{"id":"https://openalex.org/W7212064314","doi":"https://doi.org/10.26434/chemrxiv.15008530/v1","title":"Plasma Protein Binding Prediction under Scaffold Split: Tree Models, ChemBERTa, Graph Networks, and Late Fusion","display_name":"Plasma Protein Binding Prediction under Scaffold Split: Tree Models, ChemBERTa, Graph Networks, and Late Fusion","publication_year":2026,"publication_date":"2026-09-09","ids":{"openalex":"https://openalex.org/W7212064314","doi":"https://doi.org/10.26434/chemrxiv.15008530/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15008530/v1","doi":"https://doi.org/10.26434/chemrxiv.15008530/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008530/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008530/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":"acceptedVersion","is_accepted":true,"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.15008530/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071996996","display_name":"Pradyumna K. Pradhan","orcid":"https://orcid.org/0009-0005-3311-1270","observed_orcids":["https://orcid.org/0009-0005-3311-1270"]},"institutions":[{"id":"https://openalex.org/I169335092","display_name":"University of North Carolina at Greensboro","ror":"https://ror.org/04fnxsj42","country_code":"US","type":"education","lineage":["https://openalex.org/I169335092"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pradyumna Kumar Pradhan","raw_affiliation_strings":["University of North Carolina at Greensboro (UNC Greensboro"],"raw_orcid":"https://orcid.org/0009-0005-3311-1270","affiliations":[{"raw_affiliation_string":"University of North Carolina at Greensboro (UNC Greensboro","institution_ids":["https://openalex.org/I169335092"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5071996996"],"corresponding_institution_ids":["https://openalex.org/I169335092"],"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":0.00019999999494757503,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/bemis-murcko-scaffolds","display_name":"Bemis-Murcko scaffolds","score":0.7979999780654907},{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.8830000162124634},{"id":"https://openalex.org/keywords/chemberta","display_name":"ChemBERTa","score":0.9959999918937683},{"id":"https://openalex.org/keywords/decision-level-fusion","display_name":"decision fusion","score":0.7649999856948853},{"id":"https://openalex.org/keywords/tree-based-models","display_name":"tree-based models","score":0.8799999952316284},{"id":"https://openalex.org/keywords/random-forest","display_name":"random forest","score":0.9470000267028809},{"id":"https://openalex.org/keywords/xgboost","display_name":"XGBoost","score":0.9990000128746033},{"id":"https://openalex.org/keywords/admet-properties","display_name":"ADMET properties","score":0.7490000128746033},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"drug discovery","score":0.7149999737739563}],"concepts":[{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.7504000067710876},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6424999833106995},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5626000165939331},{"id":"https://openalex.org/C89429830","wikidata":"https://www.wikidata.org/wiki/Q735710","display_name":"Scaffold","level":2,"score":0.5105999708175659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.498199999332428},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4722999930381775},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.44769999384880066},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4320000112056732},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.398499995470047},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3937000036239624},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C47458327","wikidata":"https://www.wikidata.org/wiki/Q910404","display_name":"Random graph","level":3,"score":0.33709999918937683},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3230000138282776},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.310699999332428},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29350000619888306},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2816999852657318},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.27230000495910645},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15008530/v1","doi":"https://doi.org/10.26434/chemrxiv.15008530/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008530/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008530/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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15008530/v1","doi":"https://doi.org/10.26434/chemrxiv.15008530/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008530/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008530/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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.4000000059604645}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212064314.pdf","grobid_xml":"https://content.openalex.org/works/W7212064314.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1988037271","https://openalex.org/W2019678805","https://openalex.org/W2060531713","https://openalex.org/W2118630726","https://openalex.org/W2157052444","https://openalex.org/W2594183968","https://openalex.org/W2766878249","https://openalex.org/W3093934881"],"related_works":["https://openalex.org/W4406658272","https://openalex.org/W4213426032","https://openalex.org/W4411248094","https://openalex.org/W2781120690","https://openalex.org/W4409909846","https://openalex.org/W2984014547","https://openalex.org/W4403827637","https://openalex.org/W4380786758","https://openalex.org/W3116202926","https://openalex.org/W7217788835"],"abstract_inverted_index":{"From":[0],"idea":[1],"generation":[2],"to":[3,29,34,36,45],"testing,":[4],"drug":[5],"discovery":[6],"is":[7,101],"a":[8,168,190,196],"lengthy":[9],"and":[10,41,61,90,111,136,158],"expensive":[11],"process.":[12],"Rather":[13],"than":[14,163,176,194,214],"chasing":[15],"all":[16],"of":[17,88,92,97,114,117],"their":[18,47],"molecule":[19],"ideas,":[20],"scientists":[21],"prioritize":[22],"certain":[23],"molecules":[24,131],"that":[25,129,152],"are":[26],"more":[27,212],"likely":[28],"be":[30],"successful,":[31],"from":[32,72],"synthesis":[33],"safety":[35],"therapeutic":[37],"use.":[38],"Machine":[39],"learning":[40],"AI":[42],"enable":[43],"researchers":[44],"narrow":[46],"candidate":[48],"choices":[49],"by":[50,132],"predicting":[51],"important":[52],"properties":[53],"such":[54],"as":[55],"ADMET":[56],"(Absorption,":[57],"Distribution,":[58],"Metabolism,":[59],"Excretion,":[60],"Toxicity).":[62],"This":[63,149],"study":[64,121,150],"uses":[65],"the":[66,118,123,133,138,143,154,164,171,177,186,203,209],"Plasma":[67],"Protein":[68],"Binding":[69],"(PPB)":[70],"dataset":[71],"DeepChem\u2019s":[73],"MoleculeNet,":[74],"with":[75],"several":[76],"graph":[77],"neural":[78,99],"networks":[79],"(GNNs),":[80],"ChemBERTa":[81,159],"(a":[82],"language":[83],"model":[84,188,204],"for":[85,153],"SMILES":[86],"strings":[87],"molecules),":[89],"fusions":[91],"these":[93,98],"models.":[94,166,182],"The":[95],"performance":[96],"models":[100,124,160,173],"compared":[102],"against":[103],"two":[104],"standard":[105],"tree-based":[106],"models:":[107],"Random":[108,183],"Forest":[109],"(RF)":[110],"XGBoost.":[112],"Instead":[113],"random":[115,217],"splitting":[116,128,184,202],"dataset,":[119,156],"this":[120],"evaluates":[122],"based":[125],"on":[126,185,195,206],"scaffold":[127,135,201],"separates":[130],"Bemis\u2013Murcko":[134],"puts":[137],"entire":[139],"group":[140],"into":[141],"only":[142],"training,":[144],"validation,":[145],"or":[146,180],"test":[147],"set.":[148],"demonstrates":[151],"PPB":[155],"GNNs":[157,179],"perform":[161,174],"better":[162,175,191],"tree":[165],"On":[167],"mean":[169],"basis,":[170],"fusion":[172],"individual":[178],"ChemBERTa-only":[181],"RF":[187],"exhibits":[189],"R2":[192],"score":[193],"scaffold-split":[197],"dataset.":[198],"Because":[199],"under":[200,215],"predicts":[205],"unseen":[207],"cores,":[208],"task":[210],"becomes":[211],"difficult":[213],"regular":[216],"splitting.":[218]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-09-10T00:00:00"}