{"id":"https://openalex.org/W4416204720","doi":"https://doi.org/10.1186/s13321-025-01108-y","title":"How evaluation choices distort the outcome of generative drug discovery","display_name":"How evaluation choices distort the outcome of generative drug discovery","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W4416204720","doi":"https://doi.org/10.1186/s13321-025-01108-y","pmid":"https://pubmed.ncbi.nlm.nih.gov/41225661"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-025-01108-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01108-y","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01108-y","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/s13321-025-01108-y","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015409355","display_name":"R\u0131za \u00d6z\u00e7elik","orcid":"https://orcid.org/0000-0002-4052-9721"},"institutions":[{"id":"https://openalex.org/I3018483916","display_name":"University Medical Center Utrecht","ror":"https://ror.org/0575yy874","country_code":"NL","type":"healthcare","lineage":["https://openalex.org/I3018483916"]},{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"R\u0131za \u00d6z\u00e7elik","raw_affiliation_strings":["Centre for Living Technologies, Alliance TU/e, WUR, UU, UMC Utrecht, Utrecht, The Netherlands","Institute for Complex Molecular Systems and Dept. Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Centre for Living Technologies, Alliance TU/e, WUR, UU, UMC Utrecht, Utrecht, The Netherlands","institution_ids":["https://openalex.org/I3018483916"]},{"raw_affiliation_string":"Institute for Complex Molecular Systems and Dept. Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078946433","display_name":"Francesca Grisoni","orcid":"https://orcid.org/0000-0001-8552-6615"},"institutions":[{"id":"https://openalex.org/I173063890","display_name":"University of Applied Sciences Utrecht","ror":"https://ror.org/028z9kw20","country_code":"NL","type":"education","lineage":["https://openalex.org/I173063890"]},{"id":"https://openalex.org/I3018483916","display_name":"University Medical Center Utrecht","ror":"https://ror.org/0575yy874","country_code":"NL","type":"healthcare","lineage":["https://openalex.org/I3018483916"]},{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Francesca Grisoni","raw_affiliation_strings":["Centre for Living Technologies, Alliance TU/e, WUR, UU, UMC Utrecht, Utrecht, The Netherlands. f.grisoni@tue.nl","Institute for Complex Molecular Systems and Dept. Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands. f.grisoni@tue.nl","Centre for Living Technologies, Alliance TU/e, WUR, UU, UMC Utrecht, Utrecht, The Netherlands","Institute for Complex Molecular Systems and Dept. Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Centre for Living Technologies, Alliance TU/e, WUR, UU, UMC Utrecht, Utrecht, The Netherlands. f.grisoni@tue.nl","institution_ids":["https://openalex.org/I173063890"]},{"raw_affiliation_string":"Institute for Complex Molecular Systems and Dept. Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands. f.grisoni@tue.nl","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"Centre for Living Technologies, Alliance TU/e, WUR, UU, UMC Utrecht, Utrecht, The Netherlands","institution_ids":["https://openalex.org/I3018483916"]},{"raw_affiliation_string":"Institute for Complex Molecular Systems and Dept. Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5015409355"],"corresponding_institution_ids":["https://openalex.org/I3018483916","https://openalex.org/I83019370"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":2.6622,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.92222817,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"17","issue":"1","first_page":"169","last_page":"169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.4936000108718872,"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":0.4936000108718872,"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":0.4117000102996826,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.013000000268220901,"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/generative-grammar","display_name":"Generative grammar","score":0.7692999839782715},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5515999794006348},{"id":"https://openalex.org/keywords/generative-design","display_name":"Generative Design","score":0.5088000297546387},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5045999884605408},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4113999903202057},{"id":"https://openalex.org/keywords/transformative-learning","display_name":"Transformative learning","score":0.39969998598098755},{"id":"https://openalex.org/keywords/parallels","display_name":"Parallels","score":0.39570000767707825},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.39089998602867126}],"concepts":[{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7692999839782715},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7250999808311462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5896999835968018},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.578000009059906},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5515999794006348},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5252000093460083},{"id":"https://openalex.org/C184408114","wikidata":"https://www.wikidata.org/wiki/Q1502022","display_name":"Generative Design","level":3,"score":0.5088000297546387},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5045999884605408},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4113999903202057},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.4007999897003174},{"id":"https://openalex.org/C70587473","wikidata":"https://www.wikidata.org/wiki/Q7834111","display_name":"Transformative learning","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C2775922551","wikidata":"https://www.wikidata.org/wiki/Q7135033","display_name":"Parallels","level":2,"score":0.39570000767707825},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.39089998602867126},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.37720000743865967},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.37070000171661377},{"id":"https://openalex.org/C2778701210","wikidata":"https://www.wikidata.org/wiki/Q28130034","display_name":"Constructive","level":3,"score":0.36730000376701355},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.32339999079704285},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.29600000381469727},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2752000093460083},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.26269999146461487},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2506999969482422},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1186/s13321-025-01108-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01108-y","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01108-y","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:41225661","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41225661","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:pure.tue.nl:openaire/f1c27cc1-95c2-44ea-9dfd-0d8ed2633ec4","is_oa":false,"landing_page_url":"https://research.tue.nl/en/publications/f1c27cc1-95c2-44ea-9dfd-0d8ed2633ec4","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"\u00d6z\u00e7elik, R & Grisoni, F 2025, 'How evaluation choices distort the outcome of generative drug discovery', Journal of Cheminformatics, vol. 17, no. 1, 169. https://doi.org/10.1186/s13321-025-01108-y","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:doaj.org/article:a4b56b6c56b3426b95a41657e3f71544","is_oa":true,"landing_page_url":"https://doaj.org/article/a4b56b6c56b3426b95a41657e3f71544","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 1-14 (2025)","raw_type":"article"},{"id":"pmh:oai:dspace.library.uu.nl:1874/468364","is_oa":true,"landing_page_url":"https://dspace.library.uu.nl/handle/1874/468364","pdf_url":null,"source":{"id":"https://openalex.org/S4306401649","display_name":"Utrecht University Repository (Utrecht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193662353","host_organization_name":"Utrecht University","host_organization_lineage":["https://openalex.org/I193662353"],"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":"Article"},{"id":"pmh:oai:europepmc.org:11421863","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12613558","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/s13321-025-01108-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01108-y","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01108-y","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":[{"id":"https://openalex.org/G2309483012","display_name":null,"funder_award_id":"ReMINDER, 101077879","funder_id":"https://openalex.org/F4320338453","funder_display_name":"HORIZON EUROPE European Research Council"},{"id":"https://openalex.org/G4866335649","display_name":null,"funder_award_id":"101077879","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320338453","display_name":"HORIZON EUROPE European Research Council","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416204720.pdf","grobid_xml":"https://content.openalex.org/works/W4416204720.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W1975147762","https://openalex.org/W1988037271","https://openalex.org/W2017254234","https://openalex.org/W2020994990","https://openalex.org/W2060531713","https://openalex.org/W2064675550","https://openalex.org/W2066273100","https://openalex.org/W2110971533","https://openalex.org/W2273267066","https://openalex.org/W2416176918","https://openalex.org/W2529996553","https://openalex.org/W2558999090","https://openalex.org/W2578240541","https://openalex.org/W2580289839","https://openalex.org/W2594328795","https://openalex.org/W2765224015","https://openalex.org/W2773987374","https://openalex.org/W2784270883","https://openalex.org/W2806547269","https://openalex.org/W2887447356","https://openalex.org/W2900694120","https://openalex.org/W2925830236","https://openalex.org/W2963096510","https://openalex.org/W3007309629","https://openalex.org/W3009999522","https://openalex.org/W3036527662","https://openalex.org/W3042826782","https://openalex.org/W3050693196","https://openalex.org/W3094553402","https://openalex.org/W3116865743","https://openalex.org/W3127493072","https://openalex.org/W3185391990","https://openalex.org/W3195161349","https://openalex.org/W3209056694","https://openalex.org/W3209416355","https://openalex.org/W4213451219","https://openalex.org/W4221054065","https://openalex.org/W4221062742","https://openalex.org/W4225335692","https://openalex.org/W4281619372","https://openalex.org/W4293257826","https://openalex.org/W4306179830","https://openalex.org/W4309047034","https://openalex.org/W4313703391","https://openalex.org/W4315767347","https://openalex.org/W4318952054","https://openalex.org/W4361989906","https://openalex.org/W4378212018","https://openalex.org/W4378802816","https://openalex.org/W4389991855","https://openalex.org/W4390771096","https://openalex.org/W4393038273","https://openalex.org/W4393317648","https://openalex.org/W4395053803","https://openalex.org/W4399175418","https://openalex.org/W4399781535","https://openalex.org/W4400598258","https://openalex.org/W4400831251","https://openalex.org/W4400876473","https://openalex.org/W4402441163","https://openalex.org/W4405437765","https://openalex.org/W4406946019"],"related_works":[],"abstract_inverted_index":{"\"How":[0],"to":[1,109,129,187,208,279,297,306],"evaluate":[2],"the":[3,13,38,44,96,99,116,185,189,218,237,266],"de":[4,65],"novo":[5,66],"designs":[6,80,119,258],"proposed":[7],"by":[8],"a":[9,56,93,121,233],"generative":[10,17,41,155,214,225,245],"model?\"":[11],"Despite":[12],"transformative":[14],"potential":[15],"of":[16,33,40,46,98,118,154,241,268],"deep":[18,199,260],"learning":[19,200,261],"in":[20,138,213,244,322],"drug":[21,202,215,246],"discovery,":[22,216],"this":[23,52,299],"seemingly":[24],"simple":[25],"question":[26],"has":[27],"no":[28],"clear":[29],"answer.":[30],"The":[31],"absence":[32],"standardized":[34],"guidelines":[35,313],"challenges":[36],"both":[37],"benchmarking":[39],"approaches":[42],"and":[43,60,81,89,123,126,146,164,171,179,192,196,201,223,239,282,301,318],"selection":[45,178,317],"molecules":[47],"for":[48,167,220,314],"prospective":[49,315],"studies.":[50,309],"In":[51],"work,":[53],"we":[54,74,161,285,302],"take":[55],"fresh":[57],"-":[58,62,142,149],"critical":[59,136],"constructive":[61],"perspective":[63],"on":[64],"design":[67,172,290],"evaluation.":[68,173],"By":[69],"training":[70],"chemical":[71],"language":[72],"models,":[73],"analyze":[75,250],"approximately":[76,255],"1":[77],"billion":[78,257],"molecule":[79,177,316],"discover":[82],"principles":[83],"consistent":[84],"across":[85],"different":[86],"neural":[87],"networks":[88],"datasets.":[90],"We":[91,113,133,204,248,263,310],"uncover":[92,319],"key":[94],"confounder:":[95],"size":[97],"generated":[100,190],"molecular":[101,324],"library":[102],"significantly":[103],"impacts":[104],"evaluation":[105,211,242,252],"outcomes,":[106],"often":[107,270],"leading":[108],"misleading":[110],"model":[111,169],"comparisons.":[112],"find":[114,264],"increasing":[115],"number":[117,267],"as":[120,144],"remedy":[122],"propose":[124,162,312],"new":[125,163,194],"compute-efficient":[127],"metrics":[128,141],"compute":[130],"at":[131],"large-scale.":[132],"also":[134,311],"identify":[135],"pitfalls":[137],"commonly":[139],"used":[140],"such":[143],"uniqueness":[145],"distributional":[147,280],"similarity":[148,281],"that":[150,265,287],"can":[151,274],"distort":[152,275],"assessments":[153],"performance.":[156],"To":[157],"address":[158],"these":[159],"issues,":[160],"refined":[165],"strategies":[166],"reliable":[168,222],"comparison":[170],"Furthermore,":[174],"when":[175],"examining":[176],"sampling":[180],"strategies,":[181],"our":[182,206],"findings":[183,207],"reveal":[184],"constraints":[186,321],"diversify":[188],"libraries":[191,291],"draw":[193],"parallels":[195],"distinctions":[197],"between":[198],"discovery.":[203,247],"anticipate":[205],"help":[209],"reshape":[210],"pipelines":[212],"paving":[217],"way":[219],"more":[221],"reproducible":[224],"modeling":[226],"approaches.":[227],"SCIENTIFIC":[228],"CONTRIBUTION:":[229],"Our":[230],"work":[231],"takes":[232],"step":[234],"toward":[235],"enhancing":[236],"robustness":[238],"reliability":[240],"practices":[243,253],"systematically":[249],"current":[251],"using":[254,288],"one":[256],"from":[259],"models.":[262],"designs,":[269],"an":[271],"overlooked":[272],"parameter,":[273],"scientific":[276],"outcomes":[277],"related":[278],"diversity.":[283],"Moreover,":[284],"show":[286],"larger":[289],"than":[292],"are":[293],"typically":[294],"adopted":[295],"helps":[296],"avoid":[298],"pitfall,":[300],"develop":[303],"efficient":[304],"algorithms":[305],"enable":[307],"large-scale":[308],"inherent":[320],"diversifying":[323],"designs.":[325]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-11-12T00:00:00"}