{"id":"https://openalex.org/W4417129054","doi":"https://doi.org/10.1186/s13321-025-01136-8","title":"SMARTS-RX: a SMARTS-based representation of chemical functions for reactivity analysis","display_name":"SMARTS-RX: a SMARTS-based representation of chemical functions for reactivity analysis","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W4417129054","doi":"https://doi.org/10.1186/s13321-025-01136-8","pmid":"https://pubmed.ncbi.nlm.nih.gov/41361326"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-025-01136-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01136-8","pdf_url":null,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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://doi.org/10.1186/s13321-025-01136-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031504624","display_name":"Thierry Kogej","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Thierry Kogej","raw_affiliation_strings":["Molecular AI, Discovery Sciences, R&D AstraZeneca, 431 83, Gothenburg, Sweden. thierry.kogej@astrazeneca.com"],"affiliations":[{"raw_affiliation_string":"Molecular AI, Discovery Sciences, R&D AstraZeneca, 431 83, Gothenburg, Sweden. thierry.kogej@astrazeneca.com","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084040777","display_name":"Christos Kannas","orcid":"https://orcid.org/0000-0001-7312-8193"},"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"]},{"id":"https://openalex.org/I4210137263","display_name":"AstraZeneca (Finland)","ror":"https://ror.org/035n56j11","country_code":"FI","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210137263"]},{"id":"https://openalex.org/I4210128490","display_name":"AstraZeneca (Japan)","ror":"https://ror.org/047k23798","country_code":"JP","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210128490"]}],"countries":["FI","JP","SE"],"is_corresponding":false,"raw_author_name":"Christos Kannas","raw_affiliation_strings":["Molecular AI, Discovery Sciences, R&D AstraZeneca, 431 83, Gothenburg, Sweden"],"affiliations":[{"raw_affiliation_string":"Molecular AI, Discovery Sciences, R&D AstraZeneca, 431 83, Gothenburg, Sweden","institution_ids":["https://openalex.org/I4210137263","https://openalex.org/I4210128490","https://openalex.org/I4210143795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006219866","display_name":"Samuel Genheden","orcid":"https://orcid.org/0000-0002-7624-7363"},"institutions":[{"id":"https://openalex.org/I4210128490","display_name":"AstraZeneca (Japan)","ror":"https://ror.org/047k23798","country_code":"JP","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210128490"]},{"id":"https://openalex.org/I4210137263","display_name":"AstraZeneca (Finland)","ror":"https://ror.org/035n56j11","country_code":"FI","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210137263"]},{"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":["FI","JP","SE"],"is_corresponding":false,"raw_author_name":"Samuel Genheden","raw_affiliation_strings":["Molecular AI, Discovery Sciences, R&D AstraZeneca, 431 83, Gothenburg, Sweden"],"affiliations":[{"raw_affiliation_string":"Molecular AI, Discovery Sciences, R&D AstraZeneca, 431 83, Gothenburg, Sweden","institution_ids":["https://openalex.org/I4210137263","https://openalex.org/I4210128490","https://openalex.org/I4210143795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026718416","display_name":"Eike Caldeweyher","orcid":"https://orcid.org/0000-0002-3985-595X"},"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":"Eike Caldeweyher","raw_affiliation_strings":["Augmented DMTA Engineering, R&D IT, AstraZeneca, 43183, Gothenburg, Sweden"],"affiliations":[{"raw_affiliation_string":"Augmented DMTA Engineering, R&D IT, AstraZeneca, 43183, Gothenburg, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077283575","display_name":"Mikhail Kabeshov","orcid":"https://orcid.org/0009-0009-2290-6130"},"institutions":[{"id":"https://openalex.org/I4210137263","display_name":"AstraZeneca (Finland)","ror":"https://ror.org/035n56j11","country_code":"FI","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210137263"]},{"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"]},{"id":"https://openalex.org/I4210128490","display_name":"AstraZeneca (Japan)","ror":"https://ror.org/047k23798","country_code":"JP","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210128490"]}],"countries":["FI","JP","SE"],"is_corresponding":false,"raw_author_name":"Mikhail Kabeshov","raw_affiliation_strings":["Molecular AI, Discovery Sciences, R&D AstraZeneca, 431 83, Gothenburg, Sweden"],"affiliations":[{"raw_affiliation_string":"Molecular AI, Discovery Sciences, R&D AstraZeneca, 431 83, Gothenburg, Sweden","institution_ids":["https://openalex.org/I4210137263","https://openalex.org/I4210128490","https://openalex.org/I4210143795"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5031504624"],"corresponding_institution_ids":[],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":1.348,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87525479,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"17","issue":"1","first_page":"177","last_page":"177"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.6376000046730042,"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":0.6376000046730042,"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":0.3012999892234802,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.005200000014156103,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cheminformatics","display_name":"Cheminformatics","score":0.8273000121116638},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6442999839782715},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6000000238418579},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.5489000082015991},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.5249999761581421},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.4652999937534332},{"id":"https://openalex.org/keywords/toolbox","display_name":"Toolbox","score":0.45489999651908875},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.44279998540878296},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4223000109195709}],"concepts":[{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.8273000121116638},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.779699981212616},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6442999839782715},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6000000238418579},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.5489000082015991},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.5249999761581421},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.4652999937534332},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.45489999651908875},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4494999945163727},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.44279998540878296},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4223000109195709},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42170000076293945},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.38580000400543213},{"id":"https://openalex.org/C203394866","wikidata":"https://www.wikidata.org/wiki/Q2881060","display_name":"Chemical database","level":2,"score":0.382999986410141},{"id":"https://openalex.org/C147497476","wikidata":"https://www.wikidata.org/wiki/Q54872","display_name":"RDF","level":3,"score":0.37529999017715454},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3474999964237213},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.31029999256134033},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30790001153945923},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C2777332933","wikidata":"https://www.wikidata.org/wiki/Q170409","display_name":"Functional group","level":3,"score":0.3027999997138977},{"id":"https://openalex.org/C26320393","wikidata":"https://www.wikidata.org/wiki/Q597053","display_name":"Functional dependency","level":3,"score":0.30250000953674316},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C155261790","wikidata":"https://www.wikidata.org/wiki/Q1122544","display_name":"DrugBank","level":3,"score":0.29170000553131104},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2655999958515167},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C2776910235","wikidata":"https://www.wikidata.org/wiki/Q18574","display_name":"Reactivity (psychology)","level":3,"score":0.25760000944137573}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-025-01136-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01136-8","pdf_url":null,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:41361326","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41361326","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:doaj.org/article:7e71d03cd2df4cd0817463c81258c192","is_oa":true,"landing_page_url":"https://doaj.org/article/7e71d03cd2df4cd0817463c81258c192","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 17, Iss 1, Pp 1-13 (2025)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12690859","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12690859/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13321-025-01136-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01136-8","pdf_url":null,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2105058945","https://openalex.org/W2121096341","https://openalex.org/W2122010784","https://openalex.org/W2219397146","https://openalex.org/W2247581895","https://openalex.org/W2622206241","https://openalex.org/W2907192831","https://openalex.org/W4306943619"],"related_works":[],"abstract_inverted_index":{"Chemical":[0],"functional":[1,27,52,94,187],"group":[2,28,95,188],"annotation":[3,189],"provides":[4],"a":[5,42,137,147],"mechanistically":[6],"meaningful":[7],"framework":[8],"to":[9,30,55,121,170],"interpret":[10],"model":[11],"outcomes":[12],"and":[13,34,46,58,71,109,158,174,181,194,199],"guide":[14,122],"synthetic":[15],"strategies.":[16],"Here,":[17],"we":[18,112],"present":[19],"SMARTS-RX-a":[20],"curated,":[21,148],"hierarchical":[22,149],"ontology":[23,150],"of":[24,65,78,83,93,140,151],"406":[25,152],"SMARTS-based":[26,153],"descriptors-designed":[29],"characterize":[31],"chemically":[32],"relevant":[33],"reactive":[35],"functionalities":[36],"in":[37],"small":[38],"molecules.":[39],"SMARTS-RX":[40,84,145,165],"achieves":[41],"balance":[43],"between":[44],"granularity":[45],"computational":[47,182,195],"efficiency":[48],"by":[49,190],"focusing":[50],"on":[51],"groups":[53],"central":[54],"pharmaceutical":[56,156],"synthesis":[57],"medicinal":[59],"chemistry.":[60],"We":[61],"describe":[62],"the":[63,141],"development":[64],"SMARTS-RX,":[66],"including":[67],"its":[68],"systematic":[69],"nomenclature":[70],"SMARTS":[72,116],"encoding,":[73],"which":[74],"enable":[75],"precise":[76],"tracking":[77],"chemical":[79,87,168,192],"environments.":[80],"The":[81],"utility":[82],"for":[85,136,177],"mapping":[86,173],"reactivity":[88,172],"is":[89],"demonstrated":[90],"through":[91],"analyses":[92],"distributions":[96],"across":[97],"major":[98],"reaction":[99],"types,":[100],"using":[101],"large-scale":[102],"datasets":[103],"from":[104,125,162],"AstraZeneca's":[105],"Electronic":[106],"Lab":[107],"Notebooks":[108],"Reaxys.":[110],"Finally,":[111],"illustrate":[113],"how":[114],"this":[115],"library":[117],"can":[118],"be":[119],"applied":[120],"building-block":[123],"selection":[124],"commercial":[126],"catalogues.":[127],"A":[128],"public":[129],"GitHub":[130],"repository":[131],"has":[132],"been":[133],"created":[134],"aiming":[135],"continuous":[138],"improvement":[139],"current":[142],"SMARTS_RX.Scientific":[143],"Contribution:":[144],"introduces":[146],"descriptors":[154],"prioritizing":[155],"relevance":[157],"mechanistic":[159],"interpretability.":[160],"Distinct":[161],"prior":[163],"efforts,":[164],"encodes":[166],"detailed":[167],"environments":[169],"improve":[171],"feature":[175],"extraction":[176],"both":[178],"expert":[179],"analysis":[180],"modelling.":[183],"This":[184],"resource":[185],"advances":[186],"balancing":[191],"specificity":[193],"performance,":[196],"supporting":[197],"reproducible":[198],"scalable":[200],"cheminformatics":[201],"research.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-12-08T00:00:00"}