{"id":"https://openalex.org/W4226092504","doi":"https://doi.org/10.1371/journal.pcbi.1009802","title":"Polypolish: Short-read polishing of long-read bacterial genome assemblies","display_name":"Polypolish: Short-read polishing of long-read bacterial genome assemblies","publication_year":2022,"publication_date":"2022-01-24","ids":{"openalex":"https://openalex.org/W4226092504","doi":"https://doi.org/10.1371/journal.pcbi.1009802","pmid":"https://pubmed.ncbi.nlm.nih.gov/35073327"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1009802","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1009802","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1009802&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.1009802&type=printable","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082498266","display_name":"Ryan R. Wick","orcid":"https://orcid.org/0000-0001-8349-0778"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Ryan R. Wick","raw_affiliation_strings":["Department of Infectious Diseases, Central Clinical School, Monash University, Melbourne, Victoria, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8349-0778","affiliations":[{"raw_affiliation_string":"Department of Infectious Diseases, Central Clinical School, Monash University, Melbourne, Victoria, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080608098","display_name":"Kathryn E. Holt","orcid":"https://orcid.org/0000-0003-3949-2471"},"institutions":[{"id":"https://openalex.org/I4210089966","display_name":"London School of Hygiene & Tropical Medicine","ror":"https://ror.org/00a0jsq62","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I4210089966"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU","GB"],"is_corresponding":false,"raw_author_name":"Kathryn E. Holt","raw_affiliation_strings":["Department of Infection Biology, London School of Hygiene & Tropical Medicine, London, United Kingdom","Department of Infectious Diseases, Central Clinical School, Monash University, Melbourne, Victoria, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3949-2471","affiliations":[{"raw_affiliation_string":"Department of Infection Biology, London School of Hygiene & Tropical Medicine, London, United Kingdom","institution_ids":["https://openalex.org/I4210089966"]},{"raw_affiliation_string":"Department of Infectious Diseases, Central Clinical School, Monash University, Melbourne, Victoria, Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5082498266"],"corresponding_institution_ids":["https://openalex.org/I56590836"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2450,"currency":"EUR","value_usd":2642},"fwci":58.1536,"has_fulltext":true,"cited_by_count":696,"citation_normalized_percentile":{"value":0.99961167,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"18","issue":"1","first_page":"e1009802","last_page":"e1009802"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998999834060669,"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":0.9998999834060669,"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/T11578","display_name":"Plant Pathogenic Bacteria Studies","score":0.9940000176429749,"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"}},{"id":"https://openalex.org/T11470","display_name":"Legume Nitrogen Fixing Symbiosis","score":0.9625999927520752,"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/polishing","display_name":"Polishing","score":0.9194248914718628},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6048769950866699},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5018789768218994},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.44975394010543823},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2512081265449524},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1112651526927948},{"id":"https://openalex.org/keywords/mechanical-engineering","display_name":"Mechanical engineering","score":0.09744918346405029}],"concepts":[{"id":"https://openalex.org/C138113353","wikidata":"https://www.wikidata.org/wiki/Q611639","display_name":"Polishing","level":2,"score":0.9194248914718628},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6048769950866699},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5018789768218994},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.44975394010543823},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2512081265449524},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1112651526927948},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.09744918346405029},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D004269","descriptor_name":"DNA, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004269","descriptor_name":"DNA, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004269","descriptor_name":"DNA, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012091","descriptor_name":"Repetitive Sequences, Nucleic Acid","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012091","descriptor_name":"Repetitive Sequences, Nucleic Acid","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012091","descriptor_name":"Repetitive Sequences, Nucleic Acid","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","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},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.1371/journal.pcbi.1009802","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1009802","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1009802&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:35073327","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35073327","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:researchonline.lshtm.ac.uk:4664791","is_oa":false,"landing_page_url":"https://researchonline.lshtm.ac.uk/view/creators/ipmbkhot.html>;","pdf_url":null,"source":{"id":"https://openalex.org/S4306402527","display_name":"LSHTM Research Online (London School of Hygiene and Tropical Medicine)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210089966","host_organization_name":"London School of Hygiene & Tropical Medicine","host_organization_lineage":["https://openalex.org/I4210089966"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:datacompass.lshtm.ac.uk:4674","is_oa":false,"landing_page_url":"https://orcid.org/0000-0001-8349-0778>","pdf_url":null,"source":{"id":"https://openalex.org/S4306400091","display_name":"London School of Hygiene & Tropical Medicine","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210089966","host_organization_name":"London School of Hygiene & Tropical Medicine","host_organization_lineage":["https://openalex.org/I4210089966"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"pmh:oai:doaj.org/article:ff6336c161c44e3182e658685b3c7c85","is_oa":true,"landing_page_url":"https://doaj.org/article/ff6336c161c44e3182e658685b3c7c85","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 1, p e1009802 (2022)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8812927","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8812927","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.1009802","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1009802","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1009802&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/G815390546","display_name":null,"funder_award_id":"OPP1175797","funder_id":"https://openalex.org/F4320306137","funder_display_name":"Bill and Melinda Gates Foundation"}],"funders":[{"id":"https://openalex.org/F4320306137","display_name":"Bill and Melinda Gates Foundation","ror":"https://ror.org/0456r8d26"},{"id":"https://openalex.org/F4320310745","display_name":"Sylvia and Charles Viertel Charitable Foundation","ror":"https://ror.org/05539km59"},{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4226092504.pdf","grobid_xml":"https://content.openalex.org/works/W4226092504.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1982579644","https://openalex.org/W1982855075","https://openalex.org/W2098531465","https://openalex.org/W2103441770","https://openalex.org/W2143485490","https://openalex.org/W2149452073","https://openalex.org/W2157539385","https://openalex.org/W2170551349","https://openalex.org/W2516234899","https://openalex.org/W2565628225","https://openalex.org/W2575750030","https://openalex.org/W2607669908","https://openalex.org/W2788228074","https://openalex.org/W2912969461","https://openalex.org/W2929062889","https://openalex.org/W2950150251","https://openalex.org/W2952167528","https://openalex.org/W2953174564","https://openalex.org/W2953269649","https://openalex.org/W2953326935","https://openalex.org/W2986925300","https://openalex.org/W2991295831","https://openalex.org/W2992976869","https://openalex.org/W2994947320","https://openalex.org/W2994969834","https://openalex.org/W3019706413","https://openalex.org/W3037791019","https://openalex.org/W3182153657","https://openalex.org/W3186150326","https://openalex.org/W3196145281","https://openalex.org/W3199385470","https://openalex.org/W4244292587"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699"],"abstract_inverted_index":{"Long-read-only":[0],"bacterial":[1],"genome":[2],"assemblies":[3],"usually":[4],"contain":[5],"residual":[6],"errors,":[7,22],"most":[8,24],"commonly":[9],"homopolymer-length":[10],"errors.":[11],"Short-read":[12],"polishing":[13],"tools":[14],"can":[15],"use":[16],"short":[17],"reads":[18],"to":[19,42,62],"fix":[20,43],"these":[21],"but":[23],"rely":[25],"on":[26],"short-read":[27,48,56,104],"alignment":[28],"which":[29,58],"is":[30],"unreliable":[31],"in":[32,36,65,75,100],"repeat":[33,66],"regions.":[34],"Errors":[35],"such":[37],"regions":[38],"are":[39],"therefore":[40],"challenging":[41],"and":[44,81,84],"often":[45],"remain":[46],"after":[47],"polishing.":[49,91],"Here":[50],"we":[51],"introduce":[52],"Polypolish,":[53],"a":[54],"new":[55],"polisher":[57],"uses":[59],"all-per-read":[60],"alignments":[61],"repair":[63],"errors":[64,89],"sequences":[67],"that":[68],"other":[69,103],"polishers":[70],"cannot.":[71],"Polypolish":[72,99],"performed":[73],"well":[74],"benchmarking":[76],"tests":[77],"using":[78,98],"both":[79],"simulated":[80],"real":[82],"reads,":[83],"it":[85],"almost":[86],"never":[87],"introduced":[88],"during":[90],"The":[92],"best":[93],"results":[94],"were":[95],"achieved":[96],"by":[97],"combination":[101],"with":[102],"polishers.":[105]},"counts_by_year":[{"year":2026,"cited_by_count":63},{"year":2025,"cited_by_count":215},{"year":2024,"cited_by_count":219},{"year":2023,"cited_by_count":156},{"year":2022,"cited_by_count":42},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}