{"id":"https://openalex.org/W4392847053","doi":"https://doi.org/10.1021/acs.jcim.4c00138","title":"RDCanon: A Python Package for Canonicalizing the Order of Tokens in SMARTS Queries","display_name":"RDCanon: A Python Package for Canonicalizing the Order of Tokens in SMARTS Queries","publication_year":2024,"publication_date":"2024-03-15","ids":{"openalex":"https://openalex.org/W4392847053","doi":"https://doi.org/10.1021/acs.jcim.4c00138","pmid":"https://pubmed.ncbi.nlm.nih.gov/38488634"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.4c00138","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c00138","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":true,"oa_status":"green","oa_url":"https://hdl.handle.net/1721.1/165437","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070720309","display_name":"Babak Mahjour","orcid":"https://orcid.org/0000-0002-8225-6514"},"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":"Babak A. Mahjour","raw_affiliation_strings":["Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States"],"affiliations":[{"raw_affiliation_string":"Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States","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/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, Cambridge, Massachusetts 02139, United States"],"affiliations":[{"raw_affiliation_string":"Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5076162644"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":2.1053,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.87559021,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"64","issue":"8","first_page":"2948","last_page":"2954"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9984999895095825,"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":0.9861999750137329,"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/computer-science","display_name":"Computer science","score":0.7778809070587158},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.7616121172904968},{"id":"https://openalex.org/keywords/cheminformatics","display_name":"Cheminformatics","score":0.663337230682373},{"id":"https://openalex.org/keywords/numbering","display_name":"Numbering","score":0.6627811193466187},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.5829084515571594},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.4907878339290619},{"id":"https://openalex.org/keywords/subsequence","display_name":"Subsequence","score":0.45372509956359863},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4422807991504669},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.440154105424881},{"id":"https://openalex.org/keywords/substructure","display_name":"Substructure","score":0.43974804878234863},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34213995933532715},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.33417704701423645},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1525721549987793},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.1484220325946808},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.08202609419822693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7778809070587158},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7616121172904968},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.663337230682373},{"id":"https://openalex.org/C191916993","wikidata":"https://www.wikidata.org/wiki/Q362019","display_name":"Numbering","level":2,"score":0.6627811193466187},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.5829084515571594},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.4907878339290619},{"id":"https://openalex.org/C137877099","wikidata":"https://www.wikidata.org/wiki/Q1332977","display_name":"Subsequence","level":3,"score":0.45372509956359863},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4422807991504669},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.440154105424881},{"id":"https://openalex.org/C99679407","wikidata":"https://www.wikidata.org/wiki/Q56761637","display_name":"Substructure","level":2,"score":0.43974804878234863},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34213995933532715},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.33417704701423645},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1525721549987793},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.1484220325946808},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.08202609419822693},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.0},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000080911","descriptor_name":"Cheminformatics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000080911","descriptor_name":"Cheminformatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000080911","descriptor_name":"Cheminformatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000080911","descriptor_name":"Cheminformatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000080911","descriptor_name":"Cheminformatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062126","descriptor_name":"Databases, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062126","descriptor_name":"Databases, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062126","descriptor_name":"Databases, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062126","descriptor_name":"Databases, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062126","descriptor_name":"Databases, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1021/acs.jcim.4c00138","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c00138","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:38488634","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38488634","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:dspace.mit.edu:1721.1/165437","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/165437","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":"author","raw_type":"http://purl.org/eprint/type/JournalArticle"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/165437","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/165437","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":"author","raw_type":"http://purl.org/eprint/type/JournalArticle"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309369","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44"},{"id":"https://openalex.org/F4320322436","display_name":"Novo Nordisk","ror":"https://ror.org/0435rc536"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1975147762","https://openalex.org/W1991812639","https://openalex.org/W2038702914","https://openalex.org/W2048695741","https://openalex.org/W2090523415","https://openalex.org/W2104722869","https://openalex.org/W2170973067","https://openalex.org/W2200017991","https://openalex.org/W2219397146","https://openalex.org/W2313931242","https://openalex.org/W2324964582","https://openalex.org/W2405035126","https://openalex.org/W2607438408","https://openalex.org/W2747592475","https://openalex.org/W2767891136","https://openalex.org/W2774836366","https://openalex.org/W2799620402","https://openalex.org/W2944975820","https://openalex.org/W2950955377","https://openalex.org/W3091789543","https://openalex.org/W3105920383","https://openalex.org/W3118695441","https://openalex.org/W3138801267","https://openalex.org/W3161136656","https://openalex.org/W3210489033","https://openalex.org/W4200030022","https://openalex.org/W4223920159","https://openalex.org/W4307468223","https://openalex.org/W4316507591","https://openalex.org/W4377941039"],"related_works":["https://openalex.org/W2380905223","https://openalex.org/W1573015311","https://openalex.org/W2316187651","https://openalex.org/W2889938001","https://openalex.org/W4386509167","https://openalex.org/W3165034028","https://openalex.org/W1570419641","https://openalex.org/W4293771607","https://openalex.org/W2296499206","https://openalex.org/W3153444835"],"abstract_inverted_index":{"SMARTS":[0,29,67,125,141],"is":[1,50,70,142],"a":[2,93,135],"widely":[3],"used":[4,64],"language":[5],"in":[6,123,137,159],"cheminformatics":[7],"for":[8,12,17,82,144],"defining":[9],"substructural":[10],"queries":[11,79],"database":[13],"lookups,":[14],"reaction":[15,124],"templates":[16],"chemical":[18],"transformations,":[19],"and":[20,90,116,118,162],"other":[21],"applications.":[22],"As":[23,127],"an":[24,57],"extension":[25],"to":[26,65,72,91,109,155],"SMILES,":[27],"many":[28],"patterns":[30],"can":[31,62,106],"represent":[32],"the":[33,43,75,86,104,111,139],"same":[34,87],"query.":[35],"Despite":[36],"this,":[37],"no":[38],"canonicalization":[39,131],"algorithm":[40,105],"invariant":[41],"of":[42,77,96,113,129],"line":[44],"notation":[45],"sequence":[46,76,95],"or":[47],"atomic":[48,78],"numbering":[49],"publicly":[51],"available.":[52],"Here,":[53],"we":[54],"introduce":[55],"RDCanon,":[56],"open-source":[58],"Python":[59],"package":[60],"that":[61,74],"be":[63,107],"standardize":[66],"queries.":[68],"RDCanon":[69,133],"designed":[71],"ensure":[73,92],"remains":[80],"consistent":[81],"all":[83],"graphs":[84],"representing":[85],"substructure":[88,160],"query":[89],"canonical":[94],"primitives":[97],"within":[98],"each":[99],"individual":[100],"atom":[101,120],"query;":[102],"furthermore,":[103],"applied":[108],"canonicalize":[110],"order":[112],"reactants,":[114],"agents,":[115],"products":[117],"their":[119],"map":[121],"numbers":[122],"templates.":[126],"part":[128],"its":[130],"algorithm,":[132],"provides":[134],"mechanism":[136],"which":[138],"canonicalized":[140],"optimized":[143],"speed":[145],"against":[146],"specific":[147],"molecular":[148],"databases.":[149],"Several":[150],"case":[151],"studies":[152],"are":[153],"provided":[154],"showcase":[156],"improved":[157],"efficiency":[158],"matching":[161],"retrosynthetic":[163],"analysis.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
