{"id":"https://openalex.org/W4403587903","doi":"https://doi.org/10.1093/bioinformatics/btae629","title":"<i>k</i> -nonical space: sketching with reverse complements","display_name":"<i>k</i> -nonical space: sketching with reverse complements","publication_year":2024,"publication_date":"2024-10-17","ids":{"openalex":"https://openalex.org/W4403587903","doi":"https://doi.org/10.1093/bioinformatics/btae629","pmid":"https://pubmed.ncbi.nlm.nih.gov/39432565"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btae629","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae629","pdf_url":null,"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://doi.org/10.1093/bioinformatics/btae629","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009407234","display_name":"Guillaume Mar\u00e7ais","orcid":"https://orcid.org/0000-0002-5083-5925"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Guillaume Mar\u00e7ais","raw_affiliation_strings":["Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University , Pittsburgh, PA 15213,","Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University, PA 15213, United States"],"raw_orcid":"https://orcid.org/0000-0002-5083-5925","affiliations":[{"raw_affiliation_string":"Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University , Pittsburgh, PA 15213,","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University, PA 15213, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037780559","display_name":"C.S. Elder","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C S Elder","raw_affiliation_strings":["Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University , Pittsburgh, PA 15213,","Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University, PA 15213, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University , Pittsburgh, PA 15213,","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University, PA 15213, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113653378","display_name":"Carl Kingsford","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carl Kingsford","raw_affiliation_strings":["Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University , Pittsburgh, PA 15213,","Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University, PA 15213, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University , Pittsburgh, PA 15213,","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University, PA 15213, United States","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009407234"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":1.3982,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81411512,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"40","issue":"11","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.32269999384880066,"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":0.32269999384880066,"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/T12029","display_name":"DNA and Biological Computing","score":0.13040000200271606,"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":0.10970000177621841,"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/computer-science","display_name":"Computer science","score":0.689347505569458},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6586829423904419},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6174466013908386},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5605916380882263},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.55115807056427},{"id":"https://openalex.org/keywords/folding","display_name":"Folding (DSP implementation)","score":0.5052033066749573},{"id":"https://openalex.org/keywords/reverse-engineering","display_name":"Reverse engineering","score":0.4614476263523102},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.46085304021835327},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4509503245353699},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4435870051383972},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.23546463251113892},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20995000004768372},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.0917515754699707}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.689347505569458},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6586829423904419},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6174466013908386},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5605916380882263},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.55115807056427},{"id":"https://openalex.org/C2776545253","wikidata":"https://www.wikidata.org/wiki/Q5464292","display_name":"Folding (DSP implementation)","level":2,"score":0.5052033066749573},{"id":"https://openalex.org/C207850805","wikidata":"https://www.wikidata.org/wiki/Q269608","display_name":"Reverse engineering","level":2,"score":0.4614476263523102},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.46085304021835327},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4509503245353699},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4435870051383972},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.23546463251113892},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20995000004768372},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0917515754699707},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical 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}],"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":"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":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":"D006801","descriptor_name":"Humans","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":"D006801","descriptor_name":"Humans","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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"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":"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":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","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":"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":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btae629","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae629","pdf_url":null,"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:39432565","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39432565","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:11549021","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11549021","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11549021/pdf/btae629.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,"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"},{"id":"pmh:oai:figshare.com:article/29951123","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"Journal contribution"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btae629","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae629","pdf_url":null,"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":[{"display_name":"Quality Education","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1310392732","display_name":null,"funder_award_id":"DBI-1937540","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3584959149","display_name":null,"funder_award_id":"R01 HG012470","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G3788099519","display_name":null,"funder_award_id":"R01HG012470","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3858817854","display_name":null,"funder_award_id":"III-2232121","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6667550415","display_name":"IIBR:Informatics:Toward an Automated RNA-seq Bioinformatician","funder_award_id":"1937540","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7686337660","display_name":null,"funder_award_id":"DBI-1937540","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8144893449","display_name":"III:Small: Expressiveness of Genome Graphs: Construction, Comparison, and Heterogeneity","funder_award_id":"2232121","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"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1553372930","https://openalex.org/W1980664567","https://openalex.org/W2010454899","https://openalex.org/W2060884261","https://openalex.org/W2064077828","https://openalex.org/W2066356146","https://openalex.org/W2144560237","https://openalex.org/W2159954944","https://openalex.org/W2194172909","https://openalex.org/W2763390627","https://openalex.org/W2789843538","https://openalex.org/W2937044610","https://openalex.org/W2950572599","https://openalex.org/W2951822379","https://openalex.org/W3016701095","https://openalex.org/W3043768949","https://openalex.org/W3128964673","https://openalex.org/W3182040180","https://openalex.org/W3200242814","https://openalex.org/W4225293672","https://openalex.org/W4243450674","https://openalex.org/W4307475426","https://openalex.org/W4321112378","https://openalex.org/W4385708519","https://openalex.org/W4386022705","https://openalex.org/W4386272000","https://openalex.org/W4386889019","https://openalex.org/W4386923678","https://openalex.org/W4388775333","https://openalex.org/W4388869936","https://openalex.org/W6948162331"],"related_works":["https://openalex.org/W2363831530","https://openalex.org/W2363845219","https://openalex.org/W2381057835","https://openalex.org/W1789649838","https://openalex.org/W1780668307","https://openalex.org/W1984362519","https://openalex.org/W2051831113","https://openalex.org/W2650054517","https://openalex.org/W2362738525","https://openalex.org/W1616281264"],"abstract_inverted_index":{"MOTIVATION:":[0],"Sequences":[1],"equivalent":[2],"to":[3,53,100,115,146,175,189,197],"their":[4],"reverse":[5,64],"complements":[6],"(i.e.":[7],"double-stranded":[8],"DNA)":[9],"have":[10],"no":[11],"analogue":[12],"in":[13,36,212],"text":[14],"analysis":[15,214],"and":[16,34,62,88,159,192],"non-biological":[17],"string":[18,42,111],"algorithms.":[19,43],"Despite":[20],"this":[21,213],"striking":[22],"difference,":[23],"algorithms":[24,50,112,148],"designed":[25,33,114],"for":[26,117,177,203],"computational":[27],"biology":[28],"(e.g.":[29],"sketching":[30,84,98,138,168,187,201],"algorithms)":[31],"are":[32,51,131],"tested":[35],"the":[37,80,102,127,165],"same":[38],"way":[39],"as":[40,45],"classical":[41],"Then,":[44],"a":[46,60,67,92,161,181,218],"post-processing":[47],"step,":[48,94],"these":[49,142,150,157,178],"adapted":[52],"work":[54],"with":[55,83,110],"genomic":[56,143],"sequences":[57],"by":[58,136],"folding":[59],"k-mer":[61],"its":[63],"complement":[65],"into":[66],"single":[68],"sequence:":[69],"The":[70,76,209],"canonical":[71,81,108],"representation":[72,82],"(k-nonical":[73],"space).":[74],"RESULTS:":[75],"effect":[77],"of":[78,106,126,167],"using":[79,107,149],"methods":[85,99,188,202],"is":[86,215],"understudied":[87],"not":[89,113],"understood.":[90],"As":[91],"first":[93],"we":[95,121,171],"use":[96],"context-free":[97,137],"illustrate":[101],"potentially":[103],"detrimental":[104],"effects":[105,158],"k-mers":[109],"accommodate":[116,176],"them.":[118],"In":[119],"particular,":[120],"show":[122],"that":[123,184],"large":[124],"stretches":[125],"genome":[128],"(\"sketching":[129],"deserts\")":[130],"undersampled":[132],"or":[133],"entirely":[134],"skipped":[135],"methods,":[139],"effectively":[140],"making":[141],"regions":[144],"invisible":[145],"subsequent":[147],"sketches.":[151],"We":[152],"provide":[153],"empirical":[154],"data":[155],"showing":[156],"develop":[160],"theoretical":[162],"framework":[163],"explaining":[164],"appearance":[166],"deserts.":[169],"Finally,":[170],"propose":[172],"two":[173],"schemes":[174],"effects:":[179],"(i)":[180],"new":[182,200],"procedure":[183,196],"adapts":[185],"existing":[186],"k-nonical":[190,204],"space":[191],"(ii)":[193],"an":[194],"optimization":[195],"directly":[198],"design":[199],"space.":[205],"AVAILABILITY":[206],"AND":[207],"IMPLEMENTATION:":[208],"code":[210],"used":[211],"available":[216],"under":[217],"permissive":[219],"license":[220],"at":[221],"https://github.com/Kingsford-Group/mdsscope.":[222]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-24T13:16:06.693445","created_date":"2024-10-21T00:00:00"}
