{"id":"https://openalex.org/W2892321323","doi":"https://doi.org/10.1002/pmic.201800206","title":"MaSS\u2010Simulator: A Highly Configurable Simulator for Generating MS/MS Datasets for Benchmarking of Proteomics Algorithms","display_name":"MaSS\u2010Simulator: A Highly Configurable Simulator for Generating MS/MS Datasets for Benchmarking of Proteomics Algorithms","publication_year":2018,"publication_date":"2018-09-16","ids":{"openalex":"https://openalex.org/W2892321323","doi":"https://doi.org/10.1002/pmic.201800206","mag":"2892321323","pmid":"https://pubmed.ncbi.nlm.nih.gov/30216669","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/6400488"},"language":"en","primary_location":{"id":"doi:10.1002/pmic.201800206","doi":"https://doi.org/10.1002/pmic.201800206","is_oa":false,"landing_page_url":"https://doi.org/10.1002/pmic.201800206","pdf_url":null,"source":{"id":"https://openalex.org/S182655450","display_name":"PROTEOMICS","issn_l":"1615-9853","issn":["1615-9853","1615-9861"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PROTEOMICS","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2018/04/18/302489.1.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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 Gul Awan","raw_affiliation_strings":["Department of Computer Science, Western Michigan University, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Western Michigan University, MI, USA","institution_ids":["https://openalex.org/I141649380"]}]},{"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, Miami, FL, USA"],"raw_orcid":"https://orcid.org/0000-0002-3410-9552","affiliations":[{"raw_affiliation_string":"School of Computing and Information Sciences, Florida International University, Miami, FL, USA","institution_ids":["https://openalex.org/I19700959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102729196"],"corresponding_institution_ids":["https://openalex.org/I19700959"],"apc_list":{"value":4650,"currency":"USD","value_usd":4650},"apc_paid":null,"fwci":0.6348,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.57643462,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"18","issue":"20","first_page":"e1800206","last_page":"e1800206"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9955999851226807,"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":0.9955999851226807,"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/T10683","display_name":"Mass Spectrometry Techniques and Applications","score":0.002300000051036477,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":9.999999747378752e-05,"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/ground-truth-dataset","display_name":"ground truth dataset","score":0.6309999823570251},{"id":"https://openalex.org/keywords/reproducibility","display_name":"reproducibility","score":0.8169999718666077}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8304374814033508},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6482226252555847},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4348374307155609},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.42781057953834534},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D053719","descriptor_name":"Tandem Mass Spectrometry","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1002/pmic.201800206","doi":"https://doi.org/10.1002/pmic.201800206","is_oa":false,"landing_page_url":"https://doi.org/10.1002/pmic.201800206","pdf_url":null,"source":{"id":"https://openalex.org/S182655450","display_name":"PROTEOMICS","issn_l":"1615-9853","issn":["1615-9853","1615-9861"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PROTEOMICS","raw_type":"journal-article"},{"id":"doi:10.1101/302489","doi":"https://doi.org/10.1101/302489","is_oa":true,"landing_page_url":"https://doi.org/10.1101/302489","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2018/04/18/302489.1.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"},{"id":"pmid:30216669","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30216669","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proteomics","raw_type":"Journal Article"},{"id":"pmh:oai:europepmc.org:5718291","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6400488","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:6400488","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6400488","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Proteomics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1101/302489","doi":"https://doi.org/10.1101/302489","is_oa":true,"landing_page_url":"https://doi.org/10.1101/302489","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2018/04/18/302489.1.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/G13813147","display_name":null,"funder_award_id":"ACI\u20101651724","funder_id":"https://openalex.org/F4320337563","funder_display_name":"Division of Advanced Cyberinfrastructure"},{"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"},{"id":"https://openalex.org/G8945997853","display_name":null,"funder_award_id":"R15GM120820","funder_id":"https://openalex.org/F4320306080","funder_display_name":"Foundation for the National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306080","display_name":"Foundation for the National Institutes of Health","ror":"https://ror.org/00k86s890"},{"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"},{"id":"https://openalex.org/F4320337563","display_name":"Division of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2892321323.pdf","grobid_xml":"https://content.openalex.org/works/W2892321323.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1964194772","https://openalex.org/W1971887998","https://openalex.org/W1980793852","https://openalex.org/W2000266343","https://openalex.org/W2001922182","https://openalex.org/W2003261719","https://openalex.org/W2026465178","https://openalex.org/W2038615001","https://openalex.org/W2053943711","https://openalex.org/W2098364431","https://openalex.org/W2101879802","https://openalex.org/W2102412629","https://openalex.org/W2117903500","https://openalex.org/W2122723562","https://openalex.org/W2123090260","https://openalex.org/W2124081847","https://openalex.org/W2157539385","https://openalex.org/W2239179888","https://openalex.org/W2329592726","https://openalex.org/W2519691041","https://openalex.org/W2586644082","https://openalex.org/W2706399837","https://openalex.org/W2979387401","https://openalex.org/W3031466178"],"related_works":["https://openalex.org/W1980793852","https://openalex.org/W2041856956","https://openalex.org/W7098155361","https://openalex.org/W3158290014","https://openalex.org/W2330976336","https://openalex.org/W2023735497","https://openalex.org/W7214847445","https://openalex.org/W2051009737","https://openalex.org/W1980297970","https://openalex.org/W1823857847"],"abstract_inverted_index":{"Mass":[0],"Spectrometry":[1],"(MS)-based":[2],"proteomics":[3,117],"has":[4,61],"become":[5],"an":[6,66],"essential":[7],"tool":[8],"in":[9,38],"the":[10,15,39,96,104,160,179],"study":[11],"of":[12,17,23,41,83,101,115,136,181,189],"proteins.":[13],"With":[14],"advent":[16],"modern":[18],"MS":[19],"machines":[20],"huge":[21],"amounts":[22],"data":[24,42],"is":[25,53,65,120],"being":[26],"generated,":[27],"which":[28,64,107],"can":[29,72,108,204],"only":[30],"be":[31,73,205],"processed":[32],"by":[33,122],"novel":[34],"algorithmic":[35,48],"tools.":[36],"However,":[37],"absence":[40],"benchmarks":[43],"and":[44,51,71,111,130,150,184,198],"ground":[45,87],"truth":[46],"datasets":[47,78],"integrity":[49],"testing":[50,114],"reproducibility":[52],"a":[54,80,98,152,186,199],"challenging":[55],"problem.":[56],"To":[57],"this":[58],"end,":[59],"MaSS-Simulator":[60,89,119,143,172,203],"been":[62],"presented,":[63],"easy":[67],"to":[68,75,94,176],"use":[69],"simulator":[70],"configured":[74],"simulate":[76],"MS/MS":[77],"for":[79,163,202],"wide":[81],"variety":[82],"conditions":[84],"with":[85,148],"known":[86],"truths.":[88],"offers":[90],"many":[91],"configuration":[92],"options":[93],"allow":[95],"user":[97,200],"great":[99],"degree":[100],"control":[102],"over":[103],"test":[105],"datasets,":[106],"enable":[109,174],"rigorous":[110],"large-":[112],"scale":[113],"any":[116,190],"algorithm.":[118],"assessed":[121],"comparing":[123],"its":[124],"performance":[125],"against":[126],"experimentally":[127],"generated":[128,144],"spectra":[129,131,145,162],"obtained":[132],"from":[133,207],"NIST":[134],"collections":[135],"spectral":[137],"library.":[138],"The":[139],"results":[140],"show":[141],"that":[142],"match":[146],"closely":[147],"real-spectra":[149],"have":[151,166],"relative-error":[153,167],"distribution":[154,168],"centered":[155,169],"around":[156,170],"25%.":[157],"In":[158],"contrast,":[159],"theoretical":[161],"same":[164],"peptides":[165],"150%.":[171],"will":[173],"developers":[175],"specifically":[177],"highlight":[178],"capabilities":[180],"their":[182],"algorithms":[183],"provide":[185],"strong":[187],"proof":[188],"pitfalls":[191],"they":[192],"might":[193],"face.":[194],"Source":[195],"code,":[196],"executables,":[197],"manual":[201],"downloaded":[206],"https://github.com/pcdslab/MaSS-Simulator.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2018-09-27T00:00:00"}