{"id":"https://openalex.org/W4319662043","doi":"https://doi.org/10.1021/acs.jcim.2c01189","title":"Blinded Predictions and Post Hoc Analysis of the Second Solubility Challenge Data: Exploring Training Data and Feature Set Selection for Machine and Deep Learning Models","display_name":"Blinded Predictions and Post Hoc Analysis of the Second Solubility Challenge Data: Exploring Training Data and Feature Set Selection for Machine and Deep Learning Models","publication_year":2023,"publication_date":"2023-02-09","ids":{"openalex":"https://openalex.org/W4319662043","doi":"https://doi.org/10.1021/acs.jcim.2c01189","pmid":"https://pubmed.ncbi.nlm.nih.gov/36758178"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.2c01189","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.2c01189","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1021/acs.jcim.2c01189","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001025053","display_name":"Jonathan G. M. Conn","orcid":null},"institutions":[{"id":"https://openalex.org/I181647926","display_name":"University of Strathclyde","ror":"https://ror.org/00n3w3b69","country_code":"GB","type":"education","lineage":["https://openalex.org/I181647926"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jonathan G. M. Conn","raw_affiliation_strings":["Department of Pure and Applied Chemistry, University of Strathclyde, Thomas Graham Building, 295 Cathedral Street, Glasgow G1 1XL, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Pure and Applied Chemistry, University of Strathclyde, Thomas Graham Building, 295 Cathedral Street, Glasgow G1 1XL, U.K","institution_ids":["https://openalex.org/I181647926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053426697","display_name":"James W. Carter","orcid":null},"institutions":[{"id":"https://openalex.org/I181647926","display_name":"University of Strathclyde","ror":"https://ror.org/00n3w3b69","country_code":"GB","type":"education","lineage":["https://openalex.org/I181647926"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James W. Carter","raw_affiliation_strings":["Department of Pure and Applied Chemistry, University of Strathclyde, Thomas Graham Building, 295 Cathedral Street, Glasgow G1 1XL, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Pure and Applied Chemistry, University of Strathclyde, Thomas Graham Building, 295 Cathedral Street, Glasgow G1 1XL, U.K","institution_ids":["https://openalex.org/I181647926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039812954","display_name":"Justin J. A. Conn","orcid":null},"institutions":[{"id":"https://openalex.org/I181647926","display_name":"University of Strathclyde","ror":"https://ror.org/00n3w3b69","country_code":"GB","type":"education","lineage":["https://openalex.org/I181647926"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Justin J. A. Conn","raw_affiliation_strings":["Department of Pure and Applied Chemistry, University of Strathclyde, Thomas Graham Building, 295 Cathedral Street, Glasgow G1 1XL, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Pure and Applied Chemistry, University of Strathclyde, Thomas Graham Building, 295 Cathedral Street, Glasgow G1 1XL, U.K","institution_ids":["https://openalex.org/I181647926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021946379","display_name":"Vigneshwari Subramanian","orcid":"https://orcid.org/0000-0002-7319-8885"},"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":"Vigneshwari Subramanian","raw_affiliation_strings":["Drug Metabolism and Pharmacokinetics, Research and Early Development, Respiratory & Immunology, BioPharmaceuticals R&D, AstraZeneca, Pepparedsleden 1, SE-431 83 G\u00f6teborg, Sweden"],"affiliations":[{"raw_affiliation_string":"Drug Metabolism and Pharmacokinetics, Research and Early Development, Respiratory & Immunology, BioPharmaceuticals R&D, AstraZeneca, Pepparedsleden 1, SE-431 83 G\u00f6teborg, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019294708","display_name":"Andrew Baxter","orcid":"https://orcid.org/0000-0001-8718-3265"},"institutions":[{"id":"https://openalex.org/I2800110054","display_name":"Age UK","ror":"https://ror.org/050x9d346","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2800110054"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Baxter","raw_affiliation_strings":["GSK Medicines Research Centre, Gunnels Wood Road, Stevenage SG1 2NY, U.K"],"affiliations":[{"raw_affiliation_string":"GSK Medicines Research Centre, Gunnels Wood Road, Stevenage SG1 2NY, U.K","institution_ids":["https://openalex.org/I2800110054"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076975589","display_name":"Ola Engkvist","orcid":"https://orcid.org/0000-0003-4970-6461"},"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/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Ola Engkvist","raw_affiliation_strings":["Department of Computer Science and Engineering, Chalmers University of Technology, SE-412 96 G\u00f6teborg, Sweden","Medicinal Chemistry, Research and Early Development, Cardiovascular, Renal and Metabolism (CVRM), BioPharmaceuticals R&D, AstraZeneca, SE-431 50 G\u00f6teborg, Sweden"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Chalmers University of Technology, SE-412 96 G\u00f6teborg, Sweden","institution_ids":["https://openalex.org/I66862912"]},{"raw_affiliation_string":"Medicinal Chemistry, Research and Early Development, Cardiovascular, Renal and Metabolism (CVRM), BioPharmaceuticals R&D, AstraZeneca, SE-431 50 G\u00f6teborg, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067415005","display_name":"Antonio Llin\u00e0s","orcid":"https://orcid.org/0000-0003-4620-9363"},"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":"Antonio Llinas","raw_affiliation_strings":["Drug Metabolism and Pharmacokinetics, Research and Early Development, Respiratory & Immunology, BioPharmaceuticals R&D, AstraZeneca, Pepparedsleden 1, SE-431 83 G\u00f6teborg, Sweden"],"affiliations":[{"raw_affiliation_string":"Drug Metabolism and Pharmacokinetics, Research and Early Development, Respiratory & Immunology, BioPharmaceuticals R&D, AstraZeneca, Pepparedsleden 1, SE-431 83 G\u00f6teborg, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038387457","display_name":"Ekaterina L. Ratkova","orcid":"https://orcid.org/0000-0003-4110-0078"},"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":"Ekaterina L. Ratkova","raw_affiliation_strings":["Medicinal Chemistry, Research and Early Development, Cardiovascular, Renal and Metabolism (CVRM), BioPharmaceuticals R&D, AstraZeneca, SE-431 50 G\u00f6teborg, Sweden"],"affiliations":[{"raw_affiliation_string":"Medicinal Chemistry, Research and Early Development, Cardiovascular, Renal and Metabolism (CVRM), BioPharmaceuticals R&D, AstraZeneca, SE-431 50 G\u00f6teborg, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079075074","display_name":"Stephen D. Pickett","orcid":"https://orcid.org/0000-0002-0958-9830"},"institutions":[{"id":"https://openalex.org/I188950975","display_name":"GlaxoSmithKline (United Kingdom)","ror":"https://ror.org/01xsqw823","country_code":"GB","type":"company","lineage":["https://openalex.org/I188950975"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stephen D. Pickett","raw_affiliation_strings":["Computational Sciences, GlaxoSmithKline R&D Pharmaceuticals, Stevenage SG1 2NY, U.K"],"affiliations":[{"raw_affiliation_string":"Computational Sciences, GlaxoSmithKline R&D Pharmaceuticals, Stevenage SG1 2NY, U.K","institution_ids":["https://openalex.org/I188950975"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014606088","display_name":"James L. McDonagh","orcid":"https://orcid.org/0000-0002-2323-6898"},"institutions":[{"id":"https://openalex.org/I2802015276","display_name":"Daresbury Laboratory","ror":"https://ror.org/0089bg420","country_code":"GB","type":"facility","lineage":["https://openalex.org/I162524378","https://openalex.org/I2802015276","https://openalex.org/I4210087105"]},{"id":"https://openalex.org/I4210102012","display_name":"Sci-Tech Daresbury","ror":"https://ror.org/015ff4823","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210102012"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James L. McDonagh","raw_affiliation_strings":["IBM Research Europe, Hartree Centre, SciTech Daresbury, Warrington, Cheshire WA4 4AD, U.K"],"affiliations":[{"raw_affiliation_string":"IBM Research Europe, Hartree Centre, SciTech Daresbury, Warrington, Cheshire WA4 4AD, U.K","institution_ids":["https://openalex.org/I4210102012","https://openalex.org/I2802015276"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069304320","display_name":"David Scott Palmer","orcid":"https://orcid.org/0000-0003-4356-9144"},"institutions":[{"id":"https://openalex.org/I181647926","display_name":"University of Strathclyde","ror":"https://ror.org/00n3w3b69","country_code":"GB","type":"education","lineage":["https://openalex.org/I181647926"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"David S. Palmer","raw_affiliation_strings":["Department of Pure and Applied Chemistry, University of Strathclyde, Thomas Graham Building, 295 Cathedral Street, Glasgow G1 1XL, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Pure and Applied Chemistry, University of Strathclyde, Thomas Graham Building, 295 Cathedral Street, Glasgow G1 1XL, U.K","institution_ids":["https://openalex.org/I181647926"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5069304320"],"corresponding_institution_ids":["https://openalex.org/I181647926"],"apc_list":null,"apc_paid":null,"fwci":4.495,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.95446701,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"63","issue":"4","first_page":"1099","last_page":"1113"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9940000176429749,"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":0.9940000176429749,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9886999726295471,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10799","display_name":"Data Visualization and Analytics","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.7147400379180908},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6402335166931152},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.6289011836051941},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.613850474357605},{"id":"https://openalex.org/keywords/post-hoc","display_name":"Post hoc","score":0.6073912382125854},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.548757791519165},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5403265357017517},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5190401673316956},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.50244140625},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4824824631214142},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47507399320602417},{"id":"https://openalex.org/keywords/post-hoc-analysis","display_name":"Post-hoc analysis","score":0.46794456243515015},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4180121123790741},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3272259831428528},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.10035741329193115},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09770524501800537},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07906872034072876}],"concepts":[{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7147400379180908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6402335166931152},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.6289011836051941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.613850474357605},{"id":"https://openalex.org/C2992886853","wikidata":"https://www.wikidata.org/wiki/Q18381816","display_name":"Post hoc","level":2,"score":0.6073912382125854},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.548757791519165},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5403265357017517},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5190401673316956},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.50244140625},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4824824631214142},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47507399320602417},{"id":"https://openalex.org/C67761136","wikidata":"https://www.wikidata.org/wiki/Q2105849","display_name":"Post-hoc analysis","level":2,"score":0.46794456243515015},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4180121123790741},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3272259831428528},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.10035741329193115},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09770524501800537},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07906872034072876},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199343813","wikidata":"https://www.wikidata.org/wiki/Q12128","display_name":"Dentistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012995","descriptor_name":"Solubility","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012995","descriptor_name":"Solubility","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012995","descriptor_name":"Solubility","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1021/acs.jcim.2c01189","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.2c01189","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:36758178","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36758178","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of chemical information and modeling","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9976279","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9976279","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC9976279/pdf/ci2c01189.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 Chem Inf Model","raw_type":"Text"},{"id":"pmh:oai:research.chalmers.se:534731","is_oa":true,"landing_page_url":"https://research.chalmers.se/en/publication/534731","pdf_url":"https://research.chalmers.se/publication/534731/file/534731_Fulltext.pdf","source":{"id":"https://openalex.org/S4306402469","display_name":"Chalmers Research (Chalmers University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66862912","host_organization_name":"Chalmers University of Technology","host_organization_lineage":["https://openalex.org/I66862912"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:strathprints.strath.ac.uk:83974","is_oa":true,"landing_page_url":"https://strathprints.strath.ac.uk/view/author/572613.html>","pdf_url":"https://strathprints.strath.ac.uk/83974/7/Conn_etal_JCIM_2023_Blinded_predictions_and_post_hoc_analysis_of_the_second_solubility_challenge_data.pdf","source":{"id":"https://openalex.org/S4306402226","display_name":"Strathprints: The University of Strathclyde institutional repository (University of Strathclyde)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I181647926","host_organization_name":"University of Strathclyde","host_organization_lineage":["https://openalex.org/I181647926"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"doi:10.1021/acs.jcim.2c01189","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.2c01189","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4998396177","display_name":null,"funder_award_id":"EP/S035990/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5734723116","display_name":"Accelerated Discovery and Development of New Medicines: Prosperity Partnership for a Healthier Nation","funder_award_id":"EP/S035990/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8806317374","display_name":null,"funder_award_id":"PhD studentship","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320307762","display_name":"International Business Machines Corporation","ror":"https://ror.org/05hh8d621"},{"id":"https://openalex.org/F4320307770","display_name":"AstraZeneca","ror":"https://ror.org/04r9x1a08"},{"id":"https://openalex.org/F4320307773","display_name":"GlaxoSmithKline","ror":"https://ror.org/01xsqw823"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1522161842","https://openalex.org/W1966878558","https://openalex.org/W1969416647","https://openalex.org/W1971892118","https://openalex.org/W1998123416","https://openalex.org/W2007697155","https://openalex.org/W2009307057","https://openalex.org/W2022755995","https://openalex.org/W2041392558","https://openalex.org/W2043293105","https://openalex.org/W2046589863","https://openalex.org/W2056301544","https://openalex.org/W2061481072","https://openalex.org/W2066273100","https://openalex.org/W2066363885","https://openalex.org/W2073887042","https://openalex.org/W2101212670","https://openalex.org/W2111624983","https://openalex.org/W2167482691","https://openalex.org/W2169527365","https://openalex.org/W2169678694","https://openalex.org/W2290847742","https://openalex.org/W2486924199","https://openalex.org/W2558486939","https://openalex.org/W2614735173","https://openalex.org/W2623435828","https://openalex.org/W2791355014","https://openalex.org/W2883393965","https://openalex.org/W2885474713","https://openalex.org/W2916902753","https://openalex.org/W2943486999","https://openalex.org/W2964007201","https://openalex.org/W2966797369","https://openalex.org/W2987290416","https://openalex.org/W2999786154","https://openalex.org/W3009410470","https://openalex.org/W3018495986","https://openalex.org/W3049693203","https://openalex.org/W3091066700","https://openalex.org/W3100157108","https://openalex.org/W3159157674","https://openalex.org/W3161955834","https://openalex.org/W3164427032","https://openalex.org/W3205538317","https://openalex.org/W3215002070","https://openalex.org/W4224004818","https://openalex.org/W4224313467","https://openalex.org/W4225876201","https://openalex.org/W4230626473"],"related_works":["https://openalex.org/W2182025991","https://openalex.org/W1973035946","https://openalex.org/W2087491399","https://openalex.org/W2111390454","https://openalex.org/W4383421632","https://openalex.org/W3014788916","https://openalex.org/W2995377144","https://openalex.org/W4378639993","https://openalex.org/W4383382866","https://openalex.org/W2051856999"],"abstract_inverted_index":{"Accurate":[0],"methods":[1],"to":[2,39,67,113,169],"predict":[3],"solubility":[4,149,176,250],"from":[5,229,261],"molecular":[6,87],"structure":[7],"are":[8,163,167],"highly":[9],"sought":[10],"after":[11,139],"in":[12,32,34,71,190,256],"the":[13,18,21,23,44,51,59,68,107,111,115,140,175,181,200,206,254],"chemical":[14,233,259],"sciences.":[15],"To":[16],"assess":[17],"state":[19],"of":[20,43,46,54,61,103,110,128,153,193,199,208,224,232],"art,":[22],"American":[24],"Chemical":[25],"Society":[26],"organized":[27],"a":[28,98,184],"\"Second":[29],"Solubility":[30],"Challenge\"":[31],"2019,":[33],"which":[35,74],"competitors":[36],"were":[37,65,82,95],"invited":[38],"submit":[40],"blinded":[41],"predictions":[42,118,135],"solubilities":[45],"132":[47],"drug-like":[48],"molecules.":[49,105,157],"In":[50,106],"first":[52],"part":[53,109],"this":[55],"article,":[56,112],"we":[57,131],"describe":[58],"development":[60],"two":[62],"models":[63,81,145,201,209],"that":[64,117,161,166,221,241],"submitted":[66],"Blind":[69],"Challenge":[70],"2019":[72],"but":[73,240],"have":[75],"not":[76],"previously":[77],"been":[78],"reported.":[79],"These":[80],"based":[83],"on":[84,97,147,174],"computationally":[85],"inexpensive":[86],"descriptors":[88],"and":[89,94,125,155,214],"traditional":[90],"machine":[91,248],"learning":[92,144,249],"algorithms":[93,124,165],"trained":[96,146],"relatively":[99],"small":[100],"data":[101,150,178,216,228,264],"set":[102],"300":[104],"second":[108],"test":[114],"hypothesis":[116],"would":[119],"improve":[120],"with":[121,136,180],"more":[122],"advanced":[123],"higher":[126],"volumes":[127],"training":[129,215,227,263],"data,":[130],"compare":[132],"these":[133],"original":[134],"those":[137],"made":[138],"deadline":[141],"using":[142,210],"deep":[143],"larger":[148],"sets":[151,213],"consisting":[152],"2999":[154],"5697":[156],"The":[158,218],"results":[159,219],"show":[160],"there":[162],"several":[164],"able":[168],"obtain":[170],"near":[171],"state-of-the-art":[172],"performance":[173,207],"challenge":[177],"sets,":[179],"best":[182],"model,":[183],"graph":[185],"convolutional":[186],"neural":[187],"network,":[188],"resulting":[189],"an":[191],"RMSE":[192],"0.86":[194],"log":[195],"units.":[196],"Critical":[197],"analysis":[198],"reveals":[202],"systematic":[203],"differences":[204],"between":[205],"certain":[211],"feature":[212],"sets.":[217,265],"suggest":[220],"careful":[222],"selection":[223],"high":[225],"quality":[226],"relevant":[230],"regions":[231],"space":[234],"is":[235],"critical":[236],"for":[237,247],"prediction":[238],"accuracy":[239],"other":[242],"methodological":[243],"issues":[244],"remain":[245],"problematic":[246],"models,":[251],"such":[252],"as":[253],"difficulty":[255],"modeling":[257],"complex":[258],"spaces":[260],"sparse":[262]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5}],"updated_date":"2026-04-16T15:07:20.185449","created_date":"2025-10-10T00:00:00"}