{"id":"https://openalex.org/W4409739223","doi":"https://doi.org/10.1007/978-3-031-90252-9_14","title":"Prokrustean Graph: A Substring Index for Rapid K-Mer Size Analysis","display_name":"Prokrustean Graph: A Substring Index for Rapid K-Mer Size Analysis","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409739223","doi":"https://doi.org/10.1007/978-3-031-90252-9_14","pmid":"https://pubmed.ncbi.nlm.nih.gov/38853857","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/11160577"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-90252-9_14","doi":"https://doi.org/10.1007/978-3-031-90252-9_14","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-90252-9_14","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","ki-jl-1","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"volume":{"id":"https://openalex.org/W4409739074","display_name":"Research in Computational Molecular Biology"},"type":"conference-paper","is_traditional":true,"indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2023/11/23/2023.11.21.568151.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038750229","display_name":"Adam Park","orcid":"https://orcid.org/0009-0003-4104-2960","observed_orcids":["https://orcid.org/0009-0003-4104-2960"]},"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":"Adam Park","raw_affiliation_strings":["Department of Computer Science and Engineering, The Pennsylvania State University, State College, PA, USA"],"raw_orcid":"https://orcid.org/0009-0003-4104-2960","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University, State College, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002668669","display_name":"David Koslicki","orcid":"https://orcid.org/0000-0002-0640-954X","observed_orcids":["https://orcid.org/0000-0002-0640-954X"]},"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":"David Koslicki","raw_affiliation_strings":["Department of Biology, The Pennsylvania State University, State College, PA, USA","Department of Computer Science and Engineering, The Pennsylvania State University, State College, PA, USA","Huck Institutes of the Life Sciences, The Pennsylvania State University, State College, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0640-954X","affiliations":[{"raw_affiliation_string":"Department of Biology, The Pennsylvania State University, State College, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University, State College, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Huck Institutes of the Life Sciences, The Pennsylvania State University, State College, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5002668669","https://openalex.org/A5038750229"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08957416,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"227","last_page":"249"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9804999828338623,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9804999828338623,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.018200000748038292,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.0006000000284984708,"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/k-mer-size","display_name":"k-mer size","score":0.8190000057220459},{"id":"https://openalex.org/keywords/de-bruijn-graph","display_name":"de Bruijn graph","score":0.9079999923706055},{"id":"https://openalex.org/keywords/burrows-wheeler-transform","display_name":"Burrows-Wheeler transform","score":0.8019999861717224},{"id":"https://openalex.org/keywords/pangenomics","display_name":"pangenomics","score":0.7720000147819519},{"id":"https://openalex.org/keywords/metagenomics","display_name":"metagenomics","score":1.0},{"id":"https://openalex.org/keywords/jaccard-similarity","display_name":"Jaccard similarity","score":0.8489999771118164},{"id":"https://openalex.org/keywords/bray-curtis-dissimilarity","display_name":"Bray-Curtis dissimilarity","score":0.9810000061988831},{"id":"https://openalex.org/keywords/genome-sequence-analysis","display_name":"genome sequence analysis","score":0.6549999713897705}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.8735533952713013},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7524263858795166},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5498967170715332},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.4111081063747406},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.355918288230896},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31780514121055603},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.1628386676311493},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09068131446838379}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1007/978-3-031-90252-9_14","doi":"https://doi.org/10.1007/978-3-031-90252-9_14","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-90252-9_14","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","ki-jl-1","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"doi:10.1101/2023.11.21.568151","doi":"https://doi.org/10.1101/2023.11.21.568151","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2023.11.21.568151","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2023/11/23/2023.11.21.568151.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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmid:38853857","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38853857","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":"bioRxiv : the preprint server for biology","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:11160577","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11160577","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11160577/pdf/nihpp-2023.11.21.568151v8.pdf","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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"Text"},{"id":"pmh:oai:scholarsphere.psu.edu:e16f46f8-2efc-472f-8eda-b641ec149020","doi":null,"is_oa":false,"landing_page_url":"https://scholarsphere.psu.edu/resources/15fd4d1e-9f73-4f8f-9f5c-7db3b8003970/downloads/55829","pdf_url":null,"source":{"id":"https://openalex.org/S4306401507","display_name":"ScholarSphere (Penn State Libraries)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I3130638595","host_organization_name":"Pangasinan State University","host_organization_lineage":["https://openalex.org/I3130638595"],"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":"Part Of Book"},{"id":"pmh:oai:scholarsphere.psu.edu:fdc38b87-6879-4be3-ad0b-0938effd6c48","doi":null,"is_oa":false,"landing_page_url":"https://scholarsphere.psu.edu/resources/3917bdb6-82d4-4849-b050-def61fd05102/downloads/42984","pdf_url":null,"source":{"id":"https://openalex.org/S4306401507","display_name":"ScholarSphere (Penn State Libraries)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I3130638595","host_organization_name":"Pangasinan State University","host_organization_lineage":["https://openalex.org/I3130638595"],"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":"Article"}],"best_oa_location":{"id":"doi:10.1101/2023.11.21.568151","doi":"https://doi.org/10.1101/2023.11.21.568151","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2023.11.21.568151","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2023/11/23/2023.11.21.568151.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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G9000871591","display_name":"Leveraging k-mer sketching statistics to enhance metagenomic methods and alignment algorithms","funder_award_id":"R01GM146462","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409739223.pdf","grobid_xml":"https://content.openalex.org/works/W4409739223.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W6247929","https://openalex.org/W1822485921","https://openalex.org/W1830741397","https://openalex.org/W1962019683","https://openalex.org/W1988110322","https://openalex.org/W1997401532","https://openalex.org/W2042175004","https://openalex.org/W2095498620","https://openalex.org/W2100673218","https://openalex.org/W2104677379","https://openalex.org/W2161048357","https://openalex.org/W2230749025","https://openalex.org/W2233603983","https://openalex.org/W2254734290","https://openalex.org/W2464014972","https://openalex.org/W2583363792","https://openalex.org/W2599417231","https://openalex.org/W2765284830","https://openalex.org/W2886623299","https://openalex.org/W2909615107","https://openalex.org/W2950150251","https://openalex.org/W2950964375","https://openalex.org/W2955507764","https://openalex.org/W2988734854","https://openalex.org/W2996751484","https://openalex.org/W2998959119","https://openalex.org/W3012094285","https://openalex.org/W3036135788","https://openalex.org/W3045315617","https://openalex.org/W3081912464","https://openalex.org/W3109999865","https://openalex.org/W3119507732","https://openalex.org/W3150463527","https://openalex.org/W3151743941","https://openalex.org/W3207938624","https://openalex.org/W3210714966","https://openalex.org/W3216842221","https://openalex.org/W4206102744","https://openalex.org/W4214573178","https://openalex.org/W4240302460","https://openalex.org/W4285196200","https://openalex.org/W4285494733","https://openalex.org/W4294908403","https://openalex.org/W4313643993","https://openalex.org/W4362661793","https://openalex.org/W4378783302","https://openalex.org/W4380084687","https://openalex.org/W4384833971","https://openalex.org/W4386258509","https://openalex.org/W4390988053","https://openalex.org/W4391451337","https://openalex.org/W4398770004"],"related_works":["https://openalex.org/W7117319255","https://openalex.org/W2913275746","https://openalex.org/W3018162653","https://openalex.org/W6891632473","https://openalex.org/W4387425043","https://openalex.org/W4402404871","https://openalex.org/W4226052879","https://openalex.org/W4416193244","https://openalex.org/W4391099685","https://openalex.org/W2120956621"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-04-24T00:00:00"}