{"id":"https://openalex.org/W4220776772","doi":"https://doi.org/10.1186/s13321-022-00594-8","title":"Improving the performance of models for one-step retrosynthesis through re-ranking","display_name":"Improving the performance of models for one-step retrosynthesis through re-ranking","publication_year":2022,"publication_date":"2022-03-15","ids":{"openalex":"https://openalex.org/W4220776772","doi":"https://doi.org/10.1186/s13321-022-00594-8","pmid":"https://pubmed.ncbi.nlm.nih.gov/35292121"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-022-00594-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-022-00594-8","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-022-00594-8","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-022-00594-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071246998","display_name":"Min Htoo Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Min Htoo Lin","raw_affiliation_strings":["Division of Chemistry and Biological Chemistry, School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore, 637371, Singapore"],"affiliations":[{"raw_affiliation_string":"Division of Chemistry and Biological Chemistry, School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore, 637371, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087516855","display_name":"Zhengkai Tu","orcid":"https://orcid.org/0000-0003-1715-5773"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengkai Tu","raw_affiliation_strings":["Computational Science and Engineering, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, MA, 02139, USA"],"affiliations":[{"raw_affiliation_string":"Computational Science and Engineering, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, MA, 02139, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076162644","display_name":"Connor W. Coley","orcid":"https://orcid.org/0000-0002-8271-8723"},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Connor W. Coley","raw_affiliation_strings":["Department of Chemical Engineering, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, MA, 02139, USA. ccoley@mit.edu","Department of Chemical Engineering, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, MA, 02139, USA"],"affiliations":[{"raw_affiliation_string":"Department of Chemical Engineering, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, MA, 02139, USA. ccoley@mit.edu","institution_ids":["https://openalex.org/I63966007","https://openalex.org/I4210110987"]},{"raw_affiliation_string":"Department of Chemical Engineering, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, MA, 02139, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076162644"],"corresponding_institution_ids":["https://openalex.org/I4210110987","https://openalex.org/I63966007"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":2.6374,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.90661246,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"14","issue":"1","first_page":"15","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9984999895095825,"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/T11407","display_name":"Innovative Microfluidic and Catalytic Techniques Innovation","score":0.9846000075340271,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/retrosynthetic-analysis","display_name":"Retrosynthetic analysis","score":0.8440964221954346},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7851112484931946},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7827942967414856},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6825301051139832},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.6234451532363892},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5641090273857117},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5621558427810669},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5527872443199158},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.5291386246681213},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.5199883580207825},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4808955192565918},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4519214630126953},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.155370831489563},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.11934986710548401},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11498692631721497}],"concepts":[{"id":"https://openalex.org/C42437451","wikidata":"https://www.wikidata.org/wiki/Q902227","display_name":"Retrosynthetic analysis","level":3,"score":0.8440964221954346},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7851112484931946},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7827942967414856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6825301051139832},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.6234451532363892},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5641090273857117},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5621558427810669},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5527872443199158},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.5291386246681213},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.5199883580207825},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4808955192565918},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4519214630126953},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.155370831489563},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.11934986710548401},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11498692631721497},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1186/s13321-022-00594-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-022-00594-8","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-022-00594-8","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:35292121","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35292121","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 cheminformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:8922884","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8922884","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"J Cheminform","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:80f52e3998dd4476b552b4e988f5918e","is_oa":true,"landing_page_url":"https://doaj.org/article/80f52e3998dd4476b552b4e988f5918e","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 14, Iss 1, Pp 1-13 (2022)","raw_type":"article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/163080","is_oa":true,"landing_page_url":"https://hdl.handle.net/10356/163080","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/141316","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/141316","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Springer International Publishing","raw_type":"http://purl.org/eprint/type/JournalArticle"}],"best_oa_location":{"id":"doi:10.1186/s13321-022-00594-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-022-00594-8","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-022-00594-8","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.7799999713897705,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G346432652","display_name":null,"funder_award_id":"CN Yang Scholars Programme","funder_id":"https://openalex.org/F4320320766","funder_display_name":"Nanyang Technological University"}],"funders":[{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4220776772.pdf","grobid_xml":"https://content.openalex.org/works/W4220776772.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1979641548","https://openalex.org/W1997974358","https://openalex.org/W2001496974","https://openalex.org/W2041548070","https://openalex.org/W2046747992","https://openalex.org/W2060586571","https://openalex.org/W2132022337","https://openalex.org/W2137297265","https://openalex.org/W2324964582","https://openalex.org/W2512660405","https://openalex.org/W2542898981","https://openalex.org/W2551217916","https://openalex.org/W2580919858","https://openalex.org/W2621742623","https://openalex.org/W2747592475","https://openalex.org/W2769756736","https://openalex.org/W2783658781","https://openalex.org/W2789615344","https://openalex.org/W2799620402","https://openalex.org/W2947423323","https://openalex.org/W2950955377","https://openalex.org/W2963149412","https://openalex.org/W3009202547","https://openalex.org/W3010145447","https://openalex.org/W3100545487","https://openalex.org/W3103092523","https://openalex.org/W3181403764","https://openalex.org/W4252485752","https://openalex.org/W6603707631","https://openalex.org/W6605656274"],"related_works":["https://openalex.org/W3127142483","https://openalex.org/W3160516639","https://openalex.org/W4385565564","https://openalex.org/W2898073868","https://openalex.org/W2138488530","https://openalex.org/W4390446658","https://openalex.org/W2971071571","https://openalex.org/W2798835721","https://openalex.org/W2922169395","https://openalex.org/W2387658907"],"abstract_inverted_index":{"Retrosynthesis":[0],"is":[1,176],"at":[2],"the":[3,9,62,102,106,110,126,157,172],"core":[4],"of":[5,12,20,46,159],"organic":[6],"chemistry.":[7],"Recently,":[8],"rapid":[10],"growth":[11],"artificial":[13],"intelligence":[14],"(AI)":[15],"has":[16],"spurred":[17],"a":[18,42,134,145],"variety":[19],"novel":[21],"machine":[22],"learning":[23,83,147],"approaches":[24],"for":[25,41,73,99],"data-driven":[26],"synthesis":[27],"planning.":[28],"These":[29],"methods":[30],"learn":[31],"complex":[32],"patterns":[33],"from":[34,137,149],"reaction":[35,68,104],"databases":[36],"in":[37,65],"order":[38],"to":[39,52,78,84,97,139,151,165],"predict,":[40],"given":[43],"product,":[44,101],"sets":[45],"reactants":[47],"that":[48,54,118,155],"can":[49,120,163],"be":[50],"used":[51],"synthesise":[53],"product.":[55],"However,":[56,171],"their":[57,86],"performance":[58,167],"as":[59,105,114,132],"measured":[60],"by":[61,82,179],"top-N":[63],"accuracy":[64,142,175],"matching":[66],"published":[67,103],"precedents":[69],"still":[70],"leaves":[71],"room":[72],"improvement.":[74],"This":[75],"work":[76],"aims":[77],"enhance":[79],"these":[80],"models":[81,123],"re-rank":[85],"reactant":[87,112],"predictions.":[88],"Specifically,":[89],"we":[90],"design":[91],"and":[92,109,143,153],"train":[93],"an":[94],"energy-based":[95],"model":[96],"re-rank,":[98],"each":[100],"top":[107],"suggestion":[108],"remaining":[111],"predictions":[113],"lower-ranked.":[115],"We":[116],"show":[117],"re-ranking":[119,156],"improve":[121],"one-step":[122],"significantly":[124],"using":[125],"standard":[127],"USPTO-50k":[128],"benchmark":[129],"dataset,":[130],"such":[131],"RetroSim,":[133],"similarity-based":[135],"method,":[136,148],"35.7":[138],"51.8%":[140],"top-1":[141,174],"NeuralSym,":[144],"deep":[146],"45.7":[150],"51.3%,":[152],"also":[154],"union":[158],"two":[160],"models'":[161],"suggestions":[162],"lead":[164],"better":[166],"than":[168],"either":[169],"alone.":[170],"state-of-the-art":[173],"not":[177],"improved":[178],"this":[180],"method.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}