{"id":"https://openalex.org/W4360810381","doi":"https://doi.org/10.1021/acs.jcim.2c01486","title":"AiZynthTrain: Robust, Reproducible, and Extensible Pipelines for Training Synthesis Prediction Models","display_name":"AiZynthTrain: Robust, Reproducible, and Extensible Pipelines for Training Synthesis Prediction Models","publication_year":2023,"publication_date":"2023-03-24","ids":{"openalex":"https://openalex.org/W4360810381","doi":"https://doi.org/10.1021/acs.jcim.2c01486","pmid":"https://pubmed.ncbi.nlm.nih.gov/36959737"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.2c01486","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.2c01486","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":"article","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/A5006219866","display_name":"Samuel Genheden","orcid":"https://orcid.org/0000-0002-7624-7363"},"institutions":[{"id":"https://openalex.org/I4210143795","display_name":"AstraZeneca (Sweden)","ror":"https://ror.org/04wwrrg31","country_code":"SE","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210143795"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Samuel Genheden","raw_affiliation_strings":["Molecular AI, Discovery Sciences, R&D, AstraZeneca Gothenburg, SE-431 83 M\u00f6lndal, Sweden"],"affiliations":[{"raw_affiliation_string":"Molecular AI, Discovery Sciences, R&D, AstraZeneca Gothenburg, SE-431 83 M\u00f6lndal, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007498431","display_name":"Per\u2010Ola Norrby","orcid":"https://orcid.org/0000-0002-2419-0705"},"institutions":[{"id":"https://openalex.org/I4210143795","display_name":"AstraZeneca (Sweden)","ror":"https://ror.org/04wwrrg31","country_code":"SE","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210143795"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Per-Ola Norrby","raw_affiliation_strings":["Data Science and Modelling, Pharmaceutical Sciences, R&D, AstraZeneca Gothenburg, SE-431 83 M\u00f6lndal, Sweden"],"affiliations":[{"raw_affiliation_string":"Data Science and Modelling, Pharmaceutical Sciences, R&D, AstraZeneca Gothenburg, SE-431 83 M\u00f6lndal, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076975589","display_name":"Ola Engkvist","orcid":"https://orcid.org/0000-0003-4970-6461"},"institutions":[{"id":"https://openalex.org/I4210143795","display_name":"AstraZeneca (Sweden)","ror":"https://ror.org/04wwrrg31","country_code":"SE","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210143795"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Ola Engkvist","raw_affiliation_strings":["Molecular AI, Discovery Sciences, R&D, AstraZeneca Gothenburg, SE-431 83 M\u00f6lndal, Sweden"],"affiliations":[{"raw_affiliation_string":"Molecular AI, Discovery Sciences, R&D, AstraZeneca Gothenburg, SE-431 83 M\u00f6lndal, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006219866"],"corresponding_institution_ids":["https://openalex.org/I4210143795"],"apc_list":null,"apc_paid":null,"fwci":2.8436,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.91657366,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"63","issue":"7","first_page":"1841","last_page":"1846"},"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":0.9973000288009644,"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/T10260","display_name":"Software Engineering Research","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.7741045951843262},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.760602593421936},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7395074963569641},{"id":"https://openalex.org/keywords/retrosynthetic-analysis","display_name":"Retrosynthetic analysis","score":0.6457432508468628},{"id":"https://openalex.org/keywords/extensibility","display_name":"Extensibility","score":0.6298733353614807},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6203300952911377},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6069241762161255},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5998669862747192},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.546235203742981},{"id":"https://openalex.org/keywords/code-refactoring","display_name":"Code refactoring","score":0.5446580648422241},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4531042277812958},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4488997459411621},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42564043402671814},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4069075584411621},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39491379261016846},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.24035194516181946},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16747355461120605},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11620709300041199}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7741045951843262},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.760602593421936},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7395074963569641},{"id":"https://openalex.org/C42437451","wikidata":"https://www.wikidata.org/wiki/Q902227","display_name":"Retrosynthetic analysis","level":3,"score":0.6457432508468628},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.6298733353614807},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6203300952911377},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6069241762161255},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5998669862747192},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.546235203742981},{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.5446580648422241},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4531042277812958},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4488997459411621},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42564043402671814},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4069075584411621},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39491379261016846},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.24035194516181946},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16747355461120605},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11620709300041199},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.2c01486","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.2c01486","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:36959737","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36959737","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":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1757990252","https://openalex.org/W2096541451","https://openalex.org/W2126316555","https://openalex.org/W2950955377","https://openalex.org/W2968071222","https://openalex.org/W2987091515","https://openalex.org/W3010145447","https://openalex.org/W3023658436","https://openalex.org/W3040975947","https://openalex.org/W3094686696","https://openalex.org/W3101155908","https://openalex.org/W3146384714","https://openalex.org/W3209726219","https://openalex.org/W4220747243","https://openalex.org/W4220918529","https://openalex.org/W4229044212","https://openalex.org/W4285027310","https://openalex.org/W4285193863","https://openalex.org/W4292362226","https://openalex.org/W4292395781","https://openalex.org/W4301064111"],"related_works":["https://openalex.org/W4313549863","https://openalex.org/W4231266416","https://openalex.org/W2395465245","https://openalex.org/W2072205733","https://openalex.org/W3176957927","https://openalex.org/W4296534969","https://openalex.org/W3194667890","https://openalex.org/W4312761314","https://openalex.org/W4384009715","https://openalex.org/W2965165771"],"abstract_inverted_index":{"We":[0,40,128],"introduce":[1],"the":[2,45,52,62,75,96,100,103,113,116,141],"AiZynthTrain":[3],"Python":[4],"package":[5],"for":[6,106],"training":[7,119],"synthesis":[8,138],"models":[9,43,65,139],"in":[10,37,67,95,140],"a":[11,23,29,68,121],"robust,":[12],"reproducible,":[13],"and":[14,28,55,59,80],"extensible":[15],"way.":[16],"It":[17],"contains":[18],"two":[19],"pipelines":[20],"that":[21,32,90,130],"create":[22],"template-based":[24],"one-step":[25],"retrosynthesis":[26,38,64],"model":[27,31,105],"RingBreaker":[30,104],"can":[33],"be":[34,134],"straightforwardly":[35],"integrated":[36],"software.":[39],"train":[41],"such":[42],"on":[44,120],"publicly":[46],"available":[47],"reaction":[48,77],"data":[49,78,126],"set":[50],"from":[51],"U.S.":[53],"Patent":[54],"Trademark":[56],"Office":[57],"(USPTO),":[58],"these":[60],"are":[61],"first":[63],"created":[66],"completely":[69],"reproducible":[70],"end-to-end":[71],"fashion,":[72],"starting":[73],"with":[74,82,136],"original":[76],"source":[79],"ending":[81],"trained":[83],"machine-learning":[84],"models.":[85],"In":[86],"particular,":[87],"we":[88,111],"show":[89],"employing":[91],"new":[92],"heuristics":[93],"implemented":[94],"pipeline":[97,117],"greatly":[98],"improves":[99],"ability":[101],"of":[102,115],"disconnecting":[107],"ring":[108],"systems.":[109],"Furthermore,":[110],"demonstrate":[112],"robustness":[114],"by":[118],"more":[122],"diverse":[123],"but":[124],"proprietary":[125],"set.":[127],"envisage":[129],"this":[131],"framework":[132],"will":[133],"extended":[135],"other":[137],"future.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}