{"id":"https://openalex.org/W3189809547","doi":"https://doi.org/10.1021/acs.jcim.1c00232","title":"Clustering of Synthetic Routes Using Tree Edit Distance","display_name":"Clustering of Synthetic Routes Using Tree Edit Distance","publication_year":2021,"publication_date":"2021-08-03","ids":{"openalex":"https://openalex.org/W3189809547","doi":"https://doi.org/10.1021/acs.jcim.1c00232","mag":"3189809547","pmid":"https://pubmed.ncbi.nlm.nih.gov/34342428"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.1c00232","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.1c00232","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"],"raw_orcid":"https://orcid.org/0000-0002-7624-7363","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/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"],"raw_orcid":"https://orcid.org/0000-0003-4970-6461","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":"last","author":{"id":"https://openalex.org/A5046421751","display_name":"Esben Jannik Bjerrum","orcid":"https://orcid.org/0000-0003-1614-7376"},"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":"Esben Bjerrum","raw_affiliation_strings":["Molecular AI, Discovery Sciences, R&D, AstraZeneca Gothenburg, SE-431 83 M\u00f6lndal, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-1614-7376","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":2.7396,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.91472543,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"61","issue":"8","first_page":"3899","last_page":"3907"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9940999746322632,"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":0.9940999746322632,"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":0.9936000108718872,"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/T10908","display_name":"Analytical Chemistry and Chromatography","score":0.9908999800682068,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8183265924453735},{"id":"https://openalex.org/keywords/retrosynthetic-analysis","display_name":"Retrosynthetic analysis","score":0.7881511449813843},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.722898006439209},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6367945671081543},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.6145604848861694},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6056045293807983},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5327667593955994},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5265189409255981},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.449618935585022},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34212106466293335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31584808230400085},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18618851900100708},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.08337807655334473},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08242779970169067}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8183265924453735},{"id":"https://openalex.org/C42437451","wikidata":"https://www.wikidata.org/wiki/Q902227","display_name":"Retrosynthetic analysis","level":3,"score":0.7881511449813843},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722898006439209},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6367945671081543},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.6145604848861694},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6056045293807983},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5327667593955994},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5265189409255981},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.449618935585022},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34212106466293335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31584808230400085},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18618851900100708},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.08337807655334473},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08242779970169067},{"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/C35753019","wikidata":"https://www.wikidata.org/wiki/Q644785","display_name":"Total synthesis","level":2,"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":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.1c00232","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.1c00232","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:34342428","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34342428","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W127245647","https://openalex.org/W1969487950","https://openalex.org/W1978478796","https://openalex.org/W1987971958","https://openalex.org/W1988037271","https://openalex.org/W2028509346","https://openalex.org/W2054274648","https://openalex.org/W2077721627","https://openalex.org/W2096729078","https://openalex.org/W2101234009","https://openalex.org/W2380601648","https://openalex.org/W2493109812","https://openalex.org/W2558999090","https://openalex.org/W2606363443","https://openalex.org/W2747592475","https://openalex.org/W2789615344","https://openalex.org/W2908778936","https://openalex.org/W2915930794","https://openalex.org/W2947423323","https://openalex.org/W2968071222","https://openalex.org/W2980338962","https://openalex.org/W2987091515","https://openalex.org/W3009202547","https://openalex.org/W3082712976","https://openalex.org/W3091789543","https://openalex.org/W3101155908","https://openalex.org/W3103092523","https://openalex.org/W3109834551","https://openalex.org/W3113271780","https://openalex.org/W3113340804","https://openalex.org/W3121024033","https://openalex.org/W4254210693","https://openalex.org/W4254862760"],"related_works":["https://openalex.org/W1443743067","https://openalex.org/W4385784498","https://openalex.org/W4385842036","https://openalex.org/W4288371066","https://openalex.org/W4285670373","https://openalex.org/W2910734083","https://openalex.org/W3101473090","https://openalex.org/W4390658374","https://openalex.org/W4385784463","https://openalex.org/W4285584547"],"abstract_inverted_index":{"We":[0,32],"present":[1],"a":[2,28,41,91,111,133],"novel":[3],"algorithm":[4,97,119],"to":[5,22,69,80,114],"compute":[6],"the":[7,35,59,82,96,108,123],"distance":[8],"between":[9],"synthetic":[10],"routes":[11,25,39,73,109],"based":[12],"on":[13,51],"tree":[14],"edit":[15],"distances.":[16],"Such":[17],"distances":[18],"can":[19,77,102],"be":[20,78,103],"used":[21,79],"cluster":[23,76,112],"synthesis":[24],"generated":[26],"using":[27],"retrosynthesis":[29,42],"prediction":[30],"tool.":[31],"show":[33,70,89],"that":[34,71,95,101,107],"clustering":[36],"of":[37,58,84,93,126],"selected":[38],"from":[40,74],"analysis":[43],"is":[44,120],"performed":[45],"in":[46,110,122],"less":[47],"than":[48],"10":[49],"s":[50],"average":[52],"and":[53,106,131],"only":[54],"constitutes":[55],"seven":[56],"percent":[57],"total":[60],"time":[61],"(prediction":[62],"+":[63],"clustering).":[64],"Furthermore,":[65],"we":[66,88],"are":[67],"able":[68],"representative":[72],"each":[75],"reduce":[81],"set":[83],"predicted":[85],"routes.":[86],"Finally,":[87],"with":[90],"number":[92],"examples":[94],"gives":[98],"intuitive":[99],"clusters":[100],"easily":[104],"rationalized":[105],"tend":[113],"use":[115],"similar":[116],"chemistry.":[117],"The":[118],"included":[121],"latest":[124],"version":[125],"open-source":[127],"AiZynthFinder":[128],"software":[129],"(https://github.com/MolecularAI/aizynthfinder)":[130],"as":[132],"separate":[134],"package":[135],"(https://github.com/MolecularAI/route-distances).":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3}],"updated_date":"2026-05-15T08:27:34.491423","created_date":"2025-10-10T00:00:00"}