{"id":"https://openalex.org/W3013495013","doi":"https://doi.org/10.1093/bib/bbaa039","title":"DeepCPP: a deep neural network based on nucleotide bias information and minimum distribution similarity feature selection for RNA coding potential prediction","display_name":"DeepCPP: a deep neural network based on nucleotide bias information and minimum distribution similarity feature selection for RNA coding potential prediction","publication_year":2020,"publication_date":"2020-02-26","ids":{"openalex":"https://openalex.org/W3013495013","doi":"https://doi.org/10.1093/bib/bbaa039","mag":"3013495013","pmid":"https://pubmed.ncbi.nlm.nih.gov/32227075"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbaa039","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbaa039","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"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":"Briefings in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075131520","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0003-4952-8095"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Techonological University, 50 Nanyang Avenue, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Techonological University, 50 Nanyang Avenue, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066126756","display_name":"Cangzhi Jia","orcid":"https://orcid.org/0000-0002-4682-2881"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Cangzhi Jia","raw_affiliation_strings":["School of Mathematical Sciences, Dalian University of Technology, No.2 Linggong Road, Dalian, China"],"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Dalian University of Technology, No.2 Linggong Road, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087492673","display_name":"Melissa J. Fullwood","orcid":"https://orcid.org/0000-0003-0321-7865"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Melissa Jane Fullwood","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Techonological University, 50 Nanyang Avenue, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Techonological University, 50 Nanyang Avenue, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027208445","display_name":"Chee Keong Kwoh","orcid":"https://orcid.org/0000-0002-8547-6387"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Chee Keong Kwoh","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Techonological University, 50 Nanyang Avenue, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Techonological University, 50 Nanyang Avenue, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5027208445","https://openalex.org/A5066126756"],"corresponding_institution_ids":["https://openalex.org/I172675005","https://openalex.org/I27357992"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":null,"fwci":3.9214,"has_fulltext":false,"cited_by_count":73,"citation_normalized_percentile":{"value":0.94774496,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"22","issue":"2","first_page":"2073","last_page":"2084"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9997000098228455,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9997000098228455,"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/T10515","display_name":"Cancer-related molecular mechanisms research","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10604","display_name":"RNA Research and Splicing","score":0.9962999820709229,"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/coding","display_name":"Coding (social sciences)","score":0.6390818953514099},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6273831129074097},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5857913494110107},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5666923522949219},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.540922224521637},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5145685076713562},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5004446506500244},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4874174892902374},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.47006019949913025},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4307713806629181},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4095745384693146},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2449837625026703},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16976392269134521},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11958613991737366}],"concepts":[{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.6390818953514099},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6273831129074097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5857913494110107},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5666923522949219},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.540922224521637},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5145685076713562},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5004446506500244},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4874174892902374},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.47006019949913025},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4307713806629181},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4095745384693146},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2449837625026703},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16976392269134521},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11958613991737366},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D012333","descriptor_name":"RNA, Messenger","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012333","descriptor_name":"RNA, Messenger","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012333","descriptor_name":"RNA, Messenger","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D062085","descriptor_name":"RNA, Long Noncoding","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D062085","descriptor_name":"RNA, Long Noncoding","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D062085","descriptor_name":"RNA, Long Noncoding","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bib/bbaa039","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbaa039","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"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":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:32227075","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32227075","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":"Briefings in bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.46000000834465027,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4150216259","display_name":null,"funder_award_id":"NRF-NRFF2012\u2013054","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W297888808","https://openalex.org/W1253096047","https://openalex.org/W1965555277","https://openalex.org/W1966498224","https://openalex.org/W1980069210","https://openalex.org/W1998422171","https://openalex.org/W2029173942","https://openalex.org/W2041073668","https://openalex.org/W2048194168","https://openalex.org/W2052503008","https://openalex.org/W2061548680","https://openalex.org/W2075320162","https://openalex.org/W2080052447","https://openalex.org/W2085220756","https://openalex.org/W2085651871","https://openalex.org/W2087377443","https://openalex.org/W2100779682","https://openalex.org/W2112250822","https://openalex.org/W2139658526","https://openalex.org/W2154053567","https://openalex.org/W2156125289","https://openalex.org/W2161700404","https://openalex.org/W2162417400","https://openalex.org/W2166810745","https://openalex.org/W2173732482","https://openalex.org/W2174605830","https://openalex.org/W2237493771","https://openalex.org/W2415774299","https://openalex.org/W2559953833","https://openalex.org/W2567665210","https://openalex.org/W2571489439","https://openalex.org/W2601436215","https://openalex.org/W2610181528","https://openalex.org/W2615786037","https://openalex.org/W2624274298","https://openalex.org/W2734798616","https://openalex.org/W2747811776","https://openalex.org/W2752880228","https://openalex.org/W2757287504","https://openalex.org/W2761249484","https://openalex.org/W2765094054","https://openalex.org/W2783029521","https://openalex.org/W2805813857","https://openalex.org/W2807607992","https://openalex.org/W2886900083","https://openalex.org/W2900694973","https://openalex.org/W2900836409","https://openalex.org/W2911561283","https://openalex.org/W2914698725","https://openalex.org/W2941697964","https://openalex.org/W2951413354","https://openalex.org/W3024934090","https://openalex.org/W3147833596","https://openalex.org/W6731700065","https://openalex.org/W6761475027"],"related_works":["https://openalex.org/W2375480909","https://openalex.org/W2353314428","https://openalex.org/W2012019886","https://openalex.org/W3147584709","https://openalex.org/W2166090428","https://openalex.org/W2381021552","https://openalex.org/W2354749003","https://openalex.org/W2377121353","https://openalex.org/W4386564352","https://openalex.org/W2952668426"],"abstract_inverted_index":{"The":[0],"development":[1],"of":[2,11,26,109],"deep":[3,71],"sequencing":[4],"technologies":[5],"has":[6],"led":[7],"to":[8,21,29],"the":[9,23,107],"discovery":[10],"novel":[12],"transcripts.":[13],"Many":[14],"in":[15,90,156],"silico":[16],"methods":[17,35],"have":[18],"been":[19],"developed":[20],"assess":[22],"coding":[24,46,67,76,169],"potential":[25,68,77,170],"these":[27],"transcripts":[28],"further":[30],"investigate":[31],"their":[32],"functions.":[33],"Existing":[34],"perform":[36],"well":[37],"on":[38,51,81,101,121],"distinguishing":[39],"majority":[40],"long":[41],"noncoding":[42],"RNAs":[43,47,52],"(lncRNAs)":[44],"and":[45,85,119,129,140,146],"(mRNAs)":[48],"but":[49],"poorly":[50],"with":[53],"small":[54],"open":[55],"reading":[56],"frames":[57],"(sORFs).":[58],"Here,":[59],"we":[60,134],"present":[61],"DeepCPP":[62,95,162],"(deep":[63],"neural":[64],"network":[65],"for":[66,74,124,167],"prediction),":[69],"a":[70],"learning":[72],"method":[73,152,166],"RNA":[75,168],"prediction.":[78,171],"Extensive":[79],"evaluations":[80],"four":[82],"previous":[83],"datasets":[84,88],"six":[86],"new":[87],"constructed":[89],"different":[91],"species":[92],"show":[93],"that":[94,137],"outperforms":[96],"other":[97],"state-of-the-art":[98],"methods,":[99],"especially":[100],"sORF":[102,110],"type":[103],"data,":[104,131],"which":[105],"overcomes":[106],"bottleneck":[108],"mRNA":[111],"identification":[112],"by":[113],"improving":[114],"more":[115],"than":[116],"4.31,":[117],"37.24":[118],"5.89%":[120],"its":[122],"accuracy":[123],"newly":[125,142],"discovered":[126],"human,":[127],"vertebrate":[128],"insect":[130],"respectively.":[132],"Additionally,":[133],"also":[135],"revealed":[136],"discontinuous":[138],"k-mer,":[139],"our":[141],"proposed":[143],"nucleotide":[144],"bias":[145],"minimal":[147],"distribution":[148],"similarity":[149],"feature":[150],"selection":[151],"play":[153],"crucial":[154],"roles":[155],"this":[157],"classification":[158],"problem.":[159],"Taken":[160],"together,":[161],"is":[163],"an":[164],"effective":[165]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":10}],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}