{"id":"https://openalex.org/W2092425220","doi":"https://doi.org/10.1145/2649387.2660783","title":"Identification of protein coding regions in RNA transcripts","display_name":"Identification of protein coding regions in RNA transcripts","publication_year":2014,"publication_date":"2014-09-20","ids":{"openalex":"https://openalex.org/W2092425220","doi":"https://doi.org/10.1145/2649387.2660783","mag":"2092425220"},"language":"en","primary_location":{"id":"doi:10.1145/2649387.2660783","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2649387.2660783","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"type":"conference-abstract","indexed_in":["crossref"],"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/A5111698760","display_name":"Shiyuyun Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiyuyun Tang","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA","Georgia Institute of Technology Atlanta, GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology Atlanta, GA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083410058","display_name":"Alexandre Lomsadze","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I177855293","display_name":"Emory and Henry College","ror":"https://ror.org/018rbev86","country_code":"US","type":"education","lineage":["https://openalex.org/I177855293"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexandre Lomsadze","raw_affiliation_strings":["Joint Georgia Tech and Emory, Atlanta, GA","Joint Georgia Tech and Emory, Atlanta, GA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Joint Georgia Tech and Emory, Atlanta, GA","institution_ids":["https://openalex.org/I130701444","https://openalex.org/I177855293"]},{"raw_affiliation_string":"Joint Georgia Tech and Emory, Atlanta, GA#TAB#","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057317686","display_name":"Mark Borodovsky","orcid":"https://orcid.org/0000-0002-1401-4046"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I177855293","display_name":"Emory and Henry College","ror":"https://ror.org/018rbev86","country_code":"US","type":"education","lineage":["https://openalex.org/I177855293"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Borodovsky","raw_affiliation_strings":["Joint Georgia Tech and Emory, Atlanta, GA","Joint Georgia Tech and Emory, Atlanta, GA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Joint Georgia Tech and Emory, Atlanta, GA","institution_ids":["https://openalex.org/I130701444","https://openalex.org/I177855293"]},{"raw_affiliation_string":"Joint Georgia Tech and Emory, Atlanta, GA#TAB#","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"588","last_page":"588"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9987999796867371,"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":0.9977999925613403,"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/computational-biology","display_name":"Computational biology","score":0.6207038164138794},{"id":"https://openalex.org/keywords/rna","display_name":"RNA","score":0.6043473482131958},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.5940656065940857},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5581863522529602},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5177985429763794},{"id":"https://openalex.org/keywords/open-reading-frame","display_name":"Open reading frame","score":0.49703124165534973},{"id":"https://openalex.org/keywords/non-coding-rna","display_name":"Non-coding RNA","score":0.4392354488372803},{"id":"https://openalex.org/keywords/coding-region","display_name":"Coding region","score":0.4235081076622009},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.35844647884368896},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3290861248970032},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.32340285181999207},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09974539279937744}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6207038164138794},{"id":"https://openalex.org/C67705224","wikidata":"https://www.wikidata.org/wiki/Q11053","display_name":"RNA","level":3,"score":0.6043473482131958},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.5940656065940857},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5581863522529602},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5177985429763794},{"id":"https://openalex.org/C47289529","wikidata":"https://www.wikidata.org/wiki/Q908550","display_name":"Open reading frame","level":4,"score":0.49703124165534973},{"id":"https://openalex.org/C194993378","wikidata":"https://www.wikidata.org/wiki/Q427087","display_name":"Non-coding RNA","level":4,"score":0.4392354488372803},{"id":"https://openalex.org/C91779695","wikidata":"https://www.wikidata.org/wiki/Q3780824","display_name":"Coding region","level":3,"score":0.4235081076622009},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.35844647884368896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3290861248970032},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.32340285181999207},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09974539279937744},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2649387.2660783","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2649387.2660783","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4287110707","https://openalex.org/W2058984380","https://openalex.org/W1988125422","https://openalex.org/W2900182103","https://openalex.org/W2005844856","https://openalex.org/W3183769948","https://openalex.org/W3184762873","https://openalex.org/W2393371103","https://openalex.org/W2052050039","https://openalex.org/W1974337044"],"abstract_inverted_index":{"Massive":[0],"parallel":[1],"sequencing":[2],"of":[3,16,23,27,81,96,101,103,124,140,147,151,158],"RNA":[4,88],"transcripts":[5,31,57,89,144],"by":[6,61,67],"the":[7,104,114,120,138],"next":[8],"generation":[9],"technology":[10],"(RNA-Seq)":[11],"is":[12,43,98,133],"a":[13,48,73],"powerful":[14],"method":[15],"generating":[17],"critically":[18],"important":[19],"data":[20],"for":[21,77],"discovery":[22],"structure":[24],"and":[25,145],"function":[26],"eukaryotic":[28],"genes.":[29],"The":[30],"may":[32,34],"or":[33,85],"not":[35],"carry":[36],"protein-coding":[37,82,152],"regions.":[38],"If":[39],"protein":[40],"coding":[41],"region":[42],"present,":[44],"it":[45],"should":[46],"be":[47,59],"continuous":[49],"(spliced)":[50],"open":[51],"reading":[52],"frame.":[53],"Gene":[54],"finding":[55],"in":[56,87,113,142,149,156],"can":[58],"done":[60],"statistical":[62],"(alignment-free)":[63],"as":[64,66],"well":[65],"alignment":[68],"based":[69],"methods.":[70,166],"We":[71,127],"describe":[72],"new":[74],"tool,":[75],"GeneMarkS-T,":[76],"ab":[78],"initio":[79],"identification":[80,150],"regions,":[83],"complete":[84],"incomplete,":[86],"assembled":[90,143],"from":[91],"RNA-Seq":[92],"reads.":[93],"Important":[94],"feature":[95],"GeneMarkS-T":[97,131,148],"unsupervised":[99],"estimation":[100],"parameters":[102],"algorithm":[105],"that":[106,129],"makes":[107],"unnecessary":[108],"several":[109],"conventional":[110],"steps":[111],"used":[112],"gene":[115,159],"prediction":[116,157],"protocols,":[117],"most":[118],"importantly":[119],"manually":[121],"curated":[122],"preparation":[123],"training":[125],"sets.":[126],"demonstrate":[128],"i/the":[130],"self-training":[132],"robust":[134],"with":[135],"respect":[136],"to":[137,163],"presence":[139],"errors":[141],"ii/accuracy":[146],"regions":[153],"and,":[154],"particularly,":[155],"starts":[160],"compares":[161],"favorably":[162],"other":[164],"existing":[165]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}