{"id":"https://openalex.org/W7212166140","doi":"https://doi.org/10.26434/chemrxiv.15008627/v1","title":"Comparative Evaluation of Graph Neural Networks for Molecular Lipophilicity Prediction","display_name":"Comparative Evaluation of Graph Neural Networks for Molecular Lipophilicity Prediction","publication_year":2026,"publication_date":"2026-09-10","ids":{"openalex":"https://openalex.org/W7212166140","doi":"https://doi.org/10.26434/chemrxiv.15008627/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15008627/v1","doi":"https://doi.org/10.26434/chemrxiv.15008627/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008627/v1","pdf_url":null,"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://doi.org/10.26434/chemrxiv.15008627/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010073609","display_name":"Annika Bande","orcid":"https://orcid.org/0000-0003-3827-9169","observed_orcids":["https://orcid.org/0000-0003-3827-9169"]},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]},{"id":"https://openalex.org/I2800795503","display_name":"Helmholtz-Zentrum Berlin f\u00fcr Materialien und Energie","ror":"https://ror.org/02aj13c28","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2800795503"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Annika Bande","raw_affiliation_strings":["Helmholtz-Zentrum Berlin f\u00fcr Materialien und Energie GmbH,, Helmholtz-Zentrum Berlin , Hahn-Meitner-Platz 1, Berlin, Germany, 14109","Institute of Inorganic Chemistry, Leibniz University Hannover, Callinstr. 9, Hanover, Germany, 30167"],"raw_orcid":"https://orcid.org/0000-0003-3827-9169","affiliations":[{"raw_affiliation_string":"Helmholtz-Zentrum Berlin f\u00fcr Materialien und Energie GmbH,, Helmholtz-Zentrum Berlin , Hahn-Meitner-Platz 1, Berlin, Germany, 14109","institution_ids":["https://openalex.org/I2800795503"]},{"raw_affiliation_string":"Institute of Inorganic Chemistry, Leibniz University Hannover, Callinstr. 9, Hanover, Germany, 30167","institution_ids":["https://openalex.org/I114112103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114949887","display_name":"Sandeep Kumar","orcid":"https://orcid.org/0000-0003-4043-0112","observed_orcids":["https://orcid.org/0000-0003-4043-0112"]},"institutions":[{"id":"https://openalex.org/I2800795503","display_name":"Helmholtz-Zentrum Berlin f\u00fcr Materialien und Energie","ror":"https://ror.org/02aj13c28","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2800795503"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sandeep Kumar","raw_affiliation_strings":["Helmholtz-Zentrum Berlin f\u00fcr Materialien und Energie GmbH,, Helmholtz-Zentrum Berlin , Hahn-Meitner-Platz 1, Berlin, Germany, 14109"],"raw_orcid":"https://orcid.org/0000-0003-4043-0112","affiliations":[{"raw_affiliation_string":"Helmholtz-Zentrum Berlin f\u00fcr Materialien und Energie GmbH,, Helmholtz-Zentrum Berlin , Hahn-Meitner-Platz 1, Berlin, Germany, 14109","institution_ids":["https://openalex.org/I2800795503"]}]}],"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":false,"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":0.9911999702453613,"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":0.9911999702453613,"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":0.002099999925121665,"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/T11476","display_name":"Graph theory and applications","score":0.0019000000320374966,"subfield":{"id":"https://openalex.org/subfields/2607","display_name":"Discrete Mathematics and Combinatorics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.9959999918937683},{"id":"https://openalex.org/keywords/graphsage","display_name":"GraphSAGE","score":0.8339999914169312},{"id":"https://openalex.org/keywords/gin","display_name":"gin","score":0.7519999742507935},{"id":"https://openalex.org/keywords/molecular-property-prediction","display_name":"molecular property prediction","score":0.6069999933242798},{"id":"https://openalex.org/keywords/outlier-removal","display_name":"outlier removal","score":0.8830000162124634},{"id":"https://openalex.org/keywords/physicochemical-properties","display_name":"physicochemical properties","score":0.6629999876022339},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"drug discovery","score":0.5299999713897705}],"concepts":[{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.805899977684021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7175999879837036},{"id":"https://openalex.org/C201399114","wikidata":"https://www.wikidata.org/wiki/Q898401","display_name":"Lipophilicity","level":2,"score":0.6287999749183655},{"id":"https://openalex.org/C2780022179","wikidata":"https://www.wikidata.org/wiki/Q1986794","display_name":"Molecular graph","level":3,"score":0.5830000042915344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5710999965667725},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5645999908447266},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5249000191688538},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4894999861717224},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C164923092","wikidata":"https://www.wikidata.org/wiki/Q3705921","display_name":"Molecular descriptor","level":3,"score":0.44029998779296875},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.3813000023365021},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3736000061035156},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3725000023841858},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C2991951333","wikidata":"https://www.wikidata.org/wiki/Q188403","display_name":"Quantum chemical","level":3,"score":0.3644999861717224},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2797999978065491},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C59593255","wikidata":"https://www.wikidata.org/wiki/Q901663","display_name":"Molecular dynamics","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15008627/v1","doi":"https://doi.org/10.26434/chemrxiv.15008627/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008627/v1","pdf_url":null,"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.15008627/v1","doi":"https://doi.org/10.26434/chemrxiv.15008627/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008627/v1","pdf_url":null,"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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3205538317","https://openalex.org/W4410903358","https://openalex.org/W7115904589","https://openalex.org/W3018495986","https://openalex.org/W4416423693","https://openalex.org/W6991379947","https://openalex.org/W7131869927","https://openalex.org/W7172214678","https://openalex.org/W4400039229","https://openalex.org/W4280602833"],"abstract_inverted_index":{"Predicting":[0],"molecular":[1,74,177],"properties":[2],"is":[3,33],"a":[4,11,26,34,118],"central":[5],"challenge":[6],"in":[7,14],"cheminformatics":[8],"and":[9,17,30,97,100,110,125,162],"plays":[10],"critical":[12],"role":[13],"drug":[15,39],"discovery":[16],"materials":[18],"science.":[19],"Lipophilicity,":[20],"which":[21,72],"describes":[22],"the":[23,132,138,151,170],"partitioning":[24],"of":[25,153,172],"molecule":[27],"between":[28],"lipid":[29],"aqueous":[31],"environments,":[32],"key":[35],"physicochemical":[36],"property":[37],"influencing":[38],"behavior.":[40],"Although":[41],"quantum":[42],"mechanical":[43],"methods":[44],"can":[45,59],"provide":[46,167],"accurate":[47],"predictions,":[48],"they":[49],"are":[50,115],"often":[51],"computationally":[52],"demanding.":[53],"In":[54,80],"contrast,":[55],"large":[56],"experimental":[57],"databases":[58],"be":[60],"leveraged":[61],"to":[62],"train":[63],"data-driven":[64],"models":[65,114,175],"such":[66],"as":[67],"graph":[68,91],"neural":[69],"networks":[70,89,93],"(GNNs),":[71],"learn":[73],"representations":[75],"directly":[76],"from":[77],"chemical":[78],"structures.":[79],"this":[81],"study,":[82],"we":[83],"compare":[84],"four":[85],"GNN":[86,174],"architectures\u2014graph":[87],"convolutional":[88],"(GCN),":[90],"isomorphism":[92],"(GIN),":[94],"Graph":[95],"Sample":[96],"AggregatE":[98],"(GraphSAGE),":[99],"Attentive":[101,133],"Fingerprint":[102],"(Attentive":[103],"FP)\u2014for":[104],"predicting":[105],"lipophilicity":[106,178],"using":[107],"both":[108,146],"regression":[109],"classification":[111],"approaches.":[112],"The":[113],"evaluated":[116],"on":[117],"benchmark":[119],"dataset":[120],"under":[121],"consistent":[122],"preprocessing,":[123,157],"optimization,":[124],"training":[126],"conditions.":[127],"Our":[128],"results":[129],"show":[130],"that":[131],"FP":[134],"model":[135],"consistently":[136],"outperforms":[137],"other":[139],"architectures,":[140],"yielding":[141],"improved":[142,163],"predictive":[143],"accuracy":[144],"across":[145],"tasks.":[147],"We":[148],"further":[149],"examine":[150],"impact":[152],"outlier":[154],"removal":[155],"during":[156],"observing":[158],"reduced":[159],"prediction":[160],"errors":[161],"robustness.":[164],"These":[165],"findings":[166],"insight":[168],"into":[169],"capabilities":[171],"representative":[173],"for":[176],"prediction.":[179]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-11T00:00:00"}