{"id":"https://openalex.org/W7214927326","doi":"https://doi.org/10.26434/chemrxiv.15009691/v1","title":"Small-Molecule Data Splitting for Machine Learning in Drug Design","display_name":"Small-Molecule Data Splitting for Machine Learning in Drug Design","publication_year":2026,"publication_date":"2026-09-30","ids":{"openalex":"https://openalex.org/W7214927326","doi":"https://doi.org/10.26434/chemrxiv.15009691/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15009691/v1","doi":"https://doi.org/10.26434/chemrxiv.15009691/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15009691/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009691/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009691/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111241538","display_name":"Cao-Minh Truong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I154526488","display_name":"Inserm","ror":"https://ror.org/02vjkv261","country_code":"FR","type":"government","lineage":["https://openalex.org/I154526488"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Cao-Minh Truong","raw_affiliation_strings":["INSERM ERL","Universit\u00e9 Paris Cit\u00e9"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INSERM ERL","institution_ids":["https://openalex.org/I154526488"]},{"raw_affiliation_string":"Universit\u00e9 Paris Cit\u00e9","institution_ids":["https://openalex.org/I204730241"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093204377","display_name":"Van-Thinh To","orcid":"https://orcid.org/0000-0002-7640-0807","observed_orcids":["https://orcid.org/0000-0002-7640-0807","https://orcid.org/0009-0001-5379-1593"]},"institutions":[{"id":"https://openalex.org/I154526488","display_name":"Inserm","ror":"https://ror.org/02vjkv261","country_code":"FR","type":"government","lineage":["https://openalex.org/I154526488"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Van-Thinh To","raw_affiliation_strings":["INSERM ERL","Universit\u00e9 Paris Cit\u00e9"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INSERM ERL","institution_ids":["https://openalex.org/I154526488"]},{"raw_affiliation_string":"Universit\u00e9 Paris Cit\u00e9","institution_ids":["https://openalex.org/I204730241"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093204378","display_name":"Gia-Bao Truong","orcid":"https://orcid.org/0009-0001-5379-1593","observed_orcids":["https://orcid.org/0009-0001-5379-1593"]},"institutions":[{"id":"https://openalex.org/I154526488","display_name":"Inserm","ror":"https://ror.org/02vjkv261","country_code":"FR","type":"government","lineage":["https://openalex.org/I154526488"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gia-Bao Truong","raw_affiliation_strings":["INSERM ERL","Universit\u00e9 Paris Cit\u00e9"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INSERM ERL","institution_ids":["https://openalex.org/I154526488"]},{"raw_affiliation_string":"Universit\u00e9 Paris Cit\u00e9","institution_ids":["https://openalex.org/I204730241"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069625039","display_name":"Alexey A. Orlov","orcid":"https://orcid.org/0000-0002-0597-7705","observed_orcids":["https://orcid.org/0000-0002-0597-7705","https://orcid.org/0000-0001-7889-9245"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I68947357","display_name":"Universit\u00e9 de Strasbourg","ror":"https://ror.org/00pg6eq24","country_code":"FR","type":"education","lineage":["https://openalex.org/I68947357"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Alexey Orlov","raw_affiliation_strings":["CNRS UMR","University of Strasbourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS UMR","institution_ids":["https://openalex.org/I1294671590"]},{"raw_affiliation_string":"University of Strasbourg","institution_ids":["https://openalex.org/I68947357"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005597587","display_name":"Pedro J. Ballester","orcid":"https://orcid.org/0000-0002-4078-743X","observed_orcids":["https://orcid.org/0000-0002-4078-743X","https://orcid.org/0000-0002-1367-152X"]},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pedro J. Ballester","raw_affiliation_strings":["Department of Bioengineering","Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Bioengineering","institution_ids":[]},{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005294445","display_name":"Olivier Taboureau","orcid":"https://orcid.org/0000-0001-7081-2491","observed_orcids":["https://orcid.org/0000-0001-7081-2491"]},"institutions":[{"id":"https://openalex.org/I154526488","display_name":"Inserm","ror":"https://ror.org/02vjkv261","country_code":"FR","type":"government","lineage":["https://openalex.org/I154526488"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Taboureau","raw_affiliation_strings":["INSERM ERL","Universit\u00e9 Paris Cit\u00e9"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INSERM ERL","institution_ids":["https://openalex.org/I154526488"]},{"raw_affiliation_string":"Universit\u00e9 Paris Cit\u00e9","institution_ids":["https://openalex.org/I204730241"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014611705","display_name":"Viet\u2010Khoa Tran\u2010Nguyen","orcid":"https://orcid.org/0000-0001-7497-333X","observed_orcids":["https://orcid.org/0000-0001-7497-333X"]},"institutions":[{"id":"https://openalex.org/I154526488","display_name":"Inserm","ror":"https://ror.org/02vjkv261","country_code":"FR","type":"government","lineage":["https://openalex.org/I154526488"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Viet-Khoa Tran-Nguyen","raw_affiliation_strings":["INSERM ERL","Universit\u00e9 Paris Cit\u00e9"],"raw_orcid":"https://orcid.org/0000-0001-7497-333X","affiliations":[{"raw_affiliation_string":"INSERM ERL","institution_ids":["https://openalex.org/I154526488"]},{"raw_affiliation_string":"Universit\u00e9 Paris Cit\u00e9","institution_ids":["https://openalex.org/I204730241"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.0010999999940395355,"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/T10002","display_name":"Advanced Chemical Physics Studies","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-partitioning","display_name":"data partitioning","score":0.968999981880188},{"id":"https://openalex.org/keywords/small-molecule-drug-design","display_name":"small-molecule drug design","score":0.8349999785423279},{"id":"https://openalex.org/keywords/machine-learning","display_name":"machine learning","score":0.6990000009536743},{"id":"https://openalex.org/keywords/chemical-space","display_name":"chemical space","score":0.4189999997615814},{"id":"https://openalex.org/keywords/structural-similarity","display_name":"structural similarity","score":0.8040000200271606},{"id":"https://openalex.org/keywords/temporal-order","display_name":"temporal order","score":0.6600000262260437},{"id":"https://openalex.org/keywords/data-provenance","display_name":"data provenance","score":0.9129999876022339},{"id":"https://openalex.org/keywords/model-evaluation","display_name":"model evaluation","score":0.6299999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7281000018119812},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6227999925613403},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6007999777793884},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.5238999724388123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5015000104904175},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.391400009393692},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38519999384880066},{"id":"https://openalex.org/C2780977526","wikidata":"https://www.wikidata.org/wiki/Q42417149","display_name":"Data exploration","level":3,"score":0.27790001034736633},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15009691/v1","doi":"https://doi.org/10.26434/chemrxiv.15009691/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15009691/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009691/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"posted-content"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15009691/v1","doi":"https://doi.org/10.26434/chemrxiv.15009691/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15009691/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009691/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4166090642","display_name":"Artificial Intelligence-Based Scoring Functions for Polypharmacology Prediction","funder_award_id":"ANR-25-CE45-0171","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G6232772672","display_name":"Target-specific machine-learning scoring functions for reliable structure-based virtual screening","funder_award_id":"EP/X012026/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214927326.pdf","grobid_xml":"https://content.openalex.org/works/W7214927326.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2475330876","https://openalex.org/W3020979945","https://openalex.org/W4405083074","https://openalex.org/W7133237743","https://openalex.org/W7135172355","https://openalex.org/W7172442894","https://openalex.org/W7213236792","https://openalex.org/W7221307811"],"related_works":["https://openalex.org/W7202051849","https://openalex.org/W2884898416","https://openalex.org/W7171725305","https://openalex.org/W4389564374","https://openalex.org/W7172442894","https://openalex.org/W7164826009","https://openalex.org/W4226054611","https://openalex.org/W7133237743","https://openalex.org/W4403432897","https://openalex.org/W4398133841"],"abstract_inverted_index":{"Data":[0],"splitting":[1,44],"is":[2],"a":[3],"critical":[4],"determinant":[5],"of":[6,36],"machine-learning":[7],"performance":[8],"in":[9],"small-molecule":[10],"drug":[11],"design.":[12],"Different":[13],"strategies":[14],"impose":[15],"distinct":[16],"assumptions":[17],"about":[18],"structural":[19],"similarity,":[20],"temporal":[21],"order,":[22],"data":[23],"provenance":[24],"and":[25,33,50,52],"chemical-space":[26],"coverage,":[27],"thereby":[28],"affecting":[29],"both":[30],"evaluation":[31],"realism":[32],"the":[34],"interpretation":[35],"model":[37],"performance.":[38],"This":[39],"perspective":[40],"critically":[41],"examines":[42],"major":[43],"approaches,":[45],"discusses":[46],"their":[47],"advantages,":[48],"applicability":[49],"limitations,":[51],"offers":[53],"evidence-based":[54],"considerations":[55],"for":[56],"designing":[57],"partitions":[58],"aligned":[59],"with":[60],"intended":[61],"prediction":[62],"scenarios.":[63]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-10-01T00:00:00"}