{"id":"https://openalex.org/W3206905519","doi":"https://doi.org/10.1093/bioinformatics/btab701","title":"MS2AI: automated repurposing of public peptide LC-MS data for machine learning applications","display_name":"MS2AI: automated repurposing of public peptide LC-MS data for machine learning applications","publication_year":2021,"publication_date":"2021-10-11","ids":{"openalex":"https://openalex.org/W3206905519","doi":"https://doi.org/10.1093/bioinformatics/btab701","mag":"3206905519","pmid":"https://pubmed.ncbi.nlm.nih.gov/34636883"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btab701","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab701","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://portal.findresearcher.sdu.dk/da/publications/0b9ff410-56da-4826-885f-485b71ca6e14","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035672639","display_name":"Tobias Greisager Rehfeldt","orcid":"https://orcid.org/0000-0002-1190-9485"},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Tobias Greisager Rehfeldt","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Southern Denmark , Odense, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-1190-9485","affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Southern Denmark , Odense, Denmark","institution_ids":["https://openalex.org/I177969490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028132127","display_name":"Konrad Krawczyk","orcid":"https://orcid.org/0000-0003-2012-0803"},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Konrad Krawczyk","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Southern Denmark , Odense, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Southern Denmark , Odense, Denmark","institution_ids":["https://openalex.org/I177969490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021161514","display_name":"Mathias Emil B\u00f8gebjerg","orcid":"https://orcid.org/0000-0002-5928-1439"},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Mathias B\u00f8gebjerg","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Southern Denmark , Odense, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Southern Denmark , Odense, Denmark","institution_ids":["https://openalex.org/I177969490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091329986","display_name":"Veit Schw\u00e4mmle","orcid":"https://orcid.org/0000-0002-9708-6722"},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Veit Schw\u00e4mmle","raw_affiliation_strings":["Department of Biochemistry and Molecular Biology, University of Southern Denmark , Odense, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, University of Southern Denmark , Odense, Denmark","institution_ids":["https://openalex.org/I177969490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114028199","display_name":"Richard R\u00f6ttger","orcid":null},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Richard R\u00f6ttger","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Southern Denmark , Odense, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Southern Denmark , Odense, Denmark","institution_ids":["https://openalex.org/I177969490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5091329986"],"corresponding_institution_ids":["https://openalex.org/I177969490"],"apc_list":{"value":3478,"currency":"USD","value_usd":3478},"apc_paid":null,"fwci":0.7877,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.67204821,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":"38","issue":"3","first_page":"875","last_page":"877"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9668999910354614,"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":0.9668999910354614,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.00839999970048666,"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/T10683","display_name":"Mass Spectrometry Techniques and Applications","score":0.005499999970197678,"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/repurposing","display_name":"Repurposing","score":0.854659914970398},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6432397961616516},{"id":"https://openalex.org/keywords/peptide","display_name":"Peptide","score":0.4802182614803314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4785350263118744},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45829686522483826},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.20841485261917114},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.14836165308952332},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13038158416748047}],"concepts":[{"id":"https://openalex.org/C519536355","wikidata":"https://www.wikidata.org/wiki/Q21021151","display_name":"Repurposing","level":2,"score":0.854659914970398},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6432397961616516},{"id":"https://openalex.org/C2779281246","wikidata":"https://www.wikidata.org/wiki/Q172847","display_name":"Peptide","level":2,"score":0.4802182614803314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4785350263118744},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45829686522483826},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.20841485261917114},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.14836165308952332},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13038158416748047},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D002853","descriptor_name":"Chromatography, Liquid","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002853","descriptor_name":"Chromatography, Liquid","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002853","descriptor_name":"Chromatography, Liquid","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":true},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":true},{"descriptor_ui":"D010455","descriptor_name":"Peptides","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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D053719","descriptor_name":"Tandem Mass Spectrometry","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},{"descriptor_ui":"D053719","descriptor_name":"Tandem Mass Spectrometry","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btab701","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab701","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:34636883","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34636883","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,"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":"Bioinformatics (Oxford, England)","raw_type":"Journal Article"},{"id":"pmh:oai:sdu.dk:openaire/0b9ff410-56da-4826-885f-485b71ca6e14","is_oa":true,"landing_page_url":"https://portal.findresearcher.sdu.dk/da/publications/0b9ff410-56da-4826-885f-485b71ca6e14","pdf_url":null,"source":{"id":"https://openalex.org/S4306400423","display_name":"University of Southern Denmark Research Portal (University of Southern Denmark)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177969490","host_organization_name":"University of Southern Denmark","host_organization_lineage":["https://openalex.org/I177969490"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Rehfeldt, T G, Krawczyk, K, B\u00f8gebjerg, M, Schw\u00e4mmle, V & R\u00f6ttger, R 2022, 'MS2AI : Automated repurposing of public peptide LC-MS data for machine learning applications', Bioinformatics, vol. 38, no. 3, pp. 875\u2013877. https://doi.org/10.1093/bioinformatics/btab701","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:sdu.dk:openaire/0b9ff410-56da-4826-885f-485b71ca6e14","is_oa":true,"landing_page_url":"https://portal.findresearcher.sdu.dk/da/publications/0b9ff410-56da-4826-885f-485b71ca6e14","pdf_url":null,"source":{"id":"https://openalex.org/S4306400423","display_name":"University of Southern Denmark Research Portal (University of Southern Denmark)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177969490","host_organization_name":"University of Southern Denmark","host_organization_lineage":["https://openalex.org/I177969490"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Rehfeldt, T G, Krawczyk, K, B\u00f8gebjerg, M, Schw\u00e4mmle, V & R\u00f6ttger, R 2022, 'MS2AI : Automated repurposing of public peptide LC-MS data for machine learning applications', Bioinformatics, vol. 38, no. 3, pp. 875\u2013877. https://doi.org/10.1093/bioinformatics/btab701","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3021055187","display_name":null,"funder_award_id":"00028116","funder_id":"https://openalex.org/F4320309607","funder_display_name":"Velux Stiftung"},{"id":"https://openalex.org/G6126122789","display_name":null,"funder_award_id":"00028116","funder_id":"https://openalex.org/F4320310490","funder_display_name":"Villum Fonden"}],"funders":[{"id":"https://openalex.org/F4320309607","display_name":"Velux Stiftung","ror":"https://ror.org/00kgf1c95"},{"id":"https://openalex.org/F4320310490","display_name":"Villum Fonden","ror":"https://ror.org/007ww2d15"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2080752012","https://openalex.org/W2135581618","https://openalex.org/W2611214388","https://openalex.org/W2799323124","https://openalex.org/W2955390348","https://openalex.org/W2990072002","https://openalex.org/W2991491873","https://openalex.org/W4234586755"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"MOTIVATION:":[0],"Liquid-chromatography":[1],"mass-spectrometry":[2],"(LC-MS)":[3],"is":[4,38],"the":[5,10,30,33,46,102,107,131,137,158,175,183,195],"established":[6],"standard":[7],"for":[8,84,116,147,182],"analyzing":[9],"proteome":[11],"in":[12,142,174],"biological":[13],"samples":[14],"by":[15,62],"identification":[16,184],"and":[17,152,162,164],"quantification":[18],"of":[19,21,32,68,79,90,92,109,113,177,185,194],"thousands":[20],"proteins.":[22],"Machine":[23],"learning":[24],"(ML)":[25],"promises":[26],"to":[27,40,51,165],"considerably":[28],"improve":[29],"analysis":[31],"resulting":[34],"data,":[35],"however,":[36],"there":[37],"yet":[39],"be":[41,198],"any":[42],"tool":[43,156],"that":[44,105],"mediates":[45],"path":[47],"from":[48,125,130],"raw":[49,123,138],"data":[50,71,82,115,124,139,205],"modern":[52],"ML":[53,57,93,118,172],"applications.":[54,119],"More":[55],"specifically,":[56],"applications":[58],"are":[59,140,206],"currently":[60],"hampered":[61],"three":[63],"major":[64],"limitations:":[65],"(i)":[66],"absence":[67],"balanced":[69],"training":[70],"with":[72],"large":[73],"sample":[74],"size;":[75],"(ii)":[76],"unclear":[77],"definition":[78],"sufficiently":[80],"information-rich":[81],"representations":[83],"e.g.":[85],"peptide":[86,153],"identification;":[87],"(iii)":[88],"lack":[89],"benchmarking":[91],"methods":[94],"on":[95],"specific":[96],"LC-MS":[97],"problems.":[98],"RESULTS:":[99],"We":[100],"created":[101],"MS2AI":[103],"pipeline":[104],"automates":[106],"process":[108],"gathering":[110],"vast":[111],"quantities":[112],"MS":[114,161],"large-scale":[117],"The":[120],"software":[121,196],"retrieves":[122],"either":[126],"in-house":[127],"sources":[128],"or":[129],"proteomics":[132],"identifications":[133],"database,":[134],"PRIDE.":[135],"Subsequently,":[136],"stored":[141],"a":[143,178],"standardized":[144],"format":[145],"amenable":[146],"ML,":[148],"encompassing":[149],"MS1/MS2":[150],"spectra":[151],"identifications.":[154],"This":[155],"bridges":[157],"gap":[159],"between":[160],"AI,":[163],"this":[166],"effect":[167],"we":[168],"also":[169],"present":[170],"an":[171],"application":[173],"form":[176],"convolutional":[179],"neural":[180],"network":[181],"oxidized":[186],"peptides.":[187],"AVAILABILITY":[188],"AND":[189],"IMPLEMENTATION:":[190],"An":[191],"open-source":[192],"implementation":[193],"can":[197],"found":[199],"at":[200,208],"https://gitlab.com/roettgerlab/ms2ai.":[201],"SUPPLEMENTARY":[202],"INFORMATION:":[203],"Supplementary":[204],"available":[207],"Bioinformatics":[209],"online.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4}],"updated_date":"2026-08-29T07:29:34.045763","created_date":"2025-10-10T00:00:00"}
