{"id":"https://openalex.org/W2974928461","doi":"https://doi.org/10.1021/acs.jcim.9b00476","title":"New Workflow for QSAR Model Development from Small Data Sets: Small Dataset Curator and Small Dataset Modeler. Integration of Data Curation, Exhaustive Double Cross-Validation, and a Set of Optimal Model Selection Techniques","display_name":"New Workflow for QSAR Model Development from Small Data Sets: Small Dataset Curator and Small Dataset Modeler. Integration of Data Curation, Exhaustive Double Cross-Validation, and a Set of Optimal Model Selection Techniques","publication_year":2019,"publication_date":"2019-09-16","ids":{"openalex":"https://openalex.org/W2974928461","doi":"https://doi.org/10.1021/acs.jcim.9b00476","mag":"2974928461","pmid":"https://pubmed.ncbi.nlm.nih.gov/31525295"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.9b00476","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.9b00476","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":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000323690","display_name":"Pravin Ambure","orcid":"https://orcid.org/0000-0001-7244-7117"},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]},{"id":"https://openalex.org/I4210138594","display_name":"Rede de Qu\u00edmica e Tecnologia","ror":"https://ror.org/04j14t006","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210138594"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Pravin Ambure","raw_affiliation_strings":["LAQV@REQUIMTE/Department of Chemistry and Biochemistry, University of Porto, 4169-007 Porto, Portugal"],"raw_orcid":"https://orcid.org/0000-0001-7244-7117","affiliations":[{"raw_affiliation_string":"LAQV@REQUIMTE/Department of Chemistry and Biochemistry, University of Porto, 4169-007 Porto, Portugal","institution_ids":["https://openalex.org/I182534213","https://openalex.org/I4210138594"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045359803","display_name":"Agnieszka Gajewicz","orcid":"https://orcid.org/0000-0001-7702-210X"},"institutions":[{"id":"https://openalex.org/I40413290","display_name":"University of Gda\u0144sk","ror":"https://ror.org/011dv8m48","country_code":"PL","type":"education","lineage":["https://openalex.org/I40413290"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Agnieszka Gajewicz-Skretna","raw_affiliation_strings":["Laboratory of Environmental Chemometrics, Faculty of Chemistry, University of Gdansk, Gdansk 80-308, Poland"],"raw_orcid":"https://orcid.org/0000-0001-7702-210X","affiliations":[{"raw_affiliation_string":"Laboratory of Environmental Chemometrics, Faculty of Chemistry, University of Gdansk, Gdansk 80-308, Poland","institution_ids":["https://openalex.org/I40413290"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031900984","display_name":"M. Nat\u00e1lia D. S. Cordeiro","orcid":"https://orcid.org/0000-0003-3375-8670"},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]},{"id":"https://openalex.org/I4210138594","display_name":"Rede de Qu\u00edmica e Tecnologia","ror":"https://ror.org/04j14t006","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210138594"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"M. Natalia D. S. Cordeiro","raw_affiliation_strings":["LAQV@REQUIMTE/Department of Chemistry and Biochemistry, University of Porto, 4169-007 Porto, Portugal"],"raw_orcid":"https://orcid.org/0000-0003-3375-8670","affiliations":[{"raw_affiliation_string":"LAQV@REQUIMTE/Department of Chemistry and Biochemistry, University of Porto, 4169-007 Porto, Portugal","institution_ids":["https://openalex.org/I182534213","https://openalex.org/I4210138594"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087029647","display_name":"Kunal Roy","orcid":"https://orcid.org/0000-0003-4486-8074"},"institutions":[{"id":"https://openalex.org/I170979836","display_name":"Jadavpur University","ror":"https://ror.org/02af4h012","country_code":"IN","type":"education","lineage":["https://openalex.org/I170979836"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Kunal Roy","raw_affiliation_strings":["Drug Theoretics and Cheminformatics Laboratory, Department of Pharmaceutical Technology, Jadavpur University, Kolkata 700032, India"],"raw_orcid":"https://orcid.org/0000-0003-4486-8074","affiliations":[{"raw_affiliation_string":"Drug Theoretics and Cheminformatics Laboratory, Department of Pharmaceutical Technology, Jadavpur University, Kolkata 700032, India","institution_ids":["https://openalex.org/I170979836"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5087029647"],"corresponding_institution_ids":["https://openalex.org/I170979836"],"apc_list":null,"apc_paid":null,"fwci":7.3987,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.97633376,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"59","issue":"10","first_page":"4070","last_page":"4076"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9659000039100647,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.8483914136886597},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7868534326553345},{"id":"https://openalex.org/keywords/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.7425921559333801},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6358274817466736},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.6111406087875366},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.6007750034332275},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.5472209453582764},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5220577716827393},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.49959230422973633},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44863009452819824},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32495903968811035},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.23938581347465515}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8483914136886597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7868534326553345},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.7425921559333801},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6358274817466736},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.6111406087875366},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.6007750034332275},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.5472209453582764},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5220577716827393},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.49959230422973633},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44863009452819824},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32495903968811035},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.23938581347465515},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D066264","descriptor_name":"Datasets as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D066264","descriptor_name":"Datasets as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D066264","descriptor_name":"Datasets as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.9b00476","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.9b00476","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:31525295","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31525295","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}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2","score":0.47999998927116394}],"awards":[{"id":"https://openalex.org/G2651885736","display_name":null,"funder_award_id":"UMO-2016/23/D/NZ7/03973 (SONATA-12)","funder_id":"https://openalex.org/F4320322511","funder_display_name":"Narodowe Centrum Nauki"},{"id":"https://openalex.org/G4473710813","display_name":null,"funder_award_id":"PTDC/QUI-QIN/30649/2017","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G6967460350","display_name":null,"funder_award_id":"UID/QUI/50006/2019","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320320767","display_name":"University Grants Commission","ror":"https://ror.org/04p800546"},{"id":"https://openalex.org/F4320322511","display_name":"Narodowe Centrum Nauki","ror":"https://ror.org/03ha2q922"},{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W911658671","https://openalex.org/W1645298096","https://openalex.org/W1964153265","https://openalex.org/W1964922707","https://openalex.org/W1968036702","https://openalex.org/W1977573154","https://openalex.org/W2015928143","https://openalex.org/W2038703062","https://openalex.org/W2057069496","https://openalex.org/W2067642251","https://openalex.org/W2076018148","https://openalex.org/W2112415299","https://openalex.org/W2127019019","https://openalex.org/W2128245586","https://openalex.org/W2157851318","https://openalex.org/W2254686952","https://openalex.org/W2267945123","https://openalex.org/W2293921324","https://openalex.org/W2398789413","https://openalex.org/W2412746331","https://openalex.org/W2503169225","https://openalex.org/W2520468066","https://openalex.org/W2536561253","https://openalex.org/W2549115005","https://openalex.org/W2617796567","https://openalex.org/W2765630795","https://openalex.org/W2784226073","https://openalex.org/W2791494189","https://openalex.org/W2792618216","https://openalex.org/W2802385907","https://openalex.org/W2903800243","https://openalex.org/W4234629256","https://openalex.org/W4235413268"],"related_works":["https://openalex.org/W2382340815","https://openalex.org/W1972650408","https://openalex.org/W2551736466","https://openalex.org/W1997566113","https://openalex.org/W3189652131","https://openalex.org/W2908740012","https://openalex.org/W1967793880","https://openalex.org/W2792066564","https://openalex.org/W1186905254","https://openalex.org/W2898703579"],"abstract_inverted_index":{",":[0],"to":[1,26],"effortlessly":[2],"execute":[3],"the":[4,28,31,47,52],"proposed":[5,32],"workflow.":[6],"These":[7],"tools":[8],"are":[9],"freely":[10],"available":[11],"for":[12,37],"download":[13],"from":[14],"https://dtclab.webs.com/software-tools":[15],".":[16],"We":[17],"have":[18],"performed":[19],"case":[20,43],"studies":[21,44],"employing":[22],"seven":[23],"diverse":[24],"datasets":[25],"demonstrate":[27],"performance":[29],"of":[30,51],"scheme":[33],"(including":[34],"data":[35],"curation)":[36],"small":[38],"dataset":[39],"QSAR":[40],"modeling.":[41],"The":[42],"also":[45],"confirm":[46],"usability":[48],"and":[49],"stability":[50],"developed":[53],"software":[54],"tools.":[55]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}
