{"id":"https://openalex.org/W2108993741","doi":"https://doi.org/10.1109/icdew.2008.4498343","title":"Approximate similarity search in genomic sequence databases using landmark-guided embedding","display_name":"Approximate similarity search in genomic sequence databases using landmark-guided embedding","publication_year":2008,"publication_date":"2008-04-01","ids":{"openalex":"https://openalex.org/W2108993741","doi":"https://doi.org/10.1109/icdew.2008.4498343","mag":"2108993741"},"language":"en","primary_location":{"id":"doi:10.1109/icdew.2008.4498343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdew.2008.4498343","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE 24th International Conference on Data Engineering Workshop","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/11511/45983","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016398897","display_name":"Ahmet Sa\u00e7an","orcid":"https://orcid.org/0000-0002-3570-3270"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmet Sacan","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","Ohio State Univ., Columbus#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Ohio State Univ., Columbus#TAB#","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039253696","display_name":"\u0130smail Hakk\u0131 Toroslu","orcid":"https://orcid.org/0000-0002-4524-8232"},"institutions":[{"id":"https://openalex.org/I201799495","display_name":"Middle East Technical University","ror":"https://ror.org/014weej12","country_code":"TR","type":"education","lineage":["https://openalex.org/I201799495"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"I. Hakki Toroslu","raw_affiliation_strings":["Computer Engineering Department, Middle East Technical University, Ankara, Turkey","[Computer. Eng. Dept., Middle East Technical University, Ankara, Turkey]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Engineering Department, Middle East Technical University, Ankara, Turkey","institution_ids":["https://openalex.org/I201799495"]},{"raw_affiliation_string":"[Computer. Eng. Dept., Middle East Technical University, Ankara, Turkey]","institution_ids":["https://openalex.org/I201799495"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7561,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69279369,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"17","issue":null,"first_page":"338","last_page":"345"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9986000061035156,"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":0.9986000061035156,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.8233124613761902},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6722239255905151},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6564754843711853},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6520984172821045},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6248096227645874},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6239330768585205},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.503267228603363},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.49049848318099976},{"id":"https://openalex.org/keywords/similitude","display_name":"Similitude","score":0.4224269390106201},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3872528076171875},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3429660201072693},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3270591199398041},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2750508189201355}],"concepts":[{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.8233124613761902},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6722239255905151},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6564754843711853},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6520984172821045},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6248096227645874},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6239330768585205},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.503267228603363},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.49049848318099976},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.4224269390106201},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3872528076171875},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3429660201072693},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3270591199398041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2750508189201355},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icdew.2008.4498343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdew.2008.4498343","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE 24th International Conference on Data Engineering Workshop","raw_type":"proceedings-article"},{"id":"pmh:oai:open.metu.edu.tr:11511/45983","is_oa":true,"landing_page_url":"https://hdl.handle.net/11511/45983","pdf_url":null,"source":{"id":"https://openalex.org/S4306402495","display_name":"OpenMETU (Middle East Technical University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I201799495","host_organization_name":"Middle East Technical University","host_organization_lineage":["https://openalex.org/I201799495"],"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":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:open.metu.edu.tr:11511/45983","is_oa":true,"landing_page_url":"https://hdl.handle.net/11511/45983","pdf_url":null,"source":{"id":"https://openalex.org/S4306402495","display_name":"OpenMETU (Middle East Technical University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I201799495","host_organization_name":"Middle East Technical University","host_organization_lineage":["https://openalex.org/I201799495"],"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":"","raw_type":"Conference Paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W938539187","https://openalex.org/W1523134890","https://openalex.org/W1930315378","https://openalex.org/W1973264045","https://openalex.org/W1977618577","https://openalex.org/W1990061958","https://openalex.org/W2042786254","https://openalex.org/W2045435890","https://openalex.org/W2055043387","https://openalex.org/W2056930330","https://openalex.org/W2061959470","https://openalex.org/W2087064593","https://openalex.org/W2097042476","https://openalex.org/W2103487267","https://openalex.org/W2118269922","https://openalex.org/W2128591967","https://openalex.org/W2130956021","https://openalex.org/W2131239524","https://openalex.org/W2131620262","https://openalex.org/W2134312057","https://openalex.org/W2144668146","https://openalex.org/W2151135734","https://openalex.org/W2154931799","https://openalex.org/W2156287497","https://openalex.org/W2157092487","https://openalex.org/W2161656301","https://openalex.org/W2162102353","https://openalex.org/W2167081989","https://openalex.org/W2238624099","https://openalex.org/W2975800720","https://openalex.org/W2997027240","https://openalex.org/W4236236547","https://openalex.org/W4248987599","https://openalex.org/W4254811854","https://openalex.org/W6629169928","https://openalex.org/W6631163696","https://openalex.org/W6682887809","https://openalex.org/W6682969285"],"related_works":["https://openalex.org/W2323025356","https://openalex.org/W2342977227","https://openalex.org/W3033216323","https://openalex.org/W4376875328","https://openalex.org/W3107710733","https://openalex.org/W1949910768","https://openalex.org/W1480566255","https://openalex.org/W2254397067","https://openalex.org/W2013685631","https://openalex.org/W1882921205"],"abstract_inverted_index":{"Similarity":[0],"search":[1,21,105,114],"in":[2,9,24,30,54,58,103],"sequence":[3],"databases":[4,18,26],"is":[5,84,94],"of":[6,15,22,38,71,100],"paramount":[7],"importance":[8],"bioinformatics":[10],"research.":[11],"As":[12],"the":[13,16,55,72,77,81,108],"size":[14],"genomic":[17],"increases,":[19],"similarity":[20,65,104],"proteins":[23],"these":[25],"becomes":[27],"a":[28,46],"bottle-neck":[29],"large-scale":[31],"studies,":[32],"calling":[33],"for":[34],"more":[35],"efficient":[36,62],"methods":[37],"content-based":[39],"retrieval.":[40],"In":[41],"this":[42],"study,":[43],"we":[44],"present":[45],"metric-preserving,":[47],"landmark-guided":[48],"embedding":[49,73],"approach":[50],"to":[51,60,86,96,107],"represent":[52],"sequences":[53],"vector":[56],"domain":[57],"order":[59],"allow":[61],"indexing":[63],"and":[64,74],"search.":[66],"We":[67],"analyze":[68],"various":[69],"properties":[70],"show":[75],"that":[76],"approximation":[78],"achieved":[79],"by":[80],"embedded":[82],"representation":[83,93],"sufficient":[85],"achieve":[87],"biologically":[88],"relevant":[89],"results.":[90],"The":[91],"approximate":[92],"shown":[95],"provide":[97],"several":[98],"orders":[99],"magnitude":[101],"speed-up":[102],"compared":[106],"exact":[109],"representation,":[110],"while":[111],"maintaining":[112],"comparable":[113],"accuracy.":[115]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}