{"id":"https://openalex.org/W7126272003","doi":"https://doi.org/10.1021/acs.jproteome.5c00797","title":"Improved Open Modification Searching via Unified Spectral Search with Predicted Libraries and Enhanced Vector Representations in ANN-SoLo","display_name":"Improved Open Modification Searching via Unified Spectral Search with Predicted Libraries and Enhanced Vector Representations in ANN-SoLo","publication_year":2026,"publication_date":"2026-01-31","ids":{"openalex":"https://openalex.org/W7126272003","doi":"https://doi.org/10.1021/acs.jproteome.5c00797","pmid":"https://pubmed.ncbi.nlm.nih.gov/41618929"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jproteome.5c00797","doi":"https://doi.org/10.1021/acs.jproteome.5c00797","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jproteome.5c00797","pdf_url":null,"source":{"id":"https://openalex.org/S74367812","display_name":"Journal of Proteome Research","issn_l":"1535-3893","issn":["1535-3893","1535-3907"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-d","doyens","jufo-1","ki-jl-1","medline","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Proteome Research","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2025/05/25/2025.05.20.655174.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077123521","display_name":"Issar Arab","orcid":"https://orcid.org/0000-0002-7659-1439","observed_orcids":["https://orcid.org/0000-0002-7659-1439"]},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Issar Arab","raw_affiliation_strings":["Adrem Data Lab, Department of Computer Science","University of Antwerp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adrem Data Lab, Department of Computer Science","institution_ids":[]},{"raw_affiliation_string":"University of Antwerp","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086925757","display_name":"Kris Laukens","orcid":"https://orcid.org/0000-0002-8217-2564","observed_orcids":["https://orcid.org/0000-0002-8217-2564"]},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]},{"id":"https://openalex.org/I4210125409","display_name":"Biomedical Informatics Research Center Antwerp","ror":"https://ror.org/02y3cnq68","country_code":"BE","type":"facility","lineage":["https://openalex.org/I4210125409"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Kris Laukens","raw_affiliation_strings":["Adrem Data Lab, Department of Computer Science","Biomedical Informatics Network Antwerpen (biomina)","University of Antwerp"],"raw_orcid":"https://orcid.org/0000-0002-8217-2564","affiliations":[{"raw_affiliation_string":"Adrem Data Lab, Department of Computer Science","institution_ids":[]},{"raw_affiliation_string":"Biomedical Informatics Network Antwerpen (biomina)","institution_ids":["https://openalex.org/I4210125409"]},{"raw_affiliation_string":"University of Antwerp","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053271927","display_name":"Wout Bittremieux","orcid":"https://orcid.org/0000-0002-3105-1359","observed_orcids":["https://orcid.org/0000-0002-3105-1359"]},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Wout Bittremieux","raw_affiliation_strings":["Adrem Data Lab, Department of Computer Science","University of Antwerp"],"raw_orcid":"https://orcid.org/0000-0002-3105-1359","affiliations":[{"raw_affiliation_string":"Adrem Data Lab, Department of Computer Science","institution_ids":[]},{"raw_affiliation_string":"University of Antwerp","institution_ids":["https://openalex.org/I149213910"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053271927"],"corresponding_institution_ids":["https://openalex.org/I149213910"],"apc_list":{"value":4500,"currency":"USD","value_usd":4500},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":"3","first_page":"1781","last_page":"1787"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9970999956130981,"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":0.9970999956130981,"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":0.0019000000320374966,"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":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/spectral-library-search","display_name":"spectral library search","score":0.8220000267028809},{"id":"https://openalex.org/keywords/sequence-database-searching","display_name":"sequence database searching","score":0.8820000290870667},{"id":"https://openalex.org/keywords/prosit","display_name":"Prosit","score":0.7139999866485596},{"id":"https://openalex.org/keywords/decoy-generation","display_name":"decoy generation","score":0.8320000171661377},{"id":"https://openalex.org/keywords/peptide-identification","display_name":"peptide identification","score":0.7379999756813049},{"id":"https://openalex.org/keywords/tandem-mass-spectrometry","display_name":"tandem mass spectrometry","score":0.7649999856948853},{"id":"https://openalex.org/keywords/post-translational-modification","display_name":"post-translational modification","score":0.9110000133514404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7024999856948853},{"id":"https://openalex.org/C48000682","wikidata":"https://www.wikidata.org/wiki/Q5227411","display_name":"Database search engine","level":3,"score":0.5809000134468079},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5751000046730042},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5123999714851379},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.45590001344680786},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4302000105381012},{"id":"https://openalex.org/C2777814067","wikidata":"https://www.wikidata.org/wiki/Q1752317","display_name":"Tandem","level":2,"score":0.40130001306533813},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C31827203","wikidata":"https://www.wikidata.org/wiki/Q874296","display_name":"Tandem mass spectrometry","level":3,"score":0.36239999532699585},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36149999499320984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3488999903202057},{"id":"https://openalex.org/C41584329","wikidata":"https://www.wikidata.org/wiki/Q175902","display_name":"Sequence database","level":3,"score":0.3452000021934509},{"id":"https://openalex.org/C46111723","wikidata":"https://www.wikidata.org/wiki/Q471857","display_name":"Proteomics","level":3,"score":0.3400999903678894},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32839998602867126},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C2779281246","wikidata":"https://www.wikidata.org/wiki/Q172847","display_name":"Peptide","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.29409998655319214},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C2778160393","wikidata":"https://www.wikidata.org/wiki/Q18670161","display_name":"Mascot","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.27799999713897705},{"id":"https://openalex.org/C178609977","wikidata":"https://www.wikidata.org/wiki/Q3503315","display_name":"Spectral sequence","level":3,"score":0.27300000190734863},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.25619998574256897}],"mesh":[{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011499","descriptor_name":"Protein Processing, Post-Translational","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":true},{"descriptor_ui":"D019151","descriptor_name":"Peptide Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","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":false},{"descriptor_ui":"D057386","descriptor_name":"Search Engine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1021/acs.jproteome.5c00797","doi":"https://doi.org/10.1021/acs.jproteome.5c00797","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jproteome.5c00797","pdf_url":null,"source":{"id":"https://openalex.org/S74367812","display_name":"Journal of Proteome Research","issn_l":"1535-3893","issn":["1535-3893","1535-3907"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-d","doyens","jufo-1","ki-jl-1","medline","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Proteome Research","raw_type":"journal-article"},{"id":"doi:10.1101/2025.05.20.655174","doi":"https://doi.org/10.1101/2025.05.20.655174","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2025.05.20.655174","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2025/05/25/2025.05.20.655174.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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmid:41618929","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41618929","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":"Journal of proteome research","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1101/2025.05.20.655174","doi":"https://doi.org/10.1101/2025.05.20.655174","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2025.05.20.655174","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2025/05/25/2025.05.20.655174.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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G712637546","display_name":"Bioinformatics Solutions For the Comprehensive Study of the Human Immunopeptidome","funder_award_id":"G087625N","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126272003.pdf","grobid_xml":"https://content.openalex.org/works/W7126272003.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W2008117982","https://openalex.org/W2011301426","https://openalex.org/W2013589890","https://openalex.org/W2021613526","https://openalex.org/W2073637473","https://openalex.org/W2109204063","https://openalex.org/W2110017950","https://openalex.org/W2179747797","https://openalex.org/W2289616942","https://openalex.org/W2478131123","https://openalex.org/W2593864460","https://openalex.org/W2607310450","https://openalex.org/W2624356059","https://openalex.org/W2838250877","https://openalex.org/W2905906027","https://openalex.org/W2947763854","https://openalex.org/W2949278902","https://openalex.org/W2970104449","https://openalex.org/W3003257820","https://openalex.org/W3013398083","https://openalex.org/W3035965352","https://openalex.org/W3128261063","https://openalex.org/W3131629713","https://openalex.org/W3201164942","https://openalex.org/W4290831374","https://openalex.org/W4317750000","https://openalex.org/W4317780929","https://openalex.org/W4317937347","https://openalex.org/W4378952025","https://openalex.org/W4416112717"],"related_works":["https://openalex.org/W2970104449","https://openalex.org/W2949278902","https://openalex.org/W6968879003","https://openalex.org/W4317750000","https://openalex.org/W3211268010","https://openalex.org/W7213890065","https://openalex.org/W4378347849","https://openalex.org/W4303444681","https://openalex.org/W4377030033","https://openalex.org/W2728534204"],"abstract_inverted_index":{"The":[0],"primary":[1],"computational":[2],"challenge":[3],"in":[4,147],"mass":[5,19],"spectrometry-based":[6],"proteomics":[7,151],"is":[8,23,41],"determining":[9],"the":[10,54,72,105,108],"peptide":[11,109,145],"sequence":[12,27,80,94],"responsible":[13],"for":[14,49,117],"generating":[15],"each":[16],"measured":[17],"tandem":[18],"spectrum.":[20],"This":[21],"task":[22],"traditionally":[24],"addressed":[25],"through":[26],"database":[28,81],"searching":[29,78,82],"as":[30,32,36],"well":[31],"alternative":[33],"approaches":[34],"such":[35],"spectral":[37,44,76,90,141],"library":[38,45,77],"searching.":[39],"ANN-SoLo":[40,69],"a":[42],"powerful":[43],"search":[46,122],"engine":[47],"optimized":[48,113],"open":[50],"modification":[51],"searching,":[52],"enabling":[53],"detection":[55],"of":[56,68,74],"peptides":[57],"carrying":[58],"any":[59],"post-translational":[60],"modification.":[61],"Here,":[62],"we":[63],"present":[64],"an":[65,112],"enhanced":[66],"version":[67],"that":[70],"combines":[71],"strengths":[73],"both":[75,104],"and":[79,107,120,143,149],"by":[83,124],"integrating":[84],"with":[85,139],"Prosit":[86],"to":[87,100],"generate":[88,101],"predicted":[89],"libraries":[91,142],"from":[92],"protein":[93],"databases.":[95],"Additionally,":[96],"it":[97],"provides":[98],"functionality":[99],"decoys":[102],"at":[103],"spectrum":[106,130],"levels,":[110],"introduces":[111],"internal":[114],"file":[115],"structure":[116],"large-scale":[118,148],"analytics,":[119],"improves":[121],"accuracy":[123],"incorporating":[125],"complementary":[126],"ion":[127],"information":[128],"into":[129],"vector":[131],"representations.":[132],"These":[133],"advancements":[134],"collectively":[135],"address":[136],"challenges":[137],"associated":[138],"missing":[140],"enhance":[144],"identification":[146],"complex":[150],"workflows.":[152]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-02-01T00:00:00"}