{"id":"https://openalex.org/W2171259901","doi":"https://doi.org/10.1093/bioinformatics/btu556","title":"Prediction of Indel flanking regions in protein sequences using a variable-order Markov model","display_name":"Prediction of Indel flanking regions in protein sequences using a variable-order Markov model","publication_year":2014,"publication_date":"2014-08-31","ids":{"openalex":"https://openalex.org/W2171259901","doi":"https://doi.org/10.1093/bioinformatics/btu556","mag":"2171259901","pmid":"https://pubmed.ncbi.nlm.nih.gov/25178462"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btu556","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu556","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/1/40/17126450/btu556.pdf","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":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/31/1/40/17126450/btu556.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050636829","display_name":"Mufleh Al-Shatnawi","orcid":null},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Mufleh Al-Shatnawi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Concordia University, QC H3G 2W1, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Concordia University, QC H3G 2W1, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068820891","display_name":"M. Omair Ahmad","orcid":"https://orcid.org/0000-0002-2924-6659"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"M. Omair Ahmad","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Concordia University, QC H3G 2W1, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Concordia University, QC H3G 2W1, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013967994","display_name":"M.N.S. Swamy","orcid":"https://orcid.org/0000-0002-3989-5476"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"M.N.S. Swamy","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Concordia University, QC H3G 2W1, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Concordia University, QC H3G 2W1, Canada","institution_ids":["https://openalex.org/I60158472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5013967994","https://openalex.org/A5050636829","https://openalex.org/A5068820891"],"corresponding_institution_ids":["https://openalex.org/I60158472"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.1423,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.5583658,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"31","issue":"1","first_page":"40","last_page":"47"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.41749998927116394,"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":0.41749998927116394,"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":0.14910000562667847,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.10970000177621841,"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/indel","display_name":"Indel","score":0.7857058048248291},{"id":"https://openalex.org/keywords/flanking-maneuver","display_name":"Flanking maneuver","score":0.7056198120117188},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.6893987655639648},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.5011041164398193},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.49993109703063965},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4458673894405365},{"id":"https://openalex.org/keywords/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.4277442693710327},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.4230020046234131},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.37193918228149414},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35618287324905396},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.340478777885437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3191817104816437},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2785710096359253},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.12991833686828613},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.11887398362159729},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07526895403862}],"concepts":[{"id":"https://openalex.org/C119054055","wikidata":"https://www.wikidata.org/wiki/Q1576681","display_name":"Indel","level":5,"score":0.7857058048248291},{"id":"https://openalex.org/C75728560","wikidata":"https://www.wikidata.org/wiki/Q1427134","display_name":"Flanking maneuver","level":2,"score":0.7056198120117188},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.6893987655639648},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.5011041164398193},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.49993109703063965},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4458673894405365},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.4277442693710327},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4230020046234131},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.37193918228149414},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35618287324905396},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.340478777885437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3191817104816437},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2785710096359253},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.12991833686828613},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.11887398362159729},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07526895403862},{"id":"https://openalex.org/C153209595","wikidata":"https://www.wikidata.org/wiki/Q501128","display_name":"Single-nucleotide polymorphism","level":4,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"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":"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":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","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":"D019943","descriptor_name":"Amino Acid Substitution","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019943","descriptor_name":"Amino Acid Substitution","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019943","descriptor_name":"Amino Acid Substitution","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":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},{"descriptor_ui":"D054643","descriptor_name":"INDEL Mutation","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D054643","descriptor_name":"INDEL Mutation","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D054643","descriptor_name":"INDEL Mutation","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btu556","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu556","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/1/40/17126450/btu556.pdf","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:25178462","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25178462","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},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.959.4160","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.959.4160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/content/early/2014/08/31/bioinformatics.btu556.full.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btu556","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu556","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/1/40/17126450/btu556.pdf","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"},"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2171259901.pdf","grobid_xml":"https://content.openalex.org/works/W2171259901.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W196767578","https://openalex.org/W563739540","https://openalex.org/W1864290935","https://openalex.org/W1979486483","https://openalex.org/W1981575795","https://openalex.org/W1994920552","https://openalex.org/W2011485152","https://openalex.org/W2018248334","https://openalex.org/W2019572077","https://openalex.org/W2049268173","https://openalex.org/W2051873396","https://openalex.org/W2067657048","https://openalex.org/W2093169207","https://openalex.org/W2097555181","https://openalex.org/W2102122585","https://openalex.org/W2103533532","https://openalex.org/W2103960658","https://openalex.org/W2128613007","https://openalex.org/W2128653811","https://openalex.org/W2129995544","https://openalex.org/W2133657429","https://openalex.org/W2135621733","https://openalex.org/W2135771747","https://openalex.org/W2139814676","https://openalex.org/W2140244239","https://openalex.org/W2141885858","https://openalex.org/W2143292980","https://openalex.org/W2144998676","https://openalex.org/W2151831732","https://openalex.org/W2156628505","https://openalex.org/W2158698691","https://openalex.org/W2160708989","https://openalex.org/W2161628678","https://openalex.org/W2163294786","https://openalex.org/W2163304934","https://openalex.org/W2164698543","https://openalex.org/W3104314953","https://openalex.org/W4234588445","https://openalex.org/W4320301318","https://openalex.org/W6607978808","https://openalex.org/W6638857174","https://openalex.org/W6674463856","https://openalex.org/W6681619517","https://openalex.org/W6683118431"],"related_works":["https://openalex.org/W2093169207","https://openalex.org/W2084326697","https://openalex.org/W2027903142","https://openalex.org/W2354322608","https://openalex.org/W2804608325","https://openalex.org/W2077211377","https://openalex.org/W2186675474","https://openalex.org/W2387462590","https://openalex.org/W2056274461","https://openalex.org/W2368739446"],"abstract_inverted_index":{"MOTIVATION:":[0],"Insertion/deletion":[1],"(indel)":[2],"and":[3,17,28,56,71,118,131,159],"amino":[4],"acid":[5],"substitution":[6,48],"are":[7,34,109,124,146],"two":[8],"common":[9],"events":[10],"that":[11,142,167],"lead":[12],"to":[13,37,67,82,126,148,183],"the":[14,25,47,128,143,152,164,185,195,200],"evolution":[15],"of":[16,24,54,189,194,199],"variations":[18],"in":[19,64,87,151,173,176,192],"protein":[20,68,89,94,153,177],"sequences.":[21],"Further,":[22],"many":[23],"human":[26],"diseases":[27],"functional":[29],"divergence":[30],"between":[31],"homologous":[32],"proteins":[33],"more":[35],"related":[36,66],"indel":[38,84,104],"mutations,":[39],"even":[40],"though":[41],"they":[42],"occur":[43],"less":[44],"often":[45],"than":[46],"mutations":[49],"do.":[50],"A":[51],"reliable":[52],"identification":[53],"indels":[55],"their":[57],"flanking":[58,85,105],"regions":[59,86],"is":[60,170],"a":[61,79,88,92,98,156],"major":[62],"challenge":[63],"research":[65],"evolution,":[69],"structures":[70],"functions.":[72],"RESULTS:":[73],"In":[74,162],"this":[75],"article,":[76],"we":[77],"propose":[78],"novel":[80],"scheme":[81],"predict":[83,149],"sequence":[90],"for":[91],"given":[93],"fold,":[95],"based":[96,111],"on":[97,112],"variable-order":[99],"Markov":[100],"model.":[101],"The":[102,136],"proposed":[103,144,186],"region":[106],"(IndelFR)":[107],"predictors":[108,145,187],"designed":[110],"prediction":[113],"by":[114],"partial":[115],"match":[116],"(PPM)":[117],"probabilistic":[119],"suffix":[120],"tree":[121],"(PST),":[122],"which":[123],"referred":[125],"as":[127],"PPM":[129],"IndelFR":[130,133],"PST":[132],"predictors,":[134],"respectively.":[135],"overall":[137],"performance":[138,198],"evaluation":[139],"results":[140,165],"show":[141,166],"able":[147],"IndelFRs":[150,175],"sequences":[154],"with":[155],"high":[157],"accuracy":[158],"F1":[160],"measure.":[161],"addition,":[163],"if":[168],"one":[169],"interested":[171],"only":[172],"predicting":[174],"sequences,":[178],"it":[179],"would":[180],"be":[181],"preferable":[182],"use":[184],"instead":[188],"HMMER":[190],"3.0":[191],"view":[193],"substantially":[196],"superior":[197],"former.":[201]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}
