rochereau Gustaf Ahdritz Joanna Zhang George M Church etal 2022. Single-sequence protein structure prediction using a language model and deep learning. Nature Biotechnology (2022) 1--7.  Ratul Chowdhury Nazim Bouatta Surojit Biswas Christina Floristean Anant Kharkare Koushik Roye Charlotte Rochereau Gustaf Ahdritz Joanna Zhang George M Church et al. 2022. Single-sequence protein structure prediction using a language model and deep learning. Nature Biotechnology (2022) 1--7."},{"key":"e_1_3_2_2_8_1","volume-title":"D1","author":"Dunbar James","year":"2014","unstructured":"James Dunbar , Konrad Krawczyk , Jinwoo Leem , Terry Baker , Angelika Fuchs , Guy Georges , Jiye Shi , and Charlotte M Deane . 2014. SAbDab: the structural antibody database. Nucleic acids research 42 , D1 ( 2014 ), D1140--D1146. James Dunbar, Konrad Krawczyk, Jinwoo Leem, Terry Baker, Angelika Fuchs, Guy Georges, Jiye Shi, and Charlotte M Deane. 2014. SAbDab: the structural antibody database. Nucleic acids research 42, D1 (2014), D1140--D1146."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"crossref","unstructured":"Ahmed Elnaggar Michael Heinzinger Christian Dallago Ghalia Rehawi Yu Wang Llion Jones Tom Gibbs Tamas Feher Christoph Angerer Martin Steinegger etal 2021. ProtTrans: towards cracking the language of lifes code through self-supervised deep learning and high performance computing. IEEE transactions on pattern analysis and machine intelligence (2021).  Ahmed Elnaggar Michael Heinzinger Christian Dallago Ghalia Rehawi Yu Wang Llion Jones Tom Gibbs Tamas Feher Christoph Angerer Martin Steinegger et al. 2021. ProtTrans: towards cracking the language of lifes code through self-supervised deep learning and high performance computing. IEEE transactions on pattern analysis and machine intelligence (2021).","DOI":"10.1101\/2020.07.12.199554"},{"key":"e_1_3_2_2_10_1","volume-title":"ProtGPT2 is a deep unsupervised language model for protein design. Nature communications 13, 1","author":"Ferruz Noelia","year":"2022","unstructured":"Noelia Ferruz , Steffen Schmidt , and Birte H\u00f6cker . 2022. ProtGPT2 is a deep unsupervised language model for protein design. Nature communications 13, 1 ( 2022 ), 4348. Noelia Ferruz, Steffen Schmidt, and Birte H\u00f6cker. 2022. ProtGPT2 is a deep unsupervised language model for protein design. Nature communications 13, 1 (2022), 4348."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/pro.5560020507"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539285"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejpb.2019.05.017"},{"key":"e_1_3_2_2_14_1","unstructured":"Liang He Shizhuo Zhang Lijun Wu Huanhuan Xia Fusong Ju He Zhang Siyuan Liu Yingce Xia Jianwei Zhu Pan Deng etal 2021. Pre-training co-evolutionary protein representation via a pairwise masked language model. arXiv preprint arXiv:2110.15527 (2021).  Liang He Shizhuo Zhang Lijun Wu Huanhuan Xia Fusong Ju He Zhang Siyuan Liu Yingce Xia Jianwei Zhu Pan Deng et al. 2021. Pre-training co-evolutionary protein representation via a pairwise masked language model. arXiv preprint arXiv:2110.15527 (2021)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sbi.2022.102379"},{"key":"e_1_3_2_2_16_1","volume-title":"Generative models for graph-based protein design. Advances in neural information processing systems 32","author":"Ingraham John","year":"2019","unstructured":"John Ingraham , Vikas Garg , Regina Barzilay , and Tommi Jaakkola . 2019. Generative models for graph-based protein design. Advances in neural information processing systems 32 ( 2019 ). John Ingraham, Vikas Garg, Regina Barzilay, and Tommi Jaakkola. 2019. Generative models for graph-based protein design. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_2_17_1","volume-title":"International conference on machine learning. PMLR, 4849--4859","author":"Jin Wengong","year":"2020","unstructured":"Wengong Jin , Regina Barzilay , and Tommi Jaakkola . 2020 . Multi-objective molecule generation using interpretable substructures . In International conference on machine learning. PMLR, 4849--4859 . Wengong Jin, Regina Barzilay, and Tommi Jaakkola. 2020. Multi-objective molecule generation using interpretable substructures. In International conference on machine learning. PMLR, 4849--4859."},{"key":"e_1_3_2_2_18_1","volume-title":"International Conference on Machine Learning. PMLR, 10217--10227","author":"Jin Wengong","year":"2022","unstructured":"Wengong Jin , Regina Barzilay , and Tommi Jaakkola . 2022 . Antibody-antigen docking and design via hierarchical structure refinement . In International Conference on Machine Learning. PMLR, 10217--10227 . Wengong Jin, Regina Barzilay, and Tommi Jaakkola. 2022. Antibody-antigen docking and design via hierarchical structure refinement. In International Conference on Machine Learning. PMLR, 10217--10227."},{"key":"e_1_3_2_2_19_1","volume-title":"Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design. In International Conference on Learning Representations.","author":"Jin Wengong","year":"2021","unstructured":"Wengong Jin , Jeremy Wohlwend , Regina Barzilay , and Tommi S Jaakkola . 2021 . Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design. In International Conference on Learning Representations. Wengong Jin, Jeremy Wohlwend, Regina Barzilay, and Tommi S Jaakkola. 2021. Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"crossref","unstructured":"John Jumper Richard Evans Alexander Pritzel Tim Green Michael Figurnov Olaf Ronneberger Kathryn Tunyasuvunakool Russ Bates Augustin ?\u00eddek Anna Potapenko etal 2021. Highly accurate protein structure prediction with AlphaFold. Nature 596 7873 (2021) 583--589.  John Jumper Richard Evans Alexander Pritzel Tim Green Michael Figurnov Olaf Ronneberger Kathryn Tunyasuvunakool Russ Bates Augustin ?\u00eddek Anna Potapenko et al. 2021. Highly accurate protein structure prediction with AlphaFold. Nature 596 7873 (2021) 583--589.","DOI":"10.1038\/s41586-021-03819-2"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.0c00593"},{"key":"e_1_3_2_2_22_1","volume-title":"Proceedings of NAACL-HLT. 4171--4186","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova . 2019 . BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding . In Proceedings of NAACL-HLT. 4171--4186 . Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT. 4171--4186."},{"key":"e_1_3_2_2_23_1","volume-title":"Conditional antibody design as 3d equivariant graph translation. arXiv preprint arXiv:2208.06073","author":"Kong Xiangzhe","year":"2022","unstructured":"Xiangzhe Kong , Wenbing Huang , and Yang Liu . 2022. Conditional antibody design as 3d equivariant graph translation. arXiv preprint arXiv:2208.06073 ( 2022 ). Xiangzhe Kong, Wenbing Huang, and Yang Liu. 2022. Conditional antibody design as 3d equivariant graph translation. arXiv preprint arXiv:2208.06073 (2022)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/prot.24779"},{"key":"e_1_3_2_2_25_1","volume-title":"Justin Barton, and Jacob D Galson.","author":"Leem Jinwoo","year":"2022","unstructured":"Jinwoo Leem , Laura S Mitchell , James HR Farmery , Justin Barton, and Jacob D Galson. 2022 . Deciphering the language of antibodies using self-supervised learning. Patterns ( 2022), 100513. Jinwoo Leem, Laura S Mitchell, James HR Farmery, Justin Barton, and Jacob D Galson. 2022. Deciphering the language of antibodies using self-supervised learning. Patterns (2022), 100513."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/0022-2836(80)90373-3"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0105954"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty305"},{"key":"e_1_3_2_2_32_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu , Myle Ott , Naman Goyal , Jingfei Du , Mandar Joshi , Danqi Chen , Omer Levy , Mike Lewis , Luke Zettlemoyer , and Veselin Stoyanov . 2019 . Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019). Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_2_33_1","first-page":"9754","article-title":"Antigen-Specific Antibody Design and Optimization with Diffusion-Based Generative Models for Protein Structures","volume":"35","author":"Luo Shitong","year":"2022","unstructured":"Shitong Luo , Yufeng Su , Xingang Peng , Sheng Wang , Jian Peng , and Jianzhu Ma . 2022 . Antigen-Specific Antibody Design and Optimization with Diffusion-Based Generative Models for Protein Structures . In Advances in Neural Information Processing Systems , Vol. 35. 9754 -- 9767 . Shitong Luo, Yufeng Su, Xingang Peng, Sheng Wang, Jian Peng, and Jianzhu Ma. 2022. Antigen-Specific Antibody Design and Optimization with Diffusion-Based Generative Models for Protein Structures. In Advances in Neural Information Processing Systems, Vol. 35. 9754--9767.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_34_1","volume-title":"Caiming Xiong, Zachary Z Sun, Richard Socher, et al.","author":"Madani Ali","year":"2023","unstructured":"Ali Madani , Ben Krause , Eric R Greene , Subu Subramanian , Benjamin P Mohr , James M Holton , Jose Luis Olmos Jr , Caiming Xiong, Zachary Z Sun, Richard Socher, et al. 2023 . Large language models generate functional protein sequences across diverse families. Nature Biotechnology ( 2023), 1--8. Ali Madani, Ben Krause, Eric R Greene, Subu Subramanian, Benjamin P Mohr, James M Holton, Jose Luis Olmos Jr, Caiming Xiong, Zachary Z Sun, Richard Socher, et al. 2023. Large language models generate functional protein sequences across diverse families. Nature Biotechnology (2023), 1--8."},{"key":"e_1_3_2_2_35_1","volume-title":"Benchmarking deep generative models for diverse antibody sequence design. arXiv preprint arXiv:2111.06801","author":"Melnyk Igor","year":"2021","unstructured":"Igor Melnyk , Payel Das , Vijil Chenthamarakshan , and Aurelie Lozano . 2021. Benchmarking deep generative models for diverse antibody sequence design. arXiv preprint arXiv:2111.06801 ( 2021 ). Igor Melnyk, Payel Das, Vijil Chenthamarakshan, and Aurelie Lozano. 2021. Benchmarking deep generative models for diverse antibody sequence design. arXiv preprint arXiv:2111.06801 (2021)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3388440.3412467"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1002\/prot.25489"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1002\/pro.4205"},{"key":"e_1_3_2_2_39_1","volume-title":"AbLang: An antibody language model for completing antibody sequences. bioRxiv","author":"Olsen Tobias H","year":"2022","unstructured":"Tobias H Olsen , Iain H Moal , and Charlotte M Deane . 2022. AbLang: An antibody language model for completing antibody sequences. bioRxiv ( 2022 ). Tobias H Olsen, Iain H Moal, and Charlotte M Deane. 2022. AbLang: An antibody language model for completing antibody sequences. bioRxiv (2022)."},{"key":"e_1_3_2_2_40_1","volume-title":"Sequence level training with recurrent neural networks. arXiv preprint arXiv:1511.06732","author":"Ranzato Marc'Aurelio","year":"2015","unstructured":"Marc'Aurelio Ranzato , Sumit Chopra , Michael Auli , and Wojciech Zaremba . 2015. Sequence level training with recurrent neural networks. arXiv preprint arXiv:1511.06732 ( 2015 ). Marc'Aurelio Ranzato, Sumit Chopra, Michael Auli, and Wojciech Zaremba. 2015. Sequence level training with recurrent neural networks. arXiv preprint arXiv:1511.06732 (2015)."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaa739"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.76.7.3116"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2016239118"},{"key":"e_1_3_2_2_44_1","volume-title":"Deciphering antibody affinity maturation with language models and weakly supervised learning. arXiv preprint arXiv:2112.07782","author":"Ruffolo Jeffrey A","year":"2021","unstructured":"Jeffrey A Ruffolo , Jeffrey J Gray , and Jeremias Sulam . 2021. Deciphering antibody affinity maturation with language models and weakly supervised learning. arXiv preprint arXiv:2112.07782 ( 2021 ). Jeffrey A Ruffolo, Jeffrey J Gray, and Jeremias Sulam. 2021. Deciphering antibody affinity maturation with language models and weakly supervised learning. arXiv preprint arXiv:2112.07782 (2021)."},{"key":"e_1_3_2_2_45_1","volume-title":"Antibody design using LSTM based deep generative model from phage display library for affinity maturation. Scientific reports 11, 1","author":"Saka Koichiro","year":"2021","unstructured":"Koichiro Saka , Taro Kakuzaki , Shoichi Metsugi , Daiki Kashiwagi , Kenji Yoshida , Manabu Wada , Hiroyuki Tsunoda , and Reiji Teramoto . 2021. Antibody design using LSTM based deep generative model from phage display library for affinity maturation. Scientific reports 11, 1 ( 2021 ), 1--13. Koichiro Saka, Taro Kakuzaki, Shoichi Metsugi, Daiki Kashiwagi, Kenji Yoshida, Manabu Wada, Hiroyuki Tsunoda, and Reiji Teramoto. 2021. Antibody design using LSTM based deep generative model from phage display library for affinity maturation. Scientific reports 11, 1 (2021), 1--13."},{"key":"e_1_3_2_2_46_1","volume-title":"James E Crowe Jr, and Jens Meiler","author":"Schmitz Samuel","year":"2022","unstructured":"Samuel Schmitz , Emily A Schmitz , James E Crowe Jr, and Jens Meiler . 2022 . The human antibody sequence space and structural design of the V, J regions, and CDRH3 with Rosetta. In Mabs, Vol. 14 . Taylor & Francis , 2068212. Samuel Schmitz, Emily A Schmitz, James E Crowe Jr, and Jens Meiler. 2022. The human antibody sequence space and structural design of the V, J regions, and CDRH3 with Rosetta. In Mabs, Vol. 14. Taylor & Francis, 2068212."},{"key":"e_1_3_2_2_47_1","volume-title":"Antibody therapy of cancer. Nature reviews cancer 12, 4","author":"Scott Andrew M","year":"2012","unstructured":"Andrew M Scott , Jedd D Wolchok , and Lloyd J Old . 2012. Antibody therapy of cancer. Nature reviews cancer 12, 4 ( 2012 ), 278--287. Andrew M Scott, Jedd D Wolchok, and Lloyd J Old. 2012. Antibody therapy of cancer. Nature reviews cancer 12, 4 (2012), 278--287."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2122954119"},{"key":"e_1_3_2_2_49_1","volume-title":"Protein design and variant prediction using autoregressive generative models. Nature communications 12, 1","author":"Shin Jung-Eun","year":"2021","unstructured":"Jung-Eun Shin , Adam J Riesselman , Aaron W Kollasch , Conor McMahon , Elana Simon , Chris Sander , Aashish Manglik , Andrew C Kruse , and Debora S Marks . 2021. Protein design and variant prediction using autoregressive generative models. Nature communications 12, 1 ( 2021 ), 1--11. Jung-Eun Shin, Adam J Riesselman, Aaron W Kollasch, Conor McMahon, Elana Simon, Chris Sander, Aashish Manglik, Andrew C Kruse, and Debora S Marks. 2021. Protein design and variant prediction using autoregressive generative models. Nature communications 12, 1 (2021), 1--11."},{"key":"e_1_3_2_2_50_1","volume-title":"Generative language modeling for antibody design. bioRxiv","author":"Shuai Richard W","year":"2021","unstructured":"Richard W Shuai , Jeffrey A Ruffolo , and Jeffrey J Gray . 2021. Generative language modeling for antibody design. bioRxiv ( 2021 ). Richard W Shuai, Jeffrey A Ruffolo, and Jeffrey J Gray. 2021. Generative language modeling for antibody design. bioRxiv (2021)."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.3988"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-04964-5"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaa003"},{"key":"e_1_3_2_2_54_1","volume-title":"Fast and flexible protein design using deep graph neural networks. Cell systems 11, 4","author":"Strokach Alexey","year":"2020","unstructured":"Alexey Strokach , David Becerra , Carles Corbi-Verge , Albert Perez-Riba , and Philip M Kim . 2020. Fast and flexible protein design using deep graph neural networks. Cell systems 11, 4 ( 2020 ), 402--411. Alexey Strokach, David Becerra, Carles Corbi-Verge, Albert Perez-Riba, and Philip M Kim. 2020. Fast and flexible protein design using deep graph neural networks. Cell systems 11, 4 (2020), 402--411."},{"key":"e_1_3_2_2_55_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N Gomez , \u0141ukasz Kaiser , and Illia Polosukhin . 2017. Attention is all you need. Advances in neural information processing systems 30 ( 2017 ). Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_2_56_1","volume-title":"Geir Kjetil Sandve, and Dag Trygve Truslew Haug","author":"Vu Mai Ha","year":"2022","unstructured":"Mai Ha Vu , Rahmad Akbar , Philippe A Robert , Bartlomiej Swiatczak , Victor Greiff , Geir Kjetil Sandve, and Dag Trygve Truslew Haug . 2022 . Advancing protein language models with linguistics: a roadmap for improved interpretability. arXiv preprint arXiv:2207.00982 (2022). Mai Ha Vu, Rahmad Akbar, Philippe A Robert, Bartlomiej Swiatczak, Victor Greiff, Geir Kjetil Sandve, and Dag Trygve Truslew Haug. 2022. Advancing protein language models with linguistics: a roadmap for improved interpretability. arXiv preprint arXiv:2207.00982 (2022)."},{"key":"e_1_3_2_2_57_1","volume-title":"Dag Trygve Truslew Haug, and Victor Greiff.","author":"Vu Mai Ha","year":"2022","unstructured":"Mai Ha Vu , Philippe A Robert , Rahmad Akbar , Bartlomiej Swiatczak , Geir Kjetil Sandve , Dag Trygve Truslew Haug, and Victor Greiff. 2022 . ImmunoLingo : Linguistics-based formalization of the antibody language. arXiv preprint arXiv:2209.12635 (2022). Mai Ha Vu, Philippe A Robert, Rahmad Akbar, Bartlomiej Swiatczak, Geir Kjetil Sandve, Dag Trygve Truslew Haug, and Victor Greiff. 2022. ImmunoLingo: Linguistics-based formalization of the antibody language. arXiv preprint arXiv:2209.12635 (2022)."},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1002\/jps.20727"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2933727"},{"key":"e_1_3_2_2_60_1","volume-title":"SPRoBERTa: protein embedding learning with local fragment modeling. Briefings in Bioinformatics","author":"Wu Lijun","year":"2022","unstructured":"Lijun Wu , Chengcan Yin , Jinhua Zhu , Zhen Wu , Liang He , Yingce Xia , Shufang Xie , Tao Qin , and Tie-Yan Liu . 2022. SPRoBERTa: protein embedding learning with local fragment modeling. Briefings in Bioinformatics ( 2022 ). Lijun Wu, Chengcan Yin, Jinhua Zhu, Zhen Wu, Liang He, Yingce Xia, Shufang Xie, Tao Qin, and Tie-Yan Liu. 2022. SPRoBERTa: protein embedding learning with local fragment modeling. Briefings in Bioinformatics (2022)."},{"key":"e_1_3_2_2_61_1","unstructured":"Ruidong Wu Fan Ding Rui Wang Rui Shen Xiwen Zhang Shitong Luo Chenpeng Su Zuofan Wu Qi Xie Bonnie Berger etal 2022. High-resolution de novo structure prediction from primary sequence. BioRxiv (2022).  Ruidong Wu Fan Ding Rui Wang Rui Shen Xiwen Zhang Shitong Luo Chenpeng Su Zuofan Wu Qi Xie Bonnie Berger et al. 2022. High-resolution de novo structure prediction from primary sequence. BioRxiv (2022)."},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.26434\/chemrxiv.11839230.v1"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmb.2011.07.018"},{"key":"e_1_3_2_2_64_1","volume-title":"Ontoprotein: Protein pretraining with gene ontology embedding. arXiv preprint arXiv:2201.11147","author":"Zhang Ningyu","year":"2022","unstructured":"Ningyu Zhang , Zhen Bi , Xiaozhuan Liang , Siyuan Cheng , Haosen Hong , Shumin Deng , Jiazhang Lian , Qiang Zhang , and Huajun Chen . 2022 . Ontoprotein: Protein pretraining with gene ontology embedding. arXiv preprint arXiv:2201.11147 (2022). Ningyu Zhang, Zhen Bi, Xiaozhuan Liang, Siyuan Cheng, Haosen Hong, Shumin Deng, Jiazhang Lian, Qiang Zhang, and Huajun Chen. 2022. Ontoprotein: Protein pretraining with gene ontology embedding. arXiv preprint arXiv:2201.11147 (2022)."},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"}],"event":{"name":"KDD '23: The 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Long Beach CA USA","acronym":"KDD '23","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599468","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3580305.3599468","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:37Z","timestamp":1750178257000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599468"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,4]]},"references-count":65,"alternative-id":["10.1145\/3580305.3599468","10.1145\/3580305"],"URL":"https:\/\/doi.org\/10.1145\/3580305.3599468","relation":{},"subject":[],"published":{"date-parts":[[2023,8,4]]},"assertion":[{"value":"2023-08-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}