{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T01:45:18Z","timestamp":1775871918853,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,9,21]],"date-time":"2020-09-21T00:00:00Z","timestamp":1600646400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000105","name":"Office of Advanced Cyberinfrastructure","doi-asserted-by":"publisher","award":["1725729"],"award-info":[{"award-number":["1725729"]}],"id":[{"id":"10.13039\/100000105","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000153","name":"Division of Biological Infrastructure","doi-asserted-by":"publisher","award":["1750981"],"award-info":[{"award-number":["1750981"]}],"id":[{"id":"10.13039\/100000153","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,9,21]]},"DOI":"10.1145\/3388440.3412467","type":"proceedings-article","created":{"date-parts":[[2020,11,10]],"date-time":"2020-11-10T12:43:43Z","timestamp":1605012223000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":86,"title":["Transforming the Language of Life"],"prefix":"10.1145","author":[{"given":"Ananthan","family":"Nambiar","sequence":"first","affiliation":[{"name":"Department of Bioengineering, Carl R. Woese Inst. for Genomic Biol., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA"}]},{"given":"Maeve","family":"Heflin","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Carl R. Woese Inst. for Genomic Biol., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA"}]},{"given":"Simon","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Carl R. Woese Inst. for Genomic Biol., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA"}]},{"given":"Sergei","family":"Maslov","sequence":"additional","affiliation":[{"name":"Department of Bioengineering, Department of Physics, Carl R. Woese Inst. for Genomic Biol., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA"}]},{"given":"Mark","family":"Hopkins","sequence":"additional","affiliation":[{"name":"Department of Computer Science Reed College, Portland, OR, USA"}]},{"given":"Anna","family":"Ritz","sequence":"additional","affiliation":[{"name":"Department of Biology Reed College, Portland, OR, USA"}]}],"member":"320","published-online":{"date-parts":[[2020,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1111\/j.1432-1033.1984.tb07877.x","article-title":". Nomenclature and Symbolism for Amino Acids and Peptides","volume":"138","year":"1984","unstructured":"1984 . Nomenclature and Symbolism for Amino Acids and Peptides . European Journal of Biochemistry 138 , 1 (1984), 9 -- 37 . https:\/\/doi.org\/10.1111\/j.1432--1033.1984.tb07877.x 10.1111\/j.1432--1033.1984.tb07877.x 1984. Nomenclature and Symbolism for Amino Acids and Peptides. European Journal of Biochemistry 138, 1 (1984), 9--37. https:\/\/doi.org\/10.1111\/j.1432--1033.1984.tb07877.x","journal-title":"European Journal of Biochemistry"},{"key":"e_1_3_2_1_2_1","volume-title":"Schaefer","author":"Alanis-Lobato Gregorio","year":"2016","unstructured":"Gregorio Alanis-Lobato , Miguel A. Andrade-Navarro , and Martin H . Schaefer . 2016 . HIPPIE v2.0: enhancing meaningfulness and reliability of protein-protein interaction networks. Nucleic Acids Research 45, D1 (10 2016), D408--D414. Gregorio Alanis-Lobato, Miguel A. Andrade-Navarro, and Martin H. Schaefer. 2016. HIPPIE v2.0: enhancing meaningfulness and reliability of protein-protein interaction networks. Nucleic Acids Research 45, D1 (10 2016), D408--D414."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-38746-w"},{"key":"e_1_3_2_1_4_1","volume-title":"Mofrad","author":"Asgari Ehsaneddin","year":"2015","unstructured":"Ehsaneddin Asgari and Mohammad R. K . Mofrad . 2015 . Continuous Distributed Representation of Biological Sequences for Deep Proteomics and Genomics. PLOS ONE 10, 11 (11 2015), 1--15. Ehsaneddin Asgari and Mohammad R. K. Mofrad. 2015. Continuous Distributed Representation of Biological Sequences for Deep Proteomics and Genomics. PLOS ONE 10, 11 (11 2015), 1--15."},{"key":"e_1_3_2_1_5_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E Hinton","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba , Jamie Ryan Kiros, and Geoffrey E Hinton . 2016 . Layer normalization. arXiv preprint arXiv.1607.06450 (2016). Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. 2016. Layer normalization. arXiv preprint arXiv.1607.06450 (2016)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1162\/artl_a_00279"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/645503.656271"},{"key":"e_1_3_2_1_8_1","volume-title":"Colwell","author":"Bileschi Maxwell L.","year":"2019","unstructured":"Maxwell L. Bileschi , David Belanger , Drew Bryant , Theo Sanderson , Brandon Carter , D. Sculley , Mark A. DePristo , and Lucy J . Colwell . 2019 . Using Deep Learning to Annotate the Protein Universe . bioRxiv (2019). Maxwell L. Bileschi, David Belanger, Drew Bryant, Theo Sanderson, Brandon Carter, D. Sculley, Mark A. DePristo, and Lucy J. Colwell. 2019. Using Deep Learning to Annotate the Protein Universe. bioRxiv (2019)."},{"key":"e_1_3_2_1_9_1","volume-title":"Guangyu Zhou, Xuelu Chen, Tianran Zhang, KaiWei Chang, Carlo Zaniolo, and Wei Wang.","author":"Chen Muhao","year":"2019","unstructured":"Muhao Chen , Chelsea J T Ju , Guangyu Zhou, Xuelu Chen, Tianran Zhang, KaiWei Chang, Carlo Zaniolo, and Wei Wang. 2019 . Multifaceted protein-protein interaction prediction based on Siamese residual RCNN. Bioinformatics 35, 14 (07 2019), i305--i314. Muhao Chen, Chelsea J T Ju, Guangyu Zhou, Xuelu Chen, Tianran Zhang, KaiWei Chang, Carlo Zaniolo, and Wei Wang. 2019. Multifaceted protein-protein interaction prediction based on Siamese residual RCNN. Bioinformatics 35, 14 (07 2019), i305--i314."},{"key":"e_1_3_2_1_10_1","volume-title":"D1 (11","author":"The UniProt Consortium","year":"2018","unstructured":"The UniProt Consortium . 2018. UniProt: a worldwide hub of protein knowledge. Nucleic Acids Research 47 , D1 (11 2018 ), D506--D515. The UniProt Consortium. 2018. UniProt: a worldwide hub of protein knowledge. Nucleic Acids Research 47, D1 (11 2018), D506--D515."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymeth.2015.09.029"},{"key":"e_1_3_2_1_12_1","volume-title":"Protein-Protein Interactions Essentials: Key Concepts to Building and Analyzing Interactome Networks. PLOS Computational Biology 6, 6 (06","author":"Las Rivas Javier De","year":"2010","unstructured":"Javier De Las Rivas and Celia Fontanillo . 2010. Protein-Protein Interactions Essentials: Key Concepts to Building and Analyzing Interactome Networks. PLOS Computational Biology 6, 6 (06 2010 ), 1--8. Javier De Las Rivas and Celia Fontanillo. 2010. Protein-Protein Interactions Essentials: Key Concepts to Building and Analyzing Interactome Networks. PLOS Computational Biology 6, 6 (06 2010), 1--8."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2019 . BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding . In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies , Volume 1 (Long and Short Papers). Association for Computational Linguistics, Minneapolis, Minnesota, 4171--4186. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics, Minneapolis, Minnesota, 4171--4186."},{"key":"e_1_3_2_1_14_1","first-page":"2","article-title":"A New Algorithm for Data Compression","volume":"12","author":"Gage Philip","year":"1994","unstructured":"Philip Gage . 1994 . A New Algorithm for Data Compression . C Users J. 12 , 2 (Feb. 1994), 23--38. Philip Gage. 1994. A New Algorithm for Data Compression. C Users J. 12, 2 (Feb. 1994), 23--38.","journal-title":"C Users J."},{"key":"e_1_3_2_1_15_1","volume-title":"A deep learning framework for improving protein interaction prediction using sequence properties. bioRxiv","author":"Guo Yi","year":"2019","unstructured":"Yi Guo and Xiang Chen . 2019. A deep learning framework for improving protein interaction prediction using sequence properties. bioRxiv ( 2019 ). Yi Guo and Xiang Chen. 2019. A deep learning framework for improving protein interaction prediction using sequence properties. bioRxiv (2019)."},{"key":"e_1_3_2_1_16_1","volume-title":"Using support vector machine combined with auto covariance to predict protein-protein interactions from protein sequences. Nucleic Acids Research 36, 9 (04","author":"Guo Yanzhi","year":"2008","unstructured":"Yanzhi Guo , Lezheng Yu , Zhining Wen , and Menglong Li. 2008. Using support vector machine combined with auto covariance to predict protein-protein interactions from protein sequences. Nucleic Acids Research 36, 9 (04 2008 ), 3025--3030. Yanzhi Guo, Lezheng Yu, Zhining Wen, and Menglong Li. 2008. Using support vector machine combined with auto covariance to predict protein-protein interactions from protein sequences. Nucleic Acids Research 36, 9 (04 2008), 3025--3030."},{"key":"e_1_3_2_1_17_1","volume-title":"Evolutionary profiles improve protein-protein interaction prediction from sequence. Bioinformatics 31, 12 (02","author":"Hamp Tobias","year":"2015","unstructured":"Tobias Hamp and Burkhard Rost . 2015. Evolutionary profiles improve protein-protein interaction prediction from sequence. Bioinformatics 31, 12 (02 2015 ), 1945--1950. Tobias Hamp and Burkhard Rost. 2015. Evolutionary profiles improve protein-protein interaction prediction from sequence. Bioinformatics 31, 12 (02 2015), 1945--1950."},{"key":"e_1_3_2_1_18_1","volume-title":"Predicting protein-protein interactions through sequence-based deep learning. Bioinformatics 34, 17 (09","author":"Hashemifar Somaye","year":"2018","unstructured":"Somaye Hashemifar , Behnam Neyshabur , Aly A Khan , and Jinbo Xu. 2018. Predicting protein-protein interactions through sequence-based deep learning. Bioinformatics 34, 17 (09 2018 ), i802--i810. Somaye Hashemifar, Behnam Neyshabur, Aly A Khan, and Jinbo Xu. 2018. Predicting protein-protein interactions through sequence-based deep learning. Bioinformatics 34, 17 (09 2018), i802--i810."},{"key":"e_1_3_2_1_19_1","volume-title":"Modeling the Language of Life - Deep Learning Protein Sequences. bioRxiv","author":"Heinzinger Michael","year":"2019","unstructured":"Michael Heinzinger , Ahmed Elnaggar , Yu Wang , Christian Dallago , Dmitrii Nachaev , Florian Matthes , and Burkhard Rost . 2019. Modeling the Language of Life - Deep Learning Protein Sequences. bioRxiv ( 2019 ). Michael Heinzinger, Ahmed Elnaggar, Yu Wang, Christian Dallago, Dmitrii Nachaev, Florian Matthes, and Burkhard Rost. 2019. Modeling the Language of Life - Deep Learning Protein Sequences. bioRxiv (2019)."},{"key":"e_1_3_2_1_20_1","volume-title":"Bridging Nonlinearities and Stochastic Regularizers with Gaussian Error Linear Units. arXiv preprint arXiv:1606.08415","author":"Hendrycks Dan","year":"2016","unstructured":"Dan Hendrycks and Kevin Gimpel . 2016. Bridging Nonlinearities and Stochastic Regularizers with Gaussian Error Linear Units. arXiv preprint arXiv:1606.08415 ( 2016 ). Dan Hendrycks and Kevin Gimpel. 2016. Bridging Nonlinearities and Stochastic Regularizers with Gaussian Error Linear Units. arXiv preprint arXiv:1606.08415 (2016)."},{"key":"#cr-split#-e_1_3_2_1_21_1.1","doi-asserted-by":"crossref","unstructured":"Taku Kudo and John Richardson. 2018. SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing. 66--71 pages. https:\/\/doi.org\/10.18653\/v1\/D18--2012 10.18653\/v1","DOI":"10.18653\/v1\/D18-2012"},{"key":"#cr-split#-e_1_3_2_1_21_1.2","doi-asserted-by":"crossref","unstructured":"Taku Kudo and John Richardson. 2018. SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing. 66--71 pages. https:\/\/doi.org\/10.18653\/v1\/D18--2012","DOI":"10.18653\/v1\/D18-2012"},{"key":"e_1_3_2_1_22_1","unstructured":"Yinhan Liu Myle Ott Naman Goyal Jingfei Du Mandar Joshi Danqi Chen Omer Levy Mike Lewis Luke Zettlemoyer and Veselin Stoyanov. 2020. RoBERTa: A Robustly Optimized BERT Pretraining Approach. https:\/\/openreview.net\/forum?id=SyxS0T4tvS Yinhan Liu Myle Ott Naman Goyal Jingfei Du Mandar Joshi Danqi Chen Omer Levy Mike Lewis Luke Zettlemoyer and Veselin Stoyanov. 2020. RoBERTa: A Robustly Optimized BERT Pretraining Approach. https:\/\/openreview.net\/forum?id=SyxS0T4tvS"},{"key":"e_1_3_2_1_23_1","volume-title":"Huimin Zhao, and Jian Peng.","author":"Luo Yunan","year":"2020","unstructured":"Yunan Luo , Lam Vo , Hantian Ding , Yufeng Su , Yang Liu , Wesley Wei Qian , Huimin Zhao, and Jian Peng. 2020 . Evolutionary context-integrated deep sequence modeling for protein engineering. bioRxiv (2020). https:\/\/doi.org\/10.1101\/2020.01.16.908509 10.1101\/2020.01.16.908509 Yunan Luo, Lam Vo, Hantian Ding, Yufeng Su, Yang Liu, Wesley Wei Qian, Huimin Zhao, and Jian Peng. 2020. Evolutionary context-integrated deep sequence modeling for protein engineering. bioRxiv (2020). https:\/\/doi.org\/10.1101\/2020.01.16.908509"},{"key":"e_1_3_2_1_24_1","volume-title":"Foundations of statistical natural language processing","author":"Manning Christopher D","unstructured":"Christopher D Manning , Christopher D Manning , and Hinrich Sch\u00fctze . 1999. Foundations of statistical natural language processing . MIT press . Christopher D Manning, Christopher D Manning, and Hinrich Sch\u00fctze. 1999. Foundations of statistical natural language processing. MIT press."},{"key":"#cr-split#-e_1_3_2_1_25_1.1","unstructured":"Ananthan Nambiar Mark Hopkins and Anna Ritz. 2019. Computing the Language of Life: NLP Approaches to Feature Extraction for Protein Classification. In ISMB\/ECCB 2019: Poster Session. https:\/\/doi.org\/10.7490\/f1000research.1118014.1 10.7490\/f1000research.1118014.1"},{"key":"#cr-split#-e_1_3_2_1_25_1.2","unstructured":"Ananthan Nambiar Mark Hopkins and Anna Ritz. 2019. Computing the Language of Life: NLP Approaches to Feature Extraction for Protein Classification. In ISMB\/ECCB 2019: Poster Session. https:\/\/doi.org\/10.7490\/f1000research.1118014.1"},{"key":"e_1_3_2_1_26_1","volume-title":"DeepFam: deep learning based alignment-free method for protein family modeling and prediction. Bioinformatics 34, 13 (06","author":"Oh Minsik","year":"2018","unstructured":"Minsik Oh , Seokjun Seo , Sun Kim , and Youngjune Park . 2018. DeepFam: deep learning based alignment-free method for protein family modeling and prediction. Bioinformatics 34, 13 (06 2018 ), i254-i262. Minsik Oh, Seokjun Seo, Sun Kim, and Youngjune Park. 2018. DeepFam: deep learning based alignment-free method for protein family modeling and prediction. Bioinformatics 34, 13 (06 2018), i254-i262."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"e_1_3_2_1_29_1","volume-title":"Paving the way to single-molecule protein sequencing. Nature nanotechnology 13, 9","author":"Restrepo-P\u00e9rez Laura","year":"2018","unstructured":"Laura Restrepo-P\u00e9rez , Chirlmin Joo , and Cees Dekker . 2018. Paving the way to single-molecule protein sequencing. Nature nanotechnology 13, 9 ( 2018 ), 786--796. Laura Restrepo-P\u00e9rez, Chirlmin Joo, and Cees Dekker. 2018. Paving the way to single-molecule protein sequencing. Nature nanotechnology 13, 9 (2018), 786--796."},{"key":"e_1_3_2_1_30_1","volume-title":"Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. bioRxiv","author":"Rives Alexander","year":"2019","unstructured":"Alexander Rives , Siddharth Goyal , Joshua Meier , Demi Guo , Myle Ott , C. Lawrence Zitnick , Jerry Ma , and Rob Fergus . 2019. Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. bioRxiv ( 2019 ). Alexander Rives, Siddharth Goyal, Joshua Meier, Demi Guo, Myle Ott, C. Lawrence Zitnick, Jerry Ma, and Rob Fergus. 2019. Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. bioRxiv (2019)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/0022-2836(81)90087-5"},{"key":"e_1_3_2_1_33_1","volume-title":"UDSMProt: universal deep sequence models for protein classification. Bioinformatics (01","author":"Strodthoff Nils","year":"2020","unstructured":"Nils Strodthoff , Patrick Wagner , Markus Wenzel , and Wojciech Samek . 2020. UDSMProt: universal deep sequence models for protein classification. Bioinformatics (01 2020 ). btaa003. Nils Strodthoff, Patrick Wagner, Markus Wenzel, and Wojciech Samek. 2020. UDSMProt: universal deep sequence models for protein classification. Bioinformatics (01 2020). btaa003."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-017-1700-2"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_1_36_1","volume-title":"Reducing BERT Pre-Training Time from 3 Days to 76 Minutes. CoRR abs\/1904.00962","author":"You Yang","year":"2019","unstructured":"Yang You , Jing Li , Jonathan Hseu , Xiaodan Song , James Demmel , and Cho-Jui Hsieh . 2019. Reducing BERT Pre-Training Time from 3 Days to 76 Minutes. CoRR abs\/1904.00962 ( 2019 ). Yang You, Jing Li, Jonathan Hseu, Xiaodan Song, James Demmel, and Cho-Jui Hsieh. 2019. Reducing BERT Pre-Training Time from 3 Days to 76 Minutes. CoRR abs\/1904.00962 (2019)."},{"key":"e_1_3_2_1_37_1","volume-title":"Recent Trends in Deep Learning Based Natural Language Processing. CoRR abs\/1708.02709","author":"Young Tom","year":"2017","unstructured":"Tom Young , Devamanyu Hazarika , Soujanya Poria , and Erik Cambria . 2017. Recent Trends in Deep Learning Based Natural Language Processing. CoRR abs\/1708.02709 ( 2017 ). Tom Young, Devamanyu Hazarika, Soujanya Poria, and Erik Cambria. 2017. Recent Trends in Deep Learning Based Natural Language Processing. CoRR abs\/1708.02709 (2017)."}],"event":{"name":"BCB '20: 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","location":"Virtual Event USA","acronym":"BCB '20","sponsor":["SIGBio ACM Special Interest Group on Bioinformatics"]},"container-title":["Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3388440.3412467","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3388440.3412467","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3388440.3412467","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:33:30Z","timestamp":1750199610000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3388440.3412467"}},"subtitle":["Transformer Neural Networks for Protein Prediction Tasks"],"short-title":[],"issued":{"date-parts":[[2020,9,21]]},"references-count":39,"alternative-id":["10.1145\/3388440.3412467","10.1145\/3388440"],"URL":"https:\/\/doi.org\/10.1145\/3388440.3412467","relation":{},"subject":[],"published":{"date-parts":[[2020,9,21]]},"assertion":[{"value":"2020-11-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}