{"id":"https://openalex.org/W1527722080","doi":"https://doi.org/10.1109/csb.2003.1227393","title":"Fold recognition using sequence fingerprints of protein local substructures","display_name":"Fold recognition using sequence fingerprints of protein local substructures","publication_year":2004,"publication_date":"2004-03-23","ids":{"openalex":"https://openalex.org/W1527722080","doi":"https://doi.org/10.1109/csb.2003.1227393","mag":"1527722080"},"language":"en","primary_location":{"id":"doi:10.1109/csb.2003.1227393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2003.1227393","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Systems Bioinformatics. CSB2003. Proceedings of the 2003 IEEE Bioinformatics Conference. CSB2003","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/15004201","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046112262","display_name":"Andriy Kryshtafovych","orcid":"https://orcid.org/0000-0001-5066-7178"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"A. Kryshtafovych","raw_affiliation_strings":["Lawrence Livermore National Laboratories, Livermore, CA, USA","Lawrence Livermore Nat. Lab., Berkeley, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratories, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]},{"raw_affiliation_string":"Lawrence Livermore Nat. Lab., Berkeley, CA, USA#TAB#","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022568938","display_name":"Torgeir R. Hvidsten","orcid":"https://orcid.org/0000-0001-6097-2539"},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]},{"id":"https://openalex.org/I223464139","display_name":"Linnaeus University","ror":"https://ror.org/00j9qag85","country_code":"SE","type":"education","lineage":["https://openalex.org/I223464139"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"T.R. Hvidsten","raw_affiliation_strings":["The Linnaeus Centre for Bioinformatics, University of Uppsala, Uppsala, Sweden","Uppsala University , Uppsala, Sweden"],"affiliations":[{"raw_affiliation_string":"The Linnaeus Centre for Bioinformatics, University of Uppsala, Uppsala, Sweden","institution_ids":["https://openalex.org/I223464139"]},{"raw_affiliation_string":"Uppsala University , Uppsala, Sweden","institution_ids":["https://openalex.org/I123387679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050406527","display_name":"Jan Komorowski","orcid":"https://orcid.org/0000-0002-0766-8789"},"institutions":[{"id":"https://openalex.org/I223464139","display_name":"Linnaeus University","ror":"https://ror.org/00j9qag85","country_code":"SE","type":"education","lineage":["https://openalex.org/I223464139"]},{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"J. Komorowski","raw_affiliation_strings":["The Linnaeus Centre for Bioinformatics, University of Uppsala, Uppsala, Sweden","Uppsala University , Uppsala, Sweden"],"affiliations":[{"raw_affiliation_string":"The Linnaeus Centre for Bioinformatics, University of Uppsala, Uppsala, Sweden","institution_ids":["https://openalex.org/I223464139"]},{"raw_affiliation_string":"Uppsala University , Uppsala, Sweden","institution_ids":["https://openalex.org/I123387679"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074974770","display_name":"Krzysztof Fidelis","orcid":"https://orcid.org/0000-0002-8061-412X"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K. Fidelis","raw_affiliation_strings":["Lawrence Livermore National Laboratories, Livermore, CA, USA","Lawrence Livermore National            Laboratory, Livermore, CA"],"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratories, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]},{"raw_affiliation_string":"Lawrence Livermore National            Laboratory, Livermore, CA","institution_ids":["https://openalex.org/I1282311441"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5046112262"],"corresponding_institution_ids":["https://openalex.org/I1282311441"],"apc_list":null,"apc_paid":null,"fwci":0.1206,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46579327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"517","last_page":"518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9987000226974487,"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":0.9983999729156494,"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/substructure","display_name":"Substructure","score":0.8166624307632446},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6002430319786072},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5853226780891418},{"id":"https://openalex.org/keywords/polypeptide-chain","display_name":"Polypeptide chain","score":0.5610414743423462},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5199288725852966},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.515798807144165},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.512285590171814},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4960399568080902},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45108848810195923},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4479061961174011},{"id":"https://openalex.org/keywords/loop-modeling","display_name":"Loop modeling","score":0.4262591004371643},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.3654690682888031},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"Protein structure prediction","score":0.32777902483940125},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3202694356441498},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.22594574093818665},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.20228803157806396},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09524288773536682},{"id":"https://openalex.org/keywords/amino-acid","display_name":"Amino acid","score":0.07566371560096741}],"concepts":[{"id":"https://openalex.org/C99679407","wikidata":"https://www.wikidata.org/wiki/Q56761637","display_name":"Substructure","level":2,"score":0.8166624307632446},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6002430319786072},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5853226780891418},{"id":"https://openalex.org/C2993989360","wikidata":"https://www.wikidata.org/wiki/Q172847","display_name":"Polypeptide chain","level":3,"score":0.5610414743423462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5199288725852966},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.515798807144165},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.512285590171814},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4960399568080902},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45108848810195923},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4479061961174011},{"id":"https://openalex.org/C45475804","wikidata":"https://www.wikidata.org/wiki/Q6675846","display_name":"Loop modeling","level":4,"score":0.4262591004371643},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.3654690682888031},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.32777902483940125},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3202694356441498},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.22594574093818665},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.20228803157806396},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09524288773536682},{"id":"https://openalex.org/C515207424","wikidata":"https://www.wikidata.org/wiki/Q8066","display_name":"Amino acid","level":2,"score":0.07566371560096741},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/csb.2003.1227393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2003.1227393","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Systems Bioinformatics. CSB2003. Proceedings of the 2003 IEEE Bioinformatics Conference. CSB2003","raw_type":"proceedings-article"},{"id":"pmh:info:ark/67531/metadc1405563","is_oa":false,"landing_page_url":"https://digital.library.unt.edu/ark:/67531/metadc1405563/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400792","display_name":"University of North Texas Digital Library (University of North Texas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123534392","host_organization_name":"University of North Texas","host_organization_lineage":["https://openalex.org/I123534392"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Computer Society Bioinformatics Conference, Stanford, CA, Aug 11 - Aug 14, 2003","raw_type":"Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.127.8057","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.127.8057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://csdl.computer.org/comp/proceedings/csb/2003/2000/00/20000517.pdf","raw_type":"text"},{"id":"pmh:oai:osti.gov:15004201","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/15004201","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:15004201","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/15004201","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W972074244","https://openalex.org/W2028231353","https://openalex.org/W2085277871","https://openalex.org/W2145358391","https://openalex.org/W2158714788"],"related_works":["https://openalex.org/W639041153","https://openalex.org/W2013950502","https://openalex.org/W2095897567","https://openalex.org/W3204091482","https://openalex.org/W2329561428","https://openalex.org/W2134703371","https://openalex.org/W1543174845","https://openalex.org/W2253761889","https://openalex.org/W2160365538","https://openalex.org/W2407384706"],"abstract_inverted_index":{"A":[0],"protein":[1],"local":[2,20],"substructure":[3,18],"(descriptor)":[4],"is":[5],"a":[6,23],"set":[7,49,125],"of":[8,13,22,31,41,50,63,81,106,126],"several":[9],"short":[10],"nonoverlapping":[11],"fragments":[12],"the":[14,32,39,47,58,61,67,82,95,123],"polypeptide":[15],"chain.":[16],"Each":[17],"describes":[19],"environment":[21],"particular":[24],"residue":[25],"and":[26,60,120],"includes":[27],"only":[28],"those":[29],"segments":[30],"main":[33],"chain":[34],"that":[35,42],"are":[36,74],"located":[37],"in":[38,104],"proximity":[40],"residue.":[43],"Similar":[44],"descriptors":[45],"from":[46,94,122],"representative":[48],"proteins":[51],"were":[52,102],"analyzed":[53],"to":[54,76,84],"reveal":[55],"links":[56],"between":[57,117],"substructures":[59],"sequences":[62,93,119,121],"their":[64],"segments.":[65],"Using":[66],"detected":[68],"sequence-based":[69],"fingerprints,":[70],"specific":[71],"geometrical":[72],"conformations":[73],"assigned":[75],"new":[77],"sequences.":[78],"The":[79],"ability":[80],"approach":[83],"recognize":[85],"correct":[86],"SCOP":[87],"folds":[88],"was":[89,111],"tested":[90],"on":[91],"273":[92],"49":[96],"most":[97],"popular":[98],"folds.":[99],"Good":[100],"predictions":[101],"obtained":[103],"85%":[105],"cases.":[107],"No":[108],"performance":[109],"drop":[110],"observed":[112],"with":[113],"decreasing":[114],"sequence":[115],"similarity":[116],"target":[118],"training":[124],"proteins.":[127]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}