{"id":"https://openalex.org/W2911264380","doi":"https://doi.org/10.1101/531681","title":"SLM-Transform: A Method for Memory-Efficient Indexing of Spectra for Database Search in LC-MS/MS Proteomics","display_name":"SLM-Transform: A Method for Memory-Efficient Indexing of Spectra for Database Search in LC-MS/MS Proteomics","publication_year":2019,"publication_date":"2019-01-27","ids":{"openalex":"https://openalex.org/W2911264380","doi":"https://doi.org/10.1101/531681","mag":"2911264380"},"language":"en","primary_location":{"id":"doi:10.1101/531681","doi":"https://doi.org/10.1101/531681","is_oa":true,"landing_page_url":"https://doi.org/10.1101/531681","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2019/01/27/531681.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2019/01/27/531681.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082182788","display_name":"Muhammad Haseeb","orcid":"https://orcid.org/0000-0002-0697-6894","observed_orcids":["https://orcid.org/0000-0002-0697-6894"]},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muhammad Haseeb","raw_affiliation_strings":["School of Computing and Information Sciences, Florida International University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Sciences, Florida International University","institution_ids":["https://openalex.org/I19700959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074495772","display_name":"Muaaz Gul Awan","orcid":"https://orcid.org/0000-0003-1233-1862","observed_orcids":["https://orcid.org/0000-0003-1233-1862"]},"institutions":[{"id":"https://openalex.org/I141649380","display_name":"Western Michigan University","ror":"https://ror.org/04j198w64","country_code":"US","type":"education","lineage":["https://openalex.org/I141649380"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muaaz G. Awan","raw_affiliation_strings":["Department of Computer Science, Western Michigan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Western Michigan University","institution_ids":["https://openalex.org/I141649380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041945533","display_name":"Alexander S. Cadigan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I48664048","display_name":"Kalamazoo College","ror":"https://ror.org/001qst305","country_code":"US","type":"education","lineage":["https://openalex.org/I48664048"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander S. Cadigan","raw_affiliation_strings":["Department of Computer Science, Kalamazoo College"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Kalamazoo College","institution_ids":["https://openalex.org/I48664048"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102729196","display_name":"Fahad Saeed","orcid":"https://orcid.org/0000-0002-3410-9552","observed_orcids":["https://orcid.org/0000-0002-3410-9552"]},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fahad Saeed","raw_affiliation_strings":["School of Computing and Information Sciences, Florida International University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Sciences, Florida International University","institution_ids":["https://openalex.org/I19700959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102729196"],"corresponding_institution_ids":["https://openalex.org/I19700959"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"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/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9556000232696533,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9556000232696533,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.02329999953508377,"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/T10683","display_name":"Mass Spectrometry Techniques and Applications","score":0.008299999870359898,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/memory-efficient-indexing","display_name":"memory-efficient indexing","score":0.6579999923706055},{"id":"https://openalex.org/keywords/peptide-identification","display_name":"peptide identification","score":0.675000011920929},{"id":"https://openalex.org/keywords/lc-ms-ms-proteomics","display_name":"LC-MS/MS proteomics","score":0.7570000290870667},{"id":"https://openalex.org/keywords/post-translational-modification","display_name":"post-translational modification","score":0.8500000238418579},{"id":"https://openalex.org/keywords/bottom-up-proteomics","display_name":"shotgun proteomics","score":0.5550000071525574}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7186765074729919},{"id":"https://openalex.org/C48000682","wikidata":"https://www.wikidata.org/wiki/Q5227411","display_name":"Database search engine","level":3,"score":0.7175174355506897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6056778430938721},{"id":"https://openalex.org/C59276292","wikidata":"https://www.wikidata.org/wiki/Q580427","display_name":"Database index","level":3,"score":0.5842037796974182},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5216223001480103},{"id":"https://openalex.org/C68289359","wikidata":"https://www.wikidata.org/wiki/Q7502514","display_name":"Shotgun proteomics","level":4,"score":0.4405691623687744},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4196314811706543},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.4074317216873169},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32693150639533997},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.30382055044174194},{"id":"https://openalex.org/C46111723","wikidata":"https://www.wikidata.org/wiki/Q471857","display_name":"Proteomics","level":3,"score":0.21725857257843018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14050781726837158},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.11148062348365784},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1101/531681","doi":"https://doi.org/10.1101/531681","is_oa":true,"landing_page_url":"https://doi.org/10.1101/531681","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2019/01/27/531681.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.1101/531681","doi":"https://doi.org/10.1101/531681","is_oa":true,"landing_page_url":"https://doi.org/10.1101/531681","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2019/01/27/531681.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1054929489","display_name":"CRII: SHF: HPC Solutions to Big NGS Data Compression","funder_award_id":"1464268","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1505391849","display_name":"CRII: SHF: HPC Solutions to Big NGS Data Compression","funder_award_id":"1855441","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1598728340","display_name":"CAREER: Towards Fast and Scalable Algorithms for Big Proteogenomics Data Analytics","funder_award_id":"1651724","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4667047073","display_name":"Parallel Algorithms for Big Data from Mass Spectrometry based Proteomics","funder_award_id":"R15GM120820","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2911264380.pdf","grobid_xml":"https://content.openalex.org/works/W2911264380.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1480858518","https://openalex.org/W1553575840","https://openalex.org/W1577446317","https://openalex.org/W1973051173","https://openalex.org/W1973333402","https://openalex.org/W1978275829","https://openalex.org/W1981593008","https://openalex.org/W1995062121","https://openalex.org/W2007176869","https://openalex.org/W2008117982","https://openalex.org/W2017636423","https://openalex.org/W2023655541","https://openalex.org/W2026465178","https://openalex.org/W2027974246","https://openalex.org/W2031764625","https://openalex.org/W2035283832","https://openalex.org/W2036321220","https://openalex.org/W2052388444","https://openalex.org/W2058135122","https://openalex.org/W2089273345","https://openalex.org/W2158874082","https://openalex.org/W2161488606","https://openalex.org/W2166041923","https://openalex.org/W2465480251","https://openalex.org/W2592973894","https://openalex.org/W2607310450","https://openalex.org/W2892321323","https://openalex.org/W2894727674","https://openalex.org/W2949580145"],"related_works":["https://openalex.org/W2607310450","https://openalex.org/W2031764625","https://openalex.org/W7099479863","https://openalex.org/W3004571255","https://openalex.org/W2155843164","https://openalex.org/W3025057718","https://openalex.org/W2122785579","https://openalex.org/W4401919263","https://openalex.org/W4315702991","https://openalex.org/W3005297831"],"abstract_inverted_index":{"Abstract":[0],"The":[1,134],"most":[2],"commonly":[3],"used":[4,138],"strategy":[5],"for":[6,74,163,225],"peptide":[7,28,231],"identification":[8],"in":[9,51,55,149],"shotgun":[10],"LC-MS/MS":[11],"proteomics":[12],"involves":[13],"searching":[14],"of":[15,58,68,101,118,130,147,155,176,202],"MS/MS":[16],"data":[17],"against":[18],"an":[19,52],"in-silico":[20],"digested":[21,27],"protein":[22],"sequence":[23],"database.":[24],"Typically,":[25],"the":[26,33,56,66,145,153,190,220],"sequences":[29],"are":[30,167],"indexed":[31,102,120,162],"into":[32],"memory":[34,62,192],"to":[35,44,92,143,178,212],"allow":[36,116],"faster":[37],"search":[38,187,232],"times.":[39],"However,":[40],"subjecting":[41],"a":[42,84,140],"database":[43,186],"post-translational":[45],"modifications":[46],"(PTMs)":[47],"during":[48],"digestion":[49],"results":[50,170],"exponential":[53],"increase":[54],"number":[57,154],"peptides":[59,180,206],"and":[60,96,158,161],"therefore":[61],"consumption.":[63],"This":[64],"limits":[65],"usage":[67],"existing":[69],"fragment-ion":[70,86,184],"based":[71,185,198,227],"open-search":[72],"algorithms":[73],"databases":[75],"with":[76,139],"several":[77],"PTMs.":[78],"In":[79],"this":[80],"paper,":[81],"we":[82,218],"propose":[83],"novel":[85],"indexing":[87,175,201],"technique":[88,142],"which":[89],"is":[90,137],"analogous":[91],"suffix":[93],"array":[94],"transformation":[95,107],"allows":[97,174,200],"constant":[98,150,221],"time":[99,224],"querying":[100,117],"ions.":[103],"We":[104,194],"extend":[105],"our":[106],"method,":[108],"called":[109],"SLM-Transform,":[110],"by":[111,122,124,215],"constructing":[112],"ion":[113,222],"buckets":[114],"that":[115,172,196],"all":[119],"ions":[121,148],"mass":[123],"only":[125],"storing":[126],"information":[127,136],"on":[128],"distribution":[129],"ion-frequencies":[131],"within":[132,189,207],"buckets.":[133],"stored":[135],"regression":[141],"locate":[144],"position":[146],"time.":[151],"Moreover,":[152],"theoretical":[156,165],"b-":[157],"y-ions":[159],"generated":[160],"each":[164],"spectrum":[166],"limited.":[168],"Our":[169],"show":[171,195,219],"SLM-Transform":[173,197,226],"up":[177],"4x":[179],"than":[181],"other":[182],"leading":[183],"tools":[188],"same":[191],"constraints.":[193],"index":[199,228],"over":[203],"83":[204],"million":[205],"26GB":[208],"RAM":[209],"as":[210],"compared":[211],"80GB":[213],"required":[214],"MSFragger.":[216],"Finally,":[217],"retrieval":[223],"allowing":[229],"ultrafast":[230],"speeds.":[233],"Source":[234],"code":[235],"will":[236],"be":[237],"made":[238],"available":[239],"at:":[240],"https://github.com/pcdslab/slmindex":[241]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-10-15T10:00:46.086208","created_date":"2019-02-21T00:00:00"}