{"id":"https://openalex.org/W4303981501","doi":"https://doi.org/10.3389/fbinf.2022.1019597","title":"SETH predicts nuances of residue disorder from protein embeddings","display_name":"SETH predicts nuances of residue disorder from protein embeddings","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4303981501","doi":"https://doi.org/10.3389/fbinf.2022.1019597","pmid":"https://pubmed.ncbi.nlm.nih.gov/36304335"},"language":"en","primary_location":{"id":"doi:10.3389/fbinf.2022.1019597","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2022.1019597","pdf_url":null,"source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3389/fbinf.2022.1019597","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071157934","display_name":"Dagmar Ilzh\u00f6fer","orcid":"https://orcid.org/0009-0005-2088-2826"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dagmar Ilzh\u00f6fer","raw_affiliation_strings":["Faculty of Informatics, TUM (Technical University of Munich), Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Informatics, TUM (Technical University of Munich), Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075726670","display_name":"Michael Heinzinger","orcid":"https://orcid.org/0000-0002-9601-3580"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Michael Heinzinger","raw_affiliation_strings":["Center of Doctoral Studies in Informatics and Its Applications (CeDoSIA), TUM Graduate School, Garching, Germany","Faculty of Informatics, TUM (Technical University of Munich), Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Doctoral Studies in Informatics and Its Applications (CeDoSIA), TUM Graduate School, Garching, Germany","institution_ids":[]},{"raw_affiliation_string":"Faculty of Informatics, TUM (Technical University of Munich), Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064905883","display_name":"Burkhard Rost","orcid":"https://orcid.org/0000-0003-0179-8424"},"institutions":[{"id":"https://openalex.org/I4210137766","display_name":"Institute for Advanced Study","ror":"https://ror.org/03xg85719","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210137766"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Burkhard Rost","raw_affiliation_strings":["Faculty of Informatics, TUM (Technical University of Munich), Munich, Germany","Institute for Advanced Study (TUM-IAS), TUM (Technical University of Munich), Garching, Germany","TUM School of Life Sciences Weihenstephan (WZW), TUM (Technical University of Munich), Freising, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Informatics, TUM (Technical University of Munich), Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Institute for Advanced Study (TUM-IAS), TUM (Technical University of Munich), Garching, Germany","institution_ids":["https://openalex.org/I4210137766","https://openalex.org/I62916508"]},{"raw_affiliation_string":"TUM School of Life Sciences Weihenstephan (WZW), TUM (Technical University of Munich), Freising, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5075726670"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":{"value":2125,"currency":"USD","value_usd":2125},"apc_paid":{"value":1893,"currency":"EUR","value_usd":2041},"fwci":3.604,"has_fulltext":true,"cited_by_count":55,"citation_normalized_percentile":{"value":0.94650231,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"2","issue":null,"first_page":"1019597","last_page":"1019597"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987999796867371,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9983000159263611,"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/residue","display_name":"Residue (chemistry)","score":0.5723154544830322},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3824062943458557},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.35540908575057983},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.35301339626312256},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.22967690229415894},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.16419950127601624}],"concepts":[{"id":"https://openalex.org/C2781338088","wikidata":"https://www.wikidata.org/wiki/Q903495","display_name":"Residue (chemistry)","level":2,"score":0.5723154544830322},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3824062943458557},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.35540908575057983},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.35301339626312256},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.22967690229415894},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.16419950127601624}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3389/fbinf.2022.1019597","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2022.1019597","pdf_url":null,"source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:36304335","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36304335","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":"Frontiers in bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:de00a53caa654b539bd3f89e5b7557d1","is_oa":true,"landing_page_url":"https://doaj.org/article/de00a53caa654b539bd3f89e5b7557d1","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Bioinformatics, Vol 2 (2022)","raw_type":"article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1690895","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1690895","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"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":"","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9580958","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9580958","pdf_url":null,"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":"Front Bioinform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3389/fbinf.2022.1019597","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2022.1019597","pdf_url":null,"source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1270295441","display_name":null,"funder_award_id":"DFG-GZ: RO1320/4-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G5931231857","display_name":null,"funder_award_id":"01IS17049","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G7542597935","display_name":null,"funder_award_id":"RO1320/4-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G8104252070","display_name":null,"funder_award_id":"031L0168","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320308269","display_name":"Alexander von Humboldt-Stiftung","ror":"https://ror.org/012kf4317"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":129,"referenced_works":["https://openalex.org/W45157614","https://openalex.org/W1236133676","https://openalex.org/W1501531009","https://openalex.org/W1554017431","https://openalex.org/W1834070694","https://openalex.org/W1948859676","https://openalex.org/W1971803615","https://openalex.org/W1985818354","https://openalex.org/W1989235034","https://openalex.org/W1994369967","https://openalex.org/W2004698009","https://openalex.org/W2006192061","https://openalex.org/W2008840001","https://openalex.org/W2010840375","https://openalex.org/W2016170088","https://openalex.org/W2027302413","https://openalex.org/W2028369611","https://openalex.org/W2030776726","https://openalex.org/W2038972833","https://openalex.org/W2045925085","https://openalex.org/W2050625197","https://openalex.org/W2051210555","https://openalex.org/W2055193239","https://openalex.org/W2061271983","https://openalex.org/W2063389953","https://openalex.org/W2064675550","https://openalex.org/W2069458148","https://openalex.org/W2070126374","https://openalex.org/W2073080662","https://openalex.org/W2075095565","https://openalex.org/W2089468765","https://openalex.org/W2094005653","https://openalex.org/W2097891553","https://openalex.org/W2101220662","https://openalex.org/W2101234009","https://openalex.org/W2101600610","https://openalex.org/W2102461176","https://openalex.org/W2102818658","https://openalex.org/W2108508060","https://openalex.org/W2114604135","https://openalex.org/W2117237768","https://openalex.org/W2117407746","https://openalex.org/W2122558314","https://openalex.org/W2123969230","https://openalex.org/W2131965976","https://openalex.org/W2137974866","https://openalex.org/W2144288821","https://openalex.org/W2149751094","https://openalex.org/W2152282874","https://openalex.org/W2154501851","https://openalex.org/W2156407548","https://openalex.org/W2156465034","https://openalex.org/W2156678798","https://openalex.org/W2161072217","https://openalex.org/W2162980545","https://openalex.org/W2163870822","https://openalex.org/W2168970921","https://openalex.org/W2187089797","https://openalex.org/W2193177440","https://openalex.org/W2303521084","https://openalex.org/W2316662864","https://openalex.org/W2334543732","https://openalex.org/W2344156640","https://openalex.org/W2510934692","https://openalex.org/W2557595285","https://openalex.org/W2566370974","https://openalex.org/W2582743722","https://openalex.org/W2785523195","https://openalex.org/W2896457183","https://openalex.org/W2898364362","https://openalex.org/W2900078410","https://openalex.org/W2909727437","https://openalex.org/W2912083425","https://openalex.org/W2923154232","https://openalex.org/W2949342052","https://openalex.org/W2950954328","https://openalex.org/W2953008890","https://openalex.org/W2962739339","https://openalex.org/W2969180072","https://openalex.org/W2970966816","https://openalex.org/W2980789587","https://openalex.org/W2989747508","https://openalex.org/W2995514860","https://openalex.org/W3011698511","https://openalex.org/W3044929118","https://openalex.org/W3083871792","https://openalex.org/W3112376646","https://openalex.org/W3118936575","https://openalex.org/W3144701084","https://openalex.org/W3146944767","https://openalex.org/W3156051371","https://openalex.org/W3156428263","https://openalex.org/W3157437194","https://openalex.org/W3161612534","https://openalex.org/W3163970098","https://openalex.org/W3166142427","https://openalex.org/W3177500196","https://openalex.org/W3177828909","https://openalex.org/W3184265853","https://openalex.org/W3184858490","https://openalex.org/W3204490060","https://openalex.org/W3214870576","https://openalex.org/W4205620281","https://openalex.org/W4206275111","https://openalex.org/W4214861623","https://openalex.org/W4224259818","https://openalex.org/W4225438928","https://openalex.org/W4225868104","https://openalex.org/W4238622896","https://openalex.org/W4281752347","https://openalex.org/W4281790889","https://openalex.org/W4281903464","https://openalex.org/W4282984452","https://openalex.org/W4283583027","https://openalex.org/W4288089799","https://openalex.org/W4295312788","https://openalex.org/W4303981501","https://openalex.org/W4303983095","https://openalex.org/W4308463927","https://openalex.org/W4319593844","https://openalex.org/W4367598498","https://openalex.org/W6601814709","https://openalex.org/W6675354045","https://openalex.org/W6677768210","https://openalex.org/W6739901393","https://openalex.org/W6747620207","https://openalex.org/W6758485811","https://openalex.org/W6797514830","https://openalex.org/W6809106990"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W2948807893","https://openalex.org/W2899084033","https://openalex.org/W2778153218","https://openalex.org/W2748952813","https://openalex.org/W1531601525","https://openalex.org/W4391375266","https://openalex.org/W2078814861","https://openalex.org/W2527526854","https://openalex.org/W1976181487"],"abstract_inverted_index":{"Predictions":[0],"for":[1,19,103,170,225,259],"millions":[2],"of":[3,16,55,114,211,230,233],"protein":[4,134],"three-dimensional":[5],"structures":[6,35,252],"are":[7,40,98,106],"only":[8,140],"a":[9,151,179,190],"few":[10],"clicks":[11],"away":[12],"since":[13],"the":[14,112,115,121,133,171,208,231,256],"release":[15],"AlphaFold2":[17,56,250],"results":[18],"UniProt.":[20],"However,":[21,72],"many":[22],"proteins":[23,246],"have":[24],"so-called":[25],"intrinsically":[26],"disordered":[27],"regions":[28,244],"(IDRs)":[29],"that":[30,50,125,220],"do":[31],"not":[32,99],"adopt":[33],"unique":[34],"in":[36,174,201],"isolation.":[37],"These":[38],"IDRs":[39,76],"associated":[41,116],"with":[42,70,85,182,217,247],"several":[43],"diseases,":[44],"including":[45],"Alzheimer\u2019s":[46],"Disease.":[47],"We":[48],"showed":[49],"three":[51],"recent":[52],"disorder":[53,128,192,223],"measures":[54],"predictions":[57,169,224,258],"(pLDDT,":[58],"\u201cexperimentally":[59],"resolved\u201d":[60],"prediction":[61],"and":[62,89,105],"\u201crelative":[63],"solvent":[64],"accessibility\u201d)":[65],"correlated":[66],"to":[67,109,167,241,253],"some":[68],"extent":[69],"IDRs.":[71],"expert":[73],"methods":[74],"predict":[75],"more":[77,159],"reliably":[78],"by":[79,132],"combining":[80],"complex":[81,160],"machine":[82],"learning":[83],"models":[84],"expert-crafted":[86],"input":[87],"features":[88],"evolutionary":[90],"information":[91,206],"from":[92,129],"multiple":[93],"sequence":[94],"alignments":[95],"(MSAs).":[96],"MSAs":[97],"always":[100],"available,":[101],"especially":[102],"IDRs,":[104],"computationally":[107],"expensive":[108],"generate,":[110],"limiting":[111],"scalability":[113],"tools.":[117],"Here,":[118],"we":[119],"present":[120],"novel":[122],"method":[123,197],"SETH":[124,236,263],"predicts":[126],"residue":[127],"embeddings":[130],"generated":[131],"Language":[135],"Model":[136],"ProtT5,":[137],"which":[138],"explicitly":[139],"uses":[141],"single":[142],"sequences":[143],"as":[144],"input.":[145],"Thereby,":[146],"our":[147,196],"method,":[148],"relying":[149],"on":[150,178,189],"relatively":[152],"shallow":[153],"convolutional":[154],"neural":[155],"network,":[156],"outperformed":[157],"much":[158,164],"solutions":[161],"while":[162],"being":[163],"faster,":[165],"allowing":[166],"create":[168],"human":[172],"proteome":[173],"about":[175],"1":[176],"hour":[177],"consumer-grade":[180],"PC":[181],"one":[183],"NVIDIA":[184],"GeForce":[185],"RTX":[186],"3060.":[187],"Trained":[188],"continuous":[191],"scale":[193],"(CheZOD":[194],"scores),":[195],"captured":[198],"subtle":[199],"variations":[200],"disorder,":[202],"thereby":[203],"providing":[204],"important":[205],"beyond":[207],"binary":[209],"classification":[210],"most":[212],"methods.":[213],"High":[214],"performance":[215],"paired":[216],"speed":[218],"revealed":[219],"SETH\u2019s":[221],"nuanced":[222],"entire":[226],"proteomes":[227],"capture":[228],"aspects":[229],"evolution":[232],"organisms.":[234],"Additionally,":[235],"could":[237],"also":[238],"be":[239],"used":[240],"filter":[242],"out":[243],"or":[245],"probable":[248],"low-quality":[249],"3D":[251],"prioritize":[254],"running":[255],"compute-intensive":[257],"large":[260],"data":[261],"sets.":[262],"is":[264],"freely":[265],"publicly":[266],"available":[267],"at:":[268],"https://github.com/Rostlab/SETH":[269],".":[270]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}