{"id":"https://openalex.org/W76317090","doi":null,"title":"Integrating Sequence and Structure for Annotating Proteins in the Twilight Zone: A Machine Learning Approach","display_name":"Integrating Sequence and Structure for Annotating Proteins in the Twilight Zone: A Machine Learning Approach","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W76317090","mag":"76317090"},"language":"en","primary_location":{"id":"mag:76317090","doi":null,"is_oa":false,"landing_page_url":"https://espace.library.uq.edu.au/view/UQ:191113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"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/A5081632304","display_name":"Isye Arieshanti","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Isye Arieshanti","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5081632304"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00647692,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.8353999853134155,"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":0.8353999853134155,"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":0.15760000050067902,"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":0.002899999963119626,"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/protein-function-annotation","display_name":"protein annotation","score":0.7089999914169312},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"protein structure prediction","score":0.5410000085830688},{"id":"https://openalex.org/keywords/enzyme-classification","display_name":"enzyme classification","score":0.8460000157356262},{"id":"https://openalex.org/keywords/disulfide-bond-prediction","display_name":"disulfide bond prediction","score":0.9179999828338623},{"id":"https://openalex.org/keywords/sequence-structure-integration","display_name":"sequence-structure integration","score":0.8309999704360962},{"id":"https://openalex.org/keywords/kernel-canonical-correlation-analysis","display_name":"kernel canonical correlation analysis","score":0.9010000228881836},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"support vector machine","score":0.8679999709129333},{"id":"https://openalex.org/keywords/protein-sequence-representation","display_name":"protein sequence representation","score":0.3440000116825104},{"id":"https://openalex.org/keywords/structural-features","display_name":"structural features","score":0.4699999988079071}],"concepts":[{"id":"https://openalex.org/C136475424","wikidata":"https://www.wikidata.org/wiki/Q7251500","display_name":"Protein structure database","level":4,"score":0.7271888852119446},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.6312466859817505},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5994720458984375},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.5497742295265198},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5468361973762512},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.532853901386261},{"id":"https://openalex.org/C200307862","wikidata":"https://www.wikidata.org/wiki/Q7797175","display_name":"Threading (protein sequence)","level":3,"score":0.5303208231925964},{"id":"https://openalex.org/C4668613","wikidata":"https://www.wikidata.org/wiki/Q4116110","display_name":"Structural alignment","level":5,"score":0.5259925127029419},{"id":"https://openalex.org/C139489369","wikidata":"https://www.wikidata.org/wiki/Q770846","display_name":"Structural similarity","level":2,"score":0.5055050849914551},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.5023629665374756},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.49831056594848633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4960664212703705},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.49196431040763855},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.44846922159194946},{"id":"https://openalex.org/C45475804","wikidata":"https://www.wikidata.org/wiki/Q6675846","display_name":"Loop modeling","level":4,"score":0.4304559528827667},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.38903525471687317},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.3876464068889618},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.3783588409423828},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2185470461845398},{"id":"https://openalex.org/C41584329","wikidata":"https://www.wikidata.org/wiki/Q175902","display_name":"Sequence database","level":3,"score":0.1925819218158722},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.10757708549499512},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:76317090","doi":null,"is_oa":false,"landing_page_url":"https://espace.library.uq.edu.au/view/UQ:191113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2144982353","https://openalex.org/W2506122267","https://openalex.org/W2285206312","https://openalex.org/W32577426","https://openalex.org/W2017229033","https://openalex.org/W2092750499","https://openalex.org/W2168667184","https://openalex.org/W7097703378","https://openalex.org/W2737578470","https://openalex.org/W2076460489"],"abstract_inverted_index":{"Determining":[0],"protein":[1,14,48,107,163,196,241,317,338],"structure":[2,101,221,242,318,339],"and":[3,9,67,71,82,100,165,236],"function":[4,135],"experimentally":[5],"is":[6,20,49,86,210,217,233],"both":[7,69,98,123],"costly":[8],"time":[10],"consuming.":[11],"Transferring":[12],"function-related":[13],"annotations":[15],"based":[16,260],"on":[17,105,116,128,141,240,251,261],"homology-based":[18],"methods":[19,61,80],"relatively":[21],"straightforward":[22],"for":[23,219,225,288,299],"proteins":[24,37,145,175],"that":[25,62,96,110,158,238,266,280,285],"have":[26,133,150],"sequence":[27,43,70,99,117,138,164,252,278],"identity":[28],"of":[29,65,77,89,125,162,171,228,302,312,328,336],"more":[30],"than":[31],"40%.":[32],"However,":[33],"there":[34],"are":[35,63,103,111,243,286],"many":[36],"in":[38,194,202,322],"the":[39,87,142,159,169,220,310,323],"twilight":[40],"zone":[41],"where":[42],"similarity":[44,139,205],"with":[45,136,146,176,282],"any":[46],"other":[47,143],"very":[50,212,234],"weak,":[51],"while":[52,140],"being":[53],"structurally":[54],"similar":[55,147,177,224],"to":[56,183,214,222,319,333],"several.":[57],"Such":[58],"cases":[59],"require":[60],"capable":[64],"using":[66,187],"exploiting":[68],"structural":[72,208,268,283,313],"similarity.":[73],"To":[74],"understand":[75],"ways":[76],"how":[78],"such":[79,207,231],"can":[81,132],"should":[83,331],"be":[84,223,320],"designed":[85],"focus":[88],"this":[90,93,329],"study.":[91],"In":[92],"thesis,":[94],"models":[95],"use":[97,170],"features":[102,126,167,269,284,314],"applied":[104],"two":[106],"prediction":[108,227,297,324,340],"problems":[109],"particularly":[112],"challenging":[113],"when":[114],"relying":[115],"alone.":[118,253],"Enzyme":[119],"classification":[120,185],"benefits":[121],"from":[122],"kinds":[124],"because":[127],"one":[129],"hand,":[130,144],"enzymes":[131],"identical":[134],"limited":[137],"fold":[148],"may":[149,199],"disparate":[151],"enzyme":[152],"class":[153],"annotation.":[154],"This":[155,254],"thesis":[156,255],"shows":[157],"full":[160],"integration":[161],"structure-related":[166],"(via":[168],"kernels)":[172],"automatically":[173],"places":[174],"biological":[178],"properties":[179,209],"closer":[180],"together,":[181],"leading":[182],"superior":[184],"accuracy":[186,298],"Support":[188],"Vector":[189],"Machines.":[190],"Disulfide-bonds":[191],"link":[192],"residues":[193],"a":[195,257,289,300,334],"structure,":[197],"but":[198,230],"appear":[200],"distant":[201],"sequence.":[203],"Sequence":[204],"reflecting":[206],"thus":[211,308],"hard":[213],"detect.":[215],"It":[216,273],"sufficient":[218],"accurate":[226],"disulfide-bonds,":[229],"information":[232],"scarce":[235],"predictors":[237],"rely":[239],"not":[244],"nearly":[245],"as":[246,248],"useful":[247],"those":[249],"operating":[250],"proposes":[256],"novel":[258],"approach":[259,330],"Kernel":[262],"Canonical":[263],"Correlation":[264],"Analysis":[265],"uses":[267],"during":[270],"training":[271],"only.":[272],"does":[274],"so":[275],"by":[276],"finding":[277],"representations":[279,294],"correlate":[281],"essential":[287],"disulfide":[290],"bond.":[291],"The":[292,305,326],"resulting":[293],"enable":[295],"high":[296],"range":[301],"disulfide-bond":[303],"problems.":[304,341],"proposed":[306],"model":[307],"taps":[309],"advantage":[311],"without":[315],"requiring":[316],"available":[321],"process.":[325],"merits":[327],"apply":[332],"number":[335],"open":[337]},"counts_by_year":[],"updated_date":"2026-09-12T09:15:50.089291","created_date":"2016-06-24T00:00:00"}