{"id":"https://openalex.org/W2765298570","doi":"https://doi.org/10.1002/prot.25405","title":"Protein contact prediction by integrating deep multiple sequence alignments, coevolution and machine learning","display_name":"Protein contact prediction by integrating deep multiple sequence alignments, coevolution and machine learning","publication_year":2017,"publication_date":"2017-10-19","ids":{"openalex":"https://openalex.org/W2765298570","doi":"https://doi.org/10.1002/prot.25405","mag":"2765298570","pmid":"https://pubmed.ncbi.nlm.nih.gov/29047157","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/5820155"},"language":"en","primary_location":{"id":"doi:10.1002/prot.25405","doi":"https://doi.org/10.1002/prot.25405","is_oa":false,"landing_page_url":"https://doi.org/10.1002/prot.25405","pdf_url":null,"source":{"id":"https://openalex.org/S121161810","display_name":"Proteins Structure Function and Bioinformatics","issn_l":"0887-3585","issn":["0887-3585","1097-0134"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-100","russia-white-list-2"],"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proteins: Structure, Function, and Bioinformatics","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://europepmc.org/pmc/articles/PMC5820155","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071481060","display_name":"Badri Adhikari","orcid":"https://orcid.org/0000-0002-1547-0238","observed_orcids":["https://orcid.org/0000-0002-1547-0238"]},"institutions":[{"id":"https://openalex.org/I208333798","display_name":"University of Missouri\u2013St. Louis","ror":"https://ror.org/037cnag11","country_code":"US","type":"education","lineage":["https://openalex.org/I208333798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Badri Adhikari","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Missouri-St. Louis, St. Louis, Missouri"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Missouri-St. Louis, St. Louis, Missouri","institution_ids":["https://openalex.org/I208333798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022495891","display_name":"Jie Hou","orcid":"https://orcid.org/0000-0002-8584-5154","observed_orcids":["https://orcid.org/0000-0002-8584-5154","https://orcid.org/0009-0003-2250-0532"]},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Hou","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, Missouri"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, Missouri","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044354277","display_name":"Jianlin Jack Cheng","orcid":"https://orcid.org/0000-0003-0305-2853","observed_orcids":["https://orcid.org/0000-0003-0305-2853"]},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jianlin Cheng","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, Missouri"],"raw_orcid":"https://orcid.org/0000-0003-0305-2853","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, Missouri","institution_ids":["https://openalex.org/I76835614"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5044354277"],"corresponding_institution_ids":["https://openalex.org/I76835614"],"apc_list":{"value":4550,"currency":"USD","value_usd":4550},"apc_paid":null,"fwci":1.3398,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.79869583,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"86","issue":"S1","first_page":"84","last_page":"96"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9613999724388123,"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":0.9613999724388123,"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":0.029100000858306885,"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":0.001500000013038516,"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/protein-contact-prediction","display_name":"protein contact prediction","score":0.9079999923706055},{"id":"https://openalex.org/keywords/residue-residue-contacts","display_name":"residue-residue contacts","score":0.8640000224113464},{"id":"https://openalex.org/keywords/residue-coevolution","display_name":"residue coevolution","score":0.9100000262260437},{"id":"https://openalex.org/keywords/long-range-contacts","display_name":"long-range contacts","score":0.7630000114440918},{"id":"https://openalex.org/keywords/sequence-profiles","display_name":"sequence profiles","score":0.42500001192092896},{"id":"https://openalex.org/keywords/secondary-structure","display_name":"secondary structure","score":0.8009999990463257},{"id":"https://openalex.org/keywords/solvent-accessibility","display_name":"solvent accessibility","score":0.996999979019165},{"id":"https://openalex.org/keywords/neural-network","display_name":"artificial neural networks","score":0.5080000162124634},{"id":"https://openalex.org/keywords/caspase-12","display_name":"caspase-12","score":0.781000018119812}],"concepts":[{"id":"https://openalex.org/C33009525","wikidata":"https://www.wikidata.org/wiki/Q208841","display_name":"Coevolution","level":2,"score":0.8341115117073059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7137898206710815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6173540353775024},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.5698357820510864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5097255110740662},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49085789918899536},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.48804178833961487},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4696713387966156},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.40478795766830444},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34204530715942383},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.13324105739593506},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1114562451839447},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","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":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":true},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","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":false},{"descriptor_ui":"D018360","descriptor_name":"Crystallography, X-Ray","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, 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":"D066264","descriptor_name":"Datasets as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1002/prot.25405","doi":"https://doi.org/10.1002/prot.25405","is_oa":false,"landing_page_url":"https://doi.org/10.1002/prot.25405","pdf_url":null,"source":{"id":"https://openalex.org/S121161810","display_name":"Proteins Structure Function and Bioinformatics","issn_l":"0887-3585","issn":["0887-3585","1097-0134"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-100","russia-white-list-2"],"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proteins: Structure, Function, and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:29047157","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29047157","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,"listed_in":[],"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":"Proteins","raw_type":"Journal Article"},{"id":"pmh:oai:europepmc.org:5370203","doi":null,"is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC5820155","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:5820155","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5820155","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,"listed_in":[],"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Proteins","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:europepmc.org:5370203","doi":null,"is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC5820155","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G7450496187","display_name":"Distance-based ab initio protein structure prediction","funder_award_id":"R01GM093123","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1540530720","https://openalex.org/W1967292572","https://openalex.org/W1982420443","https://openalex.org/W1988790447","https://openalex.org/W2002129624","https://openalex.org/W2033354942","https://openalex.org/W2051210555","https://openalex.org/W2069458148","https://openalex.org/W2102245393","https://openalex.org/W2107110246","https://openalex.org/W2108101947","https://openalex.org/W2110510374","https://openalex.org/W2114251106","https://openalex.org/W2114340287","https://openalex.org/W2119843684","https://openalex.org/W2136799255","https://openalex.org/W2145991251","https://openalex.org/W2160784118","https://openalex.org/W2166701319","https://openalex.org/W2213268248","https://openalex.org/W2280207768","https://openalex.org/W2560695073","https://openalex.org/W2949867299","https://openalex.org/W6695187313"],"related_works":["https://openalex.org/W2801109052","https://openalex.org/W2110510374","https://openalex.org/W2968295962","https://openalex.org/W2970594786","https://openalex.org/W2765742208","https://openalex.org/W3132487128","https://openalex.org/W3003647270","https://openalex.org/W2547388037","https://openalex.org/W2949867299","https://openalex.org/W6960983256"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3],"report":[4],"the":[5,8,18,24,103,106,144,149,171,178,182,188,196,202,206,219,222,228,231],"evaluation":[6],"of":[7,26,102,105,121,131,143,154,164,173,200,224,230,233],"residue-residue":[9],"contacts":[10,58,215],"predicted":[11,174,213],"by":[12,86],"our":[13,69,112,125],"three":[14,145],"different":[15],"methods":[16,113,126,146],"in":[17,236],"CASP12":[19,116,180],"experiment,":[20],"focusing":[21],"on":[22,35,114],"studying":[23],"impact":[25],"multiple":[27,76,155],"sequence":[28,77,156],"alignment,":[29],"residue":[30],"coevolution,":[31],"and":[32,50,59,151,160,167,195,227],"machine":[33,161,197],"learning":[34,55,162,198],"contact":[36,139,225],"prediction.":[37],"The":[38,64,94,141],"first":[39,107],"method":[40,66,90,96],"(MULTICOM-NOVEL)":[41],"uses":[42,68],"only":[43],"traditional":[44,168],"features":[45,166,169,184,203],"(sequence":[46],"profile,":[47],"secondary":[48],"structure,":[49],"solvent":[51],"accessibility)":[52],"with":[53],"deep":[54,75],"to":[56,73,79,91,133,193,208],"predict":[57,92],"serves":[60],"as":[61],"a":[62,87,99,119],"baseline.":[63],"second":[65],"(MULTICOM-CONSTRUCT)":[67],"new":[70],"alignment":[71,78],"algorithm":[72],"generate":[74],"derive":[80],"coevolution-based":[81,158,165,183],"features,":[82,159],"which":[83],"are":[84,216],"integrated":[85],"neural":[88],"network":[89],"contacts.":[93,176],"third":[95],"(MULTICOM-CLUSTER)":[97],"is":[98,238],"consensus":[100],"combination":[101],"predictions":[104],"two":[108],"methods.":[109],"We":[110],"evaluated":[111],"94":[115],"domains.":[117],"On":[118,177],"subset":[120],"38":[122],"free-modeling":[123],"domains,":[124],"achieved":[127],"an":[128],"average":[129,189],"precision":[130,190,207,223],"up":[132],"41.7%":[134],"for":[135],"top":[136,211],"L/5":[137,212],"long-range":[138,214],"predictions.":[140],"comparison":[142],"shows":[147],"that":[148],"quality":[150,172],"effective":[152,234],"depth":[153],"alignments,":[157],"integration":[163,199],"drive":[170],"protein":[175],"full":[179],"dataset,":[181],"alone":[185],"can":[186],"improve":[187],"from":[191],"28.4%":[192],"41.6%,":[194],"all":[201],"further":[204],"raises":[205],"56.3%,":[209],"when":[210],"evaluated.":[217],"And":[218],"correlation":[220],"between":[221],"prediction":[226],"logarithm":[229],"number":[232],"sequences":[235],"alignments":[237],"0.66.":[239]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2017-11-10T00:00:00"}