{"id":"https://openalex.org/W1931014516","doi":"https://doi.org/10.1109/cibcb.2015.7300324","title":"Assembly independent functional annotation of short-read data using SOFA: Short-ORF functional annotation","display_name":"Assembly independent functional annotation of short-read data using SOFA: Short-ORF functional annotation","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W1931014516","doi":"https://doi.org/10.1109/cibcb.2015.7300324","mag":"1931014516"},"language":"en","primary_location":{"id":"doi:10.1109/cibcb.2015.7300324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cibcb.2015.7300324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055521337","display_name":"Aria S Hahn","orcid":"https://orcid.org/0000-0001-6105-7172"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Aria S. Hahn","raw_affiliation_strings":["Department of Microbiology, University of British Columbia, Vancouver, Canada","Department of Microbiology, University of British Columbia Vancouver, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Microbiology, University of British Columbia, Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"Department of Microbiology, University of British Columbia Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069094618","display_name":"Niels W. Hanson","orcid":"https://orcid.org/0000-0003-3081-0736"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Niels W. Hanson","raw_affiliation_strings":["Graduate Program in Bioinformatics, University of British Columbia, Vancouver, Canada"],"affiliations":[{"raw_affiliation_string":"Graduate Program in Bioinformatics, University of British Columbia, Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000581119","display_name":"Dongjae Kim","orcid":"https://orcid.org/0000-0003-2871-7815"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Dongjae Kim","raw_affiliation_strings":["Department of Computer Science, University of British Columbia, Vancouver, Canada","Department of Computer Science,  University of British Columbia,  Vancouver, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of British Columbia, Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"Department of Computer Science,  University of British Columbia,  Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035678865","display_name":"Kishori M. Konwar","orcid":"https://orcid.org/0000-0001-5152-4777"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kishori M. Konwar","raw_affiliation_strings":["Department of Microbiology, University of British Columbia, Vancouver, Canada","Department of Microbiology, University of British Columbia Vancouver, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Microbiology, University of British Columbia, Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"Department of Microbiology, University of British Columbia Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101411528","display_name":"Steven Hallam","orcid":"https://orcid.org/0000-0002-4889-6876"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Steven J. Hallam","raw_affiliation_strings":["Graduate Program in Bioinformatics, University of British Columbia, Vancouver, Canada","Department of Microbiology, University of British Columbia Vancouver, Canada"],"affiliations":[{"raw_affiliation_string":"Graduate Program in Bioinformatics, University of British Columbia, Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"Department of Microbiology, University of British Columbia Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5055521337"],"corresponding_institution_ids":["https://openalex.org/I141945490"],"apc_list":null,"apc_paid":null,"fwci":1.2188,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.80176355,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11791","display_name":"Microbial Community Ecology and Physiology","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T11791","display_name":"Microbial Community Ecology and Physiology","score":0.9991000294685364,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9988999962806702,"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/T12640","display_name":"Environmental DNA in Biodiversity Studies","score":0.9921000003814697,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8553496599197388},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6950526833534241},{"id":"https://openalex.org/keywords/mit-license","display_name":"MIT License","score":0.6934380531311035},{"id":"https://openalex.org/keywords/orfs","display_name":"ORFS","score":0.6609686613082886},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.6600413918495178},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5259856581687927},{"id":"https://openalex.org/keywords/retargeting","display_name":"Retargeting","score":0.5032426714897156},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4029456377029419},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3509114980697632},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3464164733886719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30356040596961975},{"id":"https://openalex.org/keywords/open-reading-frame","display_name":"Open reading frame","score":0.2697875499725342},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2227681577205658},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1834370195865631},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11968880891799927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8553496599197388},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6950526833534241},{"id":"https://openalex.org/C174183944","wikidata":"https://www.wikidata.org/wiki/Q334661","display_name":"MIT License","level":3,"score":0.6934380531311035},{"id":"https://openalex.org/C2780530800","wikidata":"https://www.wikidata.org/wiki/Q7072921","display_name":"ORFS","level":5,"score":0.6609686613082886},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.6600413918495178},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5259856581687927},{"id":"https://openalex.org/C2780575108","wikidata":"https://www.wikidata.org/wiki/Q7316652","display_name":"Retargeting","level":2,"score":0.5032426714897156},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4029456377029419},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3509114980697632},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3464164733886719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30356040596961975},{"id":"https://openalex.org/C47289529","wikidata":"https://www.wikidata.org/wiki/Q908550","display_name":"Open reading frame","level":4,"score":0.2697875499725342},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2227681577205658},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1834370195865631},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11968880891799927},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cibcb.2015.7300324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cibcb.2015.7300324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1964315675","https://openalex.org/W1988925586","https://openalex.org/W1989348205","https://openalex.org/W2003947856","https://openalex.org/W2009906332","https://openalex.org/W2011486440","https://openalex.org/W2066656905","https://openalex.org/W2069689025","https://openalex.org/W2072420737","https://openalex.org/W2072970694","https://openalex.org/W2091922579","https://openalex.org/W2107000647","https://openalex.org/W2107903949","https://openalex.org/W2108893650","https://openalex.org/W2116895571","https://openalex.org/W2126809954","https://openalex.org/W2131342905","https://openalex.org/W2133790733","https://openalex.org/W2143485490","https://openalex.org/W2149429041","https://openalex.org/W2156125289","https://openalex.org/W2157107905","https://openalex.org/W2161546116","https://openalex.org/W2162473677","https://openalex.org/W2162758337","https://openalex.org/W2163830511","https://openalex.org/W2168330474"],"related_works":["https://openalex.org/W2039410154","https://openalex.org/W2051856433","https://openalex.org/W2140948740","https://openalex.org/W1976390578","https://openalex.org/W2552089663","https://openalex.org/W2360726289","https://openalex.org/W1991032667","https://openalex.org/W1980765857","https://openalex.org/W2944244829","https://openalex.org/W4205801320"],"abstract_inverted_index":{"Accurate":[0],"description":[1],"of":[2,28,45,87,111,140],"the":[3,26,84,101,149,166],"microbial":[4],"communities":[5],"driving":[6],"matter":[7],"and":[8,66,74,118,123,136,153],"energy":[9],"transformations":[10],"in":[11,56],"complex":[12],"ecosystems":[13],"such":[14],"as":[15,69,71,158],"soils":[16],"cannot":[17],"yet":[18],"be":[19],"effectively":[20],"accomplished":[21],"using":[22],"assembly-based":[23],"approaches":[24],"despite":[25],"rise":[27],"next":[29],"generation":[30],"sequencing":[31],"technologies.":[32],"Here":[33],"we":[34,79],"present":[35],"SOFA,":[36],"an":[37,76,137],"open":[38,60],"source":[39],"pipeline":[40,50],"enabling":[41],"comparative":[42],"functional":[43],"annotation":[44],"unassembled":[46],"short-read":[47],"data.":[48],"The":[49,109],"attempts":[51],"to":[52,128],"merge":[53],"mate":[54],"pairs":[55],"fastq":[57],"files,":[58],"predicts":[59],"reading":[61],"frames":[62],"(ORFs)":[63],"on":[64],"merged":[65],"unmerged":[67,91],"reads":[68,93],"small":[70],"70":[72],"bps,":[73],"completes":[75],"additional":[77],"step,":[78],"term":[80],"`deduplication'.":[81],"Deduplication":[82],"prevents":[83],"double":[85],"counting":[86],"ORFs":[88],"predicted":[89],"from":[90],"paired-end":[92],"by":[94],"checking":[95],"for":[96,105,131,156],"homologous":[97],"annotations":[98],"that":[99],"span":[100],"same":[102],"ORF,":[103],"allowing":[104],"quantitatively":[106],"accurate":[107,133],"predictions.":[108],"effectiveness":[110],"SOFA":[112,143],"is":[113,154],"validated":[114],"with":[115],"both":[116],"simulated":[117],"bone":[119],"fide":[120],"soil":[121],"metagenomes,":[122],"empirical":[124],"results":[125],"are":[126],"compared":[127],"existing":[129,150],"strategies":[130],"obtaining":[132],"ORF":[134],"counts,":[135],"analytical":[138],"model":[139],"read":[141],"duplication.":[142],"enables":[144],"downstream":[145],"processing":[146],"stages":[147],"within":[148],"MetaPathways":[151],"pipeline,":[152],"available":[155],"download":[157],"a":[159],"stand":[160],"alone":[161],"application":[162],"at":[163],"https://github.com":[164],"under":[165],"MIT":[167],"license.":[168]},"counts_by_year":[{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
