{"id":"https://openalex.org/W4281698562","doi":"https://doi.org/10.1186/s13321-022-00606-7","title":"canSAR chemistry registration and standardization pipeline","display_name":"canSAR chemistry registration and standardization pipeline","publication_year":2022,"publication_date":"2022-05-28","ids":{"openalex":"https://openalex.org/W4281698562","doi":"https://doi.org/10.1186/s13321-022-00606-7","pmid":"https://pubmed.ncbi.nlm.nih.gov/35643512"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-022-00606-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-022-00606-7","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-022-00606-7","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","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/counter/pdf/10.1186/s13321-022-00606-7","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050073978","display_name":"Daniela Dolciami","orcid":"https://orcid.org/0000-0001-6532-1671"},"institutions":[{"id":"https://openalex.org/I2801316944","display_name":"Cancer Research UK","ror":"https://ror.org/054225q67","country_code":"GB","type":"funder","lineage":["https://openalex.org/I2801316944"]},{"id":"https://openalex.org/I142947616","display_name":"Institute of Cancer Research","ror":"https://ror.org/043jzw605","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I142947616"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Daniela Dolciami","raw_affiliation_strings":["BenevolentAI, London, W1T 5HD, UK","Cancer Research UK Cancer Therapeutics Unit, The Institute of Cancer Research, London, SM2 5NG, UK","Department of Data Science, The Institute of Cancer Research, London, SM2 5NG, UK"],"affiliations":[{"raw_affiliation_string":"BenevolentAI, London, W1T 5HD, UK","institution_ids":[]},{"raw_affiliation_string":"Cancer Research UK Cancer Therapeutics Unit, The Institute of Cancer Research, London, SM2 5NG, UK","institution_ids":["https://openalex.org/I142947616","https://openalex.org/I2801316944"]},{"raw_affiliation_string":"Department of Data Science, The Institute of Cancer Research, London, SM2 5NG, UK","institution_ids":["https://openalex.org/I142947616"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022457368","display_name":"Eloy D. Villasclaras-Fern\u00e1ndez","orcid":null},"institutions":[{"id":"https://openalex.org/I142947616","display_name":"Institute of Cancer Research","ror":"https://ror.org/043jzw605","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I142947616"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Eloy Villasclaras-Fernandez","raw_affiliation_strings":["Department of Data Science, The Institute of Cancer Research, London, SM2 5NG, UK"],"affiliations":[{"raw_affiliation_string":"Department of Data Science, The Institute of Cancer Research, London, SM2 5NG, UK","institution_ids":["https://openalex.org/I142947616"]}]},{"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"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Christos Kannas","raw_affiliation_strings":["Molecular AI, Discovery Sciences, R&D, AstraZeneca, Gothenburg, Sweden"],"affiliations":[{"raw_affiliation_string":"Molecular AI, Discovery Sciences, R&D, AstraZeneca, Gothenburg, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075575600","display_name":"Mirco Meniconi","orcid":"https://orcid.org/0000-0001-9919-8472"},"institutions":[{"id":"https://openalex.org/I142947616","display_name":"Institute of Cancer Research","ror":"https://ror.org/043jzw605","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I142947616"]},{"id":"https://openalex.org/I2801316944","display_name":"Cancer Research UK","ror":"https://ror.org/054225q67","country_code":"GB","type":"funder","lineage":["https://openalex.org/I2801316944"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mirco Meniconi","raw_affiliation_strings":["Cancer Research UK Cancer Therapeutics Unit, The Institute of Cancer Research, London, SM2 5NG, UK","Dunad therapeutics, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Cancer Research UK Cancer Therapeutics Unit, The Institute of Cancer Research, London, SM2 5NG, UK","institution_ids":["https://openalex.org/I142947616","https://openalex.org/I2801316944"]},{"raw_affiliation_string":"Dunad therapeutics, Cambridge, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007910628","display_name":"Bissan Al\u2010Lazikani","orcid":"https://orcid.org/0000-0003-3367-2519"},"institutions":[{"id":"https://openalex.org/I1343551460","display_name":"The University of Texas MD Anderson Cancer Center","ror":"https://ror.org/04twxam07","country_code":"US","type":"funder","lineage":["https://openalex.org/I1343551460"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bissan Al-Lazikani","raw_affiliation_strings":["MD Anderson Cancer Center, Houston, TX, 77054, USA. ballazikani@mdanderson.org","MD Anderson Cancer Center, Houston, TX, 77054, USA"],"affiliations":[{"raw_affiliation_string":"MD Anderson Cancer Center, Houston, TX, 77054, USA. ballazikani@mdanderson.org","institution_ids":[]},{"raw_affiliation_string":"MD Anderson Cancer Center, Houston, TX, 77054, USA","institution_ids":["https://openalex.org/I1343551460"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062183469","display_name":"Albert A. Antol\u00edn","orcid":"https://orcid.org/0000-0002-1634-9034"},"institutions":[{"id":"https://openalex.org/I142947616","display_name":"Institute of Cancer Research","ror":"https://ror.org/043jzw605","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I142947616"]},{"id":"https://openalex.org/I2801316944","display_name":"Cancer Research UK","ror":"https://ror.org/054225q67","country_code":"GB","type":"funder","lineage":["https://openalex.org/I2801316944"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Albert A. Antolin","raw_affiliation_strings":["Cancer Research UK Cancer Therapeutics Unit, The Institute of Cancer Research, London, SM2 5NG, UK. Albert.Antolin@icr.ac.uk","Department of Data Science, The Institute of Cancer Research, London, SM2 5NG, UK. Albert.Antolin@icr.ac.uk","Cancer Research UK Cancer Therapeutics Unit, The Institute of Cancer Research, London, SM2 5NG, UK"],"affiliations":[{"raw_affiliation_string":"Cancer Research UK Cancer Therapeutics Unit, The Institute of Cancer Research, London, SM2 5NG, UK. Albert.Antolin@icr.ac.uk","institution_ids":[]},{"raw_affiliation_string":"Department of Data Science, The Institute of Cancer Research, London, SM2 5NG, UK. Albert.Antolin@icr.ac.uk","institution_ids":[]},{"raw_affiliation_string":"Cancer Research UK Cancer Therapeutics Unit, The Institute of Cancer Research, London, SM2 5NG, UK","institution_ids":["https://openalex.org/I142947616","https://openalex.org/I2801316944"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5007910628"],"corresponding_institution_ids":["https://openalex.org/I1343551460"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":1.8198,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.85436994,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"14","issue":"1","first_page":"28","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9983000159263611,"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"}},"topics":[{"id":"https://openalex.org/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9983000159263611,"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"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9925000071525574,"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/T10683","display_name":"Mass Spectrometry Techniques and Applications","score":0.9703999757766724,"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/standardization","display_name":"Standardization","score":0.8810206651687622},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6335829496383667},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6143097281455994},{"id":"https://openalex.org/keywords/chemical-nomenclature","display_name":"Chemical nomenclature","score":0.48545414209365845},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.48533955216407776},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.24650463461875916},{"id":"https://openalex.org/keywords/organic-chemistry","display_name":"Organic chemistry","score":0.08912459015846252},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0857149064540863}],"concepts":[{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.8810206651687622},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6335829496383667},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6143097281455994},{"id":"https://openalex.org/C125832229","wikidata":"https://www.wikidata.org/wiki/Q6503924","display_name":"Chemical nomenclature","level":2,"score":0.48545414209365845},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.48533955216407776},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.24650463461875916},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.08912459015846252},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0857149064540863},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-022-00606-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-022-00606-7","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-022-00606-7","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:35643512","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35643512","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:f4b09ed7191441dfb6d8a4ffad630753","is_oa":true,"landing_page_url":"https://doaj.org/article/f4b09ed7191441dfb6d8a4ffad630753","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 1-20 (2022)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9148294","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9148294","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13321-022-00606-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-022-00606-7","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-022-00606-7","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G1571652552","display_name":null,"funder_award_id":"204735/Z/16/Z","funder_id":"https://openalex.org/F4320311904","funder_display_name":"Wellcome Trust"},{"id":"https://openalex.org/G1830539922","display_name":null,"funder_award_id":"C309/A11566","funder_id":"https://openalex.org/F4320319985","funder_display_name":"Cancer Research UK"},{"id":"https://openalex.org/G3319054893","display_name":null,"funder_award_id":"FP7/2007\u20132013","funder_id":"https://openalex.org/F4320338368","funder_display_name":"FP7 People: Marie-Curie Actions"},{"id":"https://openalex.org/G6611980046","display_name":null,"funder_award_id":"C35696/A23187","funder_id":"https://openalex.org/F4320319985","funder_display_name":"Cancer Research UK"},{"id":"https://openalex.org/G7596808270","display_name":null,"funder_award_id":"212969/Z/18/Z","funder_id":"https://openalex.org/F4320311904","funder_display_name":"Wellcome Trust"}],"funders":[{"id":"https://openalex.org/F4320311904","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08"},{"id":"https://openalex.org/F4320319985","display_name":"Cancer Research UK","ror":"https://ror.org/054225q67"},{"id":"https://openalex.org/F4320338368","display_name":"FP7 People: Marie-Curie Actions","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4281698562.pdf","grobid_xml":"https://content.openalex.org/works/W4281698562.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1508604947","https://openalex.org/W1516646538","https://openalex.org/W1835740130","https://openalex.org/W1971761242","https://openalex.org/W1975147762","https://openalex.org/W1980090013","https://openalex.org/W1984678368","https://openalex.org/W2016455326","https://openalex.org/W2038080389","https://openalex.org/W2038702914","https://openalex.org/W2041610798","https://openalex.org/W2087563523","https://openalex.org/W2097186436","https://openalex.org/W2122709242","https://openalex.org/W2204695023","https://openalex.org/W2523800160","https://openalex.org/W2737277464","https://openalex.org/W2887459817","https://openalex.org/W2900090807","https://openalex.org/W2903181389","https://openalex.org/W2978232173","https://openalex.org/W3006394635","https://openalex.org/W3082081167","https://openalex.org/W3205219207","https://openalex.org/W4232460528"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2765674682","https://openalex.org/W2095596879","https://openalex.org/W4251955477","https://openalex.org/W4386027229","https://openalex.org/W2065541177","https://openalex.org/W2171646645","https://openalex.org/W2473178225"],"abstract_inverted_index":{"We":[0,69],"use":[1],"canSARchem":[2,71],"to":[3],"standardize":[4],"all":[5],"the":[6,19,60],"compounds":[7],"uploaded":[8],"in":[9,39],"canSAR":[10,46,50],"(>":[11],"3":[12],"million)":[13],"enabling":[14],"efficient":[15],"data":[16,67],"integration":[17],"and":[18,33,45,49],"rapid":[20],"identification":[21],"of":[22,62],"alternative":[23],"compound":[24,40,63],"forms":[25],"with":[26,31],"useful":[27],"bioactivity":[28,66],"data.":[29],"Comparison":[30],"PubChem":[32,44],"ChEMBL":[34],"pipelines":[35],"evidenced":[36],"comparable":[37],"performances":[38],"standardization,":[41],"but":[42],"only":[43],"canonicalize":[47],"tautomers":[48],"has":[51],"a":[52,74],"slightly":[53],"lower":[54],"rejection":[55],"rate.":[56],"Our":[57],"results":[58],"highlight":[59],"importance":[61],"hierarchies":[64],"for":[65],"exploration.":[68],"make":[70],"available":[72],"under":[73],"Creative":[75],"Commons":[76],"Attribution-ShareAlike":[77],"4.0":[78],"International":[79],"License":[80],"(CC":[81],"BY-SA":[82],"4.0)":[83],"at":[84],"https://gitlab.icr.ac.uk/cansar-public/compound-registration-pipeline":[85],".":[86]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-31T07:56:22.981413","created_date":"2025-10-10T00:00:00"}
