{"id":"https://openalex.org/W7212042004","doi":"https://doi.org/10.48550/arxiv.2609.05436","title":"Novel hybrid protein scaffold gap filling using weighted machine learning ensemble, beam search, and mass-constrained reranking","display_name":"Novel hybrid protein scaffold gap filling using weighted machine learning ensemble, beam search, and mass-constrained reranking","publication_year":2026,"publication_date":"2026-07-16","ids":{"openalex":"https://openalex.org/W7212042004","doi":"https://doi.org/10.48550/arxiv.2609.05436"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.05436","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.05436","pdf_url":"https://arxiv.org/pdf/2609.05436","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.05436","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5098790308","display_name":"Tahmid Enam Shrestha","orcid":"https://orcid.org/0009-0007-0075-5699","observed_orcids":["https://orcid.org/0009-0007-0075-5699"]},"institutions":[{"id":"https://openalex.org/I103434671","display_name":"American International University-Bangladesh","ror":"https://ror.org/02j8ga255","country_code":"BD","type":"education","lineage":["https://openalex.org/I103434671"]},{"id":"https://openalex.org/I4210096345","display_name":"City University","ror":"https://ror.org/00r1j9q42","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210096345"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Shrestha, Tahmid Enam","raw_affiliation_strings":["Department of Computer Science , American International University-Bangladesh , Dhaka 1229 , Bangladesh","Department of Computer Science and Engineering , City University , Dhaka 1340 , Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , American International University-Bangladesh , Dhaka 1229 , Bangladesh","institution_ids":["https://openalex.org/I103434671"]},{"raw_affiliation_string":"Department of Computer Science and Engineering , City University , Dhaka 1340 , Bangladesh","institution_ids":["https://openalex.org/I4210096345"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5150989624","display_name":"Md. Manzurul Hasan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hasan, Md. Manzurul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100714272","display_name":"Md. Rafiqul Islam","orcid":"https://orcid.org/0000-0002-8652-5187","observed_orcids":["https://orcid.org/0000-0002-8652-5187"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Islam, Md. Rafiqul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.8403000235557556,"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"}},"topics":[{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.8403000235557556,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.04490000009536743,"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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.032499998807907104,"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/ensemble-learning","display_name":"ensemble learning","score":0.5740000009536743},{"id":"https://openalex.org/keywords/beam-search","display_name":"beam search","score":0.828000009059906},{"id":"https://openalex.org/keywords/homologous-protein-sequences","display_name":"homologous protein sequences","score":0.7260000109672546},{"id":"https://openalex.org/keywords/carbonic-anhydrase-ii","display_name":"carbonic anhydrase II","score":0.9599999785423279}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6347000002861023},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5978000164031982},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5591999888420105},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5009999871253967},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4984999895095825},{"id":"https://openalex.org/C178180057","wikidata":"https://www.wikidata.org/wiki/Q7251477","display_name":"Protein superfamily","level":3,"score":0.48989999294281006},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4253000020980835},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.4052000045776367},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.3686999976634979},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33379998803138733},{"id":"https://openalex.org/C2779281246","wikidata":"https://www.wikidata.org/wiki/Q172847","display_name":"Peptide","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C27420735","wikidata":"https://www.wikidata.org/wiki/Q5968721","display_name":"Peptide mass fingerprinting","level":4,"score":0.2831999957561493},{"id":"https://openalex.org/C64894306","wikidata":"https://www.wikidata.org/wiki/Q849622","display_name":"Homologous chromosome","level":3,"score":0.27570000290870667},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.2554999887943268},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.05436","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.05436","pdf_url":"https://arxiv.org/pdf/2609.05436","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.05436","doi":"https://doi.org/10.48550/arxiv.2609.05436","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.05436","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.05436","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.05436","pdf_url":"https://arxiv.org/pdf/2609.05436","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212042004.pdf","grobid_xml":"https://content.openalex.org/works/W7212042004.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2078526678","https://openalex.org/W3164279786"],"related_works":["https://openalex.org/W4412584231","https://openalex.org/W4400519563","https://openalex.org/W4387425529","https://openalex.org/W4403680497","https://openalex.org/W2479935068","https://openalex.org/W4366310494","https://openalex.org/W4412810269","https://openalex.org/W7165131400","https://openalex.org/W4408954450","https://openalex.org/W4402553583"],"abstract_inverted_index":{"Protein":[0],"scaffold":[1,23,39],"gap":[2,40,115],"filling":[3,41],"is":[4],"an":[5],"important":[6],"computational":[7],"task":[8,73],"in":[9],"protein":[10,38,48,191],"sequence":[11,196],"reconstruction,":[12,116,133],"where":[13],"missing":[14,124,190],"amino":[15,79],"acid":[16,80],"regions":[17,192],"must":[18],"be":[19],"inferred":[20],"from":[21,50,127],"incomplete":[22],"information.":[24],"This":[25],"study":[26],"proposes":[27],"a":[28,77,110],"hybrid":[29,141],"machine":[30,91],"learning":[31,92],"and":[32,44,54,66,86,100,103,155,170,203],"mass":[33,145,153,201],"constrained":[34],"reranking":[35,142],"framework":[36,160,186],"for":[37],"under":[42],"known-gap-size":[43],"known-gapmass":[45],"settings.":[46],"Homologous":[47],"sequences":[49,126],"MabCampath,":[51],"P5A":[52],"proteoform,":[53],"carbonic":[55],"anhydrase":[56],"2":[57],"were":[58,94,107],"used":[59,120],"to":[60,121],"generate":[61,122],"masked":[62],"11-mer":[63],"residue-level":[64,128,163],"samples":[65],"fullgap":[67],"evaluation":[68],"cases.":[69,179],"The":[70,158],"residue":[71],"prediction":[72],"was":[74,119,138],"formulated":[75],"as":[76],"20-class":[78],"classification":[81],"problem":[82],"using":[83,96],"first-,":[84],"middle-,":[85],"last-position":[87],"masking.":[88],"Multiple":[89],"classical":[90],"models":[93,106],"trained":[95],"raw":[97],"encoded,":[98],"row-average,":[99],"SVD-reduced":[101],"features,":[102],"the":[104,184],"strongest":[105],"combined":[108,139],"through":[109],"validation-accuracy-weighted":[111],"ensemble.":[112],"For":[113,131],"known-size":[114,167],"beam":[117],"search":[118],"complete":[123],"peptide":[125,200],"probability":[129],"estimates.":[130],"known-mass":[132,177],"mass-constrained":[134],"homologous":[135,147,198],"candidate":[136],"retrieval":[137],"with":[140],"based":[143],"on":[144,174],"validity,":[146],"frequency,":[148],"context":[149],"support,":[150],"ensemble":[151],"likelihood,":[152],"error,":[154],"length":[156],"penalty.":[157],"proposed":[159,185],"achieved":[161],"95.41%":[162],"validation":[164],"accuracy,":[165,169],"87.50%":[166],"exact-match":[168],"100%":[171],"top-5":[172],"recovery":[173],"seven":[175],"CAH2":[176],"benchmark":[178],"These":[180],"results":[181],"indicate":[182],"that":[183],"can":[187],"effectively":[188],"reconstruct":[189],"by":[193],"integrating":[194],"local":[195],"learning,":[197],"evidence,":[199],"constraints,":[202],"biochemical":[204],"validation.":[205]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-10T00:00:00"}