{"id":"https://openalex.org/W2145021682","doi":"https://doi.org/10.14778/2367502.2367534","title":"Massive genomic data processing and deep analysis","display_name":"Massive genomic data processing and deep analysis","publication_year":2012,"publication_date":"2012-08-01","ids":{"openalex":"https://openalex.org/W2145021682","doi":"https://doi.org/10.14778/2367502.2367534","mag":"2145021682"},"language":"en","primary_location":{"id":"doi:10.14778/2367502.2367534","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2367502.2367534","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5102756987","display_name":"Abhishek Roy","orcid":"https://orcid.org/0009-0002-3569-7621"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhishek Roy","raw_affiliation_strings":["University of Massachusetts, Amherst","University of Massachusetts: Amherst#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts: Amherst#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109548832","display_name":"Yanlei Diao","orcid":"https://orcid.org/0009-0000-7793-9671"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanlei Diao","raw_affiliation_strings":["University of Massachusetts, Amherst","University of Massachusetts: Amherst#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts: Amherst#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111906486","display_name":"Evan Mauceli","orcid":null},"institutions":[{"id":"https://openalex.org/I1288882113","display_name":"Boston Children's Hospital","ror":"https://ror.org/00dvg7y05","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1288882113"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evan Mauceli","raw_affiliation_strings":["Harvard Medical School &amp; Children's Hospital Boston","Harvard Medical School and Children's Hospital Boston#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard Medical School &amp; Children's Hospital Boston","institution_ids":["https://openalex.org/I1288882113","https://openalex.org/I136199984"]},{"raw_affiliation_string":"Harvard Medical School and Children's Hospital Boston#TAB#","institution_ids":["https://openalex.org/I1288882113"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053509144","display_name":"Yiping Shen","orcid":"https://orcid.org/0000-0001-5820-0839"},"institutions":[{"id":"https://openalex.org/I1288882113","display_name":"Boston Children's Hospital","ror":"https://ror.org/00dvg7y05","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1288882113"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiping Shen","raw_affiliation_strings":["Harvard Medical School &amp; Children's Hospital Boston","Harvard Medical School and Children's Hospital Boston#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard Medical School &amp; Children's Hospital Boston","institution_ids":["https://openalex.org/I1288882113","https://openalex.org/I136199984"]},{"raw_affiliation_string":"Harvard Medical School and Children's Hospital Boston#TAB#","institution_ids":["https://openalex.org/I1288882113"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015149676","display_name":"Bai-Lin Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I1288882113","display_name":"Boston Children's Hospital","ror":"https://ror.org/00dvg7y05","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1288882113"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bai-Lin Wu","raw_affiliation_strings":["Harvard Medical School &amp; Children's Hospital Boston","Harvard Medical School and Children's Hospital Boston#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard Medical School &amp; Children's Hospital Boston","institution_ids":["https://openalex.org/I1288882113","https://openalex.org/I136199984"]},{"raw_affiliation_string":"Harvard Medical School and Children's Hospital Boston#TAB#","institution_ids":["https://openalex.org/I1288882113"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2648,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.58663274,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"5","issue":"12","first_page":"1906","last_page":"1909"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9980000257492065,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9883999824523926,"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/terabyte","display_name":"Terabyte","score":0.8236905932426453},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7887662649154663},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7692995071411133},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.5636120438575745},{"id":"https://openalex.org/keywords/data-processing","display_name":"Data processing","score":0.5584713816642761},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.44776472449302673},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4458509087562561},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42641910910606384},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4156271517276764},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33690541982650757},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20574328303337097},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09536212682723999},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.087592214345932}],"concepts":[{"id":"https://openalex.org/C199683683","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Terabyte","level":2,"score":0.8236905932426453},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7887662649154663},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7692995071411133},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.5636120438575745},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.5584713816642761},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.44776472449302673},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4458509087562561},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42641910910606384},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4156271517276764},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33690541982650757},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20574328303337097},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09536212682723999},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.087592214345932},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"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/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.14778/2367502.2367534","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2367502.2367534","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.294.2871","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.294.2871","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://vldb.org/pvldb/vol5/p1906_abhishekroy_vldb2012.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.304.5344","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.304.5344","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.umass.edu/%7Eyanlei/publications/genomic-vldb12.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1984606279","https://openalex.org/W1990073900","https://openalex.org/W2063220786","https://openalex.org/W2091178934","https://openalex.org/W2103441770","https://openalex.org/W2105821863","https://openalex.org/W2110796598","https://openalex.org/W2112099725","https://openalex.org/W2124985265","https://openalex.org/W2143307936","https://openalex.org/W2168133698"],"related_works":["https://openalex.org/W3138818610","https://openalex.org/W2084395052","https://openalex.org/W2006196966","https://openalex.org/W2792375448","https://openalex.org/W2276618304","https://openalex.org/W3033117735","https://openalex.org/W3024941504","https://openalex.org/W2034771340","https://openalex.org/W2746208547","https://openalex.org/W646678958"],"abstract_inverted_index":{"Today":[0],"large":[1],"sequencing":[2],"centers":[3],"are":[4],"producing":[5],"genomic":[6,43,82],"data":[7,27,67,83,88],"at":[8],"the":[9,76,91,93,104],"rate":[10],"of":[11,24,42,47,61,87,95,106],"10":[12],"terabytes":[13],"a":[14,37,59],"day":[15],"and":[16,53,69,111,114],"require":[17],"complicated":[18],"processing":[19,41,71],"to":[20,65,84],"transform":[21],"massive":[22],"amounts":[23],"noisy":[25],"raw":[26],"into":[28],"biological":[29],"information.":[30],"To":[31],"address":[32],"these":[33],"needs,":[34],"we":[35,78],"develop":[36],"system":[38],"for":[39,73,99],"end-to-end":[40],"data,":[44],"including":[45],"alignment":[46],"short":[48],"read":[49],"sequences,":[50],"variation":[51],"discovery,":[52],"deep":[54],"analysis.":[55],"We":[56],"also":[57],"employ":[58],"range":[60],"quality":[62,68,108],"control":[63,109],"mechanisms":[64,110],"improve":[66],"parallel":[70],"techniques":[72],"performance.":[74],"In":[75],"demo,":[77],"will":[79],"use":[80,100],"real":[81],"show":[85],"details":[86],"transformation":[89],"through":[90],"workflow,":[92],"usefulness":[94],"end":[96],"results":[97],"(ready":[98],"as":[101],"testable":[102],"hypotheses),":[103],"effects":[105],"our":[107],"improved":[112],"algorithms,":[113],"finally":[115],"performance":[116],"improvement.":[117]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
