{"id":"https://openalex.org/W2116955103","doi":"https://doi.org/10.1093/bioinformatics/btr275","title":"Identification of prokaryotic small proteins using a comparative genomic approach","display_name":"Identification of prokaryotic small proteins using a comparative genomic approach","publication_year":2011,"publication_date":"2011-05-05","ids":{"openalex":"https://openalex.org/W2116955103","doi":"https://doi.org/10.1093/bioinformatics/btr275","mag":"2116955103","pmid":"https://pubmed.ncbi.nlm.nih.gov/21551138"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btr275","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btr275","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/27/13/1765/48869273/bioinformatics_27_13_1765.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/27/13/1765/48869273/bioinformatics_27_13_1765.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014321941","display_name":"Josue Samayoa","orcid":"https://orcid.org/0000-0003-3609-8954"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Josue Samayoa","raw_affiliation_strings":["1 Department of Biomedical Engineering, Institute for Computational Medicine, Johns Hopkins University, Baltimore, MD 21218, 2Department of Microbiology and Environmental Toxicology and 3Department of Biomolecular Engineering, University of California, Santa Cruz, CA 95064, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Biomedical Engineering, Institute for Computational Medicine, Johns Hopkins University, Baltimore, MD 21218, 2Department of Microbiology and Environmental Toxicology and 3Department of Biomolecular Engineering, University of California, Santa Cruz, CA 95064, USA","institution_ids":["https://openalex.org/I2799853436","https://openalex.org/I145311948","https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021320199","display_name":"Fitnat H. Yildiz","orcid":"https://orcid.org/0000-0002-6384-7167"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fitnat H. Yildiz","raw_affiliation_strings":["1 Department of Biomedical Engineering, Institute for Computational Medicine, Johns Hopkins University, Baltimore, MD 21218, 2Department of Microbiology and Environmental Toxicology and 3Department of Biomolecular Engineering, University of California, Santa Cruz, CA 95064, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Biomedical Engineering, Institute for Computational Medicine, Johns Hopkins University, Baltimore, MD 21218, 2Department of Microbiology and Environmental Toxicology and 3Department of Biomolecular Engineering, University of California, Santa Cruz, CA 95064, USA","institution_ids":["https://openalex.org/I2799853436","https://openalex.org/I145311948","https://openalex.org/I185103710"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059033237","display_name":"Kevin Karplus","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Karplus","raw_affiliation_strings":["1 Department of Biomedical Engineering, Institute for Computational Medicine, Johns Hopkins University, Baltimore, MD 21218, 2Department of Microbiology and Environmental Toxicology and 3Department of Biomolecular Engineering, University of California, Santa Cruz, CA 95064, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Biomedical Engineering, Institute for Computational Medicine, Johns Hopkins University, Baltimore, MD 21218, 2Department of Microbiology and Environmental Toxicology and 3Department of Biomolecular Engineering, University of California, Santa Cruz, CA 95064, USA","institution_ids":["https://openalex.org/I2799853436","https://openalex.org/I145311948","https://openalex.org/I185103710"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014321941"],"corresponding_institution_ids":["https://openalex.org/I145311948","https://openalex.org/I185103710","https://openalex.org/I2799853436"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.3115,"has_fulltext":true,"cited_by_count":41,"citation_normalized_percentile":{"value":0.79682468,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"27","issue":"13","first_page":"1765","last_page":"1771"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.5888000130653381,"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":0.5888000130653381,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.18310000002384186,"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":0.08609999716281891,"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/identification","display_name":"Identification (biology)","score":0.7924797534942627},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.678125262260437},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5244448781013489},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3683604598045349}],"concepts":[{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.7924797534942627},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.678125262260437},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5244448781013489},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3683604598045349},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[{"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":"D003062","descriptor_name":"Codon","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003062","descriptor_name":"Codon","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003062","descriptor_name":"Codon","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004755","descriptor_name":"Enterobacteriaceae","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004755","descriptor_name":"Enterobacteriaceae","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004755","descriptor_name":"Enterobacteriaceae","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004755","descriptor_name":"Enterobacteriaceae","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004755","descriptor_name":"Enterobacteriaceae","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004755","descriptor_name":"Enterobacteriaceae","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D029968","descriptor_name":"Escherichia coli Proteins","qualifier_ui":"Q000302","qualifier_name":"isolation & purification","is_major_topic":false},{"descriptor_ui":"D029968","descriptor_name":"Escherichia coli Proteins","qualifier_ui":"Q000302","qualifier_name":"isolation & purification","is_major_topic":false},{"descriptor_ui":"D029968","descriptor_name":"Escherichia coli Proteins","qualifier_ui":"Q000302","qualifier_name":"isolation & purification","is_major_topic":false},{"descriptor_ui":"D029968","descriptor_name":"Escherichia coli Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D029968","descriptor_name":"Escherichia coli Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D029968","descriptor_name":"Escherichia coli Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D048168","descriptor_name":"Escherichia coli K12","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D048168","descriptor_name":"Escherichia coli K12","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D048168","descriptor_name":"Escherichia coli K12","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D048168","descriptor_name":"Escherichia coli K12","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D048168","descriptor_name":"Escherichia coli K12","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D048168","descriptor_name":"Escherichia coli K12","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.1093/bioinformatics/btr275","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btr275","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/27/13/1765/48869273/bioinformatics_27_13_1765.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:21551138","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21551138","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:10.1.1.153.3783","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.153.3783","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.ucsc.edu/~karplus/papers/short-proteins-draft.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.865.3578","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.865.3578","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/2011/05/05/bioinformatics.btr275.full.pdf","raw_type":"text"},{"id":"pmh:oai:open-archive.highwire.org:bioinfo:27/13/1765","is_oa":false,"landing_page_url":"http://bioinformatics.oxfordjournals.org/cgi/content/short/27/13/1765","pdf_url":null,"source":{"id":"https://openalex.org/S4406923041","display_name":"HighWire Press Open Archive","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"TEXT"},{"id":"pmh:oai:pubmedcentral.nih.gov:3117347","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3117347","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btr275","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btr275","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/27/13/1765/48869273/bioinformatics_27_13_1765.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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G1093254645","display_name":null,"funder_award_id":"2 R25 GM58903","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G4566534403","display_name":null,"funder_award_id":"P41 HG002371","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G6523754766","display_name":null,"funder_award_id":"5P41HG002371-09","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G8880514769","display_name":null,"funder_award_id":"R25 GM058903","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2116955103.pdf","grobid_xml":"https://content.openalex.org/works/W2116955103.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1873623553","https://openalex.org/W1984027552","https://openalex.org/W1984708728","https://openalex.org/W2001660787","https://openalex.org/W2029415822","https://openalex.org/W2032870665","https://openalex.org/W2038670470","https://openalex.org/W2056474690","https://openalex.org/W2073578638","https://openalex.org/W2091560728","https://openalex.org/W2099671505","https://openalex.org/W2104073328","https://openalex.org/W2106090237","https://openalex.org/W2109110770","https://openalex.org/W2112132489","https://openalex.org/W2119825686","https://openalex.org/W2120498503","https://openalex.org/W2123153443","https://openalex.org/W2131892542","https://openalex.org/W2133253129","https://openalex.org/W2143235667","https://openalex.org/W2152473511","https://openalex.org/W2153173493","https://openalex.org/W2154478075","https://openalex.org/W2156320594","https://openalex.org/W2157540858","https://openalex.org/W2160053034","https://openalex.org/W2397773488","https://openalex.org/W2582743722","https://openalex.org/W4285719527","https://openalex.org/W6696597226","https://openalex.org/W6712163357"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2082860237","https://openalex.org/W2119695867","https://openalex.org/W2130076355","https://openalex.org/W1990804418","https://openalex.org/W1993764875","https://openalex.org/W2046158694","https://openalex.org/W2788277189","https://openalex.org/W2013243191","https://openalex.org/W2151865869"],"abstract_inverted_index":{"MOTIVATION:":[0],"Accurate":[1],"prediction":[2,31],"of":[3,11,25,59,73,103,122,165,215,225,228,237,243,252,261,302,341],"genes":[4,65],"encoding":[5,95],"small":[6,51,62,76,87,133,187,219,256,265,286,305,324,335,345],"proteins":[7,88,134,220,266,306,336,346],"(on":[8],"the":[9,26,69,83,96,106,196,238,244,250,263,268,303,309,332,342,348],"order":[10],"50":[12],"amino":[13,98],"acids":[14],"or":[15,37,66,119,176],"less)":[16],"remains":[17],"an":[18],"elusive":[19],"open":[20,180],"problem":[21],"in":[22,308],"bioinformatics.":[23],"Some":[24],"best":[27],"methods":[28,47],"for":[29,50,94,101,109,151,174,185,199,330],"gene":[30],"use":[32],"either":[33,54,117],"sequence":[34,38],"composition":[35],"analysis":[36],"similarity":[39],"to":[40,56,68,171,195,249,276,315,320],"a":[41,57,123,157,162,178,186,213,226,279,284,291],"known":[42],"protein":[43,63,125,139],"coding":[44,64],"sequence.":[45],"These":[46],"often":[48],"fail":[49],"proteins,":[52],"however,":[53],"due":[55,67,319],"lack":[58],"experimentally":[60,217,254,333],"verified":[61,218,255,334],"limited":[70],"statistical":[71],"significance":[72],"statistics":[74],"on":[75,212,317],"sequences.":[77],"Our":[78,146],"approach":[79,160],"is":[80],"based":[81],"upon":[82],"hypothesis":[84],"that":[85,132,235],"true":[86,264,304,344],"will":[89],"be":[90,115],"under":[91],"selective":[92],"pressure":[93],"particular":[97],"acid":[99],"sequence,":[100],"ease":[102],"translation":[104],"by":[105],"ribosome":[107],"and":[108,204,241,283],"structural":[110],"stability.":[111],"This":[112],"stability":[113],"can":[114],"achieved":[116],"independently":[118],"as":[120],"part":[121],"larger":[124,144],"complex.":[126],"Given":[127],"this":[128,193,222],"assumption,":[129],"it":[130],"follows":[131],"should":[135],"display":[136],"conserved":[137],"local":[138,153],"structure":[140,154],"properties":[141],"much":[142],"like":[143],"proteins.":[145,257],"method":[147,194,210,275],"incorporates":[148],"neural-net":[149],"predictions":[150,173,247,329],"three":[152],"alphabets":[155],"within":[156,267,347],"comparative":[158],"genomic":[159,163],"using":[161,278],"alignment":[164],"22":[166],"closely":[167],"related":[168],"bacteria":[169],"genomes":[170],"generate":[172],"whether":[175],"not":[177],"given":[179],"reading":[181],"frame":[182],"(ORF)":[183],"encodes":[184],"protein.":[188],"RESULTS:":[189],"We":[190,258,272],"have":[191],"applied":[192],"complete":[197],"genome":[198],"Escherichia":[200],"coli":[201],"strain":[202],"K12":[203],"looked":[205],"at":[206],"how":[207],"well":[208],"our":[209,274],"performed":[211],"set":[214,251],"60":[216,253,343],"from":[221],"organism.":[223],"Out":[224],"total":[227],"11":[229],"407":[230],"possible":[231],"ORFs,":[232],"we":[233],"found":[234,259],"6":[236],"top":[239,245,269,310,349],"10":[240],"27":[242],"100":[246],"belonged":[248],"35":[260],"all":[262,331],"200":[270,311,350],"predictions.":[271,351],"compared":[273],"Glimmer,":[277],"default":[280,297],"Glimmer":[281,288,298,326],"protocol":[282,289,299,327],"modified":[285],"ORF":[287,325],"with":[290],"lower":[292],"minimum":[293],"size":[294,321],"cutoff.":[295],"The":[296,323],"identified":[300],"16":[301],"(all":[307],"predictions),":[312],"but":[313,337],"failed":[314],"predict":[316],"34":[318],"cutoffs.":[322],"made":[328],"only":[338],"contained":[339],"9":[340],"CONTACT:":[352],"jsamayoa@jhu.edu":[353]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-13T07:31:44.756512","created_date":"2025-10-10T00:00:00"}
