{"id":"https://openalex.org/W2777400030","doi":"https://doi.org/10.1186/s12859-017-1896-1","title":"Effective computational detection of piRNAs using n-gram models and support vector machine","display_name":"Effective computational detection of piRNAs using n-gram models and support vector machine","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2777400030","doi":"https://doi.org/10.1186/s12859-017-1896-1","mag":"2777400030","pmid":"https://pubmed.ncbi.nlm.nih.gov/29297285"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-017-1896-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-017-1896-1","pdf_url":null,"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://doi.org/10.1186/s12859-017-1896-1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100629596","display_name":"Chun\u2010Chi Chen","orcid":"https://orcid.org/0000-0002-7459-5591"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chun-Chi Chen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073946580","display_name":"Xiaoning Qian","orcid":"https://orcid.org/0000-0002-4347-2476"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoning Qian","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081620315","display_name":"Byung-Jun Yoon","orcid":"https://orcid.org/0000-0001-9328-1101"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Byung-Jun Yoon","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843, USA. bjyoon@ece.tamu.edu","Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843, USA. bjyoon@ece.tamu.edu","institution_ids":[]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843, USA","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100629596"],"corresponding_institution_ids":["https://openalex.org/I91045830"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":1.5197,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88587334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"18","issue":"S14","first_page":"517","last_page":"517"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10434","display_name":"Chromosomal and Genetic Variations","score":0.5709999799728394,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10434","display_name":"Chromosomal and Genetic Variations","score":0.5709999799728394,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.23350000381469727,"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/T10062","display_name":"MicroRNA in disease regulation","score":0.02370000071823597,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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/piwi-interacting-rna","display_name":"Piwi-interacting RNA","score":0.8570057153701782},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5880637168884277},{"id":"https://openalex.org/keywords/transposable-element","display_name":"Transposable element","score":0.5172339081764221},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5118514895439148},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5059472918510437},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.44896721839904785},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.4119926691055298},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.38221102952957153},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2807317078113556},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.22768762707710266},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.08807912468910217}],"concepts":[{"id":"https://openalex.org/C147724379","wikidata":"https://www.wikidata.org/wiki/Q2367421","display_name":"Piwi-interacting RNA","level":5,"score":0.8570057153701782},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5880637168884277},{"id":"https://openalex.org/C4918238","wikidata":"https://www.wikidata.org/wiki/Q121438","display_name":"Transposable element","level":4,"score":0.5172339081764221},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5118514895439148},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5059472918510437},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.44896721839904785},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.4119926691055298},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.38221102952957153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2807317078113556},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.22768762707710266},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08807912468910217}],"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":"D012372","descriptor_name":"ROC Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012372","descriptor_name":"ROC Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012372","descriptor_name":"ROC Curve","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":"D019540","descriptor_name":"Area Under Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019540","descriptor_name":"Area Under Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019540","descriptor_name":"Area Under Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D034741","descriptor_name":"RNA, Small Interfering","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D034741","descriptor_name":"RNA, Small Interfering","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D034741","descriptor_name":"RNA, Small Interfering","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-017-1896-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-017-1896-1","pdf_url":null,"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:29297285","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29297285","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:6760b363d3d64b208334b54e2226fb7b","is_oa":true,"landing_page_url":"https://doaj.org/article/6760b363d3d64b208334b54e2226fb7b","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 18, Iss S14, Pp 103-109 (2017)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:4668014","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5751586","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-017-1896-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-017-1896-1","pdf_url":null,"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":[{"id":"https://metadata.un.org/sdg/15","score":0.5199999809265137,"display_name":"Life in Land"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332299","display_name":"National Institute of Food and Agriculture","ror":"https://ror.org/05qx3fv49"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1544435011","https://openalex.org/W1836859378","https://openalex.org/W1974486163","https://openalex.org/W1976342457","https://openalex.org/W1977733607","https://openalex.org/W1991022130","https://openalex.org/W1996640618","https://openalex.org/W2013424227","https://openalex.org/W2020441317","https://openalex.org/W2035930185","https://openalex.org/W2040975355","https://openalex.org/W2046318418","https://openalex.org/W2047988520","https://openalex.org/W2048218599","https://openalex.org/W2050385516","https://openalex.org/W2065669787","https://openalex.org/W2104465908","https://openalex.org/W2108230379","https://openalex.org/W2108421854","https://openalex.org/W2109305617","https://openalex.org/W2122000580","https://openalex.org/W2130659976","https://openalex.org/W2148105495","https://openalex.org/W2153635508","https://openalex.org/W2155653793","https://openalex.org/W2158381555","https://openalex.org/W2160828096","https://openalex.org/W2161207862","https://openalex.org/W2234938965","https://openalex.org/W2342051973","https://openalex.org/W2562883458","https://openalex.org/W4285665422"],"related_works":["https://openalex.org/W2015402753","https://openalex.org/W1596971406","https://openalex.org/W2322107403","https://openalex.org/W2943992342","https://openalex.org/W4254016008","https://openalex.org/W1976342457","https://openalex.org/W3203020171","https://openalex.org/W1511345757","https://openalex.org/W4297837501","https://openalex.org/W2544598565"],"abstract_inverted_index":{"BACKGROUND:":[0],"Piwi-interacting":[1],"RNAs":[2,11],"(piRNAs)":[3],"are":[4,13,43,154],"a":[5,50,62,107,159],"new":[6],"class":[7],"of":[8,52,76,98,115,146,170,178,218],"small":[9],"non-coding":[10],"that":[12,41,69,133,163,209],"known":[14],"to":[15,45,56,157],"be":[16,71,165],"associated":[17],"with":[18],"RNA":[19],"silencing.":[20],"The":[21,150],"piRNAs":[22,42,79,99,116,189],"play":[23],"an":[24],"important":[25],"role":[26],"in":[27,34,117,129,190,216],"protecting":[28],"the":[29,35,46,121,130,144,176,179,205,212],"genome":[30,47,118],"from":[31,204],"invasive":[32],"transposons":[33],"germline.":[36],"Recent":[37],"studies":[38],"have":[39],"shown":[40],"linked":[44],"stability":[48],"and":[49,84,138,199,207,220],"variety":[51],"human":[53],"cancers.":[54],"Due":[55],"their":[57],"clinical":[58],"importance,":[59],"there":[60],"is":[61],"pressing":[63],"need":[64],"for":[65,73,111,167],"effective":[66,140],"computational":[67,74,96,113],"methods":[68,215],"can":[70,164],"used":[72,156,166],"identification":[75],"piRNAs.":[77,172],"However,":[78],"lack":[80],"conserved":[81],"structural":[82],"motifs":[83,137],"show":[85,208],"relatively":[86],"low":[87],"sequence":[88,136],"similarity":[89],"across":[90],"different":[91,192],"species,":[92],"which":[93],"makes":[94],"accurate":[95,168],"prediction":[97,114,169],"challenging.":[100],"RESULTS:":[101],"In":[102,120],"this":[103],"paper,":[104],"we":[105,124],"propose":[106],"novel":[108,171],"method,":[109,123],"piRNAdetect,":[110],"reliable":[112],"sequences.":[119],"proposed":[122,180],"first":[125],"classify":[126],"piRNA":[127],"sequences":[128],"training":[131],"dataset":[132],"share":[134],"similar":[135],"extract":[139],"predictive":[141],"features":[142,153],"through":[143,183],"use":[145],"n-gram":[147],"models":[148],"(NGMs).":[149],"extracted":[151],"NGM-based":[152],"then":[155],"construct":[158],"support":[160],"vector":[161],"machine":[162],"CONCLUSIONS:":[173],"We":[174],"demonstrate":[175],"effectiveness":[177],"piRNAdetect":[181,210],"algorithm":[182],"extensive":[184],"performance":[185],"evaluation":[186],"based":[187],"on":[188],"three":[191],"species":[193],"-":[194,202],"H.":[195],"sapiens,":[196],"R.":[197],"norvegicus,":[198],"M.":[200],"musculus":[201],"obtained":[203],"piRBase":[206],"outperforms":[211],"current":[213],"state-of-the-art":[214],"terms":[217],"efficiency":[219],"accuracy.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
