{"id":"https://openalex.org/W2770608691","doi":"https://doi.org/10.1109/iccabs.2017.8114318","title":"Efficient filtering algorithm for detection of genetic similarity between large genomic datasets","display_name":"Efficient filtering algorithm for detection of genetic similarity between large genomic datasets","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2770608691","doi":"https://doi.org/10.1109/iccabs.2017.8114318","mag":"2770608691"},"language":"en","primary_location":{"id":"doi:10.1109/iccabs.2017.8114318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccabs.2017.8114318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 7th International Conference on Computational Advances in Bio and Medical Sciences (ICCABS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041661925","display_name":"Viachaslau Tsyvina","orcid":"https://orcid.org/0000-0002-7230-4009"},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Viachaslau Tsyvina","raw_affiliation_strings":["Department of Computer Science, Georgia State University Atlanta, GA 30302"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Georgia State University Atlanta, GA 30302","institution_ids":["https://openalex.org/I181565077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018798814","display_name":"David S. Campo","orcid":"https://orcid.org/0000-0002-8970-3436"},"institutions":[{"id":"https://openalex.org/I1289490764","display_name":"Centers for Disease Control and Prevention","ror":"https://ror.org/042twtr12","country_code":"US","type":"funder","lineage":["https://openalex.org/I1289490764","https://openalex.org/I1299022934"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Campo","raw_affiliation_strings":["Molecular Epidemiology and Bioinformatics Laboratory, Division of Viral Hepatitis, Centers for Disease Control and Prevention, Atlanta, GA 30333"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Molecular Epidemiology and Bioinformatics Laboratory, Division of Viral Hepatitis, Centers for Disease Control and Prevention, Atlanta, GA 30333","institution_ids":["https://openalex.org/I1289490764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062028212","display_name":"Seth Sims","orcid":"https://orcid.org/0000-0003-2126-0197"},"institutions":[{"id":"https://openalex.org/I1289490764","display_name":"Centers for Disease Control and Prevention","ror":"https://ror.org/042twtr12","country_code":"US","type":"funder","lineage":["https://openalex.org/I1289490764","https://openalex.org/I1299022934"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seth Sims","raw_affiliation_strings":["Molecular Epidemiology and Bioinformatics Laboratory, Division of Viral Hepatitis, Centers for Disease Control and Prevention, Atlanta, GA 30333"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Molecular Epidemiology and Bioinformatics Laboratory, Division of Viral Hepatitis, Centers for Disease Control and Prevention, Atlanta, GA 30333","institution_ids":["https://openalex.org/I1289490764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072751459","display_name":"Alex Zelikovsky","orcid":"https://orcid.org/0000-0003-4424-4691"},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Zelikovsky","raw_affiliation_strings":["Department of Computer Science, Georgia State University Atlanta, GA 30302"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Georgia State University Atlanta, GA 30302","institution_ids":["https://openalex.org/I181565077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085435304","display_name":"Yury Khudyakov","orcid":null},"institutions":[{"id":"https://openalex.org/I1289490764","display_name":"Centers for Disease Control and Prevention","ror":"https://ror.org/042twtr12","country_code":"US","type":"funder","lineage":["https://openalex.org/I1289490764","https://openalex.org/I1299022934"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yury Khudyakov","raw_affiliation_strings":["Molecular Epidemiology and Bioinformatics Laboratory, Division of Viral Hepatitis, Centers for Disease Control and Prevention, Atlanta, GA 30333"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Molecular Epidemiology and Bioinformatics Laboratory, Division of Viral Hepatitis, Centers for Disease Control and Prevention, Atlanta, GA 30333","institution_ids":["https://openalex.org/I1289490764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052456631","display_name":"Pavel Skums","orcid":"https://orcid.org/0000-0003-4007-5624"},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pavel Skums","raw_affiliation_strings":["Department of Computer Science, Georgia State University Atlanta, GA 30302"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Georgia State University Atlanta, GA 30302","institution_ids":["https://openalex.org/I181565077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17688892,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9993000030517578,"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":0.9993000030517578,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9973999857902527,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9830999970436096,"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/similarity","display_name":"Similarity (geometry)","score":0.7165234088897705},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6189192533493042},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.5578140020370483},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5195186734199524},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43300533294677734},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.39602071046829224},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3772764801979065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3634681701660156},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34994828701019287},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.29211074113845825},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.16849815845489502},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.14250671863555908},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06578907370567322}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7165234088897705},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6189192533493042},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.5578140020370483},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5195186734199524},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43300533294677734},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.39602071046829224},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3772764801979065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3634681701660156},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34994828701019287},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.29211074113845825},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.16849815845489502},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.14250671863555908},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06578907370567322}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccabs.2017.8114318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccabs.2017.8114318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 7th International Conference on Computational Advances in Bio and Medical Sciences (ICCABS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2100548092","https://openalex.org/W2288266106","https://openalex.org/W2947255767"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2375480909","https://openalex.org/W2353314428","https://openalex.org/W2012019886","https://openalex.org/W2166090428","https://openalex.org/W2381021552","https://openalex.org/W2354749003","https://openalex.org/W2377121353","https://openalex.org/W2350529538","https://openalex.org/W2076713575"],"abstract_inverted_index":{"Many":[0],"biological":[1],"analysis":[2],"techniques":[3],"require":[4],"measurement":[5],"of":[6,18,21],"similarity":[7,37],"between":[8],"sequences":[9],"from":[10],"large":[11,40],"genomic":[12],"datasets,":[13],"which":[14],"often":[15],"involves":[16],"extraction":[17],"all":[19],"pairs":[20],"close":[22],"DNA":[23],"or":[24],"RNA":[25],"sequences.":[26],"We":[27],"present":[28],"a":[29],"k-mer-based":[30],"tool":[31],"to":[32],"efficiently":[33],"perform":[34],"such":[35],"sequence":[36],"queries":[38],"for":[39],"viral":[41],"datasets":[42],"produced":[43],"by":[44],"next-generation":[45],"sequencing.":[46]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}