{"id":"https://openalex.org/W4415666428","doi":"https://doi.org/10.1186/s13321-025-01103-3","title":"Enhancing molecular property prediction through data integration and consistency assessment","display_name":"Enhancing molecular property prediction through data integration and consistency assessment","publication_year":2025,"publication_date":"2025-10-29","ids":{"openalex":"https://openalex.org/W4415666428","doi":"https://doi.org/10.1186/s13321-025-01103-3","pmid":"https://pubmed.ncbi.nlm.nih.gov/41163219"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-025-01103-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01103-3","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01103-3","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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/s13321-025-01103-3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116467638","display_name":"Raquel Parrondo-Pizarro","orcid":null},"institutions":[{"id":"https://openalex.org/I251424209","display_name":"Universitat de Girona","ror":"https://ror.org/01xdxns91","country_code":"ES","type":"education","lineage":["https://openalex.org/I251424209"]},{"id":"https://openalex.org/I4210166526","display_name":"Institut de Biologia Molecular de Barcelona","ror":"https://ror.org/05t8khn72","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210166526"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Raquel Parrondo-Pizarro","raw_affiliation_strings":["Chemotargets SL, Parc Cientific de Barcelona, Baldiri Reixac 4 (TR-03), 08028, Barcelona, Catalonia, Spain","Institut de Quimica Computacional i Catalisi, Facultat de Ciencies, Universitat de Girona, Maria Aurelia Capmany 69, 17003, Girona, Catalonia, Spain"],"affiliations":[{"raw_affiliation_string":"Chemotargets SL, Parc Cientific de Barcelona, Baldiri Reixac 4 (TR-03), 08028, Barcelona, Catalonia, Spain","institution_ids":["https://openalex.org/I4210166526"]},{"raw_affiliation_string":"Institut de Quimica Computacional i Catalisi, Facultat de Ciencies, Universitat de Girona, Maria Aurelia Capmany 69, 17003, Girona, Catalonia, Spain","institution_ids":["https://openalex.org/I251424209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025924664","display_name":"Luca Menestrina","orcid":"https://orcid.org/0000-0002-3397-7737"},"institutions":[{"id":"https://openalex.org/I4210166526","display_name":"Institut de Biologia Molecular de Barcelona","ror":"https://ror.org/05t8khn72","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210166526"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Luca Menestrina","raw_affiliation_strings":["Chemotargets SL, Parc Cientific de Barcelona, Baldiri Reixac 4 (TR-03), 08028, Barcelona, Catalonia, Spain"],"affiliations":[{"raw_affiliation_string":"Chemotargets SL, Parc Cientific de Barcelona, Baldiri Reixac 4 (TR-03), 08028, Barcelona, Catalonia, Spain","institution_ids":["https://openalex.org/I4210166526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077097006","display_name":"Ricard Garc\u00eda-Serna","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166526","display_name":"Institut de Biologia Molecular de Barcelona","ror":"https://ror.org/05t8khn72","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210166526"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ricard Garcia-Serna","raw_affiliation_strings":["Chemotargets SL, Parc Cientific de Barcelona, Baldiri Reixac 4 (TR-03), 08028, Barcelona, Catalonia, Spain"],"affiliations":[{"raw_affiliation_string":"Chemotargets SL, Parc Cientific de Barcelona, Baldiri Reixac 4 (TR-03), 08028, Barcelona, Catalonia, Spain","institution_ids":["https://openalex.org/I4210166526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003706895","display_name":"Adri\u00e0 Fern\u00e1ndez\u2010Torras","orcid":"https://orcid.org/0000-0003-3244-9948"},"institutions":[{"id":"https://openalex.org/I4210094501","display_name":"Ferrer Grupo (Spain)","ror":"https://ror.org/00mwcg389","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210094501"]},{"id":"https://openalex.org/I4210166526","display_name":"Institut de Biologia Molecular de Barcelona","ror":"https://ror.org/05t8khn72","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210166526"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Adri\u00e0 Fern\u00e1ndez-Torras","raw_affiliation_strings":["Chemotargets SL, Parc Cientific de Barcelona, Baldiri Reixac 4 (TR-03), 08028, Barcelona, Catalonia, Spain. adria.fernandez@chemotargets.com","Chemotargets SL, Parc Cientific de Barcelona, Baldiri Reixac 4 (TR-03), 08028, Barcelona, Catalonia, Spain"],"affiliations":[{"raw_affiliation_string":"Chemotargets SL, Parc Cientific de Barcelona, Baldiri Reixac 4 (TR-03), 08028, Barcelona, Catalonia, Spain. adria.fernandez@chemotargets.com","institution_ids":["https://openalex.org/I4210094501"]},{"raw_affiliation_string":"Chemotargets SL, Parc Cientific de Barcelona, Baldiri Reixac 4 (TR-03), 08028, Barcelona, Catalonia, Spain","institution_ids":["https://openalex.org/I4210166526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052116809","display_name":"Jordi Mestres","orcid":"https://orcid.org/0000-0002-5202-4501"},"institutions":[{"id":"https://openalex.org/I251424209","display_name":"Universitat de Girona","ror":"https://ror.org/01xdxns91","country_code":"ES","type":"education","lineage":["https://openalex.org/I251424209"]},{"id":"https://openalex.org/I4210166526","display_name":"Institut de Biologia Molecular de Barcelona","ror":"https://ror.org/05t8khn72","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210166526"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jordi Mestres","raw_affiliation_strings":["Chemotargets SL, Parc Cientific de Barcelona, Baldiri Reixac 4 (TR-03), 08028, Barcelona, Catalonia, Spain. jordi.mestres@udg.edu","Institut de Quimica Computacional i Catalisi, Facultat de Ciencies, Universitat de Girona, Maria Aurelia Capmany 69, 17003, Girona, Catalonia, Spain. jordi.mestres@udg.edu","Institut de Quimica Computacional i Catalisi, Facultat de Ciencies, Universitat de Girona, Maria Aurelia Capmany 69, 17003, Girona, Catalonia, Spain","Chemotargets SL, Parc Cientific de Barcelona, Baldiri Reixac 4 (TR-03), 08028, Barcelona, Catalonia, Spain"],"affiliations":[{"raw_affiliation_string":"Chemotargets SL, Parc Cientific de Barcelona, Baldiri Reixac 4 (TR-03), 08028, Barcelona, Catalonia, Spain. jordi.mestres@udg.edu","institution_ids":["https://openalex.org/I4210166526"]},{"raw_affiliation_string":"Institut de Quimica Computacional i Catalisi, Facultat de Ciencies, Universitat de Girona, Maria Aurelia Capmany 69, 17003, Girona, Catalonia, Spain. jordi.mestres@udg.edu","institution_ids":["https://openalex.org/I251424209"]},{"raw_affiliation_string":"Institut de Quimica Computacional i Catalisi, Facultat de Ciencies, Universitat de Girona, Maria Aurelia Capmany 69, 17003, Girona, Catalonia, Spain","institution_ids":["https://openalex.org/I251424209"]},{"raw_affiliation_string":"Chemotargets SL, Parc Cientific de Barcelona, Baldiri Reixac 4 (TR-03), 08028, Barcelona, Catalonia, Spain","institution_ids":["https://openalex.org/I4210166526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5116467638"],"corresponding_institution_ids":["https://openalex.org/I251424209","https://openalex.org/I4210166526"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":5.3028,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.96025494,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"17","issue":"1","first_page":"163","last_page":"163"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.8820000290870667,"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":0.8820000290870667,"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":0.027899999171495438,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.02410000003874302,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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/data-integration","display_name":"Data integration","score":0.656000018119812},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6201000213623047},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5913000106811523},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.5396999716758728},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.460099995136261},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4083999991416931},{"id":"https://openalex.org/keywords/adme","display_name":"ADME","score":0.38510000705718994},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.35600000619888306},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.35339999198913574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7767000198364258},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.656000018119812},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6201000213623047},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5913000106811523},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.5396999716758728},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48890000581741333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4749000072479248},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.460099995136261},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4374000132083893},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4083999991416931},{"id":"https://openalex.org/C69366308","wikidata":"https://www.wikidata.org/wiki/Q2272286","display_name":"ADME","level":3,"score":0.38510000705718994},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28999999165534973},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C19443361","wikidata":"https://www.wikidata.org/wiki/Q5282533","display_name":"Disparate system","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C163763905","wikidata":"https://www.wikidata.org/wiki/Q17075943","display_name":"Precision medicine","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C93361087","wikidata":"https://www.wikidata.org/wiki/Q4426698","display_name":"Data consistency","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.25870001316070557}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-025-01103-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01103-3","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01103-3","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:41163219","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41163219","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:a1c1a60a91c9450191fccee300bbbfed","is_oa":true,"landing_page_url":"https://doaj.org/article/a1c1a60a91c9450191fccee300bbbfed","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 17, Iss 1, Pp 1-13 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11383782","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12574261","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13321-025-01103-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01103-3","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01103-3","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415666428.pdf"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W1993046136","https://openalex.org/W2011301426","https://openalex.org/W2012929832","https://openalex.org/W2017983838","https://openalex.org/W2020987809","https://openalex.org/W2027179985","https://openalex.org/W2036846365","https://openalex.org/W2056085393","https://openalex.org/W2067468321","https://openalex.org/W2070685035","https://openalex.org/W2096541451","https://openalex.org/W2108458189","https://openalex.org/W2112182981","https://openalex.org/W2114672790","https://openalex.org/W2118630726","https://openalex.org/W2140084077","https://openalex.org/W2162723974","https://openalex.org/W2169667658","https://openalex.org/W2547330766","https://openalex.org/W2605020949","https://openalex.org/W2767714545","https://openalex.org/W2889326414","https://openalex.org/W2892221324","https://openalex.org/W2895723582","https://openalex.org/W2935857979","https://openalex.org/W2943018619","https://openalex.org/W2944466104","https://openalex.org/W2966797369","https://openalex.org/W2995175648","https://openalex.org/W3003257820","https://openalex.org/W3009999522","https://openalex.org/W3014413945","https://openalex.org/W3041133507","https://openalex.org/W3118566429","https://openalex.org/W3135127269","https://openalex.org/W3150635270","https://openalex.org/W3181995918","https://openalex.org/W3201677331","https://openalex.org/W3204865406","https://openalex.org/W4206019131","https://openalex.org/W4211238337","https://openalex.org/W4231421929","https://openalex.org/W4239082087","https://openalex.org/W4292616203","https://openalex.org/W4388455891","https://openalex.org/W4389143327","https://openalex.org/W4391752856","https://openalex.org/W4392741075","https://openalex.org/W4393410409","https://openalex.org/W4393936599","https://openalex.org/W4395481566","https://openalex.org/W4396978695","https://openalex.org/W4403678603","https://openalex.org/W4404511389","https://openalex.org/W4404642710","https://openalex.org/W4405621216","https://openalex.org/W4408067738","https://openalex.org/W4408161267","https://openalex.org/W4408213163","https://openalex.org/W4408444355","https://openalex.org/W4409235233","https://openalex.org/W4414127859"],"related_works":[],"abstract_inverted_index":{"Data":[0,63,96],"heterogeneity":[1],"and":[2,34,56,91,101,148,156,179],"distributional":[3],"misalignments":[4,47],"pose":[5],"critical":[6],"challenges":[7,17],"for":[8],"machine":[9],"learning":[10,169,174],"models,":[11],"often":[12],"compromising":[13],"predictive":[14,115],"accuracy.":[15],"These":[16,65],"are":[18],"exemplified":[19],"in":[20,27,73,79,114,167],"preclinical":[21,159],"safety":[22],"modeling,":[23],"a":[24,132,141,164],"crucial":[25,165],"step":[26],"early-stage":[28],"drug":[29],"discovery":[30],"where":[31],"limited":[32],"data":[33,80,123,177],"experimental":[35,77],"constraints":[36],"exacerbate":[37],"integration":[38,182],"issues.":[39],"Analyzing":[40],"public":[41],"ADME":[42],"datasets,":[43,137],"we":[44,138],"uncovered":[45],"significant":[46],"as":[48,50,61,82,84],"well":[49,83],"inconsistent":[51],"property":[52],"annotations":[53],"between":[54],"gold-standard":[55],"popular":[57],"benchmark":[58],"sources,":[59],"such":[60],"Therapeutic":[62],"Commons.":[64],"dataset":[66],"discrepancies,":[67],"which":[68],"can":[69,88,162],"arise":[70],"from":[71],"differences":[72],"various":[74],"factors,":[75],"including":[76],"conditions":[78],"collection":[81],"chemical":[85],"space":[86],"coverage,":[87],"introduce":[89],"noise":[90],"ultimately":[92],"degrade":[93],"model":[94],"performance.":[95,116],"standardization,":[97],"despite":[98],"harmonizing":[99],"discrepancies":[100],"increasing":[102],"the":[103,119],"training":[104],"set":[105],"size,":[106],"may":[107],"not":[108],"always":[109],"lead":[110],"to":[111,128,151],"an":[112],"improvement":[113],"This":[117],"highlights":[118],"importance":[120],"of":[121],"rigorous":[122],"consistency":[124],"assessment":[125],"(DCA)":[126],"prior":[127],"modeling.":[129],"To":[130],"facilitate":[131],"systematic":[133],"DCA":[134,161],"across":[135,175,183],"diverse":[136,184],"developed":[139],"AssayInspector,":[140],"model-agnostic":[142],"package":[143],"that":[144],"leverages":[145],"statistics,":[146],"visualizations,":[147],"diagnostic":[149],"summaries":[150],"identify":[152],"outliers,":[153],"batch":[154],"effects,":[155],"discrepancies.":[157],"Beyond":[158],"safety,":[160],"play":[163],"role":[166],"federated":[168],"scenarios,":[170],"enabling":[171],"effective":[172],"transfer":[173],"heterogeneous":[176],"sources":[178],"supporting":[180],"reliable":[181],"scientific":[185],"domains.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-04-24T08:23:43.765630","created_date":"2025-10-29T00:00:00"}
