{"id":"https://openalex.org/W2113231090","doi":"https://doi.org/10.1186/1471-2105-7-213","title":"An analysis of the Sargasso Sea resource and the consequences for database composition","display_name":"An analysis of the Sargasso Sea resource and the consequences for database composition","publication_year":2006,"publication_date":"2006-04-19","ids":{"openalex":"https://openalex.org/W2113231090","doi":"https://doi.org/10.1186/1471-2105-7-213","mag":"2113231090","pmid":"https://pubmed.ncbi.nlm.nih.gov/16623953"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-7-213","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-7-213","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-213","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/10.1186/1471-2105-7-213","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088945131","display_name":"Michael L. Tress","orcid":"https://orcid.org/0000-0001-9046-6370"},"institutions":[{"id":"https://openalex.org/I134820265","display_name":"Consejo Superior de Investigaciones Cient\u00edficas","ror":"https://ror.org/02gfc7t72","country_code":"ES","type":"government","lineage":["https://openalex.org/I134820265"]},{"id":"https://openalex.org/I4210104776","display_name":"Centro Nacional de Biotecnolog\u00eda","ror":"https://ror.org/015w4v032","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210104776"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Michael L Tress","raw_affiliation_strings":["Protein Design Group, CNB-CSIC, Calle Darwin, Cantoblanco 28049 Madrid, Spain. mtress@cnio.es","Protein Design Group, CNB-CSIC, Calle Darwin, Cantoblanco, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Protein Design Group, CNB-CSIC, Calle Darwin, Cantoblanco 28049 Madrid, Spain. mtress@cnio.es","institution_ids":["https://openalex.org/I4210104776"]},{"raw_affiliation_string":"Protein Design Group, CNB-CSIC, Calle Darwin, Cantoblanco, Spain","institution_ids":["https://openalex.org/I134820265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078956440","display_name":"Domenico Cozzetto","orcid":"https://orcid.org/0000-0001-6752-5432"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Domenico Cozzetto","raw_affiliation_strings":["Department of Biochemical Sciences, University \"La Sapienza\" Rome, Italy","Department of Biochemical Sciences, University La Sapienza Rome, , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemical Sciences, University \"La Sapienza\" Rome, Italy","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"Department of Biochemical Sciences, University La Sapienza Rome, , Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112661316","display_name":"Anna Tramontano","orcid":null},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Anna Tramontano","raw_affiliation_strings":["Department of Biochemical Sciences, University \"La Sapienza\" Rome, Italy","Department of Biochemical Sciences, University La Sapienza Rome, , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemical Sciences, University \"La Sapienza\" Rome, Italy","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"Department of Biochemical Sciences, University La Sapienza Rome, , Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015217651","display_name":"Alfonso Valencia","orcid":"https://orcid.org/0000-0002-8937-6789"},"institutions":[{"id":"https://openalex.org/I134820265","display_name":"Consejo Superior de Investigaciones Cient\u00edficas","ror":"https://ror.org/02gfc7t72","country_code":"ES","type":"government","lineage":["https://openalex.org/I134820265"]},{"id":"https://openalex.org/I4210104776","display_name":"Centro Nacional de Biotecnolog\u00eda","ror":"https://ror.org/015w4v032","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210104776"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alfonso Valencia","raw_affiliation_strings":["Protein Design Group, CNB-CSIC, Calle Darwin, Cantoblanco, 28049, Madrid, Spain","Protein Design Group, CNB-CSIC, Calle Darwin, Cantoblanco, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Protein Design Group, CNB-CSIC, Calle Darwin, Cantoblanco, 28049, Madrid, Spain","institution_ids":["https://openalex.org/I4210104776"]},{"raw_affiliation_string":"Protein Design Group, CNB-CSIC, Calle Darwin, Cantoblanco, Spain","institution_ids":["https://openalex.org/I134820265"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088945131"],"corresponding_institution_ids":["https://openalex.org/I134820265","https://openalex.org/I4210104776"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.9545,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.73497373,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"7","issue":"1","first_page":"213","last_page":"213"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.3199999928474426,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.3199999928474426,"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/T11791","display_name":"Microbial Community Ecology and Physiology","score":0.15209999680519104,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.12460000067949295,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sargasso-sea","display_name":"Sargasso sea","score":0.8129146099090576},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.7025230526924133},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5536012053489685},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5359042286872864},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.4937840402126312},{"id":"https://openalex.org/keywords/shotgun-sequencing","display_name":"Shotgun sequencing","score":0.4551345109939575},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4421822130680084},{"id":"https://openalex.org/keywords/massive-parallel-sequencing","display_name":"Massive parallel sequencing","score":0.41647377610206604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3978639245033264},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.38080528378486633},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.38063865900039673},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.3490805923938751},{"id":"https://openalex.org/keywords/evolutionary-biology","display_name":"Evolutionary biology","score":0.2868935465812683},{"id":"https://openalex.org/keywords/oceanography","display_name":"Oceanography","score":0.20799347758293152},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.19551467895507812},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.15750223398208618}],"concepts":[{"id":"https://openalex.org/C2992963954","wikidata":"https://www.wikidata.org/wiki/Q169274","display_name":"Sargasso sea","level":2,"score":0.8129146099090576},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.7025230526924133},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5536012053489685},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5359042286872864},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4937840402126312},{"id":"https://openalex.org/C101985253","wikidata":"https://www.wikidata.org/wiki/Q1073526","display_name":"Shotgun sequencing","level":4,"score":0.4551345109939575},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4421822130680084},{"id":"https://openalex.org/C192800701","wikidata":"https://www.wikidata.org/wiki/Q6784807","display_name":"Massive parallel sequencing","level":4,"score":0.41647377610206604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3978639245033264},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.38080528378486633},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.38063865900039673},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.3490805923938751},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.2868935465812683},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.20799347758293152},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.19551467895507812},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.15750223398208618},{"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[{"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":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","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":"D005798","descriptor_name":"Genes, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005798","descriptor_name":"Genes, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005798","descriptor_name":"Genes, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D008386","descriptor_name":"Marine Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D008386","descriptor_name":"Marine Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D008386","descriptor_name":"Marine Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009792","descriptor_name":"Oceans and Seas","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009792","descriptor_name":"Oceans and Seas","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009792","descriptor_name":"Oceans and Seas","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014871","descriptor_name":"Water Microbiology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014871","descriptor_name":"Water Microbiology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014871","descriptor_name":"Water Microbiology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","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":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":8,"locations":[{"id":"doi:10.1186/1471-2105-7-213","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-7-213","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-213","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:16623953","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16623953","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:digital.csic.es:10261/1399","is_oa":true,"landing_page_url":"http://hdl.handle.net/10261/1399","pdf_url":null,"source":{"id":"https://openalex.org/S4306400616","display_name":"DIGITAL.CSIC (Spanish National Research Council (CSIC))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I134820265","host_organization_name":"Consejo Superior de Investigaciones Cient\u00edficas","host_organization_lineage":["https://openalex.org/I134820265"],"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":"","raw_type":"art\u00edculo"},{"id":"pmh:oai:doaj.org/article:cc3f9006296e4301b5fd45243edb075a","is_oa":false,"landing_page_url":"https://doaj.org/article/cc3f9006296e4301b5fd45243edb075a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"BMC Bioinformatics, Vol 7, Iss 1, p 213 (2006)","raw_type":"article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:53740","is_oa":false,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/53740/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"   BMC BIOINFORMATICS , 7     , Article 213. (2006)      ","raw_type":"Article"},{"id":"pmh:oai:europepmc.org:302593","is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC1513258","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":"","raw_type":"Text"},{"id":"pmh:oai:iris.uniroma1.it:11573/362907","is_oa":false,"landing_page_url":"http://hdl.handle.net/11573/362907","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","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":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pubmedcentral.nih.gov:1513258","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/1513258","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":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-7-213","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-7-213","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-213","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/14","display_name":"Life below water","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2113231090.pdf","grobid_xml":"https://content.openalex.org/works/W2113231090.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W158386632","https://openalex.org/W1480952678","https://openalex.org/W1513332069","https://openalex.org/W1971449260","https://openalex.org/W1992811353","https://openalex.org/W2011235285","https://openalex.org/W2020481171","https://openalex.org/W2031834810","https://openalex.org/W2052161618","https://openalex.org/W2054980108","https://openalex.org/W2067913741","https://openalex.org/W2072649575","https://openalex.org/W2098290178","https://openalex.org/W2099299706","https://openalex.org/W2101229087","https://openalex.org/W2101877384","https://openalex.org/W2103115373","https://openalex.org/W2106882534","https://openalex.org/W2108211735","https://openalex.org/W2109715166","https://openalex.org/W2110483430","https://openalex.org/W2113601822","https://openalex.org/W2123858481","https://openalex.org/W2126627383","https://openalex.org/W2126809954","https://openalex.org/W2130280638","https://openalex.org/W2130479394","https://openalex.org/W2130595050","https://openalex.org/W2132926880","https://openalex.org/W2141022852","https://openalex.org/W2141663730","https://openalex.org/W2141737941","https://openalex.org/W2141885858","https://openalex.org/W2158714788","https://openalex.org/W2161529001","https://openalex.org/W2178329765","https://openalex.org/W2915964049","https://openalex.org/W4210400672","https://openalex.org/W4241391257"],"related_works":["https://openalex.org/W4379373911","https://openalex.org/W4379374345","https://openalex.org/W2096837288","https://openalex.org/W2887244195","https://openalex.org/W2791852654","https://openalex.org/W4244694755","https://openalex.org/W4390966252","https://openalex.org/W4255788549","https://openalex.org/W205507804","https://openalex.org/W2921468924"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,51,139],"environmental":[2,230],"sequencing":[3,68,231],"of":[4,14,58,65,152,168],"the":[5,18,23,27,66,76,105,132,136,150,165,172,187,197,211,226],"Sargasso":[6,28,140],"Sea":[7,29,141],"has":[8],"introduced":[9],"a":[10,33,62,72,146,208],"huge":[11],"new":[12,133,161,188],"resource":[13,52,173],"genomic":[15],"information.":[16],"Unlike":[17],"protein":[19,60],"sequences":[20,30,70,103,134,142,189],"held":[21],"in":[22,135,171,177,203,217],"current":[24,77,106,126,153],"searchable":[25,78],"databases,":[26],"originate":[31],"from":[32,41],"single":[34],"marine":[35],"environment":[36],"and":[37,108,158,219],"have":[38],"been":[39],"sequenced":[40],"species":[42],"that":[43,148,186],"are":[44],"not":[45],"easily":[46],"obtainable":[47],"by":[48,229],"laboratory":[49],"cultivation.":[50],"also":[53,81,121],"contains":[54],"very":[55],"many":[56],"fragments":[57,170,227],"whole":[59],"sequences,":[61],"side":[63],"effect":[64],"shotgun":[67],"method.These":[69],"form":[71],"significant":[73],"addendum":[74],"to":[75,92,98,101,115,123,144,155,175,200,222],"databases":[79],"but":[80],"present":[82],"us":[83],"with":[84,104,131,193],"some":[85],"intrinsic":[86],"difficulties.":[87],"While":[88],"it":[89,95,119],"is":[90,96,120,199],"important":[91],"know":[93,124],"whether":[94,109],"possible":[97],"assign":[99],"function":[100,159],"these":[102],"methods":[107,154,221],"they":[110],"will":[111,129],"increase":[112],"our":[113],"capacity":[114],"explore":[116],"sequence":[117,169],"space,":[118],"interesting":[122],"how":[125],"bioinformatics":[127],"techniques":[128],"deal":[130],"resource.":[137],"RESULTS:":[138],"seem":[143],"introduce":[145],"bias":[147],"decreases":[149],"potential":[151],"propose":[156],"structure":[157],"for":[160],"proteins.":[162],"In":[163],"particular":[164],"high":[166],"proportion":[167],"seems":[174],"result":[176],"poor":[178],"quality":[179],"multiple":[180],"alignments.":[181],"CONCLUSION:":[182],"These":[183],"observations":[184],"suggest":[185],"should":[190],"be":[191,201],"used":[192,202],"care,":[194],"especially":[195],"if":[196],"information":[198],"large":[204],"scale":[205],"analyses.":[206],"On":[207],"positive":[209],"note,":[210],"results":[212],"may":[213],"just":[214],"spark":[215],"improvements":[216],"computational":[218],"experimental":[220],"take":[223],"into":[224],"account":[225],"generated":[228],"techniques.":[232]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}
