{"id":"https://openalex.org/W4412530104","doi":"https://doi.org/10.1186/s13321-025-01041-0","title":"Benchmarking ML in ADMET predictions: the practical impact of feature representations in ligand-based models","display_name":"Benchmarking ML in ADMET predictions: the practical impact of feature representations in ligand-based models","publication_year":2025,"publication_date":"2025-07-21","ids":{"openalex":"https://openalex.org/W4412530104","doi":"https://doi.org/10.1186/s13321-025-01041-0","pmid":"https://pubmed.ncbi.nlm.nih.gov/40691635"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-025-01041-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01041-0","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01041-0","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01041-0","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000823676","display_name":"Gintautas Kamuntavi\u010dius","orcid":"https://orcid.org/0000-0001-5141-4535"},"institutions":[{"id":"https://openalex.org/I96749437","display_name":"Texas A&M University \u2013 Corpus Christi","ror":"https://ror.org/01mrfdz82","country_code":"US","type":"education","lineage":["https://openalex.org/I96749437"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gintautas Kamuntavi\u010dius","raw_affiliation_strings":["AI Chemistry, Ro5, 2801 Gateway Drive, 75063, Irving, TX, USA. gkamuntavicius@ro5.ai"],"affiliations":[{"raw_affiliation_string":"AI Chemistry, Ro5, 2801 Gateway Drive, 75063, Irving, TX, USA. gkamuntavicius@ro5.ai","institution_ids":["https://openalex.org/I96749437"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043001553","display_name":"Tanya Paquet","orcid":"https://orcid.org/0000-0001-8847-3977"},"institutions":[{"id":"https://openalex.org/I182980787","display_name":"University of Dallas","ror":"https://ror.org/00v3ak792","country_code":"US","type":"education","lineage":["https://openalex.org/I182980787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanya Paquet","raw_affiliation_strings":["AI Chemistry, Ro5, 2801 Gateway Drive, 75063, Irving, TX, USA"],"affiliations":[{"raw_affiliation_string":"AI Chemistry, Ro5, 2801 Gateway Drive, 75063, Irving, TX, USA","institution_ids":["https://openalex.org/I182980787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054350377","display_name":"Orestis Bastas","orcid":null},"institutions":[{"id":"https://openalex.org/I182980787","display_name":"University of Dallas","ror":"https://ror.org/00v3ak792","country_code":"US","type":"education","lineage":["https://openalex.org/I182980787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Orestis Bastas","raw_affiliation_strings":["AI Chemistry, Ro5, 2801 Gateway Drive, 75063, Irving, TX, USA"],"affiliations":[{"raw_affiliation_string":"AI Chemistry, Ro5, 2801 Gateway Drive, 75063, Irving, TX, USA","institution_ids":["https://openalex.org/I182980787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095746212","display_name":"Dainius \u0160alkauskas","orcid":null},"institutions":[{"id":"https://openalex.org/I182980787","display_name":"University of Dallas","ror":"https://ror.org/00v3ak792","country_code":"US","type":"education","lineage":["https://openalex.org/I182980787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dainius \u0160alkauskas","raw_affiliation_strings":["AI Chemistry, Ro5, 2801 Gateway Drive, 75063, Irving, TX, USA"],"affiliations":[{"raw_affiliation_string":"AI Chemistry, Ro5, 2801 Gateway Drive, 75063, Irving, TX, USA","institution_ids":["https://openalex.org/I182980787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055123789","display_name":"Alvaro Prat","orcid":"https://orcid.org/0000-0003-0094-6659"},"institutions":[{"id":"https://openalex.org/I182980787","display_name":"University of Dallas","ror":"https://ror.org/00v3ak792","country_code":"US","type":"education","lineage":["https://openalex.org/I182980787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alvaro Prat","raw_affiliation_strings":["AI Chemistry, Ro5, 2801 Gateway Drive, 75063, Irving, TX, USA"],"affiliations":[{"raw_affiliation_string":"AI Chemistry, Ro5, 2801 Gateway Drive, 75063, Irving, TX, USA","institution_ids":["https://openalex.org/I182980787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031627472","display_name":"Hisham Abdel Aty","orcid":null},"institutions":[{"id":"https://openalex.org/I182980787","display_name":"University of Dallas","ror":"https://ror.org/00v3ak792","country_code":"US","type":"education","lineage":["https://openalex.org/I182980787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hisham Abdel Aty","raw_affiliation_strings":["AI Chemistry, Ro5, 2801 Gateway Drive, 75063, Irving, TX, USA"],"affiliations":[{"raw_affiliation_string":"AI Chemistry, Ro5, 2801 Gateway Drive, 75063, Irving, TX, USA","institution_ids":["https://openalex.org/I182980787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007707223","display_name":"Aurimas Pabrinkis","orcid":null},"institutions":[{"id":"https://openalex.org/I182980787","display_name":"University of Dallas","ror":"https://ror.org/00v3ak792","country_code":"US","type":"education","lineage":["https://openalex.org/I182980787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aurimas Pabrinkis","raw_affiliation_strings":["AI Chemistry, Ro5, 2801 Gateway Drive, 75063, Irving, TX, USA"],"affiliations":[{"raw_affiliation_string":"AI Chemistry, Ro5, 2801 Gateway Drive, 75063, Irving, TX, USA","institution_ids":["https://openalex.org/I182980787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025230471","display_name":"Povilas Norvai\u0161as","orcid":"https://orcid.org/0000-0003-4790-9820"},"institutions":[{"id":"https://openalex.org/I182980787","display_name":"University of Dallas","ror":"https://ror.org/00v3ak792","country_code":"US","type":"education","lineage":["https://openalex.org/I182980787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Povilas Norvai\u0161as","raw_affiliation_strings":["AI Chemistry, Ro5, 2801 Gateway Drive, 75063, Irving, TX, USA"],"affiliations":[{"raw_affiliation_string":"AI Chemistry, Ro5, 2801 Gateway Drive, 75063, Irving, TX, USA","institution_ids":["https://openalex.org/I182980787"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071326210","display_name":"Roy Tal","orcid":"https://orcid.org/0000-0001-8551-2547"},"institutions":[{"id":"https://openalex.org/I182980787","display_name":"University of Dallas","ror":"https://ror.org/00v3ak792","country_code":"US","type":"education","lineage":["https://openalex.org/I182980787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roy Tal","raw_affiliation_strings":["AI Chemistry, Ro5, 2801 Gateway Drive, 75063, Irving, TX, USA"],"affiliations":[{"raw_affiliation_string":"AI Chemistry, Ro5, 2801 Gateway Drive, 75063, Irving, TX, USA","institution_ids":["https://openalex.org/I182980787"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5000823676"],"corresponding_institution_ids":["https://openalex.org/I96749437"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":7.8437,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.97485876,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"17","issue":"1","first_page":"108","last_page":"108"},"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":0.9961000084877014,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9697999954223633,"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/benchmarking","display_name":"Benchmarking","score":0.826188325881958},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.684848427772522},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6630975604057312},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4361456632614136},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.39694744348526},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33717775344848633},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.06753650307655334}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.826188325881958},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.684848427772522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6630975604057312},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4361456632614136},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39694744348526},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33717775344848633},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.06753650307655334},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-025-01041-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01041-0","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01041-0","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:40691635","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40691635","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:6ac75c56e74044d2a666b651a794d6f3","is_oa":true,"landing_page_url":"https://doaj.org/article/6ac75c56e74044d2a666b651a794d6f3","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 1-40 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11093365","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12281724","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13321-025-01041-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01041-0","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01041-0","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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412530104.pdf","grobid_xml":"https://content.openalex.org/works/W4412530104.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1857789879","https://openalex.org/W1966716734","https://openalex.org/W1971849220","https://openalex.org/W1976526581","https://openalex.org/W1988037271","https://openalex.org/W2021748110","https://openalex.org/W2022978420","https://openalex.org/W2064440950","https://openalex.org/W2087561463","https://openalex.org/W2097100227","https://openalex.org/W2119821739","https://openalex.org/W2221103459","https://openalex.org/W2535436227","https://openalex.org/W2777416523","https://openalex.org/W2911964244","https://openalex.org/W2962862931","https://openalex.org/W3111216799","https://openalex.org/W4205801901","https://openalex.org/W4241727697","https://openalex.org/W4283750463","https://openalex.org/W4296551289","https://openalex.org/W4306873926","https://openalex.org/W4313485929","https://openalex.org/W4376131490","https://openalex.org/W4377232456","https://openalex.org/W4387617009","https://openalex.org/W4390221451","https://openalex.org/W4398765742","https://openalex.org/W4404079238","https://openalex.org/W4407319372","https://openalex.org/W6600590830"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967","https://openalex.org/W2112883198"],"abstract_inverted_index":{"This":[0,90],"study,":[1],"focusing":[2],"on":[3,79,86,169,173],"predicting":[4],"Absorption,":[5],"Distribution,":[6],"Metabolism,":[7],"Excretion,":[8],"and":[9,103],"Toxicology":[10],"(ADMET)":[11],"properties,":[12],"addresses":[13],"the":[14,37,66,95,144,158],"key":[15],"challenges":[16],"of":[17,40,63,82,97],"ML":[18],"models":[19,77,148,167],"trained":[20,78,168],"using":[21,179],"ligand-based":[22],"representations.":[23],"We":[24,116],"propose":[25],"a":[26,34,61,73,87,110,153],"structured":[27,111],"approach":[28,91,112],"to":[29,65,93,113],"data":[30,83,181],"feature":[31,114,141],"selection,":[32,142],"taking":[33],"step":[35],"beyond":[36,140],"conventional":[38],"practice":[39],"combining":[41,121],"different":[42,88],"representations":[43],"without":[44],"systematic":[45],"reasoning.":[46],"Additionally,":[47,162],"we":[48,163],"enhance":[49],"model":[50,67,105,118],"evaluation":[51,119],"methods":[52],"by":[53,120],"integrating":[54],"cross-validation":[55,122],"with":[56,123],"statistical":[57,124],"hypothesis":[58,125],"testing,":[59,126],"adding":[60],"layer":[62],"reliability":[64,96],"assessments.":[68],"Our":[69],"final":[70],"evaluations":[71],"include":[72],"practical":[74,176],"scenario,":[75],"where":[76],"one":[80,170],"source":[81],"are":[84],"evaluated":[85],"one.":[89],"aims":[92],"bolster":[94],"ADMET":[98,159],"predictions,":[99],"providing":[100],"more":[101,129],"dependable":[102],"informative":[104],"evaluations.Scientific":[106],"contributionThis":[107],"study":[108,136],"provided":[109],"selection.":[115],"improve":[117],"making":[127],"results":[128],"reliable.":[130],"The":[131],"methodology":[132],"used":[133],"in":[134,146,152,182],"our":[135],"can":[137],"be":[138],"generalized":[139],"boosting":[143],"confidence":[145],"selected":[147],"which":[149],"is":[150],"crucial":[151],"noisy":[154],"domain":[155],"such":[156],"as":[157],"prediction":[160],"tasks.":[161],"assess":[164],"how":[165],"well":[166],"dataset":[171],"perform":[172],"another,":[174],"offering":[175],"insights":[177],"for":[178],"external":[180],"drug":[183],"discovery.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
