{"id":"https://openalex.org/W7204912005","doi":"https://doi.org/10.48550/arxiv.2608.30472","title":"ToxLens: A Reproducible Graph-Learning Framework for Leakage-Aware, Uncertainty-Calibrated Molecular Toxicity Prediction","display_name":"ToxLens: A Reproducible Graph-Learning Framework for Leakage-Aware, Uncertainty-Calibrated Molecular Toxicity Prediction","publication_year":2026,"publication_date":"2026-08-31","ids":{"openalex":"https://openalex.org/W7204912005","doi":"https://doi.org/10.48550/arxiv.2608.30472"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.30472","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.30472","pdf_url":"https://arxiv.org/pdf/2608.30472","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.30472","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130952780","display_name":"Magnus H. Str\u00f8mme","orcid":"https://orcid.org/0009-0001-9405-0919","observed_orcids":["https://orcid.org/0009-0001-9405-0919"]},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Str\u00f8mme, Magnus H.","raw_affiliation_strings":["The Australian Centre for Ecogenomics , School of Chemistry and Molecular Biosciences , The University of Queensland , Brisbane , Queensland , 4072 , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Australian Centre for Ecogenomics , School of Chemistry and Molecular Biosciences , The University of Queensland , Brisbane , Queensland , 4072 , Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010414038","display_name":"Alex G. C. de S\u00e1","orcid":"https://orcid.org/0000-0002-7276-7839","observed_orcids":["https://orcid.org/0000-0002-7276-7839"]},"institutions":[{"id":"https://openalex.org/I142471025","display_name":"Baker Heart and Diabetes Institute","ror":"https://ror.org/03rke0285","country_code":"AU","type":"nonprofit","lineage":["https://openalex.org/I142471025"]},{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"de S\u00e1, Alex G. C.","raw_affiliation_strings":["Computational Biology and Clinical Informatics , Baker Heart and Diabetes Institute , Melbourne , Victoria , 3004 , Australia","The Australian Centre for Ecogenomics , School of Chemistry and Molecular Biosciences , The University of Queensland , Brisbane , Queensland , 4072 , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology and Clinical Informatics , Baker Heart and Diabetes Institute , Melbourne , Victoria , 3004 , Australia","institution_ids":["https://openalex.org/I142471025"]},{"raw_affiliation_string":"The Australian Centre for Ecogenomics , School of Chemistry and Molecular Biosciences , The University of Queensland , Brisbane , Queensland , 4072 , Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091903225","display_name":"David Benjamin Ascher","orcid":"https://orcid.org/0000-0003-2948-2413","observed_orcids":["https://orcid.org/0000-0003-2948-2413"]},"institutions":[{"id":"https://openalex.org/I142471025","display_name":"Baker Heart and Diabetes Institute","ror":"https://ror.org/03rke0285","country_code":"AU","type":"nonprofit","lineage":["https://openalex.org/I142471025"]},{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ascher, David B.","raw_affiliation_strings":["Computational Biology and Clinical Informatics , Baker Heart and Diabetes Institute , Melbourne , Victoria , 3004 , Australia","The Australian Centre for Ecogenomics , School of Chemistry and Molecular Biosciences , The University of Queensland , Brisbane , Queensland , 4072 , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology and Clinical Informatics , Baker Heart and Diabetes Institute , Melbourne , Victoria , 3004 , Australia","institution_ids":["https://openalex.org/I142471025"]},{"raw_affiliation_string":"The Australian Centre for Ecogenomics , School of Chemistry and Molecular Biosciences , The University of Queensland , Brisbane , Queensland , 4072 , Australia","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.9951000213623047,"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":0.9951000213623047,"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":0.0008999999845400453,"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/T13297","display_name":"History and advancements in chemistry","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1207","display_name":"History and Philosophy of Science"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/chemical-toxicity-prediction","display_name":"chemical toxicity prediction","score":0.9980000257492065},{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.6850000023841858},{"id":"https://openalex.org/keywords/data-leakage","display_name":"data leakage","score":0.746999979019165},{"id":"https://openalex.org/keywords/uncertainty-calibration","display_name":"uncertainty calibration","score":0.9039999842643738},{"id":"https://openalex.org/keywords/conformal-prediction","display_name":"conformal prediction","score":0.9300000071525574},{"id":"https://openalex.org/keywords/monte-carlo-dropout","display_name":"Monte Carlo dropout","score":0.8820000290870667},{"id":"https://openalex.org/keywords/shap","display_name":"SHAP","score":0.44600000977516174},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.6690000295639038},{"id":"https://openalex.org/keywords/tox21","display_name":"Tox21","score":0.7149999737739563},{"id":"https://openalex.org/keywords/ames-mutagenicity","display_name":"Ames mutagenicity","score":0.9639999866485596},{"id":"https://openalex.org/keywords/herg-inhibition","display_name":"hERG inhibition","score":0.9470000267028809},{"id":"https://openalex.org/keywords/acute-oral-toxicity","display_name":"acute oral toxicity","score":0.7860000133514404},{"id":"https://openalex.org/keywords/applicability-domain","display_name":"applicability domain","score":0.7519999742507935},{"id":"https://openalex.org/keywords/data-curation","display_name":"data curation","score":0.47099998593330383},{"id":"https://openalex.org/keywords/soft-voting-ensemble","display_name":"soft voting ensemble","score":0.4650000035762787},{"id":"https://openalex.org/keywords/subgraph-mining","display_name":"subgraph mining","score":0.45399999618530273}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5254999995231628},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.512499988079071},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4713999927043915},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45809999108314514},{"id":"https://openalex.org/C164085508","wikidata":"https://www.wikidata.org/wiki/Q4811327","display_name":"Matthews correlation coefficient","level":3,"score":0.42080000042915344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41830000281333923},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C23531484","wikidata":"https://www.wikidata.org/wiki/Q3196863","display_name":"Calibration curve","level":3,"score":0.375900000333786},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3249000012874603},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.322299987077713},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31040000915527344},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3059000074863434},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30410000681877136},{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.2987000048160553},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C58471807","wikidata":"https://www.wikidata.org/wiki/Q327120","display_name":"Receiver operating characteristic","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C76318530","wikidata":"https://www.wikidata.org/wiki/Q16833590","display_name":"Area under the curve","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.26420000195503235},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.259799987077713},{"id":"https://openalex.org/C103463560","wikidata":"https://www.wikidata.org/wiki/Q4456449","display_name":"Score test","level":3,"score":0.25519999861717224}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.30472","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.30472","pdf_url":"https://arxiv.org/pdf/2608.30472","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.30472","doi":"https://doi.org/10.48550/arxiv.2608.30472","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.30472","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.30472","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.30472","pdf_url":"https://arxiv.org/pdf/2608.30472","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.46810001134872437,"id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320334705","display_name":"National Health and Medical Research Council","ror":"https://ror.org/011kf5r70"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204912005.pdf","grobid_xml":"https://content.openalex.org/works/W7204912005.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W2786672974","https://openalex.org/W2968734407","https://openalex.org/W3034516664","https://openalex.org/W3085380432","https://openalex.org/W3093934881"],"related_works":["https://openalex.org/W7208781546","https://openalex.org/W7140277438","https://openalex.org/W7207553942","https://openalex.org/W7115608228","https://openalex.org/W7172428630","https://openalex.org/W2808710274","https://openalex.org/W4360948819","https://openalex.org/W7162327940","https://openalex.org/W7160865722","https://openalex.org/W7222999095"],"abstract_inverted_index":{"Molecular":[0],"toxicity":[1,40],"prediction":[2,83,173],"is":[3],"increasingly":[4],"used":[5],"to":[6,189],"prioritise":[7],"compounds":[8],"before":[9],"experimental":[10],"testing,":[11],"but":[12,204],"conventional":[13],"benchmark":[14],"performance":[15],"can":[16],"overstate":[17],"practical":[18],"utility":[19],"when":[20],"structurally":[21],"related":[22],"molecules":[23],"occur":[24],"across":[25],"training":[26,191],"and":[27,50,53,70,87,122,146,166,182,184,199,211],"test":[28,97],"folds.":[29],"We":[30],"introduce":[31],"ToxLens,":[32],"a":[33,64,99,104],"reproducible":[34],"multi-task":[35],"graph-learning":[36],"framework":[37],"for":[38],"11":[39,140],"endpoints":[41,141],"spanning":[42],"Ames":[43],"mutagenicity,":[44],"acute":[45],"oral":[46],"toxicity,":[47],"hERG":[48],"inhibition,":[49],"Tox21":[51,197],"nuclear-receptor":[52],"stress-response":[54],"assays.":[55],"The":[56],"workflow":[57],"combines":[58],"conservative":[59],"chemical":[60],"curation,":[61],"sphere-exclusion":[62],"filtering,":[63],"leakage-aware":[65],"UMAP-HDBSCAN":[66],"split,":[67],"parallel":[68],"graph":[69],"global-feature":[71],"encoders":[72],"joined":[73],"by":[74],"late":[75,160],"concatenation,":[76],"temperature-scaled":[77],"Monte":[78],"Carlo":[79],"dropout":[80],"with":[81,91,187],"conformal-style":[82],"sets,":[84],"applicability-domain":[85],"analysis,":[86],"SHAP-guided":[88,209],"toxicophore":[89],"discovery":[90],"occlusion":[92,210],"controls.":[93],"On":[94],"the":[95,114,126,143,154,163,190,229],"leakage-controlled":[96],"fold,":[98],"five-seed":[100],"soft-voting":[101],"ensemble":[102],"achieved":[103],"Matthews":[105],"correlation":[106],"coefficient":[107],"score":[108,119,129],"of":[109,120,130,220],"0.44,":[110],"an":[111,123],"area":[112,124],"under":[113,125,142],"receiver":[115],"operating":[116],"characteristic":[117],"curve":[118,128],"0.83,":[121],"precision-recall":[127],"0.58.":[131],"It":[132],"exceeded":[133],"four":[134],"ECFP4-based":[135],"shallow":[136],"baselines":[137],"on":[138,194],"all":[139],"same":[144],"split":[145],"validation-based":[147],"threshold-selection":[148],"protocol.":[149],"Controlled":[150],"ablations":[151],"showed":[152],"that":[153,227],"global":[155],"pathway":[156],"was":[157],"important,":[158],"whereas":[159],"concatenation":[161],"outperformed":[162],"tested":[164],"gated":[165],"feature-wise":[167],"linear":[168],"modulation":[169],"fusion":[170],"variants.":[171],"Conformal-style":[172],"sets":[174],"revealed":[175],"substantial":[176],"endpoint-specific":[177],"variation":[178],"in":[179],"set":[180],"efficiency,":[181],"discrimination":[183],"calibration":[185],"improved":[186],"similarity":[188],"domain.":[192],"Retraining":[193],"fixed":[195],"published":[196],"Challenge":[198],"TDA":[200],"folds":[201],"produced":[202],"competitive,":[203],"not":[205],"uniformly":[206],"state-of-the-art,":[207],"performance.":[208],"consensus":[212],"subgraph":[213],"mining":[214],"yielded":[215],"model-derived":[216],"structural":[217],"hypotheses,":[218],"44":[219],"which":[221],"contained":[222],"at":[223],"least":[224],"one":[225],"occurrence":[226],"passed":[228],"predefined":[230],"counterfactual":[231],"criteria.":[232]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-02T00:00:00"}