{"id":"https://openalex.org/W2775303078","doi":"https://doi.org/10.1109/bibm.2017.8217657","title":"Probabilistic estimation of overlap graphs for large sequence datasets","display_name":"Probabilistic estimation of overlap graphs for large sequence datasets","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2775303078","doi":"https://doi.org/10.1109/bibm.2017.8217657","mag":"2775303078"},"language":"en","primary_location":{"id":"doi:10.1109/bibm.2017.8217657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2017.8217657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","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/A5090757326","display_name":"Rahul Nihalani","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rahul Nihalani","raw_affiliation_strings":["College of Computing, Georgia Institute of Technology, Atlanta, USA"],"affiliations":[{"raw_affiliation_string":"College of Computing, Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070968071","display_name":"Sriram P. Chockalingam","orcid":"https://orcid.org/0000-0003-1358-7691"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sriram P Chockalingam","raw_affiliation_strings":["College of Computing, Georgia Institute of Technology, Atlanta, USA"],"affiliations":[{"raw_affiliation_string":"College of Computing, Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086744035","display_name":"Shaowei Zhu","orcid":"https://orcid.org/0000-0002-0335-1151"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaowei Zhu","raw_affiliation_strings":["College of Computing, Georgia Institute of Technology, Atlanta, USA"],"affiliations":[{"raw_affiliation_string":"College of Computing, Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007368382","display_name":"Vijay V. Vazirani","orcid":"https://orcid.org/0000-0002-4106-9077"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay Vazirani","raw_affiliation_strings":["College of Computing, Georgia Institute of Technology, Atlanta, USA"],"affiliations":[{"raw_affiliation_string":"College of Computing, Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074347913","display_name":"Srinivas Aluru","orcid":"https://orcid.org/0000-0003-4279-469X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srinivas Aluru","raw_affiliation_strings":["College of Computing, Georgia Institute of Technology, Atlanta, USA"],"affiliations":[{"raw_affiliation_string":"College of Computing, Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5090757326"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14837511,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"247","last_page":"252"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9990000128746033,"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":0.9990000128746033,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9987000226974487,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9966999888420105,"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":0.6574162244796753},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5100956559181213},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.42704224586486816},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21446272730827332}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6574162244796753},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5100956559181213},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42704224586486816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21446272730827332}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm.2017.8217657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2017.8217657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1579534339","https://openalex.org/W1596818353","https://openalex.org/W1635391495","https://openalex.org/W1993399552","https://openalex.org/W2023911006","https://openalex.org/W2081193615","https://openalex.org/W2127651281","https://openalex.org/W2128114769","https://openalex.org/W2140437680","https://openalex.org/W2144662851","https://openalex.org/W2152565070","https://openalex.org/W2166265186","https://openalex.org/W2171475724","https://openalex.org/W2194172909","https://openalex.org/W2532403383","https://openalex.org/W2557391416","https://openalex.org/W2566610827","https://openalex.org/W6670726752"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W1497573972","https://openalex.org/W2071659383","https://openalex.org/W1846253165"],"abstract_inverted_index":{"Sequence":[0],"overlap":[1,41,61,85,102],"graphs,":[2],"constructed":[3],"based":[4,55],"on":[5,70,80],"suffix-prefix":[6],"relationships":[7],"between":[8],"pairs":[9],"of":[10,40,73,83,95],"sequences,":[11,75],"are":[12],"an":[13],"important":[14],"data":[15],"structure":[16],"in":[17,33],"computational":[18],"biology.":[19],"High":[20],"throughput":[21],"sequencers":[22],"can":[23],"read":[24],"several":[25],"million":[26],"to":[27,59],"a":[28,34,52],"few":[29],"billion":[30],"DNA":[31],"fragments":[32],"single":[35],"experiment,":[36],"making":[37],"the":[38,71,81,84,91],"construction":[39],"graphs":[42,62,86,103],"for":[43,63],"such":[44],"datasets":[45,105],"compute-intensive.":[46],"In":[47],"this":[48],"paper,":[49],"we":[50,76],"present":[51],"Locality-Sensitive":[53],"Hashing":[54],"parallel":[56],"heuristic":[57],"algorithm":[58],"construct":[60],"large":[64,112],"genomic":[65],"datasets.":[66],"With":[67],"reasonable":[68],"assumptions":[69],"characteristics":[72],"input":[74],"establish":[77],"probabilistic":[78],"bounds":[79],"quality":[82],"so":[87],"produced.":[88],"We":[89],"demonstrate":[90],"validity":[92],"and":[93,111],"efficiency":[94],"our":[96],"approach":[97],"by":[98],"comparing":[99],"against":[100],"true":[101],"using":[104],"derived":[106],"from":[107],"small":[108],"(E.":[109],"coli)":[110],"(H.":[113],"sapiens)":[114],"genomes.":[115]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
