{"id":"https://openalex.org/W4412628284","doi":"https://doi.org/10.1093/bioinformatics/btaf418","title":"Efficient seeding for error-prone sequences with SubseqHash2","display_name":"Efficient seeding for error-prone sequences with SubseqHash2","publication_year":2025,"publication_date":"2025-07-23","ids":{"openalex":"https://openalex.org/W4412628284","doi":"https://doi.org/10.1093/bioinformatics/btaf418","pmid":"https://pubmed.ncbi.nlm.nih.gov/40705438"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaf418","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf418","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf418/63841215/btaf418.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"gold","oa_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf418/63841215/btaf418.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100432200","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0001-8499-4740"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiang Li","raw_affiliation_strings":["Department of Computer Science and Engineering, The Pennsylvania State University , Pennsylvania, PA 16802,","Department of Computer Science and Engineering, The Pennsylvania State University, Pennsylvania, PA 16802, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University , Pennsylvania, PA 16802,","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University, Pennsylvania, PA 16802, United States","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ke Chen","orcid":"https://orcid.org/0000-0001-5470-6621"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Chen","raw_affiliation_strings":["Department of Computer Science and Engineering, The Pennsylvania State University , Pennsylvania, PA 16802,","Department of Computer Science and Engineering, The Pennsylvania State University, Pennsylvania, PA 16802, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University , Pennsylvania, PA 16802,","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University, Pennsylvania, PA 16802, United States","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052979637","display_name":"Mingfu Shao","orcid":"https://orcid.org/0000-0001-6112-5139"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingfu Shao","raw_affiliation_strings":["Department of Computer Science and Engineering, The Pennsylvania State University , Pennsylvania, PA 16802,","Huck Institutes of the Life Sciences, The Pennsylvania State University , Pennsylvania, PA 16802,","Huck Institutes of the Life Sciences, The Pennsylvania State University, Pennsylvania, PA 16802, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University , Pennsylvania, PA 16802,","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Huck Institutes of the Life Sciences, The Pennsylvania State University , Pennsylvania, PA 16802,","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Huck Institutes of the Life Sciences, The Pennsylvania State University, Pennsylvania, PA 16802, United States","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100432200"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":2.3431,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90127457,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"41","issue":"8","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.995199978351593,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.995199978351593,"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/T11247","display_name":"Plant nutrient uptake and metabolism","score":0.9948999881744385,"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/T10494","display_name":"Plant Virus Research Studies","score":0.9904000163078308,"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/substring","display_name":"Substring","score":0.9520152807235718},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7388210892677307},{"id":"https://openalex.org/keywords/subsequence","display_name":"Subsequence","score":0.683302640914917},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6453731060028076},{"id":"https://openalex.org/keywords/seeding","display_name":"Seeding","score":0.6420496702194214},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6409841775894165},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5258883833885193},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.5115426778793335},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4765608608722687},{"id":"https://openalex.org/keywords/longest-increasing-subsequence","display_name":"Longest increasing subsequence","score":0.4267118573188782},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2829411029815674},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2503938674926758},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.23469996452331543}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.9520152807235718},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7388210892677307},{"id":"https://openalex.org/C137877099","wikidata":"https://www.wikidata.org/wiki/Q1332977","display_name":"Subsequence","level":3,"score":0.683302640914917},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6453731060028076},{"id":"https://openalex.org/C36248471","wikidata":"https://www.wikidata.org/wiki/Q7445669","display_name":"Seeding","level":2,"score":0.6420496702194214},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6409841775894165},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5258883833885193},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.5115426778793335},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4765608608722687},{"id":"https://openalex.org/C170006305","wikidata":"https://www.wikidata.org/wiki/Q4183855","display_name":"Longest increasing subsequence","level":4,"score":0.4267118573188782},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2829411029815674},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2503938674926758},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.23469996452331543},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","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},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":"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":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btaf418","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf418","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf418/63841215/btaf418.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:40705438","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40705438","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:pubmedcentral.nih.gov:12317743","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12317743","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btaf418","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf418","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf418/63841215/btaf418.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1877879165","display_name":null,"funder_award_id":"2145171","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4477481506","display_name":null,"funder_award_id":"R01HG011065","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6827177365","display_name":null,"funder_award_id":"2019797","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","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"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412628284.pdf","grobid_xml":"https://content.openalex.org/works/W4412628284.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2017265532","https://openalex.org/W2055043387","https://openalex.org/W2058415829","https://openalex.org/W2111295912","https://openalex.org/W2128591967","https://openalex.org/W2131702282","https://openalex.org/W2144560237","https://openalex.org/W2175671778","https://openalex.org/W2416529140","https://openalex.org/W2789843538","https://openalex.org/W2950354111","https://openalex.org/W2950572599","https://openalex.org/W2961460076","https://openalex.org/W3016766662","https://openalex.org/W3047598142","https://openalex.org/W3049406222","https://openalex.org/W3128964673","https://openalex.org/W3206657624","https://openalex.org/W4310786235","https://openalex.org/W4311803917","https://openalex.org/W4361298788","https://openalex.org/W4377245286","https://openalex.org/W4382632048"],"related_works":["https://openalex.org/W4205474360","https://openalex.org/W2969919693","https://openalex.org/W3122601395","https://openalex.org/W2125120904","https://openalex.org/W4390923554","https://openalex.org/W2035123411","https://openalex.org/W2112772040","https://openalex.org/W4389489786","https://openalex.org/W4385963882","https://openalex.org/W1540010783"],"abstract_inverted_index":{"SubseqHash2":[0],"is":[1],"available":[2],"at":[3],"https://github.com/Shao-Group/SubseqHash2":[4],"and":[5],"have":[6],"also":[7],"been":[8],"archived":[9],"on":[10],"Software":[11],"Heritage":[12],"(swh:1:dir:86738fc4b919eb6a9a26f7f533c25eb69f9a96d5).":[13]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
