{"id":"https://openalex.org/W7212388221","doi":"https://doi.org/10.64898/2026.09.10.750674","title":"Predicting Capsid Protein Binding Sites in Single-Stranded RNA Viruses Using Machine Learning from Local Geometric Features","display_name":"Predicting Capsid Protein Binding Sites in Single-Stranded RNA Viruses Using Machine Learning from Local Geometric Features","publication_year":2026,"publication_date":"2026-09-11","ids":{"openalex":"https://openalex.org/W7212388221","doi":"https://doi.org/10.64898/2026.09.10.750674","pmid":"https://pubmed.ncbi.nlm.nih.gov/42818729","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13622615"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.10.750674","doi":"https://doi.org/10.64898/2026.09.10.750674","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.10.750674","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/11/2026.09.10.750674.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/11/2026.09.10.750674.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5151465967","display_name":"Yunong Melody Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunong Melody Wu","raw_affiliation_strings":["Rye Country Day School, Rye, NY 10580"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rye Country Day School, Rye, NY 10580","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075861212","display_name":"Junjie Zhang","orcid":"https://orcid.org/0000-0002-7912-0819","observed_orcids":["https://orcid.org/0000-0002-7912-0819"]},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Junjie Zhang","raw_affiliation_strings":["Center for Phage Technology, Department of Biochemistry and Biophysics, Texas A&M University, College Station, TX 77843"],"raw_orcid":"https://orcid.org/0000-0002-7912-0819","affiliations":[{"raw_affiliation_string":"Center for Phage Technology, Department of Biochemistry and Biophysics, Texas A&M University, College Station, TX 77843","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5075861212"],"corresponding_institution_ids":["https://openalex.org/I91045830"],"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.6288999915122986,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.6288999915122986,"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":0.19529999792575836,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.0560000017285347,"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/single-stranded-rna-viruses","display_name":"single-stranded RNA viruses","score":0.9639999866485596},{"id":"https://openalex.org/keywords/rna-tertiary-structure","display_name":"RNA tertiary structure","score":0.7400000095367432},{"id":"https://openalex.org/keywords/local-geometric-features","display_name":"local geometric features","score":0.8140000104904175},{"id":"https://openalex.org/keywords/viral-genome-packaging","display_name":"viral genome packaging","score":0.7519999742507935},{"id":"https://openalex.org/keywords/neural-network-classification","display_name":"neural network classification","score":0.5889999866485596},{"id":"https://openalex.org/keywords/benchmark-dataset","display_name":"benchmark dataset","score":0.546999990940094}],"concepts":[{"id":"https://openalex.org/C202878990","wikidata":"https://www.wikidata.org/wiki/Q830465","display_name":"Capsid","level":3,"score":0.8641999959945679},{"id":"https://openalex.org/C67705224","wikidata":"https://www.wikidata.org/wiki/Q11053","display_name":"RNA","level":3,"score":0.8144000172615051},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.7037000060081482},{"id":"https://openalex.org/C41282012","wikidata":"https://www.wikidata.org/wiki/Q3928341","display_name":"RNA-binding protein","level":4,"score":0.48919999599456787},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.44369998574256897},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4431000053882599},{"id":"https://openalex.org/C107824862","wikidata":"https://www.wikidata.org/wiki/Q616005","display_name":"Binding site","level":2,"score":0.4415000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43860000371932983},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C126142528","wikidata":"https://www.wikidata.org/wiki/Q3771876","display_name":"Nucleic acid structure","level":4,"score":0.3885999917984009},{"id":"https://openalex.org/C85468374","wikidata":"https://www.wikidata.org/wiki/Q6589957","display_name":"Nucleic acid secondary structure","level":4,"score":0.3855000138282776},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C2775940340","wikidata":"https://www.wikidata.org/wiki/Q4840020","display_name":"Bacteriophage MS2","level":5,"score":0.36730000376701355},{"id":"https://openalex.org/C4668613","wikidata":"https://www.wikidata.org/wiki/Q4116110","display_name":"Structural alignment","level":5,"score":0.36250001192092896},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.34950000047683716},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32690000534057617},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C51639874","wikidata":"https://www.wikidata.org/wiki/Q167149","display_name":"Plasma protein binding","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C132677234","wikidata":"https://www.wikidata.org/wiki/Q3273544","display_name":"Structural motif","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.30799999833106995},{"id":"https://openalex.org/C2779174946","wikidata":"https://www.wikidata.org/wiki/Q751911","display_name":"RNA virus","level":4,"score":0.30799999833106995},{"id":"https://openalex.org/C96739231","wikidata":"https://www.wikidata.org/wiki/Q4914025","display_name":"Binding selectivity","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.2842000126838684},{"id":"https://openalex.org/C70636015","wikidata":"https://www.wikidata.org/wiki/Q4300350","display_name":"Molecular biophysics","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C191120209","wikidata":"https://www.wikidata.org/wiki/Q908902","display_name":"Structural biology","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C94671646","wikidata":"https://www.wikidata.org/wiki/Q207551","display_name":"Intron","level":3,"score":0.27309998869895935},{"id":"https://openalex.org/C119145174","wikidata":"https://www.wikidata.org/wiki/Q7251429","display_name":"Protein Data Bank","level":3,"score":0.2660999894142151},{"id":"https://openalex.org/C3018069271","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Structural protein","level":3,"score":0.26409998536109924},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C192772702","wikidata":"https://www.wikidata.org/wiki/Q2583975","display_name":"Structural genomics","level":3,"score":0.25099998712539673},{"id":"https://openalex.org/C65556437","wikidata":"https://www.wikidata.org/wiki/Q766195","display_name":"Protein Data Bank (RCSB PDB)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.64898/2026.09.10.750674","doi":"https://doi.org/10.64898/2026.09.10.750674","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.10.750674","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/11/2026.09.10.750674.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"},{"id":"pmh:oai:pubmedcentral.nih.gov:13622615","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13622615/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13622615/pdf/nihpp-2026.09.10.750674v1.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"bioRxiv","raw_type":"Text"},{"id":"pmid:42818729","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42818729","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"bioRxiv : the preprint server for biology","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.64898/2026.09.10.750674","doi":"https://doi.org/10.64898/2026.09.10.750674","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.10.750674","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/11/2026.09.10.750674.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G9000905351","display_name":"RNA penetrations into bacteria.","funder_award_id":"R01GM141659","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212388221.pdf","grobid_xml":"https://content.openalex.org/works/W7212388221.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2976217562","https://openalex.org/W2572980170","https://openalex.org/W4309362395","https://openalex.org/W4413105138","https://openalex.org/W1590764106","https://openalex.org/W7130593544","https://openalex.org/W4409628391","https://openalex.org/W2104686869","https://openalex.org/W4397009038","https://openalex.org/W1992326565"],"abstract_inverted_index":{"Selective":[0],"recognition":[1],"of":[2,16,23,45,86,98,107,123,154],"viral":[3,227],"RNA":[4,18,30,56,92,109,142,167,183,207,236,247],"by":[5,234,241],"capsid":[6,24,69,136,217],"proteins":[7],"is":[8,230],"essential":[9],"for":[10,216,264],"genome":[11,31,228],"packaging":[12,229],"during":[13],"the":[14,29,43,74,103,108,124,127,148,163,195,222],"assembly":[15],"single-stranded":[17],"(ssRNA)":[19],"viruses.":[20,271],"However,":[21],"identification":[22],"protein":[25,70,137],"binding":[26,71,89,138,168,218],"sites":[27,139,169],"in":[28,156],"remains":[32],"challenging":[33],"because":[34],"current":[35],"experimental":[36,171],"techniques":[37],"are":[38],"labor-intensive":[39],"and":[40,64,90,114,191,260],"low-throughput,":[41],"motivating":[42],"development":[44],"computational":[46],"approaches.":[47],"Here,":[48],"we":[49,81,173],"present":[50],"a":[51,78,83,96,131,157,262],"sequence-based":[52],"framework":[53],"that":[54,205,226],"integrates":[55],"tertiary":[57,208],"structural":[58,105,187,237],"modeling,":[59],"local":[60,104,177],"geometric":[61,99,118,178],"feature":[62],"extraction,":[63],"machine":[65],"learning":[66],"to":[67,101,134,176,268],"predict":[68,166],"sites.":[72],"Using":[73],"Q\u03b2":[75],"bacteriophage":[76],"as":[77],"proof-of-concept":[79],"system,":[80],"constructed":[82],"benchmark":[84,125],"dataset":[85],"experimentally":[87,192],"identified":[88],"non-binding":[91,141],"fragments.":[93],"We":[94],"designed":[95],"set":[97],"descriptors":[100,119],"characterize":[102],"features":[106,179],"backbone.":[110],"When":[111],"repeatedly":[112],"trained":[113],"tested":[115],"with":[116],"these":[117],"on":[120],"different":[121],"subsets":[122],"dataset,":[126],"neural":[128],"network":[129],"showed":[130],"strong":[132],"ability":[133],"distinguish":[135],"from":[140,181],"fragments,":[143],"achieving":[144],"an":[145],"area":[146],"under":[147],"receiver":[149],"operating":[150],"characteristic":[151],"curve":[152],"(AUC)":[153],"0.88":[155],"5-fold":[158],"cross-validation.":[159],"To":[160],"evaluate":[161],"whether":[162],"model":[164],"can":[165],"without":[170],"structures,":[172],"applied":[174],"it":[175],"derived":[180],"AlphaFold-predicted":[182],"structures.":[184],"Despite":[185],"substantial":[186],"differences":[188],"between":[189],"predicted":[190],"determined":[193],"models,":[194],"classifier":[196],"retained":[197],"considerable":[198],"predictive":[199],"performance":[200],"(AUC":[201],"=":[202],"0.75),":[203],"indicating":[204],"approximate":[206],"structures":[209],"may":[210],"still":[211],"preserve":[212],"biologically":[213],"meaningful":[214],"information":[215],"site":[219],"prediction.":[220],"Furthermore,":[221],"failed":[223],"predictions":[224],"suggest":[225],"not":[231],"only":[232],"governed":[233],"intrinsic":[235],"features,":[238],"but":[239],"also":[240],"additional":[242],"dynamic":[243],"factors":[244],"beyond":[245],"static":[246],"conformations.":[248],"In":[249],"summary,":[250],"our":[251],"findings":[252],"provide":[253],"new":[254],"mechanistic":[255],"insights":[256],"into":[257],"RNA-capsid":[258],"interactions":[259],"establish":[261],"foundation":[263],"extending":[265],"this":[266],"approach":[267],"diverse":[269],"ssRNA":[270]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-09-13T00:00:00"}