{"id":"https://openalex.org/W7220374852","doi":"https://doi.org/10.26434/chemrxiv.15009827/v1","title":"Drugon: Phase-Encoded Morgan Fingerprints Match Pretrained Chemical Transformers in Low-Data Affinity Prediction","display_name":"Drugon: Phase-Encoded Morgan Fingerprints Match Pretrained Chemical Transformers in Low-Data Affinity Prediction","publication_year":2026,"publication_date":"2026-10-04","ids":{"openalex":"https://openalex.org/W7220374852","doi":"https://doi.org/10.26434/chemrxiv.15009827/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15009827/v1","doi":"https://doi.org/10.26434/chemrxiv.15009827/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15009827/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009827/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.15009827/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157518232","display_name":"Masoud Azizi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I41832843","display_name":"University of Tabriz","ror":"https://ror.org/01papkj44","country_code":"IR","type":"education","lineage":["https://openalex.org/I41832843"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Masoud Azizi","raw_affiliation_strings":["Department of Computer Science , University of Tabriz , Tabriz , Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Tabriz , Tabriz , Iran","institution_ids":["https://openalex.org/I41832843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5157518232"],"corresponding_institution_ids":["https://openalex.org/I41832843"],"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":0.9990000128746033,"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":0.9990000128746033,"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":0.0003000000142492354,"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":9.999999747378752e-05,"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/molecular-property-prediction","display_name":"molecular property prediction","score":0.5580000281333923},{"id":"https://openalex.org/keywords/binding-affinity-prediction","display_name":"binding affinity prediction","score":0.6919999718666077},{"id":"https://openalex.org/keywords/low-data-regimes","display_name":"low-data regimes","score":0.6019999980926514},{"id":"https://openalex.org/keywords/chemberta","display_name":"ChemBERTa","score":0.9070000052452087},{"id":"https://openalex.org/keywords/lightgbm-regression","display_name":"LightGBM regression","score":0.8190000057220459},{"id":"https://openalex.org/keywords/c-abl-kinase","display_name":"c-Abl kinase","score":0.5299999713897705},{"id":"https://openalex.org/keywords/molecular-fingerprints","display_name":"molecular fingerprints","score":0.36899998784065247},{"id":"https://openalex.org/keywords/model-interpretability","display_name":"model interpretability","score":0.39100000262260437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6959999799728394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6525999903678894},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.5756000280380249},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5195000171661377},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46720001101493835},{"id":"https://openalex.org/C63222358","wikidata":"https://www.wikidata.org/wiki/Q6120337","display_name":"chEMBL","level":3,"score":0.45509999990463257},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.4348999857902527},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38179999589920044},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2777999937534332},{"id":"https://openalex.org/C168406668","wikidata":"https://www.wikidata.org/wiki/Q178022","display_name":"Fingerprint recognition","level":3,"score":0.26010000705718994},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15009827/v1","doi":"https://doi.org/10.26434/chemrxiv.15009827/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15009827/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009827/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.15009827/v1","doi":"https://doi.org/10.26434/chemrxiv.15009827/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15009827/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009827/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":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220374852.pdf","grobid_xml":"https://content.openalex.org/works/W7220374852.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W3001279689","https://openalex.org/W3093934881","https://openalex.org/W4283641078"],"related_works":["https://openalex.org/W4306976400","https://openalex.org/W4412553863","https://openalex.org/W2986232138","https://openalex.org/W7117874614","https://openalex.org/W3093934881","https://openalex.org/W7122763408","https://openalex.org/W7154955611","https://openalex.org/W7155040771","https://openalex.org/W7168281738","https://openalex.org/W4414063241"],"abstract_inverted_index":{"Pretrained":[0],"chemical":[1],"language":[2],"models":[3],"such":[4],"as":[5],"ChemBERTa":[6,99],"and":[7,27,56,100,142],"MoLFormer":[8],"have":[9],"become":[10],"the":[11,80,116,130,139],"default":[12],"choice":[13],"for":[14,97,102],"molecular":[15],"property":[16],"prediction.":[17],"However,":[18],"they":[19],"require":[20],"large":[21],"training":[22,59],"sets":[23],"to":[24,77],"fine-tune":[25],"effectively,":[26],"their":[28],"computational":[29],"footprint":[30],"is":[31],"substantial.":[32],"We":[33],"present":[34],"Drugon,":[35],"a":[36,41,47,86,111],"compact":[37],"alternative":[38],"based":[39],"on":[40,69],"Phase-Encoded":[42],"Morgan":[43,119],"fingerprint":[44,120],"combined":[45],"with":[46,95],"LightGBM":[48],"regressor.":[49],"Drugon":[50,84],"requires":[51],"approximately":[52],"15,000\u00d7":[53],"fewer":[54],"parameters":[55],"40\u00d7":[57],"less":[58],"time":[60],"than":[61],"fine-tuned":[62,98],"transformers,":[63],"while":[64],"achieving":[65],"higher":[66],"predictive":[67],"accuracy":[68],"three":[70,106],"independent":[71],"ChEMBL":[72],"targets":[73],"(n":[74,133],"=":[75,89],"1378":[76],"2000).":[78],"On":[79],"c-Abl":[81],"dataset":[82],"(CHEMBL4550),":[83],"reaches":[85],"Pearson":[87],"r":[88],"0.749":[90],"under":[91],"5-fold":[92],"cross-validation,":[93],"compared":[94],"0.605":[96],"0.551":[101],"MoLFormer.":[103],"Across":[104],"all":[105],"targets,":[107],"phase":[108],"encoding":[109],"provides":[110],"consistent,":[112],"non-negative":[113],"improvement":[114],"over":[115],"classical":[117],"binary":[118],"(\u2206r":[121],"\u2208":[122],"[0.000,":[123],"0.026]).":[124],"Our":[125],"results":[126],"suggest":[127],"that,":[128],"in":[129],"low-data":[131],"regime":[132],"<":[134],"2000),":[135],"fingerprint-based":[136],"methods":[137],"remain":[138],"most":[140],"efficient":[141],"interpretable":[143]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-10-06T00:00:00"}