{"id":"https://openalex.org/W3044620083","doi":null,"title":"A protein structure based annotation of genomes","display_name":"A protein structure based annotation of genomes","publication_year":2002,"publication_date":"2002-01-01","ids":{"openalex":"https://openalex.org/W3044620083","mag":"3044620083"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.127.2320","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.127.2320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sbg.bio.ic.ac.uk/people/mueller/thesis_bw.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000384693","display_name":"Arne M. M\u00fcller","orcid":"https://orcid.org/0000-0002-7458-274X","observed_orcids":["https://orcid.org/0000-0002-7458-274X"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Arne M\u00fcller","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5000384693"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8628000020980835,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8628000020980835,"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":0.057100001722574234,"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":0.02930000051856041,"subfield":{"id":"https://openalex.org/subfields/1315","display_name":"Structural 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/genome-annotation","display_name":"genome annotation","score":0.7900000214576721},{"id":"https://openalex.org/keywords/protein-structure","display_name":"protein structure","score":0.7590000033378601},{"id":"https://openalex.org/keywords/protein-function","display_name":"protein function","score":0.6200000047683716},{"id":"https://openalex.org/keywords/psi-blast","display_name":"PSI-BLAST","score":0.8840000033378601},{"id":"https://openalex.org/keywords/remote-homology-detection","display_name":"remote homology detection","score":0.8579999804496765},{"id":"https://openalex.org/keywords/scop","display_name":"SCOP","score":0.531000018119812},{"id":"https://openalex.org/keywords/protein-fold","display_name":"protein fold","score":0.7049999833106995},{"id":"https://openalex.org/keywords/human-proteome","display_name":"human proteome","score":0.7139999866485596},{"id":"https://openalex.org/keywords/mycoplasma-genitalium","display_name":"Mycoplasma genitalium","score":0.921999990940094},{"id":"https://openalex.org/keywords/mycobacterium-tuberculosis","display_name":"Mycobacterium tuberculosis","score":0.9990000128746033},{"id":"https://openalex.org/keywords/domain-duplication","display_name":"domain duplication","score":0.6079999804496765},{"id":"https://openalex.org/keywords/membrane-proteins","display_name":"membrane proteins","score":0.7440000176429749},{"id":"https://openalex.org/keywords/sequence-motifs","display_name":"sequence motifs","score":0.7519999742507935},{"id":"https://openalex.org/keywords/disease-genes","display_name":"disease-associated genes","score":0.7979999780654907}],"concepts":[{"id":"https://openalex.org/C104397665","wikidata":"https://www.wikidata.org/wiki/Q860947","display_name":"Proteome","level":2,"score":0.861425518989563},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7801592946052551},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.7133815288543701},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6327917575836182},{"id":"https://openalex.org/C94795543","wikidata":"https://www.wikidata.org/wiki/Q3813754","display_name":"Human proteome project","level":4,"score":0.5509200096130371},{"id":"https://openalex.org/C89566754","wikidata":"https://www.wikidata.org/wiki/Q2273828","display_name":"Genome project","level":4,"score":0.5232136249542236},{"id":"https://openalex.org/C136475424","wikidata":"https://www.wikidata.org/wiki/Q7251500","display_name":"Protein structure database","level":4,"score":0.4848517179489136},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4621041715145111},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4608430862426758},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.42922282218933105},{"id":"https://openalex.org/C41584329","wikidata":"https://www.wikidata.org/wiki/Q175902","display_name":"Sequence database","level":3,"score":0.3312285542488098},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.30627331137657166},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.30011582374572754},{"id":"https://openalex.org/C46111723","wikidata":"https://www.wikidata.org/wiki/Q471857","display_name":"Proteomics","level":3,"score":0.2871738076210022},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.22887998819351196},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.13684824109077454}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.127.2320","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.127.2320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sbg.bio.ic.ac.uk/people/mueller/thesis_bw.pdf","raw_type":"text"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10102807","doi":null,"is_oa":false,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10102807/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Doctoral thesis, UCL (University College London).","raw_type":"Thesis"},{"id":"mag:3044620083","doi":null,"is_oa":false,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10102807/","pdf_url":null,"source":{"id":"https://openalex.org/S4306508231","display_name":"Doctoral thesis, UCL (University College London).","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Doctoral thesis, UCL (University College London).","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":201,"referenced_works":["https://openalex.org/W11478868","https://openalex.org/W140427365","https://openalex.org/W1508885706","https://openalex.org/W1513332069","https://openalex.org/W1513621883","https://openalex.org/W1530397352","https://openalex.org/W1534270226","https://openalex.org/W1551915691","https://openalex.org/W1558365920","https://openalex.org/W1569904835","https://openalex.org/W1582255757","https://openalex.org/W1582655487","https://openalex.org/W1584704387","https://openalex.org/W1597538863","https://openalex.org/W1601251682","https://openalex.org/W1608218663","https://openalex.org/W1617571838","https://openalex.org/W1626008731","https://openalex.org/W1627698625","https://openalex.org/W1627863859","https://openalex.org/W1652691445","https://openalex.org/W1659313070","https://openalex.org/W1778599501","https://openalex.org/W1839423960","https://openalex.org/W1926303070","https://openalex.org/W1936630560","https://openalex.org/W1938034723","https://openalex.org/W1947962930","https://openalex.org/W1953389023","https://openalex.org/W1965231243","https://openalex.org/W1965998064","https://openalex.org/W1967386006","https://openalex.org/W1967409098","https://openalex.org/W1969995117","https://openalex.org/W1970850106","https://openalex.org/W1971155547","https://openalex.org/W1971403296","https://openalex.org/W1972436355","https://openalex.org/W1974066065","https://openalex.org/W1975796937","https://openalex.org/W1981014117","https://openalex.org/W1982533969","https://openalex.org/W1983052493","https://openalex.org/W1983493107","https://openalex.org/W1987007292","https://openalex.org/W1988670311","https://openalex.org/W1989509003","https://openalex.org/W1990453950","https://openalex.org/W1992502768","https://openalex.org/W1994025789","https://openalex.org/W1994734987","https://openalex.org/W2003443426","https://openalex.org/W2003788979","https://openalex.org/W2005453525","https://openalex.org/W2006212265","https://openalex.org/W2006572311","https://openalex.org/W2011495938","https://openalex.org/W2013595954","https://openalex.org/W2015292449","https://openalex.org/W2016299826","https://openalex.org/W2018056833","https://openalex.org/W2018686514","https://openalex.org/W2020336239","https://openalex.org/W2020644553","https://openalex.org/W2021312899","https://openalex.org/W2021639324","https://openalex.org/W2022366078","https://openalex.org/W2024645073","https://openalex.org/W2028113949","https://openalex.org/W2033496784","https://openalex.org/W2036792999","https://openalex.org/W2040048905","https://openalex.org/W2040668305","https://openalex.org/W2041652393","https://openalex.org/W2043165033","https://openalex.org/W2045119694","https://openalex.org/W2045765967","https://openalex.org/W2046310275","https://openalex.org/W2050885009","https://openalex.org/W2051119339","https://openalex.org/W2051895548","https://openalex.org/W2052729310","https://openalex.org/W2053096433","https://openalex.org/W2054251921","https://openalex.org/W2055043387","https://openalex.org/W2055118532","https://openalex.org/W2058138221","https://openalex.org/W2058336694","https://openalex.org/W2065283382","https://openalex.org/W2071699363","https://openalex.org/W2072133388","https://openalex.org/W2073064803","https://openalex.org/W2074176676","https://openalex.org/W2074231493","https://openalex.org/W2078138505","https://openalex.org/W2079441999","https://openalex.org/W2080885816","https://openalex.org/W2082873640","https://openalex.org/W2085277871","https://openalex.org/W2086208676","https://openalex.org/W2086438703","https://openalex.org/W2090438401","https://openalex.org/W2093959518","https://openalex.org/W2094519647","https://openalex.org/W2098772291","https://openalex.org/W2099254366","https://openalex.org/W2099831744","https://openalex.org/W2100361137","https://openalex.org/W2100641815","https://openalex.org/W2100882223","https://openalex.org/W2101220662","https://openalex.org/W2101783948","https://openalex.org/W2102122585","https://openalex.org/W2103150692","https://openalex.org/W2103425480","https://openalex.org/W2106013076","https://openalex.org/W2107109782","https://openalex.org/W2108508364","https://openalex.org/W2110041134","https://openalex.org/W2110132014","https://openalex.org/W2110612352","https://openalex.org/W2110668908","https://openalex.org/W2112452502","https://openalex.org/W2112493377","https://openalex.org/W2112792893","https://openalex.org/W2113505030","https://openalex.org/W2114083522","https://openalex.org/W2115780677","https://openalex.org/W2116402707","https://openalex.org/W2116513121","https://openalex.org/W2117249420","https://openalex.org/W2118729125","https://openalex.org/W2120122292","https://openalex.org/W2120561148","https://openalex.org/W2120684043","https://openalex.org/W2121745326","https://openalex.org/W2123858481","https://openalex.org/W2124073224","https://openalex.org/W2124145810","https://openalex.org/W2126377763","https://openalex.org/W2127230663","https://openalex.org/W2127335580","https://openalex.org/W2128996066","https://openalex.org/W2130479394","https://openalex.org/W2131581981","https://openalex.org/W2133312664","https://openalex.org/W2134153749","https://openalex.org/W2135146244","https://openalex.org/W2135474021","https://openalex.org/W2136134567","https://openalex.org/W2138342766","https://openalex.org/W2140000393","https://openalex.org/W2140244239","https://openalex.org/W2140514445","https://openalex.org/W2141148930","https://openalex.org/W2141652419","https://openalex.org/W2141885858","https://openalex.org/W2142529984","https://openalex.org/W2142923467","https://openalex.org/W2143011057","https://openalex.org/W2143173841","https://openalex.org/W2143210482","https://openalex.org/W2144192824","https://openalex.org/W2145385227","https://openalex.org/W2147694156","https://openalex.org/W2148474327","https://openalex.org/W2149184205","https://openalex.org/W2152517415","https://openalex.org/W2152770371","https://openalex.org/W2153187042","https://openalex.org/W2154478075","https://openalex.org/W2156099263","https://openalex.org/W2157750263","https://openalex.org/W2157975034","https://openalex.org/W2158023121","https://openalex.org/W2158304452","https://openalex.org/W2160013892","https://openalex.org/W2160216877","https://openalex.org/W2160453515","https://openalex.org/W2163181687","https://openalex.org/W2164217177","https://openalex.org/W2164567662","https://openalex.org/W2164718466","https://openalex.org/W2166187656","https://openalex.org/W2166699767","https://openalex.org/W2166745327","https://openalex.org/W2168279898","https://openalex.org/W2168669146","https://openalex.org/W2168772829","https://openalex.org/W2168909179","https://openalex.org/W2169395813","https://openalex.org/W2169929748","https://openalex.org/W2170367123","https://openalex.org/W2321127696","https://openalex.org/W2341171179","https://openalex.org/W2400275259","https://openalex.org/W2430136227","https://openalex.org/W2975890157","https://openalex.org/W4239620712","https://openalex.org/W7074179453","https://openalex.org/W7096590985"],"related_works":["https://openalex.org/W1975879553","https://openalex.org/W2802170252","https://openalex.org/W205598698","https://openalex.org/W7019502723","https://openalex.org/W2020588471","https://openalex.org/W7099354017","https://openalex.org/W2103150692","https://openalex.org/W7095427437","https://openalex.org/W7097094398","https://openalex.org/W2164801274"],"abstract_inverted_index":{"A":[0],"strategy":[1],"for":[2,64,320],"protein":[3,232,343],"structure":[4,97],"and":[5,14,98,105,116,123,167,186,208,212,220,286,347,355],"function":[6,99],"based":[7,50,140,158],"annotation":[8,131,195,214],"of":[9,19,29,54,73,85,95,102,113,120,176,184,189,210,224,236,247,268,276,293,302,312,324],"genomes":[10,21],"was":[11,45,126,133,197,218],"developed,":[12],"evaluated":[13,219],"applied":[15,91,198],"to":[16,37,92,100,135,199,231,253,297],"the":[17,23,27,30,57,66,74,109,111,117,187,203,225,237,248,254,266,272,289,298,303,313,341,350],"proteins":[18,101,270],"several":[20,153],"including":[22,202],"human":[24,204,226,304,358],"genome.":[25],"First":[26],"performance":[28],"widely-used":[31],"homology-based":[32],"sequence":[33,43,256,344],"comparison":[34,188],"program":[35],"PSI-BLAST":[36,89],"detect":[38],"distant":[39],"homologous":[40,67],"relationships":[41,68],"(\u226420%":[42],"identity)":[44],"evaluated.":[46],"The":[47,155,193,206,291],"benchmark":[48],"is":[49,90,157,240,328],"on":[51,141,159],"two":[52],"sets":[53],"sequences":[55],"from":[56,178],"Structural":[58,352],"Classification":[59],"Of":[60],"Proteins":[61],"(SCOP)":[62],"database":[63,162],"which":[65],"are":[69,87,262,284],"known.":[70],"About":[71,222],"40%":[72,223],"test":[75],"proteome":[76,130,227,238,249,305],"can":[77,149,228,250],"be":[78,150,229,251],"annotated":[79],"via":[80],"remote":[81],"homologies.":[82],"Common":[83],"sources":[84],"errors":[86],"identified.":[88,362],"assign":[93],"homologues":[94],"known":[96],"M.":[103,106],"genitalium":[104],"tuberculosis.":[107],"From":[108],"benchmark,":[110],"number":[112],"missed":[114],"assignments":[115],"potential":[118],"extent":[119,207],"new":[121],"structural":[122,211,282],"functional":[124,213,242],"families":[125],"estimated.":[127],"An":[128],"automated":[129],"system":[132,156,196],"developed":[134],"perform":[136],"large":[137],"scale":[138],"annotations":[139,190],"analyses":[142,148,180],"such":[143],"as":[144,164,171],"PSI-BLAST.":[145],"Computationally":[146],"intensive":[147],"distributed":[151],"across":[152,191,288,349],"computers.":[154],"a":[160,165,168,172],"relational":[161],"serving":[163],"back-end":[166],"software":[169],"interface":[170],"front-end.":[173],"Relational":[174],"storage":[175],"results":[177,185],"different":[179],"permits":[181],"straightforward":[182],"evaluation":[183],"genomes.":[192],"above":[194],"fourteen":[200],"proteomes":[201,217,273],"proteome.":[205],"reliability":[209],"in":[215,265,274,326,331,334,340,357],"these":[216,294],"compared.":[221],"assigned":[230,252],"folds.":[233],"For":[234],"77%":[235],"there":[239],"some":[241],"information,":[243],"but":[244],"only":[245],"26%":[246],"standard":[255],"motifs":[257],"that":[258,300],"characterise":[259],"function.":[260],"There":[261],"substantial":[263],"differences":[264],"composition":[267],"membrane":[269],"between":[271],"terms":[275],"their":[277],"globular":[278],"domains.":[279],"Commonly":[280],"occurring":[281],"superfamilies":[283,295,317,353],"identified":[285],"compared":[287,348],"proteomes.":[290,351],"frequencies":[292],"leads":[296],"estimate":[299],"98%":[301],"evolved":[306],"by":[307],"domain":[308],"duplication,":[309],"with":[310],"four":[311],"ten":[314],"most":[315],"duplicated":[316],"potentially":[318],"specific":[319],"multi-cellular":[321],"organisms.":[322,336],"Occurrence":[323],"domains":[325],"repeats":[327],"more":[329],"common":[330],"metazoa":[332],"than":[333],"single-cellular":[335],"Superfamily":[337],"pairs":[338],"co-occurring":[339],"same":[342],"were":[345,361],"analysed":[346],"over-":[354],"under-represented":[356],"disease":[359],"genes":[360]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-07-29T00:00:00"}