{"id":"https://openalex.org/W7220679730","doi":"https://doi.org/10.26434/chemrxiv.15009996/v1","title":"Hybrid-CatBoost: an empirical comparison of molecular representations for aqueous-solubility prediction on the TDC benchmark","display_name":"Hybrid-CatBoost: an empirical comparison of molecular representations for aqueous-solubility prediction on the TDC benchmark","publication_year":2026,"publication_date":"2026-10-06","ids":{"openalex":"https://openalex.org/W7220679730","doi":"https://doi.org/10.26434/chemrxiv.15009996/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15009996/v1","doi":"https://doi.org/10.26434/chemrxiv.15009996/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15009996/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009996/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.15009996/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157752697","display_name":"Ruming Li","orcid":"https://orcid.org/0009-0004-0499-429X","observed_orcids":["https://orcid.org/0009-0004-0499-429X"]},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruming Li","raw_affiliation_strings":["College of Life Science and Technology, Beijing University of Chemical Technology, North 3rd Ring, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-0499-429X","affiliations":[{"raw_affiliation_string":"College of Life Science and Technology, Beijing University of Chemical Technology, North 3rd Ring, Beijing, China","institution_ids":["https://openalex.org/I75390827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5157752697"],"corresponding_institution_ids":["https://openalex.org/I75390827"],"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":0.9940999746322632,"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":0.9940999746322632,"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":0.0020000000949949026,"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":0.0006000000284984708,"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/aqueous-solubility-prediction","display_name":"aqueous solubility prediction","score":0.9919999837875366},{"id":"https://openalex.org/keywords/molecular-representation","display_name":"molecular representation","score":0.7590000033378601},{"id":"https://openalex.org/keywords/catboost","display_name":"CatBoost","score":0.6899999976158142},{"id":"https://openalex.org/keywords/morgan-fingerprints","display_name":"Morgan fingerprints","score":0.7080000042915344},{"id":"https://openalex.org/keywords/molecular-descriptors","display_name":"molecular descriptors","score":0.9020000100135803},{"id":"https://openalex.org/keywords/graph-representation","display_name":"graph representation","score":0.8799999952316284},{"id":"https://openalex.org/keywords/residual-bias","display_name":"residual bias","score":0.5910000205039978}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8461999893188477},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.713699996471405},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6978999972343445},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.578499972820282},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5645999908447266},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.548799991607666},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5422999858856201},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5144000053405762},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4747999906539917},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.45019999146461487},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40220001339912415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3747999966144562},{"id":"https://openalex.org/C160798450","wikidata":"https://www.wikidata.org/wiki/Q4230870","display_name":"Concordance","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27950000762939453},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.2766999900341034},{"id":"https://openalex.org/C92446256","wikidata":"https://www.wikidata.org/wiki/Q3306762","display_name":"Data validation","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.26170000433921814}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15009996/v1","doi":"https://doi.org/10.26434/chemrxiv.15009996/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15009996/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009996/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.15009996/v1","doi":"https://doi.org/10.26434/chemrxiv.15009996/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15009996/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009996/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":[],"funders":[{"id":"https://openalex.org/F4320324303","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220679730.pdf","grobid_xml":"https://content.openalex.org/works/W7220679730.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2911964244","https://openalex.org/W2966357564","https://openalex.org/W2966797369","https://openalex.org/W3098530784","https://openalex.org/W4220785481","https://openalex.org/W4234698323","https://openalex.org/W4392918434","https://openalex.org/W7117321007"],"related_works":["https://openalex.org/W7203772823","https://openalex.org/W6977248547","https://openalex.org/W4387740953","https://openalex.org/W4416297816","https://openalex.org/W7161009593","https://openalex.org/W7140131557","https://openalex.org/W7215042103","https://openalex.org/W4308548134","https://openalex.org/W2947209329","https://openalex.org/W4402350721"],"abstract_inverted_index":{"Aqueous-solubility":[0],"prediction":[1],"depends":[2],"on":[3,21],"both":[4,82],"molecular":[5],"representation":[6],"and":[7,18,31,70,85,114,124],"the":[8,11,22,61,99,106,125],"definition":[9],"of":[10,36,45,75,98,127],"target.":[12],"We":[13],"compared":[14,52],"fingerprint,":[15],"descriptor,":[16],"hybrid,":[17],"graph-based":[19],"representations":[20],"TDC":[23,49],"Solubility_AqSolDB":[24],"benchmark":[25],"using":[26],"five":[27,76],"official":[28],"scaffold":[29],"splits":[30],"a":[32,41,112,128],"fixed":[33,130],"test":[34,43,131],"set":[35],"1,997":[37],"records.":[38],"Hybrid-CatBoost":[39],"achieved":[40],"five-run":[42],"MAE":[44],"0.749631":[46],"\u00b1":[47,55],"0.016216":[48],"logS":[50],"units,":[51],"with":[53],"0.764558":[54],"0.009666":[56],"for":[57],"descriptor-only":[58],"CatBoost.":[59],"However,":[60],"corresponding":[62],"validation":[63],"improvement":[64],"was":[65],"small":[66],"(\u0394MAE":[67],"=":[68],"\u22120.004932)":[69],"occurred":[71],"in":[72,102],"only":[73,111],"two":[74],"matched":[77],"splits.":[78],"Errors":[79],"increased":[80],"toward":[81],"target":[83],"extremes":[84],"showed":[86],"opposite-signed":[87],"residual":[88],"biases.":[89],"These":[90],"results":[91],"indicate":[92],"that":[93],"descriptor-based":[94],"models":[95],"capture":[96],"most":[97],"predictive":[100],"signal":[101],"this":[103],"benchmark,":[104],"while":[105],"added":[107],"Morgan":[108],"fingerprint":[109],"provides":[110],"modest":[113],"split-dependent":[115],"benefit.":[116],"Interpretation":[117],"is":[118],"limited":[119],"by":[120],"incomplete":[121],"assay":[122],"metadata":[123],"use":[126],"single":[129],"set,":[132],"which":[133],"does":[134],"not":[135],"provide":[136],"external":[137],"validation.":[138]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-10-07T00:00:00"}