{"id":"https://openalex.org/W2158678815","doi":"https://doi.org/10.1093/bioinformatics/btt594","title":"MFCompress: a compression tool for FASTA and multi-FASTA data","display_name":"MFCompress: a compression tool for FASTA and multi-FASTA data","publication_year":2013,"publication_date":"2013-10-16","ids":{"openalex":"https://openalex.org/W2158678815","doi":"https://doi.org/10.1093/bioinformatics/btt594","mag":"2158678815","pmid":"https://pubmed.ncbi.nlm.nih.gov/24132931"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btt594","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btt594","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/30/1/117/48913003/bioinformatics_30_1_117.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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/30/1/117/48913003/bioinformatics_30_1_117.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075489861","display_name":"Armando J. Pinho","orcid":"https://orcid.org/0000-0002-9164-0016"},"institutions":[{"id":"https://openalex.org/I60858718","display_name":"University of Aveiro","ror":"https://ror.org/00nt41z93","country_code":"PT","type":"education","lineage":["https://openalex.org/I60858718"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Armando J. Pinho","raw_affiliation_strings":["IEETA, Department of Electronics, Telecommunications and Informatics, University of Aveiro, 3810\u2013193 Aveiro, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IEETA, Department of Electronics, Telecommunications and Informatics, University of Aveiro, 3810\u2013193 Aveiro, Portugal","institution_ids":["https://openalex.org/I60858718"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051693451","display_name":"Diogo Pratas","orcid":"https://orcid.org/0000-0003-1176-552X"},"institutions":[{"id":"https://openalex.org/I60858718","display_name":"University of Aveiro","ror":"https://ror.org/00nt41z93","country_code":"PT","type":"education","lineage":["https://openalex.org/I60858718"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Diogo Pratas","raw_affiliation_strings":["IEETA, Department of Electronics, Telecommunications and Informatics, University of Aveiro, 3810\u2013193 Aveiro, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IEETA, Department of Electronics, Telecommunications and Informatics, University of Aveiro, 3810\u2013193 Aveiro, Portugal","institution_ids":["https://openalex.org/I60858718"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5075489861"],"corresponding_institution_ids":["https://openalex.org/I60858718"],"apc_list":{"value":3989,"currency":"USD","value_usd":3989},"apc_paid":{"value":3989,"currency":"USD","value_usd":3989},"fwci":9.885,"has_fulltext":true,"cited_by_count":119,"citation_normalized_percentile":{"value":0.97748047,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"30","issue":"1","first_page":"117","last_page":"118"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.8363000154495239,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.8363000154495239,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.02459999918937683,"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/T10885","display_name":"Gene expression and cancer classification","score":0.01600000075995922,"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":0.6387014985084534},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.47906026244163513},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.23232495784759521}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6387014985084534},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.47906026244163513},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.23232495784759521}],"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":"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":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btt594","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btt594","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/30/1/117/48913003/bioinformatics_30_1_117.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:24132931","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/24132931","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":"Journal Article"},{"id":"pmh:oai:europepmc.org:2851074","is_oa":false,"landing_page_url":"http://europepmc.org/articles/PMC3866555","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:3866555","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3866555","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/btt594","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btt594","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/30/1/117/48913003/bioinformatics_30_1_117.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1578237752","display_name":null,"funder_award_id":"COMPETE","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G2222338232","display_name":null,"funder_award_id":"FCOMP-01-0124-FEDER-022682","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G706141057","display_name":"Projecto Estrat\u00e9gico - UI 127 - 2011-2012","funder_award_id":"PEst-C/EEI/UI0127/2011","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G8868700560","display_name":null,"funder_award_id":"FCOMP-01-0124-FEDER","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2158678815.pdf","grobid_xml":"https://content.openalex.org/works/W2158678815.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1987370597","https://openalex.org/W2000466469","https://openalex.org/W2010908945","https://openalex.org/W2010928148","https://openalex.org/W2074490119","https://openalex.org/W2092880969","https://openalex.org/W2111044311","https://openalex.org/W2113855394","https://openalex.org/W2127912200","https://openalex.org/W2131106408","https://openalex.org/W2146028503","https://openalex.org/W2157745386","https://openalex.org/W2166588423","https://openalex.org/W2611071497","https://openalex.org/W6678795934","https://openalex.org/W6681790542"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1],"data":[2],"deluge":[3],"phenomenon":[4],"is":[5,43],"becoming":[6],"a":[7,75],"serious":[8],"problem":[9],"in":[10,149],"most":[11],"genomic":[12],"centers.":[13],"To":[14],"alleviate":[15],"it,":[16],"general":[17],"purpose":[18],"tools,":[19],"such":[20,96],"as":[21,46,48,83],"gzip,":[22,152],"are":[23,169],"used":[24],"to":[25,34,44,111,115],"compress":[26],"the":[27,41,50,67,102,132,137],"data.":[28],"However,":[29],"although":[30,135],"pervasive":[31],"and":[32,56,85,106,113,148,163],"easy":[33],"use,":[35],"these":[36],"tools":[37],"fall":[38],"short":[39],"when":[40],"intention":[42],"reduce":[45],"much":[47],"possible":[49],"data,":[51,71],"for":[52,54,66,101,165,172],"example,":[53],"medium-":[55],"long-term":[57],"storage.":[58],"A":[59],"number":[60],"of":[61,69,77,104,125,139],"algorithms":[62],"have":[63,79,156],"been":[64,80,157],"proposed":[65],"compression":[68,87,103,123],"genomics":[70],"but":[72],"unfortunately":[73],"only":[74],"few":[76],"them":[78],"made":[81],"available":[82,133,171],"usable":[84],"reliable":[86],"tools.":[88],"RESULTS:":[89],"In":[90,109],"this":[91],"article,":[92],"we":[93],"describe":[94],"one":[95],"tool,":[97],"MFCompress,":[98],"specially":[99],"designed":[100],"FASTA":[105],"multi-FASTA":[107,116],"files.":[108],"comparison":[110,150],"gzip":[112],"applied":[114],"files,":[117],"MFCompress":[118],"can":[119],"provide":[120],"additional":[121],"average":[122],"gains":[124],"almost":[126],"50%,":[127],"i.e.":[128],"it":[129],"potentially":[130],"doubles":[131],"storage,":[134],"at":[136,175],"cost":[138],"some":[140],"more":[141],"computation":[142],"time.":[143],"On":[144],"highly":[145],"redundant":[146],"datasets,":[147],"with":[151],"8-fold":[153],"size":[154],"reductions":[155],"obtained.":[158],"AVAILABILITY:":[159],"Both":[160],"source":[161],"code":[162],"binaries":[164],"several":[166],"operating":[167],"systems":[168],"freely":[170],"non-commercial":[173],"use":[174],"http://bioinformatics.ua.pt/software/mfcompress/.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":2}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
