{"id":"https://openalex.org/W2143834497","doi":"https://doi.org/10.1093/bioinformatics/bti1111","title":"Less is more: towards an optimal universal description of protein folds","display_name":"Less is more: towards an optimal universal description of protein folds","publication_year":2005,"publication_date":"2005-09-01","ids":{"openalex":"https://openalex.org/W2143834497","doi":"https://doi.org/10.1093/bioinformatics/bti1111","mag":"2143834497","pmid":"https://pubmed.ncbi.nlm.nih.gov/16204127"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bti1111","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti1111","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"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/A5002355055","display_name":"Joseph D. Szustakowski","orcid":"https://orcid.org/0000-0001-7900-3973"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Joseph D. Szustakowski","raw_affiliation_strings":["Department of Biomedical Engineering, Boston University, Boston, MA 02215, USA","Department of Biomedical Engineering, Boston University 44 Cummington Street, Boston, MA 02215, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering, Boston University, Boston, MA 02215, USA","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Department of Biomedical Engineering, Boston University 44 Cummington Street, Boston, MA 02215, USA#TAB#","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005103749","display_name":"Simon Kasif","orcid":"https://orcid.org/0000-0003-3297-9914"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simon Kasif","raw_affiliation_strings":["Department of Biomedical Engineering, Boston University 44 Cummington Street, Boston, MA 02215, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering, Boston University 44 Cummington Street, Boston, MA 02215, USA#TAB#","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084369008","display_name":"Zhiping Weng","orcid":"https://orcid.org/0000-0002-3032-7966"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiping Weng","raw_affiliation_strings":["Department of Biomedical Engineering, Boston University 44 Cummington Street, Boston, MA 02215, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering, Boston University 44 Cummington Street, Boston, MA 02215, USA#TAB#","institution_ids":["https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5002355055"],"corresponding_institution_ids":["https://openalex.org/I111088046"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.7115,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.68107149,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"21","issue":"suppl_2","first_page":"ii66","last_page":"ii71"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","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/T10044","display_name":"Protein Structure and Dynamics","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/T12254","display_name":"Machine Learning in Bioinformatics","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"}},{"id":"https://openalex.org/T11162","display_name":"Enzyme Structure and Function","score":0.9879000186920166,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6239550113677979},{"id":"https://openalex.org/keywords/fold","display_name":"Fold (higher-order function)","score":0.533100962638855},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5073480010032654},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.45979639887809753},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4472351372241974},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4187096953392029},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3685927987098694},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36124151945114136},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34425032138824463},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.15353217720985413},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08646106719970703}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6239550113677979},{"id":"https://openalex.org/C53942344","wikidata":"https://www.wikidata.org/wiki/Q951651","display_name":"Fold (higher-order function)","level":2,"score":0.533100962638855},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5073480010032654},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.45979639887809753},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4472351372241974},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4187096953392029},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3685927987098694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36124151945114136},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34425032138824463},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.15353217720985413},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08646106719970703},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004014","descriptor_name":"Dictionaries as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004014","descriptor_name":"Dictionaries as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004014","descriptor_name":"Dictionaries as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000648","qualifier_name":"ultrastructure","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000648","qualifier_name":"ultrastructure","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000648","qualifier_name":"ultrastructure","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":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017433","descriptor_name":"Protein Structure, Secondary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017433","descriptor_name":"Protein Structure, Secondary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017433","descriptor_name":"Protein Structure, Secondary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/bti1111","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti1111","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:16204127","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16204127","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":"Bioinformatics (Oxford, England)","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8100000023841858}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337398","display_name":"Division of Biological Infrastructure","ror":"https://ror.org/04qn9mx93"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1585827898","https://openalex.org/W1965500939","https://openalex.org/W1968908999","https://openalex.org/W1981575795","https://openalex.org/W1983661866","https://openalex.org/W1984967071","https://openalex.org/W1989415425","https://openalex.org/W1991679665","https://openalex.org/W1992502768","https://openalex.org/W2000377676","https://openalex.org/W2003443426","https://openalex.org/W2004646218","https://openalex.org/W2010352922","https://openalex.org/W2013025153","https://openalex.org/W2020644553","https://openalex.org/W2022058405","https://openalex.org/W2023790301","https://openalex.org/W2054658115","https://openalex.org/W2055233956","https://openalex.org/W2074069606","https://openalex.org/W2079249590","https://openalex.org/W2082488805","https://openalex.org/W2084224084","https://openalex.org/W2085277871","https://openalex.org/W2086221159","https://openalex.org/W2095513869","https://openalex.org/W2108067237","https://openalex.org/W2108138353","https://openalex.org/W2114598719","https://openalex.org/W2133307208","https://openalex.org/W2141920771","https://openalex.org/W2145358391","https://openalex.org/W2148077714","https://openalex.org/W2150404842","https://openalex.org/W2154106236","https://openalex.org/W2167197805","https://openalex.org/W2430631381","https://openalex.org/W3145128584"],"related_works":["https://openalex.org/W1181095405","https://openalex.org/W3014426369","https://openalex.org/W4240318783","https://openalex.org/W2311285072","https://openalex.org/W1573293794","https://openalex.org/W783636722","https://openalex.org/W2292230535","https://openalex.org/W2605994284","https://openalex.org/W4243341329","https://openalex.org/W2999866037"],"abstract_inverted_index":{"MOTIVATION:":[0],"Identification":[1],"and":[2,16,67,86,107,136],"characterization":[3],"of":[4,25,37,60,89,94,105,133,140],"protein":[5,13,97,134,143],"structure":[6],"regularities":[7],"can":[8,41],"reveal":[9],"the":[10,69,82,113,120,123],"mechanisms":[11],"governing":[12],"structure,":[14],"function":[15],"evolution.":[17],"Here":[18],"we":[19],"focus":[20],"on":[21],"an":[22],"intermediate":[23],"level":[24],"regularity.":[26],"We":[27,79,99],"have":[28],"developed":[29],"automated":[30],"methods":[31],"to":[32,47],"systematically":[33],"construct":[34],"a":[35,74,91],"dictionary":[36,53,83,128],"supersecondary":[38],"structures":[39,59,135],"that":[40,81,127],"be":[42,138],"used":[43],"as":[44],"'protein":[45],"parts'":[46],"describe":[48],"fold-sized":[49],"structures.":[50],"RESULTS:":[51],"The":[52],"was":[54],"constructed":[55],"by":[56],"aligning":[57],"representative":[58],"all":[61,95],"known":[62,96],"folds,":[63],"clustering":[64],"similar":[65],"substructures":[66,72],"selecting":[68],"most":[70],"descriptive":[71],"in":[73,122],"minimum":[75],"description":[76],"length":[77],"fashion.":[78],"show":[80],"is":[84],"compact":[85],"descriptive,":[87],"capable":[88,139],"describing":[90,141],"substantial":[92],"fraction":[93],"folds.":[98,109,144],"performed":[100],"simulations":[101],"using":[102,112],"independent":[103],"sets":[104],"training":[106,114],"testing":[108,124],"Dictionaries":[110],"generated":[111],"set":[115],"had":[116],"high":[117],"coverage":[118],"over":[119],"folds":[121],"set,":[125],"suggesting":[126],"entries":[129],"reflect":[130],"general":[131],"features":[132],"should":[137],"novel":[142]},"counts_by_year":[{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
