{"id":"https://openalex.org/W2005336557","doi":"https://doi.org/10.1186/1471-2105-10-6","title":"Automated Alphabet Reduction for Protein Datasets","display_name":"Automated Alphabet Reduction for Protein Datasets","publication_year":2009,"publication_date":"2009-01-06","ids":{"openalex":"https://openalex.org/W2005336557","doi":"https://doi.org/10.1186/1471-2105-10-6","mag":"2005336557","pmid":"https://pubmed.ncbi.nlm.nih.gov/19126227"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-10-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-10-6","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-6","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012372361","display_name":"Jaume Bacardit","orcid":"https://orcid.org/0000-0002-2692-7205"},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jaume Bacardit","raw_affiliation_strings":["ASAP research group, School of Computer Science, University of Nottingham, Jubilee Campus, Wollaton Road, Nottingham, NG8 1BB, UK. jaume.bacardit@nottingham.ac.uk","MYCIB, School of Biosciences, University of Nottingham, Sutton Bonington, UK"],"affiliations":[{"raw_affiliation_string":"ASAP research group, School of Computer Science, University of Nottingham, Jubilee Campus, Wollaton Road, Nottingham, NG8 1BB, UK. jaume.bacardit@nottingham.ac.uk","institution_ids":["https://openalex.org/I142263535"]},{"raw_affiliation_string":"MYCIB, School of Biosciences, University of Nottingham, Sutton Bonington, UK","institution_ids":["https://openalex.org/I142263535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008269407","display_name":"Michael B. Stout","orcid":"https://orcid.org/0000-0002-9996-9123"},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Michael Stout","raw_affiliation_strings":["ASAP research group, School of Computer Science, University of Nottingham, Jubilee Campus, Wollaton Road, Nottingham, NG8 1BB, UK","MYCIB, School of Biosciences, University of Nottingham, Sutton Bonington, LE12 5RD, UK","MYCIB, School of Biosciences, University of Nottingham, Sutton Bonington, UK"],"affiliations":[{"raw_affiliation_string":"ASAP research group, School of Computer Science, University of Nottingham, Jubilee Campus, Wollaton Road, Nottingham, NG8 1BB, UK","institution_ids":["https://openalex.org/I142263535"]},{"raw_affiliation_string":"MYCIB, School of Biosciences, University of Nottingham, Sutton Bonington, LE12 5RD, UK","institution_ids":["https://openalex.org/I142263535"]},{"raw_affiliation_string":"MYCIB, School of Biosciences, University of Nottingham, Sutton Bonington, UK","institution_ids":["https://openalex.org/I142263535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051687648","display_name":"Jonathan D. Hirst","orcid":"https://orcid.org/0000-0002-2726-0983"},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jonathan D Hirst","raw_affiliation_strings":["School of Chemistry, University of Nottingham, University Park, Nottingham, NG7 2RD, UK","School of Chemistry University of Nottingham, University Park  Nottingham UK"],"affiliations":[{"raw_affiliation_string":"School of Chemistry, University of Nottingham, University Park, Nottingham, NG7 2RD, UK","institution_ids":["https://openalex.org/I142263535"]},{"raw_affiliation_string":"School of Chemistry University of Nottingham, University Park  Nottingham UK","institution_ids":["https://openalex.org/I142263535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015217651","display_name":"Alfonso Valencia","orcid":"https://orcid.org/0000-0002-8937-6789"},"institutions":[{"id":"https://openalex.org/I4210089594","display_name":"Spanish National Cancer Research Centre","ror":"https://ror.org/00bvhmc43","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210089594"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alfonso Valencia","raw_affiliation_strings":["Spanish National Cancer Research Centre, Melchor Fdez Almagro, 3. 28029, Madrid, Spain","Spanish National Cancer Research Centre, Melchor Fdez Almagro, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Spanish National Cancer Research Centre, Melchor Fdez Almagro, 3. 28029, Madrid, Spain","institution_ids":["https://openalex.org/I4210089594"]},{"raw_affiliation_string":"Spanish National Cancer Research Centre, Melchor Fdez Almagro, Madrid, Spain","institution_ids":["https://openalex.org/I4210089594"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101610547","display_name":"Robert E. Smith","orcid":"https://orcid.org/0000-0002-1906-4640"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Robert E Smith","raw_affiliation_strings":["Dept. of Computer Science, University College London, Gower Street, London, WC1E 6BT, UK","Dept. of Comput. Sci., Univ. Coll. London, London, UK#TAB#"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, University College London, Gower Street, London, WC1E 6BT, UK","institution_ids":["https://openalex.org/I45129253"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Univ. Coll. London, London, UK#TAB#","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043620976","display_name":"Natalio Krasnogor","orcid":"https://orcid.org/0000-0002-2651-4320"},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Natalio Krasnogor","raw_affiliation_strings":["ASAP research group, School of Computer Science, University of Nottingham, Jubilee Campus, Wollaton Road, Nottingham, NG8 1BB, UK","ASAP research group, School of Computer Science, University of Nottingham, Jubilee Campus, Nottingham, UK"],"affiliations":[{"raw_affiliation_string":"ASAP research group, School of Computer Science, University of Nottingham, Jubilee Campus, Wollaton Road, Nottingham, NG8 1BB, UK","institution_ids":["https://openalex.org/I142263535"]},{"raw_affiliation_string":"ASAP research group, School of Computer Science, University of Nottingham, Jubilee Campus, Nottingham, UK","institution_ids":["https://openalex.org/I142263535"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5012372361"],"corresponding_institution_ids":["https://openalex.org/I142263535"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":3.1003,"has_fulltext":true,"cited_by_count":61,"citation_normalized_percentile":{"value":0.91704551,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"10","issue":"1","first_page":"6","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.6937309503555298},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6651665568351746},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.6307177543640137},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.6205425262451172},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4644256830215454},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.46229809522628784},{"id":"https://openalex.org/keywords/alphabet","display_name":"Alphabet","score":0.4548530876636505},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4523927569389343},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.44314077496528625},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.43602558970451355},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4338282644748688},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41282904148101807},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36365288496017456},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35069170594215393},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32747316360473633},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18391790986061096}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6937309503555298},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6651665568351746},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.6307177543640137},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.6205425262451172},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4644256830215454},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.46229809522628784},{"id":"https://openalex.org/C112876837","wikidata":"https://www.wikidata.org/wiki/Q837518","display_name":"Alphabet","level":2,"score":0.4548530876636505},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4523927569389343},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.44314077496528625},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.43602558970451355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4338282644748688},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41282904148101807},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36365288496017456},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35069170594215393},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32747316360473633},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18391790986061096},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"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":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","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":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","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":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","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":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1186/1471-2105-10-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-10-6","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-6","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:19126227","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19126227","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:ebf5dca5534a40e7a0051a127e2ffab7","is_oa":true,"landing_page_url":"https://doaj.org/article/ebf5dca5534a40e7a0051a127e2ffab7","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 10, Iss 1, p 6 (2009)","raw_type":"article"},{"id":"pmh:oai:eprint.ncl.ac.uk:213351","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402485","display_name":"Newcastle University ePrints (Newcastle Univesity)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I84884186","host_organization_name":"Newcastle University","host_organization_lineage":["https://openalex.org/I84884186"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pubmedcentral.nih.gov:2646702","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2646702","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-10-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-10-6","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-6","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.800000011920929}],"awards":[{"id":"https://openalex.org/G1934935867","display_name":null,"funder_award_id":"Engineering and Physical Sciences R","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3311489835","display_name":null,"funder_award_id":"GR/T07534/01","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320324","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2005336557.pdf","grobid_xml":"https://content.openalex.org/works/W2005336557.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W190638014","https://openalex.org/W1481729573","https://openalex.org/W1486919307","https://openalex.org/W1530641120","https://openalex.org/W1540706608","https://openalex.org/W1564135785","https://openalex.org/W1587610203","https://openalex.org/W1588026767","https://openalex.org/W1896955993","https://openalex.org/W1965555277","https://openalex.org/W1969051510","https://openalex.org/W1973369081","https://openalex.org/W1975670646","https://openalex.org/W1978326290","https://openalex.org/W1981132436","https://openalex.org/W1985546344","https://openalex.org/W1994550454","https://openalex.org/W1997075303","https://openalex.org/W2000315390","https://openalex.org/W2008708467","https://openalex.org/W2014059004","https://openalex.org/W2044154133","https://openalex.org/W2050625197","https://openalex.org/W2056357310","https://openalex.org/W2080382112","https://openalex.org/W2084902519","https://openalex.org/W2087929775","https://openalex.org/W2093519658","https://openalex.org/W2097892623","https://openalex.org/W2099111195","https://openalex.org/W2099254366","https://openalex.org/W2106116715","https://openalex.org/W2115679291","https://openalex.org/W2116449290","https://openalex.org/W2125652418","https://openalex.org/W2132109794","https://openalex.org/W2136778397","https://openalex.org/W2139415631","https://openalex.org/W2143210482","https://openalex.org/W2144316442","https://openalex.org/W2147209844","https://openalex.org/W2148557779","https://openalex.org/W2158714788","https://openalex.org/W2159599297","https://openalex.org/W2171546617","https://openalex.org/W3103410279","https://openalex.org/W4230276186"],"related_works":["https://openalex.org/W2002177687","https://openalex.org/W2058438338","https://openalex.org/W2019471580","https://openalex.org/W2941284322","https://openalex.org/W3176621072","https://openalex.org/W2168299207","https://openalex.org/W4224920876","https://openalex.org/W2585354854","https://openalex.org/W2026059297","https://openalex.org/W12413374"],"abstract_inverted_index":{"Our":[0],"automated":[1],"alphabet":[2],"reduction":[3],"protocol":[4],"generates":[5],"competent":[6],"reduced":[7,31],"alphabets":[8,32],"tailored":[9],"specifically":[10],"for":[11],"a":[12],"variety":[13],"of":[14,39,46],"protein":[15],"datasets.":[16],"This":[17],"process":[18],"is":[19],"done":[20],"without":[21],"any":[22],"domain":[23],"knowledge,":[24],"using":[25],"information":[26],"theory":[27],"metrics":[28],"instead.":[29],"The":[30],"contain":[33],"some":[34],"unexpected":[35],"(but":[36],"sound)":[37],"groups":[38],"amino":[40],"acids,":[41],"thus":[42],"suggesting":[43],"new":[44],"ways":[45],"interpreting":[47],"the":[48],"data.":[49]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
