{"id":"https://openalex.org/W4287307915","doi":"https://doi.org/10.1021/acs.jcim.2c00744","title":"HyFactor: A Novel Open-Source, Graph-Based Architecture for Chemical Structure Generation","display_name":"HyFactor: A Novel Open-Source, Graph-Based Architecture for Chemical Structure Generation","publication_year":2022,"publication_date":"2022-07-25","ids":{"openalex":"https://openalex.org/W4287307915","doi":"https://doi.org/10.1021/acs.jcim.2c00744","pmid":"https://pubmed.ncbi.nlm.nih.gov/35876159"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.2c00744","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.2c00744","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"review","indexed_in":["crossref","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/A5025753184","display_name":"Tagir Akhmetshin","orcid":"https://orcid.org/0000-0002-2549-6431"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I68947357","display_name":"Universit\u00e9 de Strasbourg","ror":"https://ror.org/00pg6eq24","country_code":"FR","type":"education","lineage":["https://openalex.org/I68947357"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Tagir Akhmetshin","raw_affiliation_strings":["Laboratory of Chemoinformatics, UMR 7140 CNRS, University of Strasbourg, 4 Blaise Pascal Str., 67081 Strasbourg, France"],"raw_orcid":"https://orcid.org/0000-0002-2549-6431","affiliations":[{"raw_affiliation_string":"Laboratory of Chemoinformatics, UMR 7140 CNRS, University of Strasbourg, 4 Blaise Pascal Str., 67081 Strasbourg, France","institution_ids":["https://openalex.org/I68947357","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066364650","display_name":"Arkadii Lin","orcid":"https://orcid.org/0000-0002-9546-0012"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I68947357","display_name":"Universit\u00e9 de Strasbourg","ror":"https://ror.org/00pg6eq24","country_code":"FR","type":"education","lineage":["https://openalex.org/I68947357"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Arkadii Lin","raw_affiliation_strings":["Laboratory of Chemoinformatics, UMR 7140 CNRS, University of Strasbourg, 4 Blaise Pascal Str., 67081 Strasbourg, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Chemoinformatics, UMR 7140 CNRS, University of Strasbourg, 4 Blaise Pascal Str., 67081 Strasbourg, France","institution_ids":["https://openalex.org/I68947357","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063478269","display_name":"Daniyar Mazitov","orcid":"https://orcid.org/0000-0003-1305-4377"},"institutions":[{"id":"https://openalex.org/I21203515","display_name":"Kazan Federal University","ror":"https://ror.org/05256ym39","country_code":"RU","type":"education","lineage":["https://openalex.org/I21203515"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Daniyar Mazitov","raw_affiliation_strings":["Laboratory of Chemoinformatics and Molecular Modeling, Butlerov Institute of Chemistry, Kazan Federal University, 18 Kremlyovskaya Str., 420008 Kazan, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Chemoinformatics and Molecular Modeling, Butlerov Institute of Chemistry, Kazan Federal University, 18 Kremlyovskaya Str., 420008 Kazan, Russia","institution_ids":["https://openalex.org/I21203515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077202043","display_name":"Yuliana Zabolotna","orcid":"https://orcid.org/0000-0001-9068-612X"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I68947357","display_name":"Universit\u00e9 de Strasbourg","ror":"https://ror.org/00pg6eq24","country_code":"FR","type":"education","lineage":["https://openalex.org/I68947357"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yuliana Zabolotna","raw_affiliation_strings":["Laboratory of Chemoinformatics, UMR 7140 CNRS, University of Strasbourg, 4 Blaise Pascal Str., 67081 Strasbourg, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Chemoinformatics, UMR 7140 CNRS, University of Strasbourg, 4 Blaise Pascal Str., 67081 Strasbourg, France","institution_ids":["https://openalex.org/I68947357","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090710759","display_name":"Evgenii Ziaikin","orcid":"https://orcid.org/0000-0001-6316-1301"},"institutions":[{"id":"https://openalex.org/I21203515","display_name":"Kazan Federal University","ror":"https://ror.org/05256ym39","country_code":"RU","type":"education","lineage":["https://openalex.org/I21203515"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Evgenii Ziaikin","raw_affiliation_strings":["Laboratory of Chemoinformatics and Molecular Modeling, Butlerov Institute of Chemistry, Kazan Federal University, 18 Kremlyovskaya Str., 420008 Kazan, Russia"],"raw_orcid":"https://orcid.org/0000-0001-6316-1301","affiliations":[{"raw_affiliation_string":"Laboratory of Chemoinformatics and Molecular Modeling, Butlerov Institute of Chemistry, Kazan Federal University, 18 Kremlyovskaya Str., 420008 Kazan, Russia","institution_ids":["https://openalex.org/I21203515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058265669","display_name":"Timur Madzhidov","orcid":"https://orcid.org/0000-0002-3834-6985"},"institutions":[{"id":"https://openalex.org/I21203515","display_name":"Kazan Federal University","ror":"https://ror.org/05256ym39","country_code":"RU","type":"education","lineage":["https://openalex.org/I21203515"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Timur Madzhidov","raw_affiliation_strings":["Laboratory of Chemoinformatics and Molecular Modeling, Butlerov Institute of Chemistry, Kazan Federal University, 18 Kremlyovskaya Str., 420008 Kazan, Russia"],"raw_orcid":"https://orcid.org/0000-0002-3834-6985","affiliations":[{"raw_affiliation_string":"Laboratory of Chemoinformatics and Molecular Modeling, Butlerov Institute of Chemistry, Kazan Federal University, 18 Kremlyovskaya Str., 420008 Kazan, Russia","institution_ids":["https://openalex.org/I21203515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070041767","display_name":"Alexandre Varnek","orcid":"https://orcid.org/0000-0003-1886-925X"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I68947357","display_name":"Universit\u00e9 de Strasbourg","ror":"https://ror.org/00pg6eq24","country_code":"FR","type":"education","lineage":["https://openalex.org/I68947357"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Alexandre Varnek","raw_affiliation_strings":["Laboratory of Chemoinformatics, UMR 7140 CNRS, University of Strasbourg, 4 Blaise Pascal Str., 67081 Strasbourg, France"],"raw_orcid":"https://orcid.org/0000-0003-1886-925X","affiliations":[{"raw_affiliation_string":"Laboratory of Chemoinformatics, UMR 7140 CNRS, University of Strasbourg, 4 Blaise Pascal Str., 67081 Strasbourg, France","institution_ids":["https://openalex.org/I68947357","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5058265669","https://openalex.org/A5070041767"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I21203515","https://openalex.org/I68947357"],"apc_list":null,"apc_paid":null,"fwci":0.3769,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.49957005,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"62","issue":"15","first_page":"3524","last_page":"3534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9998000264167786,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9983000159263611,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9926000237464905,"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/code-refactoring","display_name":"Code refactoring","score":0.8848309516906738},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7792624235153198},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5662192702293396},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5661038160324097},{"id":"https://openalex.org/keywords/chembl","display_name":"chEMBL","score":0.5237707495689392},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.45830583572387695},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4455380141735077},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4104294776916504},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39290881156921387},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.20599320530891418},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17658215761184692},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.17468318343162537},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.14326292276382446}],"concepts":[{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.8848309516906738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7792624235153198},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5662192702293396},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5661038160324097},{"id":"https://openalex.org/C63222358","wikidata":"https://www.wikidata.org/wiki/Q6120337","display_name":"chEMBL","level":3,"score":0.5237707495689392},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.45830583572387695},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4455380141735077},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4104294776916504},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39290881156921387},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.20599320530891418},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17658215761184692},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.17468318343162537},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.14326292276382446},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1021/acs.jcim.2c00744","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.2c00744","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:35876159","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35876159","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":"Journal of chemical information and modeling","raw_type":null},{"id":"pmh:oai:HAL:hal-05565079v1","is_oa":false,"landing_page_url":"https://univoak.hal.science/hal-05565079","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Chemical Information and Modeling, 2022, 62 (15), pp.3524-3534. &#x27E8;10.1021/acs.jcim.2c00744&#x27E9;","raw_type":"Journal articles"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1508604947","https://openalex.org/W1677182931","https://openalex.org/W1996327711","https://openalex.org/W2064675550","https://openalex.org/W2096541451","https://openalex.org/W2104742871","https://openalex.org/W2157331557","https://openalex.org/W2529996553","https://openalex.org/W2606202972","https://openalex.org/W2747592475","https://openalex.org/W2786016794","https://openalex.org/W2901454299","https://openalex.org/W2901476322","https://openalex.org/W2915175970","https://openalex.org/W2943959866","https://openalex.org/W2946928580","https://openalex.org/W2948162129","https://openalex.org/W2955727640","https://openalex.org/W2962764565","https://openalex.org/W2964015378","https://openalex.org/W2965344674","https://openalex.org/W3013169228","https://openalex.org/W3096144872","https://openalex.org/W3104956673","https://openalex.org/W3105590657","https://openalex.org/W3116865743","https://openalex.org/W3199234580","https://openalex.org/W3211043910","https://openalex.org/W4289436753","https://openalex.org/W4394666973","https://openalex.org/W6968799348"],"related_works":["https://openalex.org/W1948541244","https://openalex.org/W2768661791","https://openalex.org/W2557652470","https://openalex.org/W3023891024","https://openalex.org/W3177311804","https://openalex.org/W2973167930","https://openalex.org/W2364531466","https://openalex.org/W2383828164","https://openalex.org/W396164270","https://openalex.org/W3213030203"],"abstract_inverted_index":{"Graph-based":[0],"architectures":[1,87],"are":[2,164],"becoming":[3],"increasingly":[4],"popular":[5],"as":[6,155,157],"a":[7],"tool":[8],"for":[9],"structure":[10],"generation.":[11],"Here,":[12],"we":[13],"introduce":[14],"novel":[15],"open-source":[16],"architecture":[17,58,67],"HyFactor":[18,43,73,101,152],"in":[19,68,125,161],"which,":[20],"similar":[21,89,104],"to":[22,32,96],"the":[23,27,33,40,47,64,69,97,113,116,126,134,145],"InChI":[24],"linear":[25],"notation,":[26],"number":[28],"of":[29,39,63,83,122,137,151],"hydrogens":[30],"attached":[31],"heavy":[34,138],"atoms":[35],"was":[36,44],"considered":[37],"instead":[38],"bond":[41],"types.":[42],"benchmarked":[45],"on":[46],"ZINC":[48],"250K,":[49],"MOSES,":[50],"and":[51,92,153],"ChEMBL":[52],"data":[53,146],"sets":[54],"against":[55],"conventional":[56],"graph-based":[57],"ReFactor,":[59],"representing":[60],"our":[61,168],"implementation":[62],"reported":[65],"DEFactor":[66],"literature.":[70],"On":[71],"average,":[72],"models":[74,159],"contain":[75],"some":[76],"20%":[77],"less":[78],"fitting":[79],"parameters":[80],"than":[81,106],"those":[82],"ReFactor.":[84,107],"The":[85,149],"two":[86],"display":[88],"validity,":[90],"uniqueness,":[91],"reconstruction":[93,135],"rates.":[94],"Compared":[95],"training":[98,127],"set":[99],"compounds,":[100],"generates":[102,118],"more":[103],"structures":[105,124],"This":[108],"could":[109],"be":[110,141],"explained":[111],"by":[112],"fact":[114],"that":[115,133],"latter":[117],"many":[119],"open-chain":[120],"analogues":[121],"cyclic":[123],"set.":[128],"It":[129],"has":[130],"been":[131],"demonstrated":[132],"error":[136],"molecules":[139],"can":[140],"significantly":[142],"reduced":[143],"using":[144],"augmentation":[147],"technique.":[148],"codes":[150],"ReFactor":[154],"well":[156],"all":[158],"obtained":[160],"this":[162],"study":[163],"publicly":[165],"available":[166],"from":[167],"GitHub":[169],"repository:":[170],"https://github.com/Laboratoire-de-Chemoinformatique/HyFactor.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}
