{"id":"https://openalex.org/W2951594770","doi":"https://doi.org/10.1093/bioinformatics/btx471","title":"Faucet: streaming de novo assembly graph construction","display_name":"Faucet: streaming de novo assembly graph construction","publication_year":2017,"publication_date":"2017-07-21","ids":{"openalex":"https://openalex.org/W2951594770","doi":"https://doi.org/10.1093/bioinformatics/btx471","mag":"2951594770","pmid":"https://pubmed.ncbi.nlm.nih.gov/29036597","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/5870852"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btx471","doi":"https://doi.org/10.1093/bioinformatics/btx471","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx471","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/34/1/147/49043491/bioinformatics_34_1_147.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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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"},"volume":null,"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/34/1/147/49043491/bioinformatics_34_1_147.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026380660","display_name":"Roye Rozov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Roye Rozov","raw_affiliation_strings":["Blavatnik School of Computer Science, Tel-Aviv University, Tel Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Blavatnik School of Computer Science, Tel-Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026178062","display_name":"Gil Goldshlager","orcid":"https://orcid.org/0000-0003-4857-6407","observed_orcids":["https://orcid.org/0000-0003-4857-6407"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gil Goldshlager","raw_affiliation_strings":["Department of Mathematics, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050273239","display_name":"Eran Halperin","orcid":"https://orcid.org/0000-0002-2373-3691","observed_orcids":["https://orcid.org/0000-0002-2373-3691"]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Eran Halperin","raw_affiliation_strings":["Departments of Computer Science, Anesthesiology and Perioperative Medicine, University of California Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departments of Computer Science, Anesthesiology and Perioperative Medicine, University of California Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038806020","display_name":"Ron Shamir A","orcid":"https://orcid.org/0000-0003-1889-9870","observed_orcids":["https://orcid.org/0000-0003-1889-9870"]},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Ron Shamir","raw_affiliation_strings":["Blavatnik School of Computer Science, Tel-Aviv University, Tel Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Blavatnik School of Computer Science, Tel-Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038806020","https://openalex.org/A5050273239"],"corresponding_institution_ids":["https://openalex.org/I161318765","https://openalex.org/I16391192"],"apc_list":{"value":3989,"currency":"USD","value_usd":3989},"apc_paid":{"value":3989,"currency":"USD","value_usd":3989},"fwci":0.6942,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.66523888,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"34","issue":"1","first_page":"147","last_page":"154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9976000189781189,"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":0.9976000189781189,"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/T11269","display_name":"Algorithms and Data Compression","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":9.999999747378752e-05,"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/faucet","display_name":"faucet","score":0.9210000038146973},{"id":"https://openalex.org/keywords/de-novo-genome-assembly","display_name":"de novo genome assembly","score":0.7400000095367432},{"id":"https://openalex.org/keywords/de-bruijn-graph","display_name":"de Bruijn graph","score":0.9390000104904175},{"id":"https://openalex.org/keywords/metagenomic-assembly","display_name":"metagenome assembly","score":0.9010000228881836},{"id":"https://openalex.org/keywords/disk-space-efficiency","display_name":"disk space efficiency","score":0.7350000143051147},{"id":"https://openalex.org/keywords/contiguity","display_name":"contiguity","score":0.8519999980926514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7460165023803711},{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.6263794898986816},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.582589864730835},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.5307854413986206},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.5279126763343811},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.4904782474040985},{"id":"https://openalex.org/C2776029614","wikidata":"https://www.wikidata.org/wiki/Q1146367","display_name":"File size","level":2,"score":0.48230624198913574},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.4443274140357971},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40006157755851746},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3803437352180481},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.32672253251075745},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.16950184106826782},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15092715620994568},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[{"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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btx471","doi":"https://doi.org/10.1093/bioinformatics/btx471","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx471","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/34/1/147/49043491/bioinformatics_34_1_147.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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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":"doi:10.1101/125658","doi":"https://doi.org/10.1101/125658","is_oa":true,"landing_page_url":"https://doi.org/10.1101/125658","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2017/04/08/125658.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmh:oai:pubmedcentral.nih.gov:5870852","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5870852","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,"listed_in":[],"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"Text"},{"id":"pmid:29036597","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29036597","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,"listed_in":[],"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"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btx471","doi":"https://doi.org/10.1093/bioinformatics/btx471","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx471","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/34/1/147/49043491/bioinformatics_34_1_147.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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4718930887","display_name":null,"funder_award_id":"1425/13","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"},{"id":"https://openalex.org/G5035092382","display_name":null,"funder_award_id":"Grant 1425/13","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320320950","display_name":"United States-Israel Binational Science Foundation","ror":"https://ror.org/00j8z2m73"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"},{"id":"https://openalex.org/F4320322596","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2951594770.pdf","grobid_xml":"https://content.openalex.org/works/W2951594770.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1850079471","https://openalex.org/W1990293955","https://openalex.org/W2001079689","https://openalex.org/W2004416209","https://openalex.org/W2009119978","https://openalex.org/W2010361633","https://openalex.org/W2086898699","https://openalex.org/W2104005232","https://openalex.org/W2105656684","https://openalex.org/W2107772251","https://openalex.org/W2113679889","https://openalex.org/W2115546424","https://openalex.org/W2120902911","https://openalex.org/W2122316710","https://openalex.org/W2123845384","https://openalex.org/W2136651963","https://openalex.org/W2136986825","https://openalex.org/W2161048357","https://openalex.org/W2163830511","https://openalex.org/W2179933869","https://openalex.org/W2279083700","https://openalex.org/W2438121987","https://openalex.org/W2463351297","https://openalex.org/W2477408078","https://openalex.org/W2523856253","https://openalex.org/W2557939901","https://openalex.org/W2570372911","https://openalex.org/W2578045105","https://openalex.org/W2599417231","https://openalex.org/W2618017145","https://openalex.org/W2951325968","https://openalex.org/W2952932047","https://openalex.org/W6816997107"],"related_works":["https://openalex.org/W2463351297","https://openalex.org/W2163830511","https://openalex.org/W4383682467","https://openalex.org/W2140437680","https://openalex.org/W7034095104","https://openalex.org/W3022744167","https://openalex.org/W2113915152","https://openalex.org/W2109848222","https://openalex.org/W2113679889","https://openalex.org/W4417200522"],"abstract_inverted_index":{"Motivation:":[0],"We":[1,41,88,124],"present":[2],"Faucet,":[3],"a":[4],"two-pass":[5],"streaming":[6,47,213],"algorithm":[7],"for":[8,107],"assembly":[9,15,49,116,130],"graph":[10,16,48,77],"construction.":[11],"Faucet":[12,72,146,219],"builds":[13],"an":[14],"incrementally":[17],"as":[18,30,67,139,141],"each":[19],"read":[20],"is":[21,69,220],"processed.":[22],"Thus,":[23],"reads":[24,81],"need":[25],"not":[26],"be":[27,33],"stored":[28],"locally,":[29],"they":[31,111],"can":[32],"processed":[34],"while":[35,121,164],"downloading":[36],"data":[37,64,231],"and":[38,54,97,109,129,153,162,182,199,217],"then":[39],"discarded.":[40],"demonstrate":[42,110],"this":[43,171],"functionality":[44],"by":[45],"performing":[46],"of":[50,59,114,134,149,175],"publicly":[51],"available":[52,221,233],"data,":[53],"observe":[55],"that":[56],"the":[57,74,80,135,157,210],"ratio":[58],"disk":[60,154],"use":[61,128],"to":[62,132,201],"raw":[63],"size":[65],"decreases":[66],"coverage":[68],"increased.":[70],"Results:":[71],"pairs":[73],"de":[75],"Bruijn":[76],"obtained":[78],"from":[79,86],"with":[82,197,208],"additional":[83],"meta-data":[84],"derived":[85],"them.":[87],"show":[89],"these":[90],"metadata-coverage":[91],"counts":[92],"collected":[93],"at":[94,222,234],"junction":[95,101],"k-mers":[96],"connections":[98],"bridging":[99],"between":[100],"pairs-contain":[102],"most":[103],"salient":[104],"information":[105],"needed":[106],"assembly,":[108],"enable":[112],"cleaning":[113],"metagenome":[115,137,159],"graphs,":[117],"greatly":[118],"improving":[119,166],"contiguity":[120],"maintaining":[122],"accuracy.":[123],"compared":[125,196,207],"Fauceted":[126],"resource":[127,179],"quality":[131],"state":[133],"art":[136],"assemblers,":[138],"well":[140],"leading":[142],"resource-efficient":[143],"genome":[144],"assemblers.":[145],"used":[147],"orders":[148],"magnitude":[150],"less":[151],"time":[152],"space":[155],"than":[156],"specialized":[158],"assemblers":[160,177],"MetaSPAdes":[161],"Megahit,":[163],"also":[165],"on":[167,185],"their":[168],"memory":[169],"use;":[170],"broadly":[172],"matched":[173],"performance":[174],"other":[176,212],"optimizing":[178],"efficiency-namely,":[180],"Minia":[181],"LightAssembler.":[183],"However,":[184],"metagenomes":[186],"tested,":[187],"Faucet,o":[188],"outputs":[189],"had":[190],"14-110%":[191],"higher":[192,203],"mean":[193,204],"NGA50":[194,205],"lengths":[195,206],"Minia,":[198],"2-":[200],"11-fold":[202],"LightAssembler,":[209],"only":[211],"assembler":[214],"available.":[215],"Availability":[216],"implementation:":[218],"https://github.com/Shamir-Lab/Faucet.":[223],"Contact:":[224],"rshamir@tau.ac.il":[225],"or":[226],"eranhalperin@gmail.com.":[227],"Supplementary":[228,230],"information:":[229],"are":[232],"Bioinformatics":[235],"online.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-06-27T00:00:00"}
