{"id":"https://openalex.org/W2021495307","doi":"https://doi.org/10.1186/1471-2105-11-364","title":"Automatic structure classification of small proteins using random forest","display_name":"Automatic structure classification of small proteins using random forest","publication_year":2010,"publication_date":"2010-07-01","ids":{"openalex":"https://openalex.org/W2021495307","doi":"https://doi.org/10.1186/1471-2105-11-364","mag":"2021495307","pmid":"https://pubmed.ncbi.nlm.nih.gov/20594334"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-11-364","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-364","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-364","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-364","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101441338","display_name":"Pooja Jain","orcid":"https://orcid.org/0000-0002-6595-8194"},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pooja Jain","raw_affiliation_strings":["School of Chemistry, The University of Nottingham, University Park, Nottingham, NG7 2RD, UK","School of Chemistry The University of Nottingham, University Park Nottingham NG7 2RD UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Chemistry, The University of Nottingham, University Park, Nottingham, NG7 2RD, UK","institution_ids":["https://openalex.org/I142263535"]},{"raw_affiliation_string":"School of Chemistry The University of Nottingham, University Park Nottingham NG7 2RD UK","institution_ids":["https://openalex.org/I142263535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051687648","display_name":"Jonathan D. Hirst","orcid":"https://orcid.org/0000-0002-2726-0983"},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jonathan D Hirst","raw_affiliation_strings":["School of Chemistry, The University of Nottingham, University Park, Nottingham, NG7 2RD, UK","School of Chemistry, The University of Nottingham Nottingham, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Chemistry, The University of Nottingham, University Park, Nottingham, NG7 2RD, UK","institution_ids":["https://openalex.org/I142263535"]},{"raw_affiliation_string":"School of Chemistry, The University of Nottingham Nottingham, UK","institution_ids":["https://openalex.org/I142263535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5051687648"],"corresponding_institution_ids":["https://openalex.org/I142263535"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":1.1201,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.75512933,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"11","issue":"1","first_page":"364","last_page":"364"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.44519999623298645,"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":0.44519999623298645,"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":0.40639999508857727,"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":0.03669999912381172,"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/random-forest","display_name":"Random forest","score":0.9332018494606018},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5832678079605103},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5551483631134033},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5048071146011353},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4827350974082947},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4825969934463501},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4672914147377014},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.44909510016441345},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.435133695602417},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.43149811029434204},{"id":"https://openalex.org/keywords/structural-classification-of-proteins-database","display_name":"Structural Classification of Proteins database","score":0.42870935797691345},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.42707210779190063},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"Multi-label classification","score":0.4120435118675232},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36012327671051025},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.23303738236427307},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.15219929814338684}],"concepts":[{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.9332018494606018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5832678079605103},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5551483631134033},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5048071146011353},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4827350974082947},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4825969934463501},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4672914147377014},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.44909510016441345},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.435133695602417},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.43149811029434204},{"id":"https://openalex.org/C58773245","wikidata":"https://www.wikidata.org/wiki/Q4832556","display_name":"Structural Classification of Proteins database","level":3,"score":0.42870935797691345},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.42707210779190063},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.4120435118675232},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36012327671051025},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.23303738236427307},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.15219929814338684},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"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}],"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":"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":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","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":"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":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/1471-2105-11-364","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-364","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-364","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:20594334","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20594334","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:c4935f2835b64c89aa649b1d6cc6ef2a","is_oa":false,"landing_page_url":"https://doaj.org/article/c4935f2835b64c89aa649b1d6cc6ef2a","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 11, Iss 1, p 364 (2010)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2916923","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2916923","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":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-11-364","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-364","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-364","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2021495307.pdf","grobid_xml":"https://content.openalex.org/works/W2021495307.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1570448133","https://openalex.org/W1574111052","https://openalex.org/W1582171523","https://openalex.org/W1591118180","https://openalex.org/W1965910641","https://openalex.org/W1969842170","https://openalex.org/W1979389134","https://openalex.org/W1982396997","https://openalex.org/W1990932448","https://openalex.org/W2006782375","https://openalex.org/W2008708467","https://openalex.org/W2015696044","https://openalex.org/W2021953523","https://openalex.org/W2055043387","https://openalex.org/W2055233956","https://openalex.org/W2055631962","https://openalex.org/W2058119134","https://openalex.org/W2062403173","https://openalex.org/W2076746539","https://openalex.org/W2079470039","https://openalex.org/W2085277871","https://openalex.org/W2103079096","https://openalex.org/W2104332903","https://openalex.org/W2104873783","https://openalex.org/W2105099387","https://openalex.org/W2107432340","https://openalex.org/W2108138353","https://openalex.org/W2108432201","https://openalex.org/W2109109045","https://openalex.org/W2118347512","https://openalex.org/W2118737745","https://openalex.org/W2125055259","https://openalex.org/W2125725297","https://openalex.org/W2127906599","https://openalex.org/W2128653811","https://openalex.org/W2130479394","https://openalex.org/W2137995988","https://openalex.org/W2141127144","https://openalex.org/W2145358391","https://openalex.org/W2145427519","https://openalex.org/W2145957695","https://openalex.org/W2151180344","https://openalex.org/W2152116196","https://openalex.org/W2153024955","https://openalex.org/W2162674806","https://openalex.org/W2165882374","https://openalex.org/W2408289238","https://openalex.org/W2911964244"],"related_works":["https://openalex.org/W4386259002","https://openalex.org/W2944292463","https://openalex.org/W3014252901","https://openalex.org/W2188759683","https://openalex.org/W4317376680","https://openalex.org/W4360777922","https://openalex.org/W3208169454","https://openalex.org/W4363647452","https://openalex.org/W2295624732","https://openalex.org/W4360995561"],"abstract_inverted_index":{"BACKGROUND:":[0],"Random":[1,84],"forest,":[2,85],"an":[3,37,100],"ensemble":[4],"based":[5,22],"supervised":[6],"machine":[7],"learning":[8],"algorithm,":[9],"is":[10,51,69,180,209],"used":[11],"to":[12,30,74,97,113,138,151,171,225,228],"predict":[13],"the":[14,24,114,122,126,141,147,166,172,194,213,220,229],"SCOP":[15,88,108,115,170,192,230],"structural":[16,28,153,189],"classification":[17,112,150,214,231],"for":[18,54,149,215],"a":[19,33,92,187],"target":[20],"structure,":[21],"on":[23,87,99],"similarity":[25],"of":[26,32,40,48,57,62,77,95,125,130,143,159,169,186,196],"its":[27],"descriptors":[29],"those":[31,216],"template":[34],"structure":[35,42],"with":[36],"equal":[38],"number":[39,142],"secondary":[41],"elements":[43],"(SSEs).":[44],"An":[45],"initial":[46],"assessment":[47],"random":[49,63,160,204],"forest":[50,64,161],"carried":[52],"out":[53],"domains":[55,68,75,164],"consisting":[56,76],"three":[58],"SSEs.":[59,82],"The":[60,157],"usability":[61],"in":[65,128,162,191],"classifying":[66,163],"larger":[67],"demonstrated":[70],"by":[71,211],"applying":[72],"it":[73],"four,":[78],"five":[79],"and":[80,102,193],"six":[81],"RESULTS:":[83],"trained":[86],"version":[89,109],"1.69,":[90],"achieves":[91],"predictive":[93,123],"accuracy":[94],"up":[96],"94%":[98],"independent":[101],"non-overlapping":[103],"test":[104],"set":[105],"derived":[106],"from":[107,136,165,219],"1.73.":[110],"For":[111],"Class,":[116,174],"Fold,":[117,175],"Super-family":[118,176],"or":[119,177],"Family":[120,178],"levels,":[121],"quality":[124],"model":[127],"terms":[129],"Matthew's":[131],"correlation":[132],"coefficient":[133],"(MCC)":[134],"ranged":[135],"0.61":[137],"0.83.":[139],"As":[140],"constituent":[144],"SSEs":[145],"increases":[146],"MCC":[148],"different":[152],"levels":[154,179,198],"decreases.":[155],"CONCLUSIONS:":[156],"utility":[158],"place-holder":[167],"classes":[168],"true":[173],"demonstrated.":[181],"Issues":[182],"such":[183],"as":[184],"introduction":[185],"new":[188],"level":[190],"merger":[195],"singleton":[197],"can":[199],"also":[200],"be":[201,226],"addressed":[202],"using":[203],"forest.":[205],"A":[206],"real-world":[207],"scenario":[208],"mimicked":[210],"predicting":[212],"protein":[217],"structures":[218],"PDB,":[221],"which":[222],"are":[223],"yet":[224],"assigned":[227],"hierarchy.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":5}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
