{"id":"https://openalex.org/W4224218893","doi":"https://doi.org/10.1021/acs.jcim.1c01476","title":"RetroGNN: Fast Estimation of Synthesizability for Virtual Screening and De Novo Design by Learning from Slow Retrosynthesis Software","display_name":"RetroGNN: Fast Estimation of Synthesizability for Virtual Screening and De Novo Design by Learning from Slow Retrosynthesis Software","publication_year":2022,"publication_date":"2022-04-22","ids":{"openalex":"https://openalex.org/W4224218893","doi":"https://doi.org/10.1021/acs.jcim.1c01476","pmid":"https://pubmed.ncbi.nlm.nih.gov/35452226"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.1c01476","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.1c01476","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/A5047329586","display_name":"Chenghao Liu","orcid":"https://orcid.org/0000-0001-7923-6806"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]},{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Cheng-Hao Liu","raw_affiliation_strings":["Department of Chemistry, McGill University, 801 Sherbooke Street W, Montreal, Canada H3A 0B8","Mila and Universit\u00e9 de Montr\u00e9al, 6666 St-Urbain Street, Montreal, Canada H2S 3H1"],"affiliations":[{"raw_affiliation_string":"Department of Chemistry, McGill University, 801 Sherbooke Street W, Montreal, Canada H3A 0B8","institution_ids":["https://openalex.org/I5023651"]},{"raw_affiliation_string":"Mila and Universit\u00e9 de Montr\u00e9al, 6666 St-Urbain Street, Montreal, Canada H2S 3H1","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025796234","display_name":"Maksym Korablyov","orcid":null},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Maksym Korablyov","raw_affiliation_strings":["Mila and Universit\u00e9 de Montr\u00e9al, 6666 St-Urbain Street, Montreal, Canada H2S 3H1"],"affiliations":[{"raw_affiliation_string":"Mila and Universit\u00e9 de Montr\u00e9al, 6666 St-Urbain Street, Montreal, Canada H2S 3H1","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024552077","display_name":"Stanis\u0142aw Jastrz\u0229bski","orcid":"https://orcid.org/0000-0003-4138-1818"},"institutions":[{"id":"https://openalex.org/I126596746","display_name":"Jagiellonian University","ror":"https://ror.org/03bqmcz70","country_code":"PL","type":"education","lineage":["https://openalex.org/I126596746"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Stanis\u0142aw Jastrz\u0119bski","raw_affiliation_strings":["Faculty of Mathematics and Computer Science, Jagiellonian University, 6 \u0141ojasiewicza Street, 30-348 Krak\u00f3w, Poland","Molecule.one, Warsaw 00-815, Poland"],"affiliations":[{"raw_affiliation_string":"Faculty of Mathematics and Computer Science, Jagiellonian University, 6 \u0141ojasiewicza Street, 30-348 Krak\u00f3w, Poland","institution_ids":["https://openalex.org/I126596746"]},{"raw_affiliation_string":"Molecule.one, Warsaw 00-815, Poland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032381726","display_name":"Pawe\u0142 W\u0142odarczyk-Pruszy\u0144ski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pawe\u0142 W\u0142odarczyk-Pruszy\u0144ski","raw_affiliation_strings":["Molecule.one, Warsaw 00-815, Poland"],"affiliations":[{"raw_affiliation_string":"Molecule.one, Warsaw 00-815, Poland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086198262","display_name":"Yoshua Bengio","orcid":"https://orcid.org/0000-0002-9322-3515"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yoshua Bengio","raw_affiliation_strings":["Mila and Universit\u00e9 de Montr\u00e9al, 6666 St-Urbain Street, Montreal, Canada H2S 3H1"],"affiliations":[{"raw_affiliation_string":"Mila and Universit\u00e9 de Montr\u00e9al, 6666 St-Urbain Street, Montreal, Canada H2S 3H1","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007543032","display_name":"Marwin Segler","orcid":"https://orcid.org/0000-0001-8008-0546"},"institutions":[{"id":"https://openalex.org/I22465464","display_name":"University of M\u00fcnster","ror":"https://ror.org/00pd74e08","country_code":"DE","type":"education","lineage":["https://openalex.org/I22465464"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["DE","GB"],"is_corresponding":true,"raw_author_name":"Marwin Segler","raw_affiliation_strings":["Institute of Organic Chemistry and Center for Multiscale Theory and Computation, Westf\u00e4lische Wilhelms-Universit\u00e4t M\u00fcnster, 48149 M\u00fcnster, Germany","Microsoft Research, 21 Station Road, Cambridge, U.K. CB1 2FB"],"affiliations":[{"raw_affiliation_string":"Institute of Organic Chemistry and Center for Multiscale Theory and Computation, Westf\u00e4lische Wilhelms-Universit\u00e4t M\u00fcnster, 48149 M\u00fcnster, Germany","institution_ids":["https://openalex.org/I22465464"]},{"raw_affiliation_string":"Microsoft Research, 21 Station Road, Cambridge, U.K. CB1 2FB","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5007543032","https://openalex.org/A5047329586"],"corresponding_institution_ids":["https://openalex.org/I22465464","https://openalex.org/I4210164937","https://openalex.org/I5023651","https://openalex.org/I70931966"],"apc_list":null,"apc_paid":null,"fwci":6.1599,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.96966818,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"62","issue":"10","first_page":"2293","last_page":"2300"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T13180","display_name":"Chemistry and Chemical Engineering","score":0.9671000242233276,"subfield":{"id":"https://openalex.org/subfields/2304","display_name":"Environmental Chemistry"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/retrosynthetic-analysis","display_name":"Retrosynthetic analysis","score":0.8350109457969666},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7246958017349243},{"id":"https://openalex.org/keywords/virtual-screening","display_name":"Virtual screening","score":0.5913407206535339},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5388192534446716},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5316873788833618},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47659605741500854},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4592052102088928},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.360567569732666},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33777713775634766},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32002824544906616},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.2392992079257965},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16623887419700623},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.11698290705680847},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.11595290899276733},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.09463587403297424}],"concepts":[{"id":"https://openalex.org/C42437451","wikidata":"https://www.wikidata.org/wiki/Q902227","display_name":"Retrosynthetic analysis","level":3,"score":0.8350109457969666},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7246958017349243},{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.5913407206535339},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5388192534446716},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5316873788833618},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47659605741500854},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4592052102088928},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.360567569732666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33777713775634766},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32002824544906616},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.2392992079257965},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16623887419700623},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.11698290705680847},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.11595290899276733},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.09463587403297424},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C35753019","wikidata":"https://www.wikidata.org/wiki/Q644785","display_name":"Total synthesis","level":2,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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},{"descriptor_ui":"D015195","descriptor_name":"Drug Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015195","descriptor_name":"Drug Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015195","descriptor_name":"Drug Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.1c01476","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.1c01476","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:35452226","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35452226","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}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320319880","display_name":"Government of Canada","ror":"https://ror.org/010q4q527"},{"id":"https://openalex.org/F4320330273","display_name":"Institut de Valorisation des Donn\u00e9es","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W625776585","https://openalex.org/W1757990252","https://openalex.org/W1971069133","https://openalex.org/W2034549041","https://openalex.org/W2041686943","https://openalex.org/W2117996566","https://openalex.org/W2146984355","https://openalex.org/W2160592148","https://openalex.org/W2287058098","https://openalex.org/W2578240541","https://openalex.org/W2747592475","https://openalex.org/W2783658781","https://openalex.org/W2789615344","https://openalex.org/W2883583109","https://openalex.org/W2900694120","https://openalex.org/W2949986955","https://openalex.org/W2955727640","https://openalex.org/W2956961449","https://openalex.org/W2966357564","https://openalex.org/W2968071222","https://openalex.org/W3007309629","https://openalex.org/W3010145447","https://openalex.org/W3014154196","https://openalex.org/W3030402150","https://openalex.org/W3043486744","https://openalex.org/W3043969542","https://openalex.org/W3090915092","https://openalex.org/W3101155908","https://openalex.org/W3104830773","https://openalex.org/W3123775255","https://openalex.org/W4205455490","https://openalex.org/W4310895557"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W1443743067","https://openalex.org/W4385784498","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W4385842036"],"abstract_inverted_index":{"De":[0],"novo":[1,167],"molecule":[2,134],"design":[3,135,168],"algorithms":[4,25],"often":[5],"result":[6,45],"in":[7,46,99,118],"chemically":[8],"unfeasible":[9],"or":[10],"synthetically":[11],"inaccessible":[12],"molecules.":[13,75],"A":[14],"natural":[15],"idea":[16],"to":[17,22,57,81,87,147,173,177,192,204],"mitigate":[18],"this":[19],"problem":[20],"is":[21,78],"bias":[23],"these":[24],"toward":[26],"more":[27,175],"easily":[28],"synthesizable":[29,141],"molecules":[30,142,155,171,206],"using":[31,39,65,160,214],"a":[32,53,70,83,108,163,209],"proxy":[33],"score":[34],"for":[35,63,69,137],"synthetic":[36],"accessibility.":[37],"However,":[38],"currently":[40],"available":[41],"proxies":[42],"can":[43,104,115,199],"still":[44],"highly":[47],"unrealistic":[48],"compounds.":[49],"Here,":[50],"we":[51,61,139],"propose":[52],"novel":[54],"approach,":[55],"RetroGNN,":[56],"estimate":[58],"synthesizability.":[59],"First,":[60],"search":[62],"routes":[64],"synthesis":[66,93],"planning":[67,216],"software":[68],"large":[71],"number":[72],"of":[73,91,151],"random":[74],"This":[76],"information":[77],"then":[79],"used":[80,106,117],"train":[82],"graph":[84],"neural":[85,197],"network":[86,198],"predict":[88],"the":[89,92,96,101,148,157,179],"outcome":[90],"planner":[94],"given":[95],"target":[97],"molecule,":[98],"which":[100,138],"regression":[102],"task":[103],"be":[105,116,174],"as":[107],"synthesizability":[109],"scorer.":[110],"We":[111,127],"highlight":[112],"how":[113],"RetroGNN":[114],"generative":[119],"molecule-discovery":[120],"pipelines":[121],"together":[122],"with":[123,143,162],"other":[124],"scoring":[125],"functions.":[126],"evaluate":[128],"our":[129,195],"approach":[130],"on":[131],"several":[132],"QSAR-based":[133],"benchmarks,":[136],"find":[140],"state-of-the-art":[144],"scores.":[145],"Compared":[146],"virtual":[149],"screening":[150],"5":[152],"million":[153],"existing":[154],"from":[156],"ZINC":[158],"database,":[159],"RetroGNNScore":[161],"simple":[164],"fragment-based":[165],"de":[166],"algorithm":[169],"finds":[170],"predicted":[172],"likely":[176],"possess":[178],"desired":[180],"activity":[181],"exponentially":[182],"faster,":[183],"while":[184,207],"maintaining":[185],"good":[186],"druglike":[187],"properties":[188],"and":[189],"being":[190],"easier":[191],"synthesize.":[193],"Importantly,":[194],"deep":[196],"successfully":[200],"filter":[201],"out":[202],"hard":[203],"synthesize":[205],"achieving":[208],"10<sup>5</sup>":[210],"times":[211],"speedup":[212],"over":[213],"retrosynthesis":[215],"software.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-31T07:56:22.981413","created_date":"2025-10-10T00:00:00"}