{"id":"https://openalex.org/W4220982887","doi":"https://doi.org/10.1371/journal.pcbi.1009860","title":"The SAMBA tool uses long reads to improve the contiguity of genome assemblies","display_name":"The SAMBA tool uses long reads to improve the contiguity of genome assemblies","publication_year":2022,"publication_date":"2022-02-04","ids":{"openalex":"https://openalex.org/W4220982887","doi":"https://doi.org/10.1371/journal.pcbi.1009860","pmid":"https://pubmed.ncbi.nlm.nih.gov/35120119"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1009860","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1009860","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1009860&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1009860&type=printable","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056359638","display_name":"Aleksey V. Zimin","orcid":"https://orcid.org/0000-0001-5091-3092"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aleksey V. Zimin","raw_affiliation_strings":["Center for Computational Biology, Johns Hopkins University, Baltimore, Maryland, United States of America","Department of Biomedical Engineering, Johns Hopkins University, Baltimore, Maryland, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-5091-3092","affiliations":[{"raw_affiliation_string":"Center for Computational Biology, Johns Hopkins University, Baltimore, Maryland, United States of America","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Department of Biomedical Engineering, Johns Hopkins University, Baltimore, Maryland, United States of America","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010384159","display_name":"Steven L. Salzberg","orcid":"https://orcid.org/0000-0002-8859-7432"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven L. Salzberg","raw_affiliation_strings":["Center for Computational Biology, Johns Hopkins University, Baltimore, Maryland, United States of America","Department of Biomedical Engineering, Johns Hopkins University, Baltimore, Maryland, United States of America","Department of Biostatistics, Johns Hopkins University, Baltimore, Maryland, United States of America","Department of Computer Science, Johns Hopkins University, Baltimore, Maryland, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-8859-7432","affiliations":[{"raw_affiliation_string":"Center for Computational Biology, Johns Hopkins University, Baltimore, Maryland, United States of America","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Department of Biomedical Engineering, Johns Hopkins University, Baltimore, Maryland, United States of America","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Department of Biostatistics, Johns Hopkins University, Baltimore, Maryland, United States of America","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Department of Computer Science, Johns Hopkins University, Baltimore, Maryland, United States of America","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056359638"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":3.9058,"has_fulltext":true,"cited_by_count":51,"citation_normalized_percentile":{"value":0.94906598,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"18","issue":"2","first_page":"e1009860","last_page":"e1009860"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9926000237464905,"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/T10434","display_name":"Chromosomal and Genetic Variations","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/contiguity","display_name":"Contiguity","score":0.76523357629776},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.6148319840431213},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5268127918243408},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.4447941482067108},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44012871384620667},{"id":"https://openalex.org/keywords/evolutionary-biology","display_name":"Evolutionary biology","score":0.41940993070602417},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.3073844313621521},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.10043331980705261},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.08958041667938232}],"concepts":[{"id":"https://openalex.org/C68767595","wikidata":"https://www.wikidata.org/wiki/Q1677999","display_name":"Contiguity","level":2,"score":0.76523357629776},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6148319840431213},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5268127918243408},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4447941482067108},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44012871384620667},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.41940993070602417},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3073844313621521},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.10043331980705261},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08958041667938232}],"mesh":[{"descriptor_ui":"D012984","descriptor_name":"Software","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":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1371/journal.pcbi.1009860","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1009860","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1009860&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},{"id":"pmid:35120119","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35120119","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":"PLoS computational biology","raw_type":null},{"id":"pmh:oai:doaj.org/article:e59d3dc3f38340868488f1b80981ac2d","is_oa":true,"landing_page_url":"https://doaj.org/article/e59d3dc3f38340868488f1b80981ac2d","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, Vol 18, Iss 2, p e1009860 (2022)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8849508","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8849508","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":"PLoS Comput Biol","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1009860","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1009860","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1009860&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1914338789","display_name":null,"funder_award_id":"R01-HG006677","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G2028148253","display_name":null,"funder_award_id":"2018-67015-28199","funder_id":"https://openalex.org/F4320306114","funder_display_name":"U.S. Department of Agriculture"},{"id":"https://openalex.org/G2242269749","display_name":"RESEARCH-PGR: Algorithms and Tools for Improving Genome Assemblies","funder_award_id":"1744309","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4389248170","display_name":null,"funder_award_id":"IOS-1744309","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4570290924","display_name":null,"funder_award_id":"R01-HG006677","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4702644247","display_name":null,"funder_award_id":"2018-67015-28199","funder_id":"https://openalex.org/F4320332299","funder_display_name":"National Institute of Food and Agriculture"},{"id":"https://openalex.org/G632460639","display_name":null,"funder_award_id":"HG006677","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6682173768","display_name":null,"funder_award_id":"R35-GM130151","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306114","display_name":"U.S. Department of Agriculture","ror":"https://ror.org/01na82s61"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320332299","display_name":"National Institute of Food and Agriculture","ror":"https://ror.org/05qx3fv49"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4220982887.pdf","grobid_xml":"https://content.openalex.org/works/W4220982887.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1579534339","https://openalex.org/W2011246380","https://openalex.org/W2076163156","https://openalex.org/W2107772251","https://openalex.org/W2110145781","https://openalex.org/W2130530163","https://openalex.org/W2167757586","https://openalex.org/W2580040938","https://openalex.org/W2788228074","https://openalex.org/W2789843538","https://openalex.org/W2884954915","https://openalex.org/W2994865123","https://openalex.org/W3037791019","https://openalex.org/W3042374389","https://openalex.org/W3085758516","https://openalex.org/W3110957961","https://openalex.org/W3167062982","https://openalex.org/W4220999759","https://openalex.org/W4225908069","https://openalex.org/W6795410112"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2085498352","https://openalex.org/W2469797624","https://openalex.org/W2092518157","https://openalex.org/W182477923","https://openalex.org/W2395159952","https://openalex.org/W2532640046","https://openalex.org/W2080840866","https://openalex.org/W1996914340","https://openalex.org/W2026308749"],"abstract_inverted_index":{"Third-generation":[0],"sequencing":[1,54],"technologies":[2],"can":[3],"generate":[4,79],"very":[5],"long":[6,63],"reads":[7,64],"with":[8,62,107],"relatively":[9],"high":[10],"error":[11],"rates.":[12],"The":[13],"lengths":[14],"of":[15,53,59,121,152],"the":[16,50,89,118,130,137],"reads,":[17],"which":[18],"sometimes":[19],"exceed":[20],"one":[21],"million":[22],"bases,":[23],"make":[24],"them":[25],"invaluable":[26],"for":[27,132],"resolving":[28],"complex":[29],"repeats":[30],"that":[31,87,97,124,161,177],"cannot":[32],"be":[33],"assembled":[34,91],"using":[35,49,82,155],"shorter":[36],"reads.":[37],"Many":[38],"high-quality":[39],"genome":[40,105],"assemblies":[41,76,106,154],"have":[42],"already":[43],"been":[44],"produced,":[45],"curated,":[46],"and":[47,56,85,102,127,158,166],"annotated":[48],"previous":[51],"generation":[52],"data,":[55,84,110,157],"full":[57],"re-assembly":[58],"these":[60],"genomes":[61],"is":[65,77,94,98,117,174,178],"not":[66],"always":[67],"practical":[68],"or":[69],"cost-effective.":[70],"One":[71],"strategy":[72],"to":[73,78,88,100,147],"upgrade":[74],"existing":[75,104],"additional":[80,108],"coverage":[81],"long-read":[83,109,156],"add":[86],"previously":[90],"contigs.":[92,142],"SAMBA":[93,116,146,162,173],"a":[95],"tool":[96,120],"designed":[99],"scaffold":[101],"gap-fill":[103],"resulting":[111],"in":[112,129,136],"substantially":[113],"greater":[114],"contiguity.":[115],"only":[119],"its":[122],"kind":[123],"also":[125],"computes":[126],"fills":[128],"sequence":[131],"all":[133],"spanned":[134],"gaps":[135],"scaffolds,":[138],"yielding":[139],"much":[140],"longer":[141],"Here":[143],"we":[144,159],"compare":[145],"several":[148],"similar":[149],"tools":[150],"capable":[151],"re-scaffolding":[153],"show":[160],"yields":[163],"better":[164],"contiguity":[165],"introduces":[167],"fewer":[168],"errors":[169],"than":[170],"competing":[171],"methods.":[172],"open-source":[175],"software":[176],"distributed":[179],"at":[180],"https://github.com/alekseyzimin/masurca.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":9}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}