{"id":"https://openalex.org/W4311284238","doi":"https://doi.org/10.1093/bioinformatics/btac802","title":"Codetta: predicting the genetic code from nucleotide sequence","display_name":"Codetta: predicting the genetic code from nucleotide sequence","publication_year":2022,"publication_date":"2022-12-12","ids":{"openalex":"https://openalex.org/W4311284238","doi":"https://doi.org/10.1093/bioinformatics/btac802","pmid":"https://pubmed.ncbi.nlm.nih.gov/36511586"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btac802","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac802","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac802/48520913/btac802.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac802/48520913/btac802.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071269401","display_name":"Yekaterina Shulgina","orcid":"https://orcid.org/0000-0001-7658-9294"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yekaterina Shulgina","raw_affiliation_strings":["Department of Molecular and Cellular Biology, Harvard University , Cambridge, MA 02138, USA"],"raw_orcid":"https://orcid.org/0000-0001-7658-9294","affiliations":[{"raw_affiliation_string":"Department of Molecular and Cellular Biology, Harvard University , Cambridge, MA 02138, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020118397","display_name":"Sean R. Eddy","orcid":"https://orcid.org/0000-0001-6676-4706"},"institutions":[{"id":"https://openalex.org/I1344073410","display_name":"Howard Hughes Medical Institute","ror":"https://ror.org/006w34k90","country_code":"US","type":"facility","lineage":["https://openalex.org/I1344073410"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sean R Eddy","raw_affiliation_strings":["Department of Molecular and Cellular Biology, Harvard University , Cambridge, MA 02138, USA","Howard Hughes Medical Institute, Harvard University , Cambridge, MA 02138, USA"],"raw_orcid":"https://orcid.org/0000-0001-6676-4706","affiliations":[{"raw_affiliation_string":"Department of Molecular and Cellular Biology, Harvard University , Cambridge, MA 02138, USA","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Howard Hughes Medical Institute, Harvard University , Cambridge, MA 02138, USA","institution_ids":["https://openalex.org/I1344073410","https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020118397"],"corresponding_institution_ids":["https://openalex.org/I1344073410","https://openalex.org/I136199984"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":1.9619,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.87247932,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"39","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.5680999755859375,"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":0.5680999755859375,"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":0.17710000276565552,"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":0.04610000178217888,"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/python","display_name":"Python (programming language)","score":0.7074078321456909},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6006530523300171},{"id":"https://openalex.org/keywords/genetic-code","display_name":"Genetic code","score":0.5475148558616638},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5336908102035522},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5160295963287354},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.510534405708313},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5046876668930054},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.49709537625312805},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4898912310600281},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.4452718198299408},{"id":"https://openalex.org/keywords/sequence-logo","display_name":"Sequence logo","score":0.43609803915023804},{"id":"https://openalex.org/keywords/nucleic-acid-sequence","display_name":"Nucleic acid sequence","score":0.43119141459465027},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.37750372290611267},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.36748015880584717},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.3308585286140442},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.28259241580963135},{"id":"https://openalex.org/keywords/amino-acid","display_name":"Amino acid","score":0.20810282230377197},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.10587430000305176}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7074078321456909},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6006530523300171},{"id":"https://openalex.org/C10853874","wikidata":"https://www.wikidata.org/wiki/Q180618","display_name":"Genetic code","level":3,"score":0.5475148558616638},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5336908102035522},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5160295963287354},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.510534405708313},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5046876668930054},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.49709537625312805},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4898912310600281},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.4452718198299408},{"id":"https://openalex.org/C105082737","wikidata":"https://www.wikidata.org/wiki/Q7452470","display_name":"Sequence logo","level":5,"score":0.43609803915023804},{"id":"https://openalex.org/C84148353","wikidata":"https://www.wikidata.org/wiki/Q863908","display_name":"Nucleic acid sequence","level":3,"score":0.43119141459465027},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.37750372290611267},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.36748015880584717},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.3308585286140442},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.28259241580963135},{"id":"https://openalex.org/C515207424","wikidata":"https://www.wikidata.org/wiki/Q8066","display_name":"Amino acid","level":2,"score":0.20810282230377197},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.10587430000305176}],"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":"D005815","descriptor_name":"Genetic Code","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005815","descriptor_name":"Genetic Code","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005815","descriptor_name":"Genetic Code","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btac802","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac802","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac802/48520913/btac802.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:36511586","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36511586","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:pubmedcentral.nih.gov:9825746","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9825746","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btac802","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac802","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac802/48520913/btac802.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G142476521","display_name":"HMMER and Infernal: Finding distant homologs of sequences and RNA structures","funder_award_id":"5r01hg009116-06","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4241104939","display_name":null,"funder_award_id":"R01-HG009116","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G4927759596","display_name":null,"funder_award_id":"F31 HG010984","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G58629100","display_name":"Identifying genetic code reassignments in nucleotide sequence databases","funder_award_id":"5f31hg010984-02","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306082","display_name":"Howard Hughes Medical Institute","ror":"https://ror.org/006w34k90"},{"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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4311284238.pdf","grobid_xml":"https://content.openalex.org/works/W4311284238.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1502060396","https://openalex.org/W1992996520","https://openalex.org/W2073412013","https://openalex.org/W2122893222","https://openalex.org/W2127712523","https://openalex.org/W2138122982","https://openalex.org/W2462560104","https://openalex.org/W2668619786","https://openalex.org/W3095583226","https://openalex.org/W3211419854","https://openalex.org/W4226340952","https://openalex.org/W4281790379"],"related_works":["https://openalex.org/W2076455712","https://openalex.org/W2036521446","https://openalex.org/W997010268","https://openalex.org/W1978688271","https://openalex.org/W566472934","https://openalex.org/W2029514038","https://openalex.org/W2035120013","https://openalex.org/W2109134151","https://openalex.org/W2135434593","https://openalex.org/W1727089480"],"abstract_inverted_index":{"SUMMARY:":[0],"Codetta":[1,18,64],"is":[2,45,66,78],"a":[3,69],"Python":[4,70],"program":[5,72],"for":[6,39,73],"predicting":[7],"the":[8,42,58],"genetic":[9],"code":[10],"table":[11],"of":[12,41,49,54],"an":[13,21],"organism":[14],"from":[15,47,80],"nucleotide":[16,23],"sequences.":[17],"can":[19],"analyze":[20],"arbitrary":[22],"sequence":[24,28],"and":[25,75,77,82],"needs":[26],"no":[27],"annotation":[29],"or":[30],"taxonomic":[31],"placement.":[32],"The":[33],"most":[34],"likely":[35],"amino":[36],"acid":[37],"decoding":[38],"each":[40],"64":[43],"codons":[44],"inferred":[46],"alignments":[48],"profile":[50],"hidden":[51],"Markov":[52],"models":[53],"conserved":[55],"proteins":[56],"to":[57],"input":[59],"sequence.":[60],"AVAILABILITY":[61],"AND":[62],"IMPLEMENTATION:":[63],"2.0":[65],"implemented":[67],"as":[68],"3":[71],"MacOS":[74],"Linux":[76],"available":[79,90],"http://eddylab.org/software/codetta/codetta2.tar.gz":[81],"at":[83,91],"http://github.com/kshulgina/codetta.":[84],"SUPPLEMENTARY":[85],"INFORMATION:":[86],"Supplementary":[87],"data":[88],"are":[89],"Bioinformatics":[92],"online.":[93]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-10T00:00:00"}