{"id":"https://openalex.org/W2096715799","doi":"https://doi.org/10.1093/bioinformatics/btv052","title":"SFA-SPA: a suffix array based short peptide assembler for metagenomic data","display_name":"SFA-SPA: a suffix array based short peptide assembler for metagenomic data","publication_year":2015,"publication_date":"2015-01-30","ids":{"openalex":"https://openalex.org/W2096715799","doi":"https://doi.org/10.1093/bioinformatics/btv052","mag":"2096715799","pmid":"https://pubmed.ncbi.nlm.nih.gov/25637561"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btv052","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btv052","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/11/1833/50314421/bioinformatics_31_11_1833.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/31/11/1833/50314421/bioinformatics_31_11_1833.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054677783","display_name":"Youngik Yang","orcid":"https://orcid.org/0000-0003-3219-4471"},"institutions":[{"id":"https://openalex.org/I1301553790","display_name":"J. Craig Venter Institute","ror":"https://ror.org/049r1ts75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1301553790"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Youngik Yang","raw_affiliation_strings":["Informatics Department, J. Craig Venter Institute, La Jolla, CA 92037, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Informatics Department, J. Craig Venter Institute, La Jolla, CA 92037, USA","institution_ids":["https://openalex.org/I1301553790"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055955475","display_name":"Cuncong Zhong","orcid":"https://orcid.org/0000-0002-8777-082X"},"institutions":[{"id":"https://openalex.org/I1301553790","display_name":"J. Craig Venter Institute","ror":"https://ror.org/049r1ts75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1301553790"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cuncong Zhong","raw_affiliation_strings":["Informatics Department, J. Craig Venter Institute, La Jolla, CA 92037, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Informatics Department, J. Craig Venter Institute, La Jolla, CA 92037, USA","institution_ids":["https://openalex.org/I1301553790"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015513138","display_name":"Shibu Yooseph","orcid":"https://orcid.org/0000-0001-5581-5002"},"institutions":[{"id":"https://openalex.org/I1301553790","display_name":"J. Craig Venter Institute","ror":"https://ror.org/049r1ts75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1301553790"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shibu Yooseph","raw_affiliation_strings":["Informatics Department, J. Craig Venter Institute, La Jolla, CA 92037, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Informatics Department, J. Craig Venter Institute, La Jolla, CA 92037, USA","institution_ids":["https://openalex.org/I1301553790"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5015513138"],"corresponding_institution_ids":["https://openalex.org/I1301553790"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.6591,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.67022314,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"31","issue":"11","first_page":"1833","last_page":"1835"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.26739999651908875,"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"}},"topics":[{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.26739999651908875,"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"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.148499995470047,"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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.11959999799728394,"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/metagenomics","display_name":"Metagenomics","score":0.9245775938034058},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6488090753555298},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.608393669128418},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4723321497440338},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.46577805280685425},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4512370228767395},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4384022057056427},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.28560811281204224},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2147025167942047},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.11583340167999268},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.09372618794441223}],"concepts":[{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.9245775938034058},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6488090753555298},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.608393669128418},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4723321497440338},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.46577805280685425},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4512370228767395},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4384022057056427},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.28560811281204224},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2147025167942047},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.11583340167999268},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.09372618794441223},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","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":"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":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btv052","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btv052","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/11/1833/50314421/bioinformatics_31_11_1833.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:25637561","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25637561","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:open-archive.highwire.org:bioinfo:31/11/1833","is_oa":false,"landing_page_url":"http://bioinformatics.oxfordjournals.org/cgi/content/short/31/11/1833","pdf_url":null,"source":{"id":"https://openalex.org/S4406923041","display_name":"HighWire Press Open Archive","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"TEXT"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btv052","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btv052","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/11/1833/50314421/bioinformatics_31_11_1833.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3259472918","display_name":"ABI Development: A Novel Protein Fragment Assembler for Metagenomic Data Analysis","funder_award_id":"1262295","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2096715799.pdf","grobid_xml":"https://content.openalex.org/works/W2096715799.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W1489909987","https://openalex.org/W2022910024","https://openalex.org/W2063282826","https://openalex.org/W2158874082","https://openalex.org/W2171309014"],"related_works":["https://openalex.org/W2210738511","https://openalex.org/W2474302342","https://openalex.org/W1910109602","https://openalex.org/W4297131566","https://openalex.org/W2017364432","https://openalex.org/W2080583581","https://openalex.org/W3158976456","https://openalex.org/W2767445485","https://openalex.org/W4285082713","https://openalex.org/W2102118387"],"abstract_inverted_index":{"UNLABELLED:":[0],"The":[1,85,120],"determination":[2],"of":[3,13,18,40,110],"protein":[4,41],"sequences":[5,42],"from":[6,43,73,128],"a":[7,51,92,107],"metagenomic":[8,52,75],"dataset":[9],"enables":[10,114],"the":[11,19,25,37,61,103,125],"study":[12],"metabolism":[14],"and":[15,34,106],"functional":[16],"roles":[17],"organisms":[20],"that":[21,66,97,113],"are":[22],"present":[23,56],"in":[24,50],"sampled":[26],"microbial":[27],"community.":[28],"We":[29],"had":[30],"previously":[31],"introduced":[32],"algorithm":[33,65],"software":[35],"for":[36,99],"accurate":[38],"reconstruction":[39],"short":[44,62],"peptides":[45],"identified":[46],"on":[47],"nucleotide":[48],"reads":[49],"dataset.":[53],"Here,":[54],"we":[55],"significant":[57,108],"computational":[58,87],"improvements":[59],"to":[60,70],"peptide":[63],"assembly":[64,104,111],"make":[67],"it":[68],"practical":[69],"reconstruct":[71],"proteins":[72],"large":[74],"datasets":[76],"containing":[77],"several":[78],"hundred":[79],"million":[80],"reads,":[81],"while":[82],"maintaining":[83],"accuracy.":[84],"improved":[86],"efficiency":[88],"is":[89,122],"achieved":[90],"using":[91],"suffix":[93],"array":[94],"data":[95],"structure":[96],"allows":[98],"fast":[100],"querying":[101],"during":[102],"process,":[105],"redesign":[109],"steps":[112],"multi-threaded":[115],"execution.":[116],"AVAILABILITY":[117],"AND":[118],"IMPLEMENTATION:":[119],"program":[121],"available":[123],"under":[124],"GPLv3":[126],"license":[127],"sourceforge.net/projects/spa-assembler.":[129]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}