{"id":"https://openalex.org/W4407230372","doi":"https://doi.org/10.21203/rs.3.rs-5855710/v1","title":"Accurate Prediction of Protein Complex Stoichiometry by Integrating AlphaFold3 and Template Information","display_name":"Accurate Prediction of Protein Complex Stoichiometry by Integrating AlphaFold3 and Template Information","publication_year":2025,"publication_date":"2025-02-06","ids":{"openalex":"https://openalex.org/W4407230372","doi":"https://doi.org/10.21203/rs.3.rs-5855710/v1","pmid":"https://pubmed.ncbi.nlm.nih.gov/39975926","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/11838762"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-5855710/v1","doi":"https://doi.org/10.21203/rs.3.rs-5855710/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-5855710/v1","pdf_url":"https://www.researchsquare.com/article/rs-5855710/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"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":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.researchsquare.com/article/rs-5855710/latest.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044354277","display_name":"Jianlin Jack Cheng","orcid":"https://orcid.org/0000-0003-0305-2853","observed_orcids":["https://orcid.org/0000-0003-0305-2853"]},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianlin Cheng","raw_affiliation_strings":["University of Missouri"],"raw_orcid":"https://orcid.org/0000-0003-0305-2853","affiliations":[{"raw_affiliation_string":"University of Missouri","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414623","display_name":"Jian Liu","orcid":"https://orcid.org/0000-0001-7484-401X","observed_orcids":["https://orcid.org/0000-0001-7484-401X","https://orcid.org/0000-0002-8317-3462"]},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Liu","raw_affiliation_strings":["University of Missouri - Columbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Missouri - Columbia","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115894115","display_name":"Pawan Neupane","orcid":"https://orcid.org/0009-0008-5283-4951","observed_orcids":["https://orcid.org/0009-0008-5283-4951","https://orcid.org/0009-0009-1698-7691"]},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pawan Neupane","raw_affiliation_strings":["University of Missouri - Columbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Missouri - Columbia","institution_ids":["https://openalex.org/I76835614"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76835614"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9897000193595886,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9897000193595886,"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/T11162","display_name":"Enzyme Structure and Function","score":0.005400000140070915,"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":0.0015999999595806003,"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/quaternary-structure","display_name":"quaternary structure","score":0.8889999985694885},{"id":"https://openalex.org/keywords/alphafold-3","display_name":"AlphaFold3","score":0.9779999852180481},{"id":"https://openalex.org/keywords/template-based-structure-prediction","display_name":"template-based structure prediction","score":0.8190000057220459},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"protein structure prediction","score":0.6570000052452087},{"id":"https://openalex.org/keywords/casp16","display_name":"CASP16","score":0.7620000243186951}],"concepts":[{"id":"https://openalex.org/C144082473","wikidata":"https://www.wikidata.org/wiki/Q213185","display_name":"Stoichiometry","level":2,"score":0.8291857242584229},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.602651834487915},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5118004679679871},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.3946118950843811},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.18856710195541382},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.15313538908958435},{"id":"https://openalex.org/C147789679","wikidata":"https://www.wikidata.org/wiki/Q11372","display_name":"Physical chemistry","level":1,"score":0.06005203723907471}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21203/rs.3.rs-5855710/v1","doi":"https://doi.org/10.21203/rs.3.rs-5855710/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-5855710/v1","pdf_url":"https://www.researchsquare.com/article/rs-5855710/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"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":"Research Square","raw_type":"posted-content"},{"id":"pmid:39975926","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39975926","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":"Research square","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:11838762","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11838762","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11838762/pdf/nihpp-rs5855710v1.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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Res Sq","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-5855710/v1","doi":"https://doi.org/10.21203/rs.3.rs-5855710/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-5855710/v1","pdf_url":"https://www.researchsquare.com/article/rs-5855710/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"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":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3619790786","display_name":"Deep transformers for integrating protein sequence, structure and interaction data to predict function","funder_award_id":"2308699","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7450496187","display_name":"Distance-based ab initio protein structure prediction","funder_award_id":"R01GM093123","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G9000876154","display_name":"Deep learning methods for automated and accurate reconstruction of protein structures from cryo-EM image data","funder_award_id":"R01GM146340","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"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/W4407230372.pdf","grobid_xml":"https://content.openalex.org/works/W4407230372.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2069458148","https://openalex.org/W2106612397","https://openalex.org/W2145268834","https://openalex.org/W2161151688","https://openalex.org/W2751260413","https://openalex.org/W3136918052","https://openalex.org/W3177828909","https://openalex.org/W4293475204","https://openalex.org/W4386525930","https://openalex.org/W4388571183","https://openalex.org/W4391604520","https://openalex.org/W4396721167","https://openalex.org/W4398232099"],"related_works":["https://openalex.org/W7156179189","https://openalex.org/W4415395068","https://openalex.org/W4406817009","https://openalex.org/W7136192063","https://openalex.org/W4410941452","https://openalex.org/W4408285263","https://openalex.org/W4398232099","https://openalex.org/W4387209806","https://openalex.org/W4391604520","https://openalex.org/W7154719906"],"abstract_inverted_index":{"Abstract":[0],"Protein":[1,98],"structure":[2,15,53],"prediction":[3,27],"methods":[4,39],"require":[5],"stoichiometry":[6,26,140],"information":[7,21,86],"(i.e.,":[8],"subunit":[9],"counts)":[10],"to":[11,59],"predict":[12,60],"the":[13,90,118,123],"quaternary":[14],"of":[16,95,117,126],"protein":[17,137],"complexes.":[18],"However,":[19],"this":[20,41,44],"is":[22],"often":[23],"unavailable,":[24],"making":[25],"crucial":[28],"for":[29,70,97,135],"complexes":[30,138],"with":[31,55,84],"unknown":[32],"stoichiometry.":[33,61],"Despite":[34],"its":[35,133],"importance,":[36],"few":[37],"computational":[38],"address":[40],"challenge.":[42],"In":[43,89],"study,":[45],"we":[46],"present":[47],"an":[48],"approach":[49],"that":[50],"integrates":[51],"AlphaFold3":[52,78],"predictions":[54,83,130],"homologous":[56],"template":[57],"data":[58],"The":[62],"method":[63,103],"generates":[64],"candidate":[65],"stoichiometries,":[66],"builds":[67],"structural":[68],"models":[69],"them":[71,75],"using":[72],"AlphaFold3,":[73],"ranks":[74],"based":[76],"on":[77],"scores,":[79],"and":[80,108,128,131],"further":[81],"refine":[82],"template-based":[85,129],"when":[87],"available.":[88],"16th":[91],"community-wide":[92],"Critical":[93],"Assessment":[94],"Techniques":[96],"Structure":[99],"Prediction":[100],"(CASP16),":[101],"our":[102],"achieved":[104],"71.4%":[105],"top-1":[106],"accuracy":[107],"92.9%":[109],"top-3":[110],"accuracy,":[111],"outperforming":[112],"other":[113],"predictors":[114],"in":[115],"terms":[116],"overall":[119],"performance.":[120],"This":[121],"demonstrates":[122],"complementary":[124],"strengths":[125],"AlphaFold3-":[127],"highlights":[132],"applicability":[134],"uncharacterized":[136],"lacking":[139],"data.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2025-02-07T00:00:00"}