{"id":"https://openalex.org/W3101509328","doi":"https://doi.org/10.1145/3388440.3412467","title":"Transforming the Language of Life","display_name":"Transforming the Language of Life","publication_year":2020,"publication_date":"2020-09-21","ids":{"openalex":"https://openalex.org/W3101509328","doi":"https://doi.org/10.1145/3388440.3412467","mag":"3101509328"},"language":"en","primary_location":{"id":"doi:10.1145/3388440.3412467","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3388440.3412467","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3388440.3412467","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3388440.3412467","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080914112","display_name":"Ananthan Nambiar","orcid":"https://orcid.org/0000-0002-9767-9456"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ananthan Nambiar","raw_affiliation_strings":["Department of Bioengineering, Carl R. Woese Inst. for Genomic Biol., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Bioengineering, Carl R. Woese Inst. for Genomic Biol., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007955962","display_name":"Maeve Heflin","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maeve Heflin","raw_affiliation_strings":["Department of Computer Science, Carl R. Woese Inst. for Genomic Biol., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Carl R. Woese Inst. for Genomic Biol., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079945210","display_name":"Simon Liu","orcid":"https://orcid.org/0000-0003-0874-4533"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simon Liu","raw_affiliation_strings":["Department of Computer Science, Carl R. Woese Inst. for Genomic Biol., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Carl R. Woese Inst. for Genomic Biol., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017591427","display_name":"Sergei Maslov","orcid":"https://orcid.org/0000-0002-3701-492X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergei Maslov","raw_affiliation_strings":["Department of Bioengineering, Department of Physics, Carl R. Woese Inst. for Genomic Biol., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Bioengineering, Department of Physics, Carl R. Woese Inst. for Genomic Biol., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057318657","display_name":"Mark Hopkins","orcid":"https://orcid.org/0000-0002-7655-0215"},"institutions":[{"id":"https://openalex.org/I55486353","display_name":"Reed College","ror":"https://ror.org/00a6ram87","country_code":"US","type":"education","lineage":["https://openalex.org/I55486353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hopkins","raw_affiliation_strings":["Department of Computer Science Reed College, Portland, OR, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science Reed College, Portland, OR, USA","institution_ids":["https://openalex.org/I55486353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087718701","display_name":"Anna Ritz","orcid":"https://orcid.org/0000-0002-7925-5369"},"institutions":[{"id":"https://openalex.org/I55486353","display_name":"Reed College","ror":"https://ror.org/00a6ram87","country_code":"US","type":"education","lineage":["https://openalex.org/I55486353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anna Ritz","raw_affiliation_strings":["Department of Biology Reed College, Portland, OR, USA"],"affiliations":[{"raw_affiliation_string":"Department of Biology Reed College, Portland, OR, USA","institution_ids":["https://openalex.org/I55486353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5080914112"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":5.0159,"has_fulltext":true,"cited_by_count":97,"citation_normalized_percentile":{"value":0.96526237,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.759330153465271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.58992999792099},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5748535394668579},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5740023255348206},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5276511907577515},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.521662712097168},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5114477872848511},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.42923426628112793},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4101470708847046},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.1356343924999237},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07875269651412964}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.759330153465271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.58992999792099},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5748535394668579},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5740023255348206},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5276511907577515},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.521662712097168},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5114477872848511},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.42923426628112793},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4101470708847046},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.1356343924999237},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07875269651412964},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3388440.3412467","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3388440.3412467","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3388440.3412467","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3388440.3412467","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3388440.3412467","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3388440.3412467","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[{"id":"https://openalex.org/G1267142038","display_name":null,"funder_award_id":"1750981","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1748095818","display_name":null,"funder_award_id":"#1725729","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5110513522","display_name":null,"funder_award_id":"1750981","funder_id":"https://openalex.org/F4320337398","funder_display_name":"Division of Biological Infrastructure"},{"id":"https://openalex.org/G8940766960","display_name":null,"funder_award_id":"1725729","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320311640","display_name":"Reed College","ror":"https://ror.org/00a6ram87"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"},{"id":"https://openalex.org/F4320337398","display_name":"Division of Biological Infrastructure","ror":"https://ror.org/04qn9mx93"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3101509328.pdf","grobid_xml":"https://content.openalex.org/works/W3101509328.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W46679369","https://openalex.org/W1501531009","https://openalex.org/W1574901103","https://openalex.org/W1672197616","https://openalex.org/W1914481269","https://openalex.org/W1976937534","https://openalex.org/W2045812729","https://openalex.org/W2087064593","https://openalex.org/W2101234009","https://openalex.org/W2152705149","https://openalex.org/W2534390616","https://openalex.org/W2618265628","https://openalex.org/W2626778328","https://openalex.org/W2781528640","https://openalex.org/W2807818025","https://openalex.org/W2889454651","https://openalex.org/W2890911678","https://openalex.org/W2896457183","https://openalex.org/W2929612857","https://openalex.org/W2930786691","https://openalex.org/W2933138175","https://openalex.org/W2937766897","https://openalex.org/W2943495267","https://openalex.org/W2952209472","https://openalex.org/W2957436444","https://openalex.org/W2962784628","https://openalex.org/W2963250244","https://openalex.org/W2965373594","https://openalex.org/W2985936688","https://openalex.org/W2997591727","https://openalex.org/W2998737920","https://openalex.org/W3003243900","https://openalex.org/W3034396616","https://openalex.org/W4242341673","https://openalex.org/W6601894380"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W3032952384","https://openalex.org/W3017902212","https://openalex.org/W2964335273","https://openalex.org/W2982145560","https://openalex.org/W2095784700"],"abstract_inverted_index":{"The":[0],"scientific":[1],"community":[2],"is":[3,56,74],"rapidly":[4],"generating":[5],"protein":[6,26,62,65,69,81,100,117],"sequence":[7,52,113],"information,":[8],"but":[9],"only":[10],"a":[11,40,45,106],"fraction":[12],"of":[13],"these":[14],"proteins":[15],"can":[16],"be":[17],"experimentally":[18],"characterized.":[19],"While":[20],"promising":[21,107],"deep":[22],"learning":[23],"approaches":[24,79,98],"for":[25,80,99,109,115],"prediction":[27,63,118],"tasks":[28],"have":[29,32],"emerged,":[30],"they":[31],"computational":[33],"limitations":[34],"or":[35],"are":[36],"designed":[37],"to":[38,58,76],"solve":[39,59],"specific":[41],"task.":[42],"We":[43],"present":[44],"Transformer":[46],"neural":[47],"network":[48],"that":[49],"pre-trains":[50],"task-agnostic":[51],"representations.":[53],"This":[54],"model":[55],"fine-tuned":[57],"two":[60],"different":[61],"tasks:":[64],"family":[66,82],"classification":[67,83],"and":[68],"interaction":[70,101],"prediction.":[71,102],"Our":[72],"method":[73,94],"comparable":[75],"existing":[77],"state-of-the-art":[78],"while":[84],"being":[85],"much":[86],"more":[87],"general":[88],"than":[89],"other":[90,97,116],"architectures.":[91],"Further,":[92],"our":[93],"outperforms":[95],"all":[96],"These":[103],"results":[104],"offer":[105],"framework":[108],"fine-tuning":[110],"the":[111],"pre-trained":[112],"representations":[114],"tasks.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}