{"id":"https://openalex.org/W4200256006","doi":"https://doi.org/10.1093/bioinformatics/btab817","title":"Back translation for molecule generation","display_name":"Back translation for molecule generation","publication_year":2021,"publication_date":"2021-12-01","ids":{"openalex":"https://openalex.org/W4200256006","doi":"https://doi.org/10.1093/bioinformatics/btab817","pmid":"https://pubmed.ncbi.nlm.nih.gov/34875015"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btab817","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab817","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"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/A5101402840","display_name":"Fan Yang","orcid":"https://orcid.org/0000-0003-0308-955X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Fan","raw_affiliation_strings":["University of Science and Technology of China , Hefei, Anhui 230027, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China , Hefei, Anhui 230027, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021772140","display_name":"Yingce Xia","orcid":"https://orcid.org/0000-0001-9823-9033"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yingce Xia","raw_affiliation_strings":["Microsoft Research , Beijing 100080, China"],"raw_orcid":"https://orcid.org/0000-0001-9823-9033","affiliations":[{"raw_affiliation_string":"Microsoft Research , Beijing 100080, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028284977","display_name":"Jinhua Zhu","orcid":"https://orcid.org/0000-0003-2157-9077"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhua Zhu","raw_affiliation_strings":["University of Science and Technology of China , Hefei, Anhui 230027, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China , Hefei, Anhui 230027, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102750692","display_name":"Lijun Wu","orcid":"https://orcid.org/0000-0002-3530-590X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijun Wu","raw_affiliation_strings":["Microsoft Research , Beijing 100080, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research , Beijing 100080, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088666942","display_name":"Shufang Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shufang Xie","raw_affiliation_strings":["Microsoft Research , Beijing 100080, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research , Beijing 100080, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020025718","display_name":"Tao Qin","orcid":"https://orcid.org/0000-0002-9095-0776"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Qin","raw_affiliation_strings":["Microsoft Research , Beijing 100080, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research , Beijing 100080, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5021772140"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.3697,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.84394236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"38","issue":"5","first_page":"1244","last_page":"1251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.5511000156402588,"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":0.5511000156402588,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.1670999974012375,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.0430000014603138,"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/translation","display_name":"Translation (biology)","score":0.8121181726455688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5962196588516235},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3398098945617676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3285113573074341},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.22865280508995056},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.08329933881759644},{"id":"https://openalex.org/keywords/messenger-rna","display_name":"Messenger RNA","score":0.06471240520477295},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.05357012152671814}],"concepts":[{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.8121181726455688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5962196588516235},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3398098945617676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3285113573074341},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.22865280508995056},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.08329933881759644},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.06471240520477295},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.05357012152671814}],"mesh":[{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btab817","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab817","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:34875015","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34875015","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics (Oxford, England)","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1757990252","https://openalex.org/W1988037271","https://openalex.org/W2034549041","https://openalex.org/W2041548070","https://openalex.org/W2049633694","https://openalex.org/W2163605009","https://openalex.org/W2529996553","https://openalex.org/W2559655401","https://openalex.org/W2580919858","https://openalex.org/W2610148085","https://openalex.org/W2612690371","https://openalex.org/W2621742623","https://openalex.org/W2769423117","https://openalex.org/W2769756736","https://openalex.org/W2773987374","https://openalex.org/W2798613236","https://openalex.org/W2803526748","https://openalex.org/W2803615944","https://openalex.org/W2972608805","https://openalex.org/W2994678679","https://openalex.org/W3007309629","https://openalex.org/W3025593963","https://openalex.org/W3100751385","https://openalex.org/W3106536628","https://openalex.org/W3115755088","https://openalex.org/W3119872582","https://openalex.org/W3128405656","https://openalex.org/W3133523400","https://openalex.org/W4206174637","https://openalex.org/W4212774754","https://openalex.org/W6684191040","https://openalex.org/W6752245542","https://openalex.org/W6788034455"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W3204019825"],"abstract_inverted_index":{"MOTIVATION:":[0],"Molecule":[1],"generation,":[2,114],"which":[3,115,129,147,159],"is":[4,9,63,116,130,148,160],"to":[5,43,66,92,137,162,171,186,194,202],"generate":[6],"new":[7,108],"molecules,":[8],"an":[10,31,94],"important":[11],"problem":[12],"in":[13,82,200],"bioinformatics.":[14],"Typical":[15],"tasks":[16,245],"include":[17],"generating":[18],"molecules":[19,38,100,136],"with":[20,86,215],"given":[21,155],"properties,":[22,134],"molecular":[23,231],"property":[24,232],"improvement":[25,233],"(i.e.":[26,35],"improving":[27],"specific":[28],"properties":[29],"of":[30,61,72,79,97,133,151],"input":[32],"molecule),":[33,47],"retrosynthesis":[34,248],"predicting":[36],"the":[37,77,126,131,135,144,149,167,172,184,197,212,216,224],"that":[39],"can":[40],"be":[41,125,138,143],"used":[42],"synthesize":[44],"a":[45,107,117,156,164,179,221],"target":[46,145,173],"etc.":[48,140],"Recently,":[49],"deep-learning-based":[50],"methods":[51],"received":[52],"more":[53,206],"attention":[54],"for":[55,101,112,183,223],"molecule":[56,102,113,243],"generation.":[57,103],"The":[58],"labeled":[59,217],"data":[60,199,214,218,257,265],"bioinformatics":[62],"usually":[64],"costly":[65],"obtain,":[67],"but":[68],"there":[69],"are":[70,258,266],"millions":[71],"unlabeled":[73,87,99,198],"molecules.":[74,152],"Inspired":[75],"by":[76],"success":[78],"sequence":[80],"generation":[81,244],"natural":[83],"language":[84],"processing":[85],"data,":[88],"we":[89,176,191,210,237],"would":[90],"like":[91],"explore":[93],"effective":[95,120],"way":[96],"using":[98],"RESULTS:":[104],"We":[105,227],"propose":[106],"method,":[109],"back":[110,195],"translation":[111],"simple":[118],"yet":[119],"semisupervised":[121],"method.":[122],"Let":[123,141],"X":[124,170,187,203],"source":[127,168],"domain,":[128],"collection":[132,150],"optimized,":[139],"Y":[142,185,201],"domain":[146,169,174],"In":[153],"particular,":[154],"main":[157,225],"task":[158],"about":[161],"learn":[163],"mapping":[165],"from":[166],"Y,":[175],"first":[177],"train":[178,220],"reversed":[180],"model":[181,222],"g":[182,193],"mapping.":[188],"After":[189],"that,":[190],"use":[192],"translate":[196],"and":[204,219,234,236,246,256],"obtain":[205],"synthetic":[207,213],"data.":[208],"Finally,":[209],"combine":[211],"task.":[226],"conduct":[228],"experiments":[229],"on":[230,241],"retrosynthesis,":[235],"achieve":[238],"state-of-the-art":[239],"results":[240],"four":[242],"one":[247],"benchmark,":[249],"USPTO-50k.":[250],"AVAILABILITY":[251],"AND":[252],"IMPLEMENTATION:":[253],"Our":[254],"code":[255],"available":[259,267],"at":[260,268],"https://github.com/fyabc/BT4MolGen.":[261],"SUPPLEMENTARY":[262],"INFORMATION:":[263],"Supplementary":[264],"Bioinformatics":[269],"online.":[270]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}