{"id":"https://openalex.org/W4391962651","doi":"https://doi.org/10.1186/s13321-024-00814-3","title":"Free and open-source QSAR-ready workflow for automated standardization of chemical structures in support of QSAR modeling","display_name":"Free and open-source QSAR-ready workflow for automated standardization of chemical structures in support of QSAR modeling","publication_year":2024,"publication_date":"2024-02-20","ids":{"openalex":"https://openalex.org/W4391962651","doi":"https://doi.org/10.1186/s13321-024-00814-3","pmid":"https://pubmed.ncbi.nlm.nih.gov/38378618"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-024-00814-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00814-3","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00814-3","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","license_id":"https://openalex.org/licenses/cc-by","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/s13321-024-00814-3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072822177","display_name":"Kamel Mansouri","orcid":"https://orcid.org/0000-0002-6426-8036"},"institutions":[{"id":"https://openalex.org/I4210095140","display_name":"National Institute of Environmental Health Sciences","ror":"https://ror.org/00j4k1h63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210095140"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kamel Mansouri","raw_affiliation_strings":["National Toxicology Program Interagency Center for the Evaluation of Alternative Toxicological Methods, National Institute of Environmental Health Sciences, Research Triangle Park, NC, 27709, USA. kamel.mansouri@nih.gov","National Toxicology Program Interagency Center for the Evaluation of Alternative Toxicological Methods, National Institute of Environmental Health Sciences, Research Triangle Park, NC, 27709, USA"],"affiliations":[{"raw_affiliation_string":"National Toxicology Program Interagency Center for the Evaluation of Alternative Toxicological Methods, National Institute of Environmental Health Sciences, Research Triangle Park, NC, 27709, USA. kamel.mansouri@nih.gov","institution_ids":[]},{"raw_affiliation_string":"National Toxicology Program Interagency Center for the Evaluation of Alternative Toxicological Methods, National Institute of Environmental Health Sciences, Research Triangle Park, NC, 27709, USA","institution_ids":["https://openalex.org/I4210095140"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068314406","display_name":"Jos\u00e9 Te\u00f3filo Moreira\u2010Filho","orcid":"https://orcid.org/0000-0002-0777-280X"},"institutions":[{"id":"https://openalex.org/I4210095140","display_name":"National Institute of Environmental Health Sciences","ror":"https://ror.org/00j4k1h63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210095140"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 T. Moreira-Filho","raw_affiliation_strings":["National Toxicology Program Interagency Center for the Evaluation of Alternative Toxicological Methods, National Institute of Environmental Health Sciences, Research Triangle Park, NC, 27709, USA"],"affiliations":[{"raw_affiliation_string":"National Toxicology Program Interagency Center for the Evaluation of Alternative Toxicological Methods, National Institute of Environmental Health Sciences, Research Triangle Park, NC, 27709, USA","institution_ids":["https://openalex.org/I4210095140"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009828926","display_name":"Charles N. Lowe","orcid":"https://orcid.org/0000-0001-9151-6157"},"institutions":[{"id":"https://openalex.org/I1302368450","display_name":"Environmental Protection Agency","ror":"https://ror.org/03tns0030","country_code":"US","type":"government","lineage":["https://openalex.org/I1302368450"]},{"id":"https://openalex.org/I1309191912","display_name":"Research Triangle Park Foundation","ror":"https://ror.org/03eqttr49","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1309191912"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles N. Lowe","raw_affiliation_strings":["Center for Computational Toxicology and Exposure, Office of Research and Development, U.S. Environmental Protection Agency, Research Triangle Park, NC, 27711, USA"],"affiliations":[{"raw_affiliation_string":"Center for Computational Toxicology and Exposure, Office of Research and Development, U.S. Environmental Protection Agency, Research Triangle Park, NC, 27711, USA","institution_ids":["https://openalex.org/I1309191912","https://openalex.org/I1302368450"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050496882","display_name":"Nathaniel Charest","orcid":"https://orcid.org/0000-0003-4252-0365"},"institutions":[{"id":"https://openalex.org/I1302368450","display_name":"Environmental Protection Agency","ror":"https://ror.org/03tns0030","country_code":"US","type":"government","lineage":["https://openalex.org/I1302368450"]},{"id":"https://openalex.org/I1309191912","display_name":"Research Triangle Park Foundation","ror":"https://ror.org/03eqttr49","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1309191912"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathaniel Charest","raw_affiliation_strings":["Center for Computational Toxicology and Exposure, Office of Research and Development, U.S. Environmental Protection Agency, Research Triangle Park, NC, 27711, USA"],"affiliations":[{"raw_affiliation_string":"Center for Computational Toxicology and Exposure, Office of Research and Development, U.S. Environmental Protection Agency, Research Triangle Park, NC, 27711, USA","institution_ids":["https://openalex.org/I1309191912","https://openalex.org/I1302368450"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080032083","display_name":"Todd M. Martin","orcid":"https://orcid.org/0000-0001-5844-8754"},"institutions":[{"id":"https://openalex.org/I1302368450","display_name":"Environmental Protection Agency","ror":"https://ror.org/03tns0030","country_code":"US","type":"government","lineage":["https://openalex.org/I1302368450"]},{"id":"https://openalex.org/I1309191912","display_name":"Research Triangle Park Foundation","ror":"https://ror.org/03eqttr49","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1309191912"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Todd Martin","raw_affiliation_strings":["Center for Computational Toxicology and Exposure, Office of Research and Development, U.S. Environmental Protection Agency, Research Triangle Park, NC, 27711, USA"],"affiliations":[{"raw_affiliation_string":"Center for Computational Toxicology and Exposure, Office of Research and Development, U.S. Environmental Protection Agency, Research Triangle Park, NC, 27711, USA","institution_ids":["https://openalex.org/I1309191912","https://openalex.org/I1302368450"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112237087","display_name":"Valery Tkachenko","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Valery Tkachenko","raw_affiliation_strings":["ScienceDataExperts LLC, Rockville, MD, 20850, USA"],"affiliations":[{"raw_affiliation_string":"ScienceDataExperts LLC, Rockville, MD, 20850, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026992703","display_name":"Richard Judson","orcid":"https://orcid.org/0000-0002-2348-9633"},"institutions":[{"id":"https://openalex.org/I1302368450","display_name":"Environmental Protection Agency","ror":"https://ror.org/03tns0030","country_code":"US","type":"government","lineage":["https://openalex.org/I1302368450"]},{"id":"https://openalex.org/I1309191912","display_name":"Research Triangle Park Foundation","ror":"https://ror.org/03eqttr49","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1309191912"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Judson","raw_affiliation_strings":["Center for Computational Toxicology and Exposure, Office of Research and Development, U.S. Environmental Protection Agency, Research Triangle Park, NC, 27711, USA"],"affiliations":[{"raw_affiliation_string":"Center for Computational Toxicology and Exposure, Office of Research and Development, U.S. Environmental Protection Agency, Research Triangle Park, NC, 27711, USA","institution_ids":["https://openalex.org/I1309191912","https://openalex.org/I1302368450"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082051013","display_name":"Mike Conway","orcid":"https://orcid.org/0000-0002-3209-8108"},"institutions":[{"id":"https://openalex.org/I4210095140","display_name":"National Institute of Environmental Health Sciences","ror":"https://ror.org/00j4k1h63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210095140"]},{"id":"https://openalex.org/I4210090916","display_name":"Triangle","ror":"https://ror.org/00fhbr831","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210090916"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mike Conway","raw_affiliation_strings":["National Institute of Environmental Health Sciences, Research Triangle Park, NC, 27709, USA"],"affiliations":[{"raw_affiliation_string":"National Institute of Environmental Health Sciences, Research Triangle Park, NC, 27709, USA","institution_ids":["https://openalex.org/I4210095140","https://openalex.org/I4210090916"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084541486","display_name":"Nicole Kleinstreuer","orcid":"https://orcid.org/0000-0002-7914-3682"},"institutions":[{"id":"https://openalex.org/I4210095140","display_name":"National Institute of Environmental Health Sciences","ror":"https://ror.org/00j4k1h63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210095140"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicole C. Kleinstreuer","raw_affiliation_strings":["National Toxicology Program Interagency Center for the Evaluation of Alternative Toxicological Methods, National Institute of Environmental Health Sciences, Research Triangle Park, NC, 27709, USA"],"affiliations":[{"raw_affiliation_string":"National Toxicology Program Interagency Center for the Evaluation of Alternative Toxicological Methods, National Institute of Environmental Health Sciences, Research Triangle Park, NC, 27709, USA","institution_ids":["https://openalex.org/I4210095140"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062051745","display_name":"Antony Williams","orcid":null},"institutions":[{"id":"https://openalex.org/I1309191912","display_name":"Research Triangle Park Foundation","ror":"https://ror.org/03eqttr49","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1309191912"]},{"id":"https://openalex.org/I1302368450","display_name":"Environmental Protection Agency","ror":"https://ror.org/03tns0030","country_code":"US","type":"government","lineage":["https://openalex.org/I1302368450"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antony J. Williams","raw_affiliation_strings":["Center for Computational Toxicology and Exposure, Office of Research and Development, U.S. Environmental Protection Agency, Research Triangle Park, NC, 27711, USA"],"affiliations":[{"raw_affiliation_string":"Center for Computational Toxicology and Exposure, Office of Research and Development, U.S. Environmental Protection Agency, Research Triangle Park, NC, 27711, USA","institution_ids":["https://openalex.org/I1309191912","https://openalex.org/I1302368450"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5072822177"],"corresponding_institution_ids":["https://openalex.org/I4210095140"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":10.0116,"has_fulltext":true,"cited_by_count":44,"citation_normalized_percentile":{"value":0.98884419,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"16","issue":"1","first_page":"19","last_page":"19"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9986000061035156,"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":0.9970999956130981,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.8716440200805664},{"id":"https://openalex.org/keywords/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.7527215480804443},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7354105114936829},{"id":"https://openalex.org/keywords/standardization","display_name":"Standardization","score":0.6231887340545654},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5996362566947937},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.5410188436508179},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5278499126434326},{"id":"https://openalex.org/keywords/chemical-database","display_name":"Chemical database","score":0.4370863437652588},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.39136961102485657},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23260533809661865},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21212619543075562},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.19847393035888672},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10562217235565186}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8716440200805664},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.7527215480804443},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7354105114936829},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.6231887340545654},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5996362566947937},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.5410188436508179},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5278499126434326},{"id":"https://openalex.org/C203394866","wikidata":"https://www.wikidata.org/wiki/Q2881060","display_name":"Chemical database","level":2,"score":0.4370863437652588},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.39136961102485657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23260533809661865},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21212619543075562},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.19847393035888672},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10562217235565186},{"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/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/s13321-024-00814-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00814-3","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00814-3","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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:38378618","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38378618","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:pubmedcentral.nih.gov:10880251","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10880251","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10880251/pdf/13321_2024_Article_814.pdf","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"},{"id":"pmh:oai:doaj.org/article:ca62db38853a477f8e316d435cd15cb9","is_oa":true,"landing_page_url":"https://doaj.org/article/ca62db38853a477f8e316d435cd15cb9","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 16, Iss 1, Pp 1-18 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13321-024-00814-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00814-3","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00814-3","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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4391962651.pdf"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1546956326","https://openalex.org/W1835137027","https://openalex.org/W1835740130","https://openalex.org/W1967434540","https://openalex.org/W1970197319","https://openalex.org/W1977287658","https://openalex.org/W1983464445","https://openalex.org/W1984678368","https://openalex.org/W2003011946","https://openalex.org/W2016455326","https://openalex.org/W2016965940","https://openalex.org/W2039850166","https://openalex.org/W2041610798","https://openalex.org/W2051810242","https://openalex.org/W2057069496","https://openalex.org/W2060434347","https://openalex.org/W2122025333","https://openalex.org/W2146751752","https://openalex.org/W2163922914","https://openalex.org/W2285468881","https://openalex.org/W2394108223","https://openalex.org/W2412746331","https://openalex.org/W2483851821","https://openalex.org/W2549115005","https://openalex.org/W2555601680","https://openalex.org/W2739783898","https://openalex.org/W2766083568","https://openalex.org/W2769853272","https://openalex.org/W2779125761","https://openalex.org/W2793396277","https://openalex.org/W2794325450","https://openalex.org/W2887459817","https://openalex.org/W2888115287","https://openalex.org/W2888792171","https://openalex.org/W2955167367","https://openalex.org/W3004841653","https://openalex.org/W3006394635","https://openalex.org/W3034591577","https://openalex.org/W3040834925","https://openalex.org/W3082081167","https://openalex.org/W3123703243","https://openalex.org/W3158507782","https://openalex.org/W3215034190","https://openalex.org/W4224076411","https://openalex.org/W4238530521","https://openalex.org/W4281698562","https://openalex.org/W4323294421","https://openalex.org/W4323855954"],"related_works":["https://openalex.org/W2382340815","https://openalex.org/W1972650408","https://openalex.org/W2551736466","https://openalex.org/W2378767206","https://openalex.org/W1997566113","https://openalex.org/W2042923741","https://openalex.org/W2172533829","https://openalex.org/W2793396277","https://openalex.org/W2506241369","https://openalex.org/W1514591088"],"abstract_inverted_index":{"The":[0,130,326],"rapid":[1],"increase":[2],"of":[3,33,85,91,101,113,127,141,173,178,184,197,213,233,245],"publicly":[4],"available":[5,266,328],"chemical":[6,36,56,107,295],"structures":[7,63,108,296],"and":[8,39,64,75,94,116,139,151,186,194,224,248,261,274,304,317,324,333,341,348],"associated":[9,40],"experimental":[10,41,79],"data":[11,49,80,310],"presents":[12],"a":[13,111,146,171],"valuable":[14],"opportunity":[15],"to":[16,78,105,110,124,204,210,237,241,254,297],"build":[17],"robust":[18],"QSAR":[19,208,260,302],"models":[20,88],"for":[21,163,226,250,279,301],"applications":[22,252],"in":[23,89,134,267,291,330,346],"different":[24,218],"fields.":[25],"However,":[26],"the":[27,31,35,71,83,86,99,125,135,153,166,214,217,234,243,280],"common":[28],"concern":[29],"is":[30,44,149,157,168],"quality":[32,84,311],"both":[34],"structure":[37,147,167],"information":[38],"data.":[42],"This":[43,199,230,285],"especially":[45],"true":[46],"when":[47,192],"those":[48],"are":[50,264],"collected":[51],"from":[52,216],"multiple":[53],"sources":[54],"as":[55,275],"substance":[57,246],"mappings":[58,77,247],"can":[59,69],"contain":[60],"many":[61],"duplicate":[62],"molecular":[65,73,128,321],"inconsistencies.":[66],"Such":[67],"issues":[68],"impact":[70],"resulting":[72,154],"descriptors":[74],"their":[76,299],"and,":[81],"subsequently,":[82],"derived":[87],"terms":[90],"accuracy,":[92],"repeatability,":[93],"reliability.":[95,325],"Herein":[96],"we":[97],"describe":[98],"development":[100],"an":[102,288],"automated":[103,289],"workflow":[104,131,137,200,236,290],"standardize":[106],"according":[109],"set":[112],"standard":[114],"rules":[115],"generate":[117,238],"two":[118],"and/or":[119],"three-dimensional":[120],"\"QSAR-ready\"":[121,235],"forms":[122],"prior":[123],"calculation":[126],"descriptors.":[129],"was":[132,201,221],"designed":[133],"KNIME":[136],"environment":[138],"consists":[140],"three":[142],"high-level":[143],"steps.":[144],"First,":[145],"encoding":[148],"read,":[150],"then":[152,195,222],"in-memory":[155],"representation":[156],"cross-referenced":[158],"with":[159],"any":[160],"existing":[161],"identifiers":[162],"consistency.":[164],"Finally,":[165],"standardized":[169],"using":[170],"series":[172],"operations":[174],"including":[175],"desalting,":[176,314],"stripping":[177],"stereochemistry":[179,315],"(for":[180],"two-dimensional":[181],"structures),":[182],"standardization":[183],"tautomers":[185],"nitro":[187],"groups,":[188],"valence":[189],"correction,":[190],"neutralization":[191],"possible,":[193],"removal":[196],"duplicates.":[198],"initially":[202],"developed":[203],"support":[205,242],"collaborative":[206,339],"modeling":[207,228,303,344],"projects":[209],"ensure":[211,298],"consistency":[212],"results":[215],"participants.":[219],"It":[220],"updated":[223],"generalized":[225],"other":[227],"applications.":[229,307],"included":[231],"modification":[232],"\"MS-ready":[239],"structures\"":[240],"generation":[244],"searches":[249],"software":[251],"related":[253],"non-targeted":[255],"analysis":[256],"mass":[257,349],"spectrometry.":[258,350],"Both":[259],"MS-ready":[262],"workflows":[263],"freely":[265,327],"KNIME,":[268,292,331],"via":[269],"standalone":[270],"versions":[271],"on":[272],"GitHub,":[273,332],"docker":[276,334],"container":[277],"resources":[278,329],"scientific":[281,306],"community.":[282],"Scientific":[283],"contribution:":[284],"work":[286],"pioneers":[287],"systematically":[293],"standardizing":[294],"readiness":[300],"broader":[305],"By":[308],"addressing":[309],"concerns":[312],"through":[313],"stripping,":[316],"normalization,":[318],"it":[319],"optimizes":[320],"descriptors'":[322],"accuracy":[323],"containers":[335],"democratize":[336],"access,":[337],"benefiting":[338],"research":[340],"advancing":[342],"diverse":[343],"endeavors":[345],"chemistry":[347]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":27},{"year":2024,"cited_by_count":11}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}
