{"id":"https://openalex.org/W7202076359","doi":"https://doi.org/10.26434/chemrxiv.15003910/v3","title":"Revisiting Deep Learning DTA Methods from the Dataset Viewpoint","display_name":"Revisiting Deep Learning DTA Methods from the Dataset Viewpoint","publication_year":2026,"publication_date":"2026-08-10","ids":{"openalex":"https://openalex.org/W7202076359","doi":"https://doi.org/10.26434/chemrxiv.15003910/v3"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15003910/v3","doi":"https://doi.org/10.26434/chemrxiv.15003910/v3","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15003910/v3","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.15003910/v3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074597064","display_name":"Gustavo C\u00e1rdenas","orcid":"https://orcid.org/0000-0001-5223-3269","observed_orcids":["https://orcid.org/0000-0001-5223-3269"]},"institutions":[{"id":"https://openalex.org/I4210150906","display_name":"Ri.MED","ror":"https://ror.org/05qetrn02","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210150906"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Gustavo Ca\u0301rdenas","raw_affiliation_strings":["Molecular Informatics Group, Ri.MED Foundation, Corso Calatafimi 414, Palermo, Italy, 9100"],"raw_orcid":"https://orcid.org/0000-0001-5223-3269","affiliations":[{"raw_affiliation_string":"Molecular Informatics Group, Ri.MED Foundation, Corso Calatafimi 414, Palermo, Italy, 9100","institution_ids":["https://openalex.org/I4210150906"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136633863","display_name":"Rosalinda Marinello","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210150906","display_name":"Ri.MED","ror":"https://ror.org/05qetrn02","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210150906"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Rosalinda Marinello","raw_affiliation_strings":["Molecular Informatics Group, Ri.MED Foundation, Corso Calatafimi 414, Palermo, Italy, 9100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Molecular Informatics Group, Ri.MED Foundation, Corso Calatafimi 414, Palermo, Italy, 9100","institution_ids":["https://openalex.org/I4210150906"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003578614","display_name":"Giovanno Marcelo Renato Cardenas","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210150906","display_name":"Ri.MED","ror":"https://ror.org/05qetrn02","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210150906"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanno Marcelo Renato Ca\u0301rdenas","raw_affiliation_strings":["Molecular Informatics Group, Ri.MED Foundation, Corso Calatafimi 414, Palermo, Italy, 9100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Molecular Informatics Group, Ri.MED Foundation, Corso Calatafimi 414, Palermo, Italy, 9100","institution_ids":["https://openalex.org/I4210150906"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071626517","display_name":"Ugo Perricone","orcid":"https://orcid.org/0000-0002-2181-2468","observed_orcids":["https://orcid.org/0000-0002-2181-2468"]},"institutions":[{"id":"https://openalex.org/I4210150906","display_name":"Ri.MED","ror":"https://ror.org/05qetrn02","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210150906"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Ugo Perricone","raw_affiliation_strings":["Molecular Informatics Group, Ri.MED Foundation, Corso Calatafimi 414, Palermo, Italy, 9100"],"raw_orcid":"https://orcid.org/0000-0002-2181-2468","affiliations":[{"raw_affiliation_string":"Molecular Informatics Group, Ri.MED Foundation, Corso Calatafimi 414, Palermo, Italy, 9100","institution_ids":["https://openalex.org/I4210150906"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210150906"],"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":0.9994999766349792,"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":0.9994999766349792,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":9.999999747378752e-05,"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"}},{"id":"https://openalex.org/T12534","display_name":"Protein Degradation and Inhibitors","score":9.999999747378752e-05,"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/drug-target-binding-affinity-prediction","display_name":"drug-target affinity prediction","score":0.8899999856948853},{"id":"https://openalex.org/keywords/deep-learning","display_name":"deep learning","score":0.4959999918937683},{"id":"https://openalex.org/keywords/bindingdb","display_name":"BindingDB","score":0.7829999923706055},{"id":"https://openalex.org/keywords/data-curation","display_name":"data curation","score":0.953000009059906},{"id":"https://openalex.org/keywords/protein-embeddings","display_name":"protein embeddings","score":0.7429999709129333},{"id":"https://openalex.org/keywords/protein-superfamilies","display_name":"protein superfamilies","score":0.7419999837875366},{"id":"https://openalex.org/keywords/directional-derivatives","display_name":"directional derivatives","score":0.8339999914169312},{"id":"https://openalex.org/keywords/hyperparameter-optimization","display_name":"hyperparameter optimization","score":0.8799999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7297999858856201},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6919000148773193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6610999703407288},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6022999882698059},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5784000158309937},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5392000079154968},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.517300009727478},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4456999897956848},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3767000138759613},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2824000120162964},{"id":"https://openalex.org/C159246509","wikidata":"https://www.wikidata.org/wiki/Q5428725","display_name":"Factor graph","level":3,"score":0.28139999508857727},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26350000500679016},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.25110000371932983},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15003910/v3","doi":"https://doi.org/10.26434/chemrxiv.15003910/v3","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15003910/v3","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.15003910/v3","doi":"https://doi.org/10.26434/chemrxiv.15003910/v3","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15003910/v3","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4233613299","https://openalex.org/W2911871527","https://openalex.org/W6939677581","https://openalex.org/W4224981527","https://openalex.org/W4297008905","https://openalex.org/W7162656240","https://openalex.org/W7134951840","https://openalex.org/W3118091546","https://openalex.org/W3151148247","https://openalex.org/W4388819402"],"abstract_inverted_index":{"In":[0],"this":[1,255],"work,":[2],"we":[3],"present":[4],"a":[5,43,51,62,75,87,90,97,126,189,229],"study":[6,140],"revisiting":[7],"deep":[8,136],"learning":[9,137],"drug-target":[10],"affinity":[11,48],"models,":[12],"which":[13,261],"are":[14],"otherwise":[15],"used":[16],"as":[17,238,254],"benchmark":[18],"methods":[19],"in":[20,81,174],"the":[21,82,94,105,116,122,141,144,158,162,168,175,180,193,199,203,215,219,226,268,274,277,289],"literature":[22],"to":[23,68,114,133,153,166,188,205,223,244,264,294],"compare":[24],"more":[25,134],"complex":[26],"and":[27,34,56,65,96,146,170,240,280],"heavy-weighted":[28],"architectures.":[29],"We":[30,84,139,195],"focus":[31],"on":[32,161,179,272,281],"training":[33],"testing":[35],"these":[36],"models":[37,107],"using":[38,70,110],"pKd":[39],"values":[40,181],"from":[41],"BindingDB,":[42],"dataset":[44,95],"that":[45,77,86],"presents":[46],"binding":[47,184,252,269],"information":[49],"of":[50,54,89,93,101,104,121,143,182,198,202,218,225,228,251,259,267,276,286],"high":[52],"variety":[53],"ligans":[55],"proteins.":[57],"These":[58],"activity":[59],"data":[60],"need":[61],"proper":[63,98],"pre-treatment":[64],"curation":[66,92],"prior":[67],"actually":[69],"them":[71],"for":[72,248],"production":[73],"tasks,":[74],"factor":[76],"is":[78,291],"often":[79],"overlooked":[80],"literature.":[83],"show":[85],"combination":[88],"thorough":[91],"hyperparameter":[99],"tuning":[100],"slight":[102],"modifications":[103],"revisited":[106],"(e.g,":[108],"by":[109,213],"pretrained":[111],"protein":[112,145,191],"embeddings":[113],"describe":[115],"proteins)":[117],"provides":[118,256],"beyond":[119],"state":[120],"art":[123],"performances":[124],"at":[125,209],"much":[127],"lower":[128],"computational":[129],"cost,":[130],"with":[131,186,221,292],"respect":[132,187,222,293],"demanding":[135],"models.":[138],"distributions":[142],"ligand":[147],"learned":[148],"(or":[149],"eventually,":[150],"pre-trained)":[151],"embeddings,":[152],"observe":[154],"how":[155,171,287],"they":[156,164,172],"classify":[157],"proteins":[159],"depending":[160,178,271],"(super)families":[163],"belong":[165],"(for":[167,192],"former),":[169],"distribute":[173],"embedding":[176],"space":[177],"their":[183],"affinities,":[185,253],"given":[190],"latter).":[194],"take":[196],"advantage":[197],"graph":[200],"representations":[201],"ligands":[204],"further":[206],"approach":[207],"explainability":[208],"an":[210,265],"atom-wise":[211],"level,":[212],"computing":[214],"directional":[216,278],"derivative":[217],"model":[220],"each":[224,295],"atoms":[227,262],"ligand.":[230],"This":[231],"method,":[232],"unlike":[233],"other":[234],"derivative-based":[235],"approaches":[236],"such":[237],"Grad-CAM":[239],"variants,":[241],"turns":[242],"out":[243],"be":[245],"extremely":[246],"useful":[247],"regression":[249],"tasks":[250],"direct":[257],"means":[258],"assessing":[260],"contribute":[263],"increase/decrease":[266],"affinity,":[270],"both":[273],"sign":[275],"derivative,":[279],"its":[282],"absolute":[283],"value-an":[284],"indication":[285],"steep":[288],"function":[290],"atom.":[296]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-08-10T00:00:00"}