{"id":"https://openalex.org/W2973634761","doi":"https://doi.org/10.1186/s13321-019-0384-1","title":"Open-source QSAR models for pKa prediction using multiple machine learning approaches","display_name":"Open-source QSAR models for pKa prediction using multiple machine learning approaches","publication_year":2019,"publication_date":"2019-09-18","ids":{"openalex":"https://openalex.org/W2973634761","doi":"https://doi.org/10.1186/s13321-019-0384-1","mag":"2973634761","pmid":"https://pubmed.ncbi.nlm.nih.gov/33430972"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-019-0384-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-019-0384-1","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-019-0384-1","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","datacite","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-019-0384-1","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/I4210090916","display_name":"Triangle","ror":"https://ror.org/00fhbr831","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210090916"]},{"id":"https://openalex.org/I4210111107","display_name":"Integrated Laboratory Systems, Inc.","ror":"https://ror.org/020hchp05","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210111107"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kamel Mansouri","raw_affiliation_strings":["Integrated Laboratory Systems, Inc., P.O. Box 13501, Research Triangle Park, NC, 27709, USA. kmansouri@ils-inc.com","Integrated Laboratory Systems, Inc., P.O. Box 13501, Research Triangle Park, NC, 27709, USA"],"raw_orcid":"https://orcid.org/0000-0002-6426-8036","affiliations":[{"raw_affiliation_string":"Integrated Laboratory Systems, Inc., P.O. Box 13501, Research Triangle Park, NC, 27709, USA. kmansouri@ils-inc.com","institution_ids":["https://openalex.org/I4210111107"]},{"raw_affiliation_string":"Integrated Laboratory Systems, Inc., P.O. Box 13501, Research Triangle Park, NC, 27709, USA","institution_ids":["https://openalex.org/I4210111107","https://openalex.org/I4210090916"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072173468","display_name":"Neal F. Cariello","orcid":"https://orcid.org/0000-0001-6135-752X"},"institutions":[{"id":"https://openalex.org/I4210090916","display_name":"Triangle","ror":"https://ror.org/00fhbr831","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210090916"]},{"id":"https://openalex.org/I4210111107","display_name":"Integrated Laboratory Systems, Inc.","ror":"https://ror.org/020hchp05","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210111107"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neal F. Cariello","raw_affiliation_strings":["Integrated Laboratory Systems, Inc., P.O. Box 13501, Research Triangle Park, NC, 27709, USA"],"raw_orcid":"https://orcid.org/0000-0001-6135-752X","affiliations":[{"raw_affiliation_string":"Integrated Laboratory Systems, Inc., P.O. Box 13501, Research Triangle Park, NC, 27709, USA","institution_ids":["https://openalex.org/I4210111107","https://openalex.org/I4210090916"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070164801","display_name":"Alexandru Korotcov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandru Korotcov","raw_affiliation_strings":["Science Data Software LLC, 14914 Bradwill Court, Rockville, MD, 20850, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science Data Software LLC, 14914 Bradwill Court, Rockville, MD, 20850, USA","institution_ids":[]}]},{"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":["Science Data Software LLC, 14914 Bradwill Court, Rockville, MD, 20850, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science Data Software LLC, 14914 Bradwill Court, Rockville, MD, 20850, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054612487","display_name":"Chris Grulke","orcid":"https://orcid.org/0000-0001-5606-7560"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris M. Grulke","raw_affiliation_strings":["National Center for Computational Toxicology, U.S. Environmental Protection Agency, 109 T.W. Alexander Dr., Mail Code D143-02, Research Triangle Park, NC, 27709, USA"],"raw_orcid":"https://orcid.org/0000-0001-5606-7560","affiliations":[{"raw_affiliation_string":"National Center for Computational Toxicology, U.S. Environmental Protection Agency, 109 T.W. Alexander Dr., Mail Code D143-02, Research Triangle Park, NC, 27709, USA","institution_ids":["https://openalex.org/I1302368450"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017536476","display_name":"Catherine S. Sprankle","orcid":"https://orcid.org/0000-0001-9436-5673"},"institutions":[{"id":"https://openalex.org/I4210090916","display_name":"Triangle","ror":"https://ror.org/00fhbr831","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210090916"]},{"id":"https://openalex.org/I4210111107","display_name":"Integrated Laboratory Systems, Inc.","ror":"https://ror.org/020hchp05","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210111107"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Catherine S. Sprankle","raw_affiliation_strings":["Integrated Laboratory Systems, Inc., P.O. Box 13501, Research Triangle Park, NC, 27709, USA"],"raw_orcid":"https://orcid.org/0000-0001-9436-5673","affiliations":[{"raw_affiliation_string":"Integrated Laboratory Systems, Inc., P.O. Box 13501, Research Triangle Park, NC, 27709, USA","institution_ids":["https://openalex.org/I4210111107","https://openalex.org/I4210090916"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025969084","display_name":"David Allen","orcid":"https://orcid.org/0000-0002-8575-9547"},"institutions":[{"id":"https://openalex.org/I4210090916","display_name":"Triangle","ror":"https://ror.org/00fhbr831","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210090916"]},{"id":"https://openalex.org/I4210111107","display_name":"Integrated Laboratory Systems, Inc.","ror":"https://ror.org/020hchp05","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210111107"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Allen","raw_affiliation_strings":["Integrated Laboratory Systems, Inc., P.O. Box 13501, Research Triangle Park, NC, 27709, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Integrated Laboratory Systems, Inc., P.O. Box 13501, Research Triangle Park, NC, 27709, USA","institution_ids":["https://openalex.org/I4210111107","https://openalex.org/I4210090916"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075874157","display_name":"Warren Casey","orcid":"https://orcid.org/0000-0001-6731-1127"},"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":"Warren M. Casey","raw_affiliation_strings":["National Institute of Environmental Health Sciences, P.O. Box 12233, Mail Stop K2-16, Research Triangle Park, NC, 27709, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Environmental Health Sciences, P.O. Box 12233, Mail Stop K2-16, Research Triangle Park, NC, 27709, USA","institution_ids":["https://openalex.org/I4210095140"]}]},{"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 Institute of Environmental Health Sciences, P.O. Box 12233, Mail Stop K2-16, Research Triangle Park, NC, 27709, USA"],"raw_orcid":"https://orcid.org/0000-0002-7914-3682","affiliations":[{"raw_affiliation_string":"National Institute of Environmental Health Sciences, P.O. Box 12233, Mail Stop K2-16, 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/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":["National Center for Computational Toxicology, U.S. Environmental Protection Agency, 109 T.W. Alexander Dr., Mail Code D143-02, Research Triangle Park, NC, 27709, USA"],"raw_orcid":"https://orcid.org/0000-0002-2668-4821","affiliations":[{"raw_affiliation_string":"National Center for Computational Toxicology, U.S. Environmental Protection Agency, 109 T.W. Alexander Dr., Mail Code D143-02, Research Triangle Park, NC, 27709, USA","institution_ids":["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/I4210090916","https://openalex.org/I4210111107"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":14.9563,"has_fulltext":true,"cited_by_count":182,"citation_normalized_percentile":{"value":0.9924787,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"11","issue":"1","first_page":"60","last_page":"60"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9381999969482422,"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":0.9381999969482422,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.016499999910593033,"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/T13013","display_name":"Free Radicals and Antioxidants","score":0.011800000444054604,"subfield":{"id":"https://openalex.org/subfields/1605","display_name":"Organic Chemistry"},"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":0.6694591641426086},{"id":"https://openalex.org/keywords/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.666881799697876},{"id":"https://openalex.org/keywords/acid-dissociation-constant","display_name":"Acid dissociation constant","score":0.630031406879425},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5951761603355408},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5811781883239746},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.562381386756897},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5509968996047974},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.548901379108429},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5018329620361328},{"id":"https://openalex.org/keywords/lipophilicity","display_name":"Lipophilicity","score":0.48401448130607605},{"id":"https://openalex.org/keywords/dissociation-constant","display_name":"Dissociation constant","score":0.43492016196250916},{"id":"https://openalex.org/keywords/gradient-boosting","display_name":"Gradient boosting","score":0.4347858726978302},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.42820096015930176},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38530758023262024},{"id":"https://openalex.org/keywords/biological-system","display_name":"Biological system","score":0.3552054762840271},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.3030487596988678},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.19092947244644165},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13243892788887024},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10422831773757935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6694591641426086},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.666881799697876},{"id":"https://openalex.org/C22163223","wikidata":"https://www.wikidata.org/wiki/Q325519","display_name":"Acid dissociation constant","level":3,"score":0.630031406879425},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5951761603355408},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5811781883239746},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.562381386756897},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5509968996047974},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.548901379108429},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5018329620361328},{"id":"https://openalex.org/C201399114","wikidata":"https://www.wikidata.org/wiki/Q898401","display_name":"Lipophilicity","level":2,"score":0.48401448130607605},{"id":"https://openalex.org/C74998103","wikidata":"https://www.wikidata.org/wiki/Q898254","display_name":"Dissociation constant","level":3,"score":0.43492016196250916},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.4347858726978302},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.42820096015930176},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38530758023262024},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.3552054762840271},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.3030487596988678},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.19092947244644165},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13243892788887024},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10422831773757935},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"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/C170493617","wikidata":"https://www.wikidata.org/wiki/Q208467","display_name":"Receptor","level":2,"score":0.0},{"id":"https://openalex.org/C184651966","wikidata":"https://www.wikidata.org/wiki/Q906356","display_name":"Aqueous solution","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C147789679","wikidata":"https://www.wikidata.org/wiki/Q11372","display_name":"Physical chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1186/s13321-019-0384-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-019-0384-1","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-019-0384-1","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:33430972","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33430972","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:4f55baf346f34fe88b0e95561bea6d46","is_oa":true,"landing_page_url":"https://doaj.org/article/4f55baf346f34fe88b0e95561bea6d46","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 11, Iss 1, Pp 1-20 (2019)","raw_type":"article"},{"id":"pmh:oai:figshare.com:article/7157207","is_oa":true,"landing_page_url":"https://figshare.com/articles/poster/Open_Source_QSAR_Models_For_pKa_Prediction_Using_Multiple_Machine_Learning_Approaches/7157207","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"","raw_type":"Image"},{"id":"pmh:oai:pubmedcentral.nih.gov:6749653","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6749653","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":"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":"doi:10.23645/epacomptox.7157207.v1","is_oa":true,"landing_page_url":"https://doi.org/10.23645/epacomptox.7157207.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407051358","display_name":"U.S. Environmental Protection Agency","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"graphic"}],"best_oa_location":{"id":"doi:10.1186/s13321-019-0384-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-019-0384-1","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-019-0384-1","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":"Clean water and sanitation","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/6"}],"awards":[{"id":"https://openalex.org/G6308604930","display_name":null,"funder_award_id":"HHSN273201500010C","funder_id":"https://openalex.org/F4320337361","funder_display_name":"National Institute of Environmental Health Sciences"}],"funders":[{"id":"https://openalex.org/F4320309037","display_name":"Office of Research and Development","ror":"https://ror.org/05rsv9s98"},{"id":"https://openalex.org/F4320329429","display_name":"Idorsia Pharmaceuticals","ror":"https://ror.org/03va9ng43"},{"id":"https://openalex.org/F4320337361","display_name":"National Institute of Environmental Health Sciences","ror":"https://ror.org/00j4k1h63"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2973634761.pdf","grobid_xml":"https://content.openalex.org/works/W2973634761.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W124248331","https://openalex.org/W1831050183","https://openalex.org/W1835740130","https://openalex.org/W1879339955","https://openalex.org/W1895187576","https://openalex.org/W1971849220","https://openalex.org/W1990399577","https://openalex.org/W1999798000","https://openalex.org/W2001179019","https://openalex.org/W2016909911","https://openalex.org/W2017398555","https://openalex.org/W2020116600","https://openalex.org/W2047245810","https://openalex.org/W2061477847","https://openalex.org/W2063396347","https://openalex.org/W2073511756","https://openalex.org/W2082627744","https://openalex.org/W2087347434","https://openalex.org/W2094802206","https://openalex.org/W2099071242","https://openalex.org/W2113104789","https://openalex.org/W2119821739","https://openalex.org/W2140796250","https://openalex.org/W2153635508","https://openalex.org/W2159887157","https://openalex.org/W2269194472","https://openalex.org/W2295598076","https://openalex.org/W2306570595","https://openalex.org/W2394108223","https://openalex.org/W2412746331","https://openalex.org/W2473190403","https://openalex.org/W2502949459","https://openalex.org/W2520468066","https://openalex.org/W2528491735","https://openalex.org/W2549115005","https://openalex.org/W2551485778","https://openalex.org/W2556851635","https://openalex.org/W2577678628","https://openalex.org/W2582187633","https://openalex.org/W2730947260","https://openalex.org/W2741088520","https://openalex.org/W2758866647","https://openalex.org/W2769569970","https://openalex.org/W2783486156","https://openalex.org/W2790481358","https://openalex.org/W2791653123","https://openalex.org/W2793396277","https://openalex.org/W3102476541","https://openalex.org/W4211079109"],"related_works":["https://openalex.org/W2047571932","https://openalex.org/W1988118571","https://openalex.org/W2009906913","https://openalex.org/W1983060123","https://openalex.org/W2026681105","https://openalex.org/W2950094274","https://openalex.org/W2002360066","https://openalex.org/W2509822752","https://openalex.org/W2091416880","https://openalex.org/W1988410471"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,83],"logarithmic":[2],"acid":[3],"dissociation":[4],"constant":[5],"pKa":[6,28,80,90,168,205],"reflects":[7],"the":[8,24,44,50,126,215,231,243],"ionization":[9],"of":[10,46,52,125,147,225,250],"a":[11,65,101,121],"chemical,":[12],"which":[13],"affects":[14,29],"lipophilicity,":[15],"solubility,":[16],"protein":[17],"binding,":[18],"and":[19,35,57,70,87,110,120,160,167,193,209,223,246,257,261],"ability":[20],"to":[21,49,137,213,230,241],"pass":[22],"through":[23],"plasma":[25],"membrane.":[26],"Thus,":[27],"chemical":[30,148],"absorption,":[31],"distribution,":[32],"metabolism,":[33],"excretion,":[34],"toxicity":[36],"properties.":[37],"Multiple":[38],"proprietary":[39],"software":[40,104,263],"packages":[41],"exist":[42,60],"for":[43,61,79,94,112,131],"prediction":[45,169],"pKa,":[47],"but":[48],"best":[51,217],"our":[53,226],"knowledge":[54],"no":[55],"free":[56,260],"open-source":[58,77,262],"programs":[59],"this":[62,221],"purpose.":[63],"Using":[64],"freely":[66,102],"available":[67,103,255],"data":[68],"set":[69,128],"three":[71,174,216],"machine":[72,175],"learning":[73,176],"approaches,":[74],"we":[75],"developed":[76,219],"models":[78,170,218,227,240],"prediction.":[81],"METHODS:":[82],"experimental":[84],"strongest":[85,88,244,247],"acidic":[86,151,245],"basic":[89,153,248],"values":[91],"in":[92,220],"water":[93],"7912":[95],"chemicals":[96],"were":[97,108,141,163,171,211],"obtained":[98],"from":[99,207],"DataWarrior,":[100],"package.":[105],"Chemical":[106],"structures":[107,149],"curated":[109],"standardized":[111],"quantitative":[113],"structure-activity":[114],"relationship":[115],"(QSAR)":[116],"modeling":[117],"using":[118,165,173,253],"KNIME,":[119],"subset":[122],"comprising":[123],"79%":[124],"initial":[127],"was":[129],"used":[130,212],"modeling.":[132],"To":[133],"evaluate":[134],"different":[135,145],"approaches":[136],"modeling,":[138],"several":[139],"datasets":[140],"constructed":[142],"based":[143],"on":[144,264],"processing":[146],"with":[150,184],"and/or":[152],"pKas.":[154],"Continuous":[155],"molecular":[156],"descriptors,":[157],"binary":[158],"fingerprints,":[159],"fragment":[161],"counts":[162],"generated":[164],"PaDEL,":[166],"created":[172],"methods,":[177],"(1)":[178],"support":[179],"vector":[180],"machines":[181],"(SVM)":[182],"combined":[183],"k-nearest":[185],"neighbors":[186],"(kNN),":[187],"(2)":[188],"extreme":[189],"gradient":[190],"boosting":[191],"(XGB)":[192],"(3)":[194],"deep":[195],"neural":[196],"networks":[197],"(DNN).":[198],"RESULTS:":[199],")":[200],"around":[201],"0.80.":[202],"Two":[203],"commercial":[204,232],"predictors":[206],"ACD/Labs":[208],"ChemAxon":[210],"benchmark":[214],"work,":[222],"performance":[224],"compared":[228],"favorably":[229],"products.":[233],"CONCLUSIONS:":[234],"This":[235],"work":[236],"provides":[237],"multiple":[238],"QSAR":[239],"predict":[242],"pKas":[249],"chemicals,":[251],"built":[252],"publicly":[254],"data,":[256],"provided":[258],"as":[259],"GitHub.":[265]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":31},{"year":2023,"cited_by_count":39},{"year":2022,"cited_by_count":30},{"year":2021,"cited_by_count":30},{"year":2020,"cited_by_count":14}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}