{"id":"https://openalex.org/W2731064643","doi":"https://doi.org/10.48550/arxiv.1707.01631","title":"MAGNET: Understanding and Improving the Accuracy of Genome Pre-Alignment Filtering","display_name":"MAGNET: Understanding and Improving the Accuracy of Genome Pre-Alignment Filtering","publication_year":2017,"publication_date":"2017-07-06","ids":{"openalex":"https://openalex.org/W2731064643","doi":"https://doi.org/10.48550/arxiv.1707.01631","mag":"2731064643"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1707.01631","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1707.01631","pdf_url":"https://arxiv.org/pdf/1707.01631","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1707.01631","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081055664","display_name":"Mohammed Alser","orcid":"https://orcid.org/0000-0002-6117-3701","observed_orcids":["https://orcid.org/0000-0002-6117-3701"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alser, Mohammed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050695684","display_name":"Onur Mutlu","orcid":"https://orcid.org/0000-0002-0075-2312","observed_orcids":["https://orcid.org/0000-0002-0075-2312"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mutlu, Onur","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5074885623","display_name":"Can Alkan","orcid":"https://orcid.org/0000-0002-5443-0706","observed_orcids":["https://orcid.org/0000-0002-5443-0706"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alkan, Can","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.6288999915122986,"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":0.6288999915122986,"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/T11269","display_name":"Algorithms and Data Compression","score":0.36059999465942383,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.005100000184029341,"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/edit-distance","display_name":"edit distance","score":0.9319999814033508},{"id":"https://openalex.org/keywords/read-mapping","display_name":"read mapping","score":0.8500000238418579},{"id":"https://openalex.org/keywords/map-accuracy","display_name":"map accuracy","score":0.5630000233650208},{"id":"https://openalex.org/keywords/next-generation-sequencing","display_name":"next-generation sequencing","score":0.7540000081062317},{"id":"https://openalex.org/keywords/magnets","display_name":"magnets","score":0.621999979019165}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8497151136398315},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7474494576454163},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.7054234743118286},{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.6633365750312805},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.637820303440094},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49434757232666016},{"id":"https://openalex.org/C2780365114","wikidata":"https://www.wikidata.org/wiki/Q169478","display_name":"MATLAB","level":2,"score":0.44891035556793213},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.43067994713783264},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36769944429397583},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32573604583740234},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.09343907237052917},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0798407793045044},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07362169027328491},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:1707.01631","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1707.01631","pdf_url":"https://arxiv.org/pdf/1707.01631","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"mag:2731064643","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1707.01631.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:repository.bilkent.edu.tr:11693/49418","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/11693/49418","pdf_url":null,"source":{"id":"https://openalex.org/S4306400079","display_name":"Bilkent University Institutional Repository (Bilkent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I168864056","host_organization_name":"Bilkent University","host_organization_lineage":["https://openalex.org/I168864056"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions on Internet Research","raw_type":"Article"},{"id":"doi:10.48550/arxiv.1707.01631","doi":"https://doi.org/10.48550/arxiv.1707.01631","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1707.01631","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1707.01631","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1707.01631","pdf_url":"https://arxiv.org/pdf/1707.01631","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2731064643.pdf","grobid_xml":"https://content.openalex.org/works/W2731064643.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W14085413","https://openalex.org/W1534435001","https://openalex.org/W1647671624","https://openalex.org/W2008627757","https://openalex.org/W2052601433","https://openalex.org/W2075996757","https://openalex.org/W2087064593","https://openalex.org/W2091193685","https://openalex.org/W2100751585","https://openalex.org/W2139747296"],"related_works":["https://openalex.org/W2121716038","https://openalex.org/W2906782946","https://openalex.org/W3092806318","https://openalex.org/W2560228154","https://openalex.org/W3177399774","https://openalex.org/W4247044463","https://openalex.org/W3103269557","https://openalex.org/W2025648894","https://openalex.org/W3213765778","https://openalex.org/W2749963622"],"abstract_inverted_index":{"In":[0,94],"the":[1,11,15,34,85,105,130],"era":[2],"of":[3,18,26,30,132,140,145],"high":[4,68,117],"throughput":[5],"DNA":[6],"sequencing":[7],"(HTS)":[8],"technologies,":[9],"calculating":[10],"edit":[12,121],"distance":[13,44,122],"(i.e.,":[14],"minimum":[16],"number":[17],"substitutions,":[19],"insertions,":[20],"and":[21,88,124,147,152],"deletions":[22],"between":[23],"a":[24,48,90,111],"pair":[25],"sequences)":[27],"for":[28],"billions":[29],"genomic":[31],"sequences":[32],"is":[33],"computational":[35,92],"bottleneck":[36],"in":[37,70],"todays":[38],"read":[39],"mappers.":[40],"The":[41,142],"shifted":[42],"Hamming":[43],"(SHD)":[45],"algorithm":[46],"proposes":[47],"fast":[49],"filtering":[50,72,106,113,134],"strategy":[51,114],"that":[52,59,102,115],"can":[53],"rapidly":[54],"filter":[55],"out":[56],"invalid":[57,75],"mappings":[58,76],"have":[60],"more":[61],"edits":[62],"than":[63],"allowed.":[64],"However,":[65],"SHD":[66,148],"shows":[67],"inaccuracy":[69],"its":[71],"by":[73,135],"admitting":[74],"to":[77,104,137],"be":[78],"marked":[79],"as":[80],"correct":[81],"ones.":[82],"This":[83],"wastes":[84],"execution":[86],"time":[87],"imposes":[89],"large":[91],"burden.":[93],"this":[95],"work,":[96],"we":[97],"comprehensively":[98],"investigate":[99],"four":[100],"sources":[101],"lead":[103],"inaccuracy.":[107],"We":[108],"propose":[109],"MAGNET,":[110],"new":[112],"maintains":[116],"accuracy":[118,131],"across":[119],"different":[120],"thresholds":[123],"data":[125],"sets.":[126],"It":[127],"significantly":[128],"improves":[129],"pre-alignment":[133],"one":[136],"two":[138],"orders":[139],"magnitude.":[141],"MATLAB":[143],"implementations":[144],"MAGNET":[146],"are":[149],"open":[150],"source":[151],"available":[153],"at:":[154],"https://github.com/BilkentCompGen/MAGNET.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2017-07-14T00:00:00"}
