{"id":"https://openalex.org/W3083074502","doi":"https://doi.org/10.1109/tcbb.2020.3021800","title":"Predicting Coding Potential of RNA Sequences by Solving Local Data Imbalance","display_name":"Predicting Coding Potential of RNA Sequences by Solving Local Data Imbalance","publication_year":2020,"publication_date":"2020-09-04","ids":{"openalex":"https://openalex.org/W3083074502","doi":"https://doi.org/10.1109/tcbb.2020.3021800","mag":"3083074502","pmid":"https://pubmed.ncbi.nlm.nih.gov/32886613"},"language":"en","primary_location":{"id":"doi:10.1109/tcbb.2020.3021800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2020.3021800","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043","2998-4165"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","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/A5074635074","display_name":"Chen Xiangan","orcid":"https://orcid.org/0000-0002-6171-8564"},"institutions":[{"id":"https://openalex.org/I174442536","display_name":"South Central Minzu University","ror":"https://ror.org/03d7sax13","country_code":"CN","type":"education","lineage":["https://openalex.org/I174442536"]},{"id":"https://openalex.org/I2799449666","display_name":"State Ethnic Affairs Commission","ror":"https://ror.org/01p9g6b97","country_code":"CN","type":"government","lineage":["https://openalex.org/I2799449666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian-gan Chen","raw_affiliation_strings":["School of Biomedical Engineering, South-Central University for Nationalities, Wuhan, China","Hubei Key Laboratory of Medical Information Analysis and Tumor Diagnosis and Treatment, South-Central University for Nationalities, Wuhan, China","Key Laboratory of Cognitive Science(South-Central University for Nationalities), State Ethnic Affairs Commission, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-6171-8564","affiliations":[{"raw_affiliation_string":"School of Biomedical Engineering, South-Central University for Nationalities, Wuhan, China","institution_ids":["https://openalex.org/I174442536"]},{"raw_affiliation_string":"Hubei Key Laboratory of Medical Information Analysis and Tumor Diagnosis and Treatment, South-Central University for Nationalities, Wuhan, China","institution_ids":["https://openalex.org/I174442536"]},{"raw_affiliation_string":"Key Laboratory of Cognitive Science(South-Central University for Nationalities), State Ethnic Affairs Commission, Wuhan, China","institution_ids":["https://openalex.org/I174442536","https://openalex.org/I2799449666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320502","display_name":"Shuai Liu","orcid":"https://orcid.org/0000-0002-9122-4952"},"institutions":[{"id":"https://openalex.org/I204823248","display_name":"Huazhong Agricultural University","ror":"https://ror.org/023b72294","country_code":"CN","type":"education","lineage":["https://openalex.org/I204823248"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Liu","raw_affiliation_strings":["College of Informatics, Huazhong Agricultural University, Wuhan, China","Hubei Engineering Technology Research Center of Agricultural Big Data, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-9122-4952","affiliations":[{"raw_affiliation_string":"College of Informatics, Huazhong Agricultural University, Wuhan, China","institution_ids":["https://openalex.org/I204823248"]},{"raw_affiliation_string":"Hubei Engineering Technology Research Center of Agricultural Big Data, Wuhan, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100448121","display_name":"Wen Zhang","orcid":"https://orcid.org/0000-0001-5221-2628"},"institutions":[{"id":"https://openalex.org/I204823248","display_name":"Huazhong Agricultural University","ror":"https://ror.org/023b72294","country_code":"CN","type":"education","lineage":["https://openalex.org/I204823248"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Zhang","raw_affiliation_strings":["College of Informatics, Huazhong Agricultural University, Wuhan, China","Hubei Engineering Technology Research Center of Agricultural Big Data, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-5221-2628","affiliations":[{"raw_affiliation_string":"College of Informatics, Huazhong Agricultural University, Wuhan, China","institution_ids":["https://openalex.org/I204823248"]},{"raw_affiliation_string":"Hubei Engineering Technology Research Center of Agricultural Big Data, Wuhan, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1928,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.77976005,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"19","issue":"2","first_page":"1075","last_page":"1083"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9984999895095825,"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/biology","display_name":"Biology","score":0.7133539915084839},{"id":"https://openalex.org/keywords/rna","display_name":"RNA","score":0.7119204998016357},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.6068670749664307},{"id":"https://openalex.org/keywords/non-coding-rna","display_name":"Non-coding RNA","score":0.598812460899353},{"id":"https://openalex.org/keywords/long-non-coding-rna","display_name":"Long non-coding RNA","score":0.5693471431732178},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5440253019332886},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.5405089259147644},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.36192068457603455},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.25370681285858154},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.24341389536857605}],"concepts":[{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.7133539915084839},{"id":"https://openalex.org/C67705224","wikidata":"https://www.wikidata.org/wiki/Q11053","display_name":"RNA","level":3,"score":0.7119204998016357},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6068670749664307},{"id":"https://openalex.org/C194993378","wikidata":"https://www.wikidata.org/wiki/Q427087","display_name":"Non-coding RNA","level":4,"score":0.598812460899353},{"id":"https://openalex.org/C62203573","wikidata":"https://www.wikidata.org/wiki/Q15087973","display_name":"Long non-coding RNA","level":4,"score":0.5693471431732178},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5440253019332886},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.5405089259147644},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.36192068457603455},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.25370681285858154},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.24341389536857605},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012313","descriptor_name":"RNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D012313","descriptor_name":"RNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D012313","descriptor_name":"RNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D022661","descriptor_name":"RNA, Untranslated","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D022661","descriptor_name":"RNA, Untranslated","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D022661","descriptor_name":"RNA, Untranslated","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcbb.2020.3021800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2020.3021800","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043","2998-4165"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:32886613","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32886613","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":"IEEE/ACM transactions on computational biology and bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[{"id":"https://openalex.org/G1311322377","display_name":"\u77e5\u8bc6\u56fe\u8c31\u9a71\u52a8\u7684\u836f\u7269-\u75be\u75c5\u5173\u8054\u9884\u6d4b\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62072206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5521685413","display_name":null,"funder_award_id":"81601461","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5524191993","display_name":null,"funder_award_id":"CZY20039","funder_id":"https://openalex.org/F4320330673","funder_display_name":"South-Central University for Nationalities"},{"id":"https://openalex.org/G5693357935","display_name":"\u57fa\u4e8e\u836f\u7269\u5927\u6570\u636e\u7684\u6f5c\u5728\u4e0d\u826f\u836f\u7269\u53cd\u5e94\u6316\u6398\u7814\u7a76","funder_award_id":"61772381","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6868366096","display_name":null,"funder_award_id":"61976227","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G793318600","display_name":"\u591a\u6e90\u57fa\u56e0\u8868\u8fbe\u5927\u6570\u636e\u6574\u5408\u53ca\u4e09\u7ef4\u52a8\u6001\u6a21\u5f0f\u8bc6\u522b\u7684\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61572368","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320330673","display_name":"South-Central University for Nationalities","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1577822803","https://openalex.org/W1970569349","https://openalex.org/W1990895545","https://openalex.org/W1998422171","https://openalex.org/W2048194168","https://openalex.org/W2061548680","https://openalex.org/W2075320162","https://openalex.org/W2104933073","https://openalex.org/W2118023394","https://openalex.org/W2118978333","https://openalex.org/W2170747616","https://openalex.org/W2177321125","https://openalex.org/W2230801863","https://openalex.org/W2295598076","https://openalex.org/W2401640772","https://openalex.org/W2512299449","https://openalex.org/W2548536600","https://openalex.org/W2571489439","https://openalex.org/W2608270353","https://openalex.org/W2615786037","https://openalex.org/W2765094054","https://openalex.org/W2789316776","https://openalex.org/W2801972999","https://openalex.org/W2805467558","https://openalex.org/W2805813857","https://openalex.org/W2806980026","https://openalex.org/W2807607992","https://openalex.org/W2885091354","https://openalex.org/W2885518121","https://openalex.org/W2900329012","https://openalex.org/W2904828342","https://openalex.org/W2910755031","https://openalex.org/W2914423099","https://openalex.org/W2914698725","https://openalex.org/W2917698234","https://openalex.org/W2918702104","https://openalex.org/W2940275179","https://openalex.org/W2946035471","https://openalex.org/W2946438679","https://openalex.org/W2946590503","https://openalex.org/W2955341903","https://openalex.org/W2958015815","https://openalex.org/W2966349991","https://openalex.org/W2990257819","https://openalex.org/W3004549117","https://openalex.org/W3010217868","https://openalex.org/W3024894285","https://openalex.org/W3030356991","https://openalex.org/W3045644454"],"related_works":["https://openalex.org/W2058984380","https://openalex.org/W1988125422","https://openalex.org/W2900182103","https://openalex.org/W4365136234","https://openalex.org/W3183769948","https://openalex.org/W2547129954","https://openalex.org/W1924910987","https://openalex.org/W3146486132","https://openalex.org/W2276469649","https://openalex.org/W3031361789"],"abstract_inverted_index":{"Non-coding":[0],"RNAs":[1,18,92,99,141],"(ncRNAs)play":[2],"an":[3],"important":[4],"role":[5],"in":[6,118],"various":[7,167],"biological":[8,34],"processes":[9],"and":[10,19,85,97,160],"are":[11,102],"associated":[12],"with":[13,64,93,100,107,121,142,152,183],"diseases.":[14],"Distinguishing":[15],"between":[16],"coding":[17,25,46,91,98,126,140,176],"ncRNAs,":[20],"also":[21],"known":[22],"as":[23,145],"predicting":[24,45],"potential":[26,47,127,177],"of":[27,48,79,82,90,114,175,187],"RNA":[28,49,62,83,119,181],"sequences,":[29,84],"is":[30,95,191],"critical":[31],"for":[32,44,139,180],"downstream":[33],"function":[35],"analysis.":[36],"Many":[37],"machine":[38],"learning-based":[39],"methods":[40,57],"have":[41,58],"been":[42],"proposed":[43,189],"sequences.":[50],"Recent":[51],"studies":[52,161],"reveal":[53,162],"that":[54,87,163],"most":[55],"existing":[56,153],"poor":[59],"performance":[60,174],"on":[61],"sequences":[63,120,182],"short":[65],"Open":[66],"Reading":[67],"Frames":[68],"(sORF,":[69],"ORF":[70,80],"length<303nt).":[71],"In":[72],"this":[73],"work,":[74],"we":[75],"analyze":[76],"the":[77,88,112,157,173,188],"distribution":[78],"length":[81],"observe":[86],"number":[89],"sORF":[94,101,143],"inadequate":[96],"much":[103],"less":[104],"than":[105],"ncRNAs":[106],"sORF.":[108,122,184],"Thus,":[109],"there":[110],"exists":[111],"problem":[113],"local":[115,148],"data":[116,133,149,164,168],"imbalance":[117],"We":[123],"propose":[124],"a":[125],"prediction":[128],"method":[129,190],"CPE-SLDI,":[130],"which":[131],"uses":[132],"oversampling":[134,169],"techniques":[135,170],"to":[136,146],"augment":[137],"samples":[138],"so":[144],"alleviate":[147],"imbalance.":[150],"Compared":[151],"methods,":[154],"CPE-SLDI":[155],"produces":[156],"better":[158],"performances,":[159],"augmentation":[165],"by":[166],"can":[171],"enhance":[172],"prediction,":[178],"especially":[179],"The":[185],"implementation":[186],"available":[192],"at":[193],"https://github.com/chenxgscuec/CPESLDI.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}
