{"id":"https://openalex.org/W1983810656","doi":"https://doi.org/10.1186/1471-2105-9-297","title":"Identification of deleterious non-synonymous single nucleotide polymorphisms using sequence-derived information","display_name":"Identification of deleterious non-synonymous single nucleotide polymorphisms using sequence-derived information","publication_year":2008,"publication_date":"2008-06-27","ids":{"openalex":"https://openalex.org/W1983810656","doi":"https://doi.org/10.1186/1471-2105-9-297","mag":"1983810656","pmid":"https://pubmed.ncbi.nlm.nih.gov/18588693"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-9-297","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-9-297","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-9-297","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/10.1186/1471-2105-9-297","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101421877","display_name":"Jing Hu","orcid":"https://orcid.org/0000-0003-1348-8773"},"institutions":[{"id":"https://openalex.org/I121980950","display_name":"Utah State University","ror":"https://ror.org/00h6set76","country_code":"US","type":"education","lineage":["https://openalex.org/I121980950"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Hu","raw_affiliation_strings":["Department of Computer Science, Utah State University, Logan, UT 84322, USA. jinghu@cc.usu.edu","Department of Computer Science, Utah State University, Logan, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Utah State University, Logan, UT 84322, USA. jinghu@cc.usu.edu","institution_ids":["https://openalex.org/I121980950"]},{"raw_affiliation_string":"Department of Computer Science, Utah State University, Logan, USA","institution_ids":["https://openalex.org/I121980950"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100871727","display_name":"Changhui Yan","orcid":"https://orcid.org/0000-0003-3048-8628"},"institutions":[{"id":"https://openalex.org/I121980950","display_name":"Utah State University","ror":"https://ror.org/00h6set76","country_code":"US","type":"education","lineage":["https://openalex.org/I121980950"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Changhui Yan","raw_affiliation_strings":["Department of Computer Science, Utah State University, Logan, UT, 84322, USA","Department of Computer Science, Utah State University, Logan, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Utah State University, Logan, UT, 84322, USA","institution_ids":["https://openalex.org/I121980950"]},{"raw_affiliation_string":"Department of Computer Science, Utah State University, Logan, USA","institution_ids":["https://openalex.org/I121980950"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100871727"],"corresponding_institution_ids":["https://openalex.org/I121980950"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.9739,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.77741711,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"9","issue":"1","first_page":"297","last_page":"297"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.8848999738693237,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T11642","display_name":"Genomics and Rare Diseases","score":0.8848999738693237,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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":0.08190000057220459,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.006200000178068876,"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/feature-selection","display_name":"Feature selection","score":0.5393080711364746},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5143231153488159},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.504181981086731},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4864063262939453},{"id":"https://openalex.org/keywords/matthews-correlation-coefficient","display_name":"Matthews correlation coefficient","score":0.456053227186203},{"id":"https://openalex.org/keywords/mutation","display_name":"Mutation","score":0.44021567702293396},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.4333268404006958},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.4312354028224945},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.4216729998588562},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41775715351104736},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4143252968788147},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39871323108673096},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.38415244221687317},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3816894292831421},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2966741621494293},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.14965075254440308},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.08717679977416992}],"concepts":[{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5393080711364746},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5143231153488159},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.504181981086731},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4864063262939453},{"id":"https://openalex.org/C164085508","wikidata":"https://www.wikidata.org/wiki/Q4811327","display_name":"Matthews correlation coefficient","level":3,"score":0.456053227186203},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.44021567702293396},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.4333268404006958},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.4312354028224945},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.4216729998588562},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41775715351104736},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4143252968788147},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39871323108673096},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.38415244221687317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3816894292831421},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2966741621494293},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.14965075254440308},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.08717679977416992},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","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":"D006801","descriptor_name":"Humans","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":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","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":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/1471-2105-9-297","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-9-297","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-9-297","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:18588693","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/18588693","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:856b3f1496fe450997606df938485938","is_oa":false,"landing_page_url":"https://doaj.org/article/856b3f1496fe450997606df938485938","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 9, Iss 1, p 297 (2008)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2446391","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2446391","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:10.1186/1471-2105-9-297","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-9-297","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-9-297","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1983810656.pdf","grobid_xml":"https://content.openalex.org/works/W1983810656.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1497905029","https://openalex.org/W1570448133","https://openalex.org/W1975017420","https://openalex.org/W1987242394","https://openalex.org/W1995648971","https://openalex.org/W2000140185","https://openalex.org/W2010595044","https://openalex.org/W2014731953","https://openalex.org/W2022368654","https://openalex.org/W2025670719","https://openalex.org/W2045389157","https://openalex.org/W2057029228","https://openalex.org/W2075155374","https://openalex.org/W2081254674","https://openalex.org/W2085005062","https://openalex.org/W2087486085","https://openalex.org/W2099564671","https://openalex.org/W2099589970","https://openalex.org/W2105131949","https://openalex.org/W2107432340","https://openalex.org/W2108028755","https://openalex.org/W2122732537","https://openalex.org/W2131234009","https://openalex.org/W2135252110","https://openalex.org/W2141481588","https://openalex.org/W2143210482","https://openalex.org/W2143238378","https://openalex.org/W2153127576","https://openalex.org/W2164004777","https://openalex.org/W2170109912","https://openalex.org/W2601913882","https://openalex.org/W2607436248","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4307883119","https://openalex.org/W2345184372","https://openalex.org/W27971500","https://openalex.org/W2348097614","https://openalex.org/W2316780152","https://openalex.org/W2592385986","https://openalex.org/W2314710578","https://openalex.org/W2154383834","https://openalex.org/W2022684485","https://openalex.org/W2111662190"],"abstract_inverted_index":{"BACKGROUND:":[0],"As":[1],"the":[2,49,64,77,111,114,130,136,145,176,179,184,198,206,208,278,284,287],"number":[3],"of":[4,48,54,79,99,138,241,263,280,286],"non-synonymous":[5],"single":[6,13],"nucleotide":[7],"polymorphisms":[8,16],"(nsSNPs),":[9],"also":[10,196],"known":[11],"as":[12],"amino":[14],"acid":[15],"(SAPs),":[17],"increases":[18],"rapidly,":[19],"computational":[20],"methods":[21,33,56],"that":[22,58,102,132,171],"can":[23,152],"distinguish":[24,38],"disease-causing":[25,39,83],"SAPs":[26,29,40,81,203],"from":[27,91,105,205,232,259],"neutral":[28,85],"are":[30,60,69,228],"needed.":[31],"Many":[32],"have":[34],"been":[35],"developed":[36],"to":[37,63,128,221,254],"based":[41],"on":[42,167,201],"both":[43],"structural":[44],"and":[45,84,117,181,246],"sequence":[46],"features":[47,101,131,141,242,258,264],"mutation":[50],"point.":[51],"One":[52],"limitation":[53],"these":[55],"is":[57,273,289],"they":[59],"not":[61,70,173,229,290],"applicable":[62],"cases":[65],"where":[66],"protein":[67,92,106,226,288],"structures":[68,227],"available.":[71,230,291],"In":[72],"this":[73],"study,":[74],"we":[75,249],"explore":[76],"feasibility":[78],"classifying":[80],"into":[82],"mutations":[86],"using":[87],"only":[88,237],"information":[89],"derived":[90,104],"sequence.":[93,107],"RESULTS:":[94],"We":[95,195],"compiled":[96],"a":[97,123,148,238,260,274],"set":[98,170,240,262],"686":[100],"were":[103,133,142,243],"For":[108],"each":[109],"feature,":[110],"distance":[112],"between":[113],"wild-type":[115],"residue":[116,119],"mutant-type":[118],"was":[120,126,172],"computed.":[121],"Then":[122],"greedy":[124],"approach":[125],"used":[127,250],"select":[129],"useful":[134,257,275],"for":[135,277],"classification":[137,279],"SAPs.":[139],"10":[140],"selected.":[143],"Using":[144],"selected":[146],"features,":[147],"decision":[149,185],"tree":[150,186],"method":[151,177,187,200,209,218,253,272],"achieve":[153],"82.6%":[154,189],"overall":[155,190,215],"accuracy":[156,191],"with":[157,192,213],"0.607":[158],"Matthews":[159],"Correlation":[160],"Coefficient":[161],"(MCC)":[162],"in":[163,235,266],"cross-validation.":[164],"When":[165],"tested":[166],"an":[168,251],"independent":[169],"seen":[174],"by":[175],"during":[178],"training":[180],"feature":[182],"selection,":[183],"achieves":[188,210],"0.604":[193],"MCC.":[194],"evaluated":[197],"proposed":[199,271],"all":[202],"obtained":[204],"Swiss-Prot,":[207],"0.42":[211],"MCC":[212],"73.2%":[214],"accuracy.":[216],"This":[217],"allows":[219],"users":[220],"make":[222],"reliable":[223],"predictions":[224],"when":[225,283],"Different":[231],"previous":[233],"studies,":[234],"which":[236],"small":[239],"arbitrarily":[244],"chosen":[245],"considered,":[247],"here":[248],"automated":[252],"systematically":[255],"discover":[256],"large":[261],"well-annotated":[265],"public":[267],"databases.":[268],"CONCLUSION:":[269],"The":[270],"tool":[276],"SAPs,":[281],"especially,":[282],"structure":[285]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}
