{"id":"https://openalex.org/W2749279690","doi":"https://doi.org/10.1145/3107411.3107424","title":"Seq2seq Fingerprint","display_name":"Seq2seq Fingerprint","publication_year":2017,"publication_date":"2017-08-20","ids":{"openalex":"https://openalex.org/W2749279690","doi":"https://doi.org/10.1145/3107411.3107424","mag":"2749279690"},"language":"en","primary_location":{"id":"doi:10.1145/3107411.3107424","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3107411.3107424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology,and Health Informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101651952","display_name":"Zheng Xu","orcid":"https://orcid.org/0000-0002-9811-2646"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zheng Xu","raw_affiliation_strings":["The University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371324","display_name":"Sheng Wang","orcid":"https://orcid.org/0000-0003-4210-1670"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sheng Wang","raw_affiliation_strings":["The University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103796253","display_name":"Feiyun Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feiyun Zhu","raw_affiliation_strings":["The University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068865316","display_name":"Junzhou Huang","orcid":"https://orcid.org/0000-0002-9548-1227"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junzhou Huang","raw_affiliation_strings":["The University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101651952"],"corresponding_institution_ids":["https://openalex.org/I189196454"],"apc_list":null,"apc_paid":null,"fwci":9.4807,"has_fulltext":false,"cited_by_count":141,"citation_normalized_percentile":{"value":0.98497795,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"285","last_page":"294"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9890999794006348,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.9837999939918518,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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/embedding","display_name":"Embedding","score":0.7117714285850525},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.706140398979187},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.6255645155906677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5882302522659302},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5800981521606445},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.555647611618042},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5223970413208008},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5021402835845947},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4391593337059021},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.43252843618392944},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38393744826316833},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.11150503158569336}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7117714285850525},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.706140398979187},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.6255645155906677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5882302522659302},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5800981521606445},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.555647611618042},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5223970413208008},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5021402835845947},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4391593337059021},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.43252843618392944},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38393744826316833},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.11150503158569336},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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:10.1145/3107411.3107424","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3107411.3107424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology,and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6920702533","display_name":null,"funder_award_id":"IIS-1423056,CMMI-1434401,CNS-1405985,IIS-1553687","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1526543462","https://openalex.org/W1546015235","https://openalex.org/W1591801644","https://openalex.org/W1592238003","https://openalex.org/W1597224949","https://openalex.org/W1678356000","https://openalex.org/W1924770834","https://openalex.org/W1930624869","https://openalex.org/W1975147762","https://openalex.org/W1981939910","https://openalex.org/W1982792699","https://openalex.org/W1988037271","https://openalex.org/W1988790447","https://openalex.org/W1991286793","https://openalex.org/W2003209620","https://openalex.org/W2009576740","https://openalex.org/W2016979469","https://openalex.org/W2021748110","https://openalex.org/W2022476850","https://openalex.org/W2022885801","https://openalex.org/W2030971064","https://openalex.org/W2040389962","https://openalex.org/W2044834685","https://openalex.org/W2055888446","https://openalex.org/W2060531713","https://openalex.org/W2062875420","https://openalex.org/W2094278785","https://openalex.org/W2099471712","https://openalex.org/W2121853844","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2153657185","https://openalex.org/W2166114438","https://openalex.org/W2168480393","https://openalex.org/W2212883665","https://openalex.org/W2214665483","https://openalex.org/W2247312011","https://openalex.org/W2269544137","https://openalex.org/W2271840356","https://openalex.org/W2290847742","https://openalex.org/W2294125144","https://openalex.org/W2294309140","https://openalex.org/W2313771561","https://openalex.org/W2440458627","https://openalex.org/W2461470610","https://openalex.org/W2525036370","https://openalex.org/W2526712471","https://openalex.org/W2557283755","https://openalex.org/W2565684601","https://openalex.org/W2604306554","https://openalex.org/W2605207311","https://openalex.org/W2609765027","https://openalex.org/W2745940724","https://openalex.org/W2752879928","https://openalex.org/W2964113829","https://openalex.org/W3098269892","https://openalex.org/W3100157108","https://openalex.org/W4302085792","https://openalex.org/W4319704957"],"related_works":["https://openalex.org/W4296209631","https://openalex.org/W2081900870","https://openalex.org/W2561617217","https://openalex.org/W2090763504","https://openalex.org/W2025378473","https://openalex.org/W2355801475","https://openalex.org/W2037549926","https://openalex.org/W148178222","https://openalex.org/W4206659427","https://openalex.org/W1909208367"],"abstract_inverted_index":{"Many":[0],"of":[1,24,41,51,103],"today's":[2],"drug":[3],"discoveries":[4],"require":[5],"expertise":[6],"knowledge":[7],"and":[8,44,106,136,144,176,180,184],"insanely":[9],"expensive":[10],"biological":[11],"experiments":[12],"for":[13,70,159],"identifying":[14],"the":[15,21,42,48,81,95,116,121,127,141,160,168,170],"chemical":[16,34,147],"molecular":[17,35,62],"properties.":[18,148],"However,":[19],"despite":[20],"growing":[22],"interests":[23],"using":[25],"supervised":[26],"machine":[27],"learning":[28],"algorithms":[29],"to":[30,47,73,93,114,120,133,139],"automatically":[31],"identify":[32],"those":[33],"properties,":[36],"there":[37],"is":[38,91,112,131,173],"little":[39],"advancement":[40],"performance":[43,179],"accuracy":[45],"due":[46],"limited":[49],"amount":[50],"training":[52,161],"data.":[53],"In":[54,80],"this":[55],"paper,":[56],"we":[57],"propose":[58],"a":[59,66,84,99,125],"novel":[60],"unsupervised":[61],"embedding":[63,151],"method,":[64,83],"providing":[65],"continuous":[67,100,117,128],"feature":[68,101],"vector":[69,102,118,130],"each":[71],"molecule":[72,97,143,157],"perform":[74],"further":[75],"tasks,":[76],"e.g.,":[77],"solubility":[78],"classification.":[79],"proposed":[82,150,171],"multi-layered":[85],"Gated":[86],"Recurrent":[87],"Unit":[88],"(GRU)":[89],"network":[90,111],"used":[92],"map":[94],"input":[96],"into":[98],"fixed":[104],"dimensionality,":[105],"then":[107],"another":[108],"deep":[109],"GRU":[110],"employed":[113],"decode":[115],"back":[119],"original":[122,142],"molecule.":[123],"As":[124],"result,":[126],"encoding":[129],"expected":[132],"contain":[134],"rigorous":[135],"enough":[137],"information":[138,165],"recover":[140],"predict":[145],"its":[146],"The":[149,178],"method":[152,172],"could":[153],"utilize":[154],"almost":[155],"unlimited":[156],"data":[158],"phase.":[162],"With":[163],"sufficient":[164],"encoded":[166],"in":[167,186],"vector,":[169],"also":[174],"robust":[175],"task-insensitive.":[177],"robustness":[181],"are":[182],"confirmed":[183],"interpreted":[185],"our":[187],"extensive":[188],"experiments.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":10}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}