{"id":"https://openalex.org/W7204958692","doi":"https://doi.org/10.48550/arxiv.2608.31004","title":"Storage-Centric System Designs for Enabling Fast, Efficient, and Low-Cost Genomic and Metagenomic Analyses","display_name":"Storage-Centric System Designs for Enabling Fast, Efficient, and Low-Cost Genomic and Metagenomic Analyses","publication_year":2026,"publication_date":"2026-08-31","ids":{"openalex":"https://openalex.org/W7204958692","doi":"https://doi.org/10.48550/arxiv.2608.31004"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.31004","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.31004","pdf_url":"https://arxiv.org/pdf/2608.31004","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.31004","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048764555","display_name":"Nika Mansouri Ghiasi","orcid":"https://orcid.org/0000-0002-0833-0042","observed_orcids":["https://orcid.org/0000-0002-0833-0042"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ghiasi, Nika Mansouri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5048764555"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.7875999808311462,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.7875999808311462,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.10209999978542328,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.019500000402331352,"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/genomic-data-analysis","display_name":"genomic data analysis","score":0.7820000052452087},{"id":"https://openalex.org/keywords/metagenomic-analysis","display_name":"metagenomic analysis","score":0.8650000095367432},{"id":"https://openalex.org/keywords/data-movement-bottleneck","display_name":"data movement bottleneck","score":0.7879999876022339},{"id":"https://openalex.org/keywords/energy-efficiency","display_name":"energy efficiency","score":0.8619999885559082},{"id":"https://openalex.org/keywords/cost-efficiency","display_name":"cost efficiency","score":0.7979999780654907}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8779000043869019},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.8016999959945679},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.609000027179718},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5102999806404114},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4830000102519989},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46639999747276306},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.3361999988555908},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.32580000162124634},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.28929999470710754},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.26350000500679016},{"id":"https://openalex.org/C31352089","wikidata":"https://www.wikidata.org/wiki/Q3750474","display_name":"Systems design","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.31004","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.31004","pdf_url":"https://arxiv.org/pdf/2608.31004","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.31004","doi":"https://doi.org/10.48550/arxiv.2608.31004","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.31004","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.31004","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.31004","pdf_url":"https://arxiv.org/pdf/2608.31004","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204958692.pdf","grobid_xml":"https://content.openalex.org/works/W7204958692.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2540062405","https://openalex.org/W2559524942","https://openalex.org/W2802845473","https://openalex.org/W2945839280","https://openalex.org/W3134295251","https://openalex.org/W3135001592","https://openalex.org/W4248987559","https://openalex.org/W4285121610","https://openalex.org/W4289827499","https://openalex.org/W4301607055","https://openalex.org/W4306799995","https://openalex.org/W4405717915","https://openalex.org/W4416083409","https://openalex.org/W7083830937"],"related_works":["https://openalex.org/W7167747395","https://openalex.org/W4388927910","https://openalex.org/W4401212125","https://openalex.org/W2599842690","https://openalex.org/W2626931021","https://openalex.org/W7133486229","https://openalex.org/W4221149933","https://openalex.org/W2612162942","https://openalex.org/W2085522429","https://openalex.org/W2181510079"],"abstract_inverted_index":{"Genomic":[0],"and":[1,30,39,45,58,80,102,112,127,149,154,169,184,207,218,228],"metagenomic":[2,46],"analyses":[3,57,206],"play":[4],"critical":[5],"roles":[6],"in":[7,75,197],"many":[8],"fields,":[9],"such":[10],"as":[11],"precision":[12],"medicine,":[13],"urgent":[14],"clinical":[15],"settings,":[16],"discovering":[17],"early":[18],"warnings":[19],"of":[20,37,43,66,97,109,157,165,187,204,220],"communicable":[21],"diseases,":[22],"ensuring":[23],"food":[24],"safety":[25],"through":[26],"pathogen":[27],"monitoring,":[28],"agriculture,":[29],"scientific":[31],"discovery.":[32],"Due":[33],"to":[34,54,83,93,123,211,226],"the":[35,64,84,88,103,107,110,114,146,163,175,193,201,214],"challenges":[36],"analyzing":[38],"storing":[40],"massive":[41],"volumes":[42],"genomic":[44],"sequence":[47,60,78,120,159],"data,":[48,160],"significant":[49],"efforts":[50],"have":[51],"been":[52],"made":[53],"accelerate":[55],"(meta)genomic":[56,143,188,205],"store":[59],"data":[61,79,89,99,115,121,144,166,170],"compressed.":[62],"Despite":[63],"benefits":[65],"these":[67],"techniques,":[68],"we":[69,134],"identify":[70],"two":[71],"major":[72],"outstanding":[73],"problems":[74],"accessing":[76],"stored":[77],"supplying":[81],"it":[82],"analysis":[85],"units:":[86],"(i)":[87,141],"movement":[90],"bottleneck":[91],"due":[92],"moving":[94],"large":[95],"amounts":[96],"low-reuse":[98],"from":[100],"storage":[101,147,153],"unnecessary":[104],"burden":[105],"on":[106],"rest":[108],"system,":[111,148],"(ii)":[113,150],"preparation":[116],"bottleneck,":[117],"where":[118],"compressed":[119],"needs":[122],"be":[124],"first":[125],"decompressed":[126],"formatted":[128],"before":[129],"analysis.":[130,189],"In":[131],"this":[132,198],"dissertation,":[133],"present":[135],"customized":[136],"storage-centric":[137,194],"systems,":[138],"which":[139],"efficiently":[140],"analyze":[142],"inside":[145],"enable":[151],"highly-compressed":[152],"high-performance":[155],"access":[156],"large-scale":[158],"thereby":[161],"alleviating":[162],"overheads":[164],"movement,":[167],"computation,":[168],"preparation.":[171],"We":[172,190],"demonstrate":[173],"that":[174,192],"proposed":[176,196],"systems":[177,195],"significantly":[178],"improve":[179,213],"system":[180,185],"performance,":[181,215],"energy":[182,216],"efficiency,":[183,217],"cost-efficiency":[186],"hope":[191],"dissertation":[199],"facilitate":[200],"broader":[202],"adoption":[203],"inspire":[208],"future":[209],"research":[210],"fundamentally":[212],"cost-effectiveness":[219],"other":[221],"data-intensive":[222],"application":[223],"domains":[224],"related":[225],"health":[227],"life":[229],"sciences.":[230]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-02T00:00:00"}
