{"id":"https://openalex.org/W4402580966","doi":"https://doi.org/10.1371/journal.pcbi.1012459","title":"The neglected giants: Uncovering the prevalence and functional groups of huge proteins in proteomes","display_name":"The neglected giants: Uncovering the prevalence and functional groups of huge proteins in proteomes","publication_year":2024,"publication_date":"2024-09-16","ids":{"openalex":"https://openalex.org/W4402580966","doi":"https://doi.org/10.1371/journal.pcbi.1012459","pmid":"https://pubmed.ncbi.nlm.nih.gov/39283951"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1012459","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1012459","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1012459&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1012459&type=printable","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107290179","display_name":"Anibal S Amaral","orcid":"https://orcid.org/0009-0000-7987-8868"},"institutions":[{"id":"https://openalex.org/I4210111405","display_name":"Centro Andaluz de Biolog\u00eda del Desarrollo","ror":"https://ror.org/01v5e3436","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210111405","https://openalex.org/I918821925","https://openalex.org/I95013407"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Anibal S. Amaral","raw_affiliation_strings":["Centro Andaluz de Biolog\u00eda del Desarrollo, Consejo Superior de Investigaciones Cient\u00edficas, Campus Universidad Pablo de Olavide, Seville, Spain"],"raw_orcid":"https://orcid.org/0009-0000-7987-8868","affiliations":[{"raw_affiliation_string":"Centro Andaluz de Biolog\u00eda del Desarrollo, Consejo Superior de Investigaciones Cient\u00edficas, Campus Universidad Pablo de Olavide, Seville, Spain","institution_ids":["https://openalex.org/I4210111405"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040059021","display_name":"Damien P. Devos","orcid":"https://orcid.org/0000-0002-9453-4753"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I154526488","display_name":"Inserm","ror":"https://ror.org/02vjkv261","country_code":"FR","type":"government","lineage":["https://openalex.org/I154526488"]},{"id":"https://openalex.org/I3018718406","display_name":"Centre Hospitalier Universitaire de Lille","ror":"https://ror.org/02ppyfa04","country_code":"FR","type":"healthcare","lineage":["https://openalex.org/I3018718406"]},{"id":"https://openalex.org/I4210098529","display_name":"Center for Infection and Immunity of Lille","ror":"https://ror.org/00dyt5s15","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I2279609970","https://openalex.org/I2800921988","https://openalex.org/I4210093160","https://openalex.org/I4210096427","https://openalex.org/I4210098529"]},{"id":"https://openalex.org/I4210111405","display_name":"Centro Andaluz de Biolog\u00eda del Desarrollo","ror":"https://ror.org/01v5e3436","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210111405","https://openalex.org/I918821925","https://openalex.org/I95013407"]}],"countries":["ES","FR"],"is_corresponding":true,"raw_author_name":"Damien P. Devos","raw_affiliation_strings":["CNRS, Inserm, CHU Lille, Institut Pasteur de Lille, U1019-UMR 9017-CIIL-Centre d'Infection et d'Immunit\u00e9 de Lille, University of Lille, Lille, France","Centro Andaluz de Biolog\u00eda del Desarrollo, Consejo Superior de Investigaciones Cient\u00edficas, Campus Universidad Pablo de Olavide, Seville, Spain"],"raw_orcid":"https://orcid.org/0000-0002-9453-4753","affiliations":[{"raw_affiliation_string":"CNRS, Inserm, CHU Lille, Institut Pasteur de Lille, U1019-UMR 9017-CIIL-Centre d'Infection et d'Immunit\u00e9 de Lille, University of Lille, Lille, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I3018718406","https://openalex.org/I4210098529"]},{"raw_affiliation_string":"Centro Andaluz de Biolog\u00eda del Desarrollo, Consejo Superior de Investigaciones Cient\u00edficas, Campus Universidad Pablo de Olavide, Seville, Spain","institution_ids":["https://openalex.org/I4210111405"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5040059021"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I3018718406","https://openalex.org/I4210098529","https://openalex.org/I4210111405"],"apc_list":{"value":3043,"currency":"USD","value_usd":3043},"apc_paid":{"value":3043,"currency":"USD","value_usd":3043},"fwci":0.3229,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57413461,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"20","issue":"9","first_page":"e1012459","last_page":"e1012459"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9987999796867371,"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":0.9987999796867371,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.998199999332428,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9976000189781189,"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/proteome","display_name":"Proteome","score":0.5826781988143921},{"id":"https://openalex.org/keywords/biological-evolution","display_name":"Biological evolution","score":0.44778335094451904},{"id":"https://openalex.org/keywords/evolutionary-biology","display_name":"Evolutionary biology","score":0.4449827969074249},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3982665538787842},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3871602714061737},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3701397776603699},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.330721914768219},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.2306504249572754},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.12456327676773071}],"concepts":[{"id":"https://openalex.org/C104397665","wikidata":"https://www.wikidata.org/wiki/Q860947","display_name":"Proteome","level":2,"score":0.5826781988143921},{"id":"https://openalex.org/C2988562018","wikidata":"https://www.wikidata.org/wiki/Q1063","display_name":"Biological evolution","level":2,"score":0.44778335094451904},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.4449827969074249},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3982665538787842},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3871602714061737},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3701397776603699},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.330721914768219},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2306504249572754},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.12456327676773071}],"mesh":[{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1371/journal.pcbi.1012459","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1012459","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1012459&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},{"id":"pmid:39283951","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39283951","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,"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":"PLoS computational biology","raw_type":"Journal Article"},{"id":"pmh:oai:digital.csic.es:10261/379969","is_oa":false,"landing_page_url":"http://hdl.handle.net/10261/379969","pdf_url":null,"source":{"id":"https://openalex.org/S4306400616","display_name":"DIGITAL.CSIC (Spanish National Research Council (CSIC))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I134820265","host_organization_name":"Consejo Superior de Investigaciones Cient\u00edficas","host_organization_lineage":["https://openalex.org/I134820265"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"http://purl.org/coar/resource_type/c_6501"},{"id":"pmh:oai:pubmedcentral.nih.gov:11573180","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11573180","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11573180/pdf/pcbi.1012459.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,"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":"PLoS Comput Biol","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:bfbb542bb1894acca65bc434933df58c","is_oa":false,"landing_page_url":"https://doaj.org/article/bfbb542bb1894acca65bc434933df58c","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, Vol 20, Iss 9, p e1012459 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1012459","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1012459","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1012459&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","score":0.5400000214576721,"display_name":"Life in Land"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306202","display_name":"Gordon and Betty Moore Foundation","ror":"https://ror.org/006wxqw41"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402580966.pdf","grobid_xml":"https://content.openalex.org/works/W4402580966.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1992121070","https://openalex.org/W2041619316","https://openalex.org/W2048606107","https://openalex.org/W2052390711","https://openalex.org/W2069268338","https://openalex.org/W2101220662","https://openalex.org/W2117337399","https://openalex.org/W2120366876","https://openalex.org/W2138024120","https://openalex.org/W2138122982","https://openalex.org/W2142961247","https://openalex.org/W2159675211","https://openalex.org/W2328903896","https://openalex.org/W2406842129","https://openalex.org/W2472341050","https://openalex.org/W2580290460","https://openalex.org/W2599791352","https://openalex.org/W2734798616","https://openalex.org/W2766342395","https://openalex.org/W2883298854","https://openalex.org/W2953008890","https://openalex.org/W3042868212","https://openalex.org/W3086669575","https://openalex.org/W3112376646","https://openalex.org/W3127140457","https://openalex.org/W3135915195","https://openalex.org/W3165745490","https://openalex.org/W3177828909","https://openalex.org/W3203343200","https://openalex.org/W3217658709","https://openalex.org/W4205192056","https://openalex.org/W4206950245","https://openalex.org/W4220855533","https://openalex.org/W4220987054","https://openalex.org/W4327568911","https://openalex.org/W4379966447","https://openalex.org/W6791819864"],"related_works":["https://openalex.org/W2165886284","https://openalex.org/W2600687590","https://openalex.org/W2900384991","https://openalex.org/W3191028122","https://openalex.org/W2075474900","https://openalex.org/W3086741367","https://openalex.org/W2018600661","https://openalex.org/W2014935796","https://openalex.org/W2083501474","https://openalex.org/W3169234491"],"abstract_inverted_index":{"An":[0],"often-overlooked":[1],"aspect":[2],"of":[3,10,45,108,110,113,140,163,183,189],"biology":[4,197],"is":[5],"formed":[6],"by":[7,154],"the":[8,11,43,48,54,57,87,138,142,164,170,178,184],"outliers":[9],"protein":[12],"length":[13],"distribution,":[14],"specifically":[15],"those":[16],"proteins":[17,30],"with":[18,47,56],"more":[19,37,85],"than":[20,38,86],"5000":[21],"amino":[22],"acids,":[23],"which":[24],"we":[25,35,67,98],"refer":[26],"to":[27,119,148],"as":[28,73,124,129,132],"huge":[29],"(HPs).":[31],"By":[32],"examining":[33],"UniprotKB,":[34],"discovered":[36],"41":[39],"000":[40],"HPs":[41,61,168,191],"throughout":[42],"tree":[44],"life,":[46],"majority":[49],"found":[50],"in":[51,135],"eukaryotes.":[52,136],"Notably,":[53],"phyla":[55],"highest":[58],"propensity":[59],"for":[60,81,166,180],"are":[62],"Apicomplexa":[63],"and":[64,127,186,192,198],"Fornicata.":[65],"Moreover,":[66],"observed":[68],"that":[69],"certain":[70],"bacteria,":[71,141],"such":[72,123],"Elusimicrobiota":[74],"or":[75,131,157],"Planctomycetota,":[76],"have":[77,145],"a":[78],"higher":[79],"tendency":[80],"encoding":[82],"HPs,":[83,114],"even":[84],"average":[88],"eukaryote.":[89],"To":[90],"investigate":[91],"if":[92],"these":[93,190],"macro-polypeptides":[94],"represent":[95],"\"real\"":[96],"proteins,":[97],"explored":[99],"several":[100],"indirect":[101],"metrics.":[102],"Additionally,":[103],"orthology":[104],"analyses":[105],"reveals":[106],"thousands":[107],"clusters":[109,144],"homologous":[111],"sequences":[112],"revealing":[115],"functional":[116,173],"groups":[117],"related":[118,147],"key":[120],"cellular":[121,185],"processes":[122],"cytoskeleton":[125],"organization":[126],"functioning":[128],"chaperones":[130],"E3-ubiquitin":[133],"ligases":[134],"In":[137],"case":[139],"major":[143],"functions":[146],"non-ribosomomal":[149],"peptide":[150],"synthesis/polyketide":[151],"synthesis,":[152],"followed":[153],"pathogen-host":[155],"attachment":[156],"recognition":[158],"surface":[159],"proteins.":[160],"Further":[161],"exploration":[162],"annotations":[165],"each":[167],"supported":[169],"previously":[171],"identified":[172],"groups.":[174],"These":[175],"findings":[176],"underscore":[177],"need":[179],"further":[181],"investigation":[182],"ecological":[187],"roles":[188],"their":[193],"potential":[194],"impact":[195],"on":[196],"biotechnology.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-27T14:10:00.468798","created_date":"2025-10-10T00:00:00"}
