{"id":"https://openalex.org/W7139987633","doi":"https://doi.org/10.1093/bioinformatics/btag134","title":"MegaPX: fast and space-efficient peptide assignment method using IBF-based multi-indexing","display_name":"MegaPX: fast and space-efficient peptide assignment method using IBF-based multi-indexing","publication_year":2026,"publication_date":"2026-03-21","ids":{"openalex":"https://openalex.org/W7139987633","doi":"https://doi.org/10.1093/bioinformatics/btag134","pmid":"https://pubmed.ncbi.nlm.nih.gov/41863347"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btag134","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag134","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"gold","oa_url":"https://doi.org/10.1093/bioinformatics/btag134","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032696071","display_name":"Ahmad Lutfi","orcid":"https://orcid.org/0000-0003-0213-075X"},"institutions":[{"id":"https://openalex.org/I24359323","display_name":"Robert Koch Institute","ror":"https://ror.org/01k5qnb77","country_code":"DE","type":"government","lineage":["https://openalex.org/I24359323"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ahmad Lutfi","raw_affiliation_strings":["Data Competence Center MF2, Robert Koch Institute , Berlin, 13353,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Competence Center MF2, Robert Koch Institute , Berlin, 13353,","institution_ids":["https://openalex.org/I24359323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058055751","display_name":"Tanja Holstein","orcid":"https://orcid.org/0000-0002-1552-1453"},"institutions":[{"id":"https://openalex.org/I4210151194","display_name":"VIB-UGent Center for Medical Biotechnology","ror":"https://ror.org/04hbttm44","country_code":"BE","type":"facility","lineage":["https://openalex.org/I2802017950","https://openalex.org/I32597200","https://openalex.org/I4210151194"]},{"id":"https://openalex.org/I68947357","display_name":"Universit\u00e9 de Strasbourg","ror":"https://ror.org/00pg6eq24","country_code":"FR","type":"education","lineage":["https://openalex.org/I68947357"]}],"countries":["BE","FR"],"is_corresponding":false,"raw_author_name":"Tanja Holstein","raw_affiliation_strings":["BioOrganic Mass Spectrometry Laboratory (LSMBO), IPHC UMR 7178, University of Strasbourg, CNRS , Strasbourg, 67000,","Infrastructure Nationale de Prot\u00e9omique ProFI, UAR2048 , Strasbourg, 67087,","VIB-UGent Center for Medical Biotechnology, VIB , Gent, 9052,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BioOrganic Mass Spectrometry Laboratory (LSMBO), IPHC UMR 7178, University of Strasbourg, CNRS , Strasbourg, 67000,","institution_ids":["https://openalex.org/I68947357"]},{"raw_affiliation_string":"Infrastructure Nationale de Prot\u00e9omique ProFI, UAR2048 , Strasbourg, 67087,","institution_ids":["https://openalex.org/I68947357"]},{"raw_affiliation_string":"VIB-UGent Center for Medical Biotechnology, VIB , Gent, 9052,","institution_ids":["https://openalex.org/I4210151194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074757485","display_name":"Sandro Andreotti","orcid":"https://orcid.org/0000-0001-7678-9720"},"institutions":[{"id":"https://openalex.org/I75951250","display_name":"Freie Universit\u00e4t Berlin","ror":"https://ror.org/046ak2485","country_code":"DE","type":"education","lineage":["https://openalex.org/I75951250"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sandro Andreotti","raw_affiliation_strings":["Department of Mathematics and Computer Science, Institute of Computer Science, Freie Universit\u00e4t Berlin , Berlin, 14195,"],"raw_orcid":"https://orcid.org/0000-0001-7678-9720","affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, Institute of Computer Science, Freie Universit\u00e4t Berlin , Berlin, 14195,","institution_ids":["https://openalex.org/I75951250"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130264641","display_name":"Thilo Muth","orcid":null},"institutions":[{"id":"https://openalex.org/I24359323","display_name":"Robert Koch Institute","ror":"https://ror.org/01k5qnb77","country_code":"DE","type":"government","lineage":["https://openalex.org/I24359323"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thilo Muth","raw_affiliation_strings":["Data Competence Center MF2, Robert Koch Institute , Berlin, 13353,"],"raw_orcid":"https://orcid.org/0000-0001-8304-2684","affiliations":[{"raw_affiliation_string":"Data Competence Center MF2, Robert Koch Institute , Berlin, 13353,","institution_ids":["https://openalex.org/I24359323"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30975538,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"42","issue":"5","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":0.9754999876022339,"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":0.9754999876022339,"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/T12012","display_name":"Diatoms and Algae Research","score":0.005900000222027302,"subfield":{"id":"https://openalex.org/subfields/2502","display_name":"Biomaterials"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.0017000000225380063,"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/search-engine-indexing","display_name":"Search engine indexing","score":0.654699981212616},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5045999884605408},{"id":"https://openalex.org/keywords/software-tool","display_name":"Software tool","score":0.3776000142097473},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.37220001220703125},{"id":"https://openalex.org/keywords/reference-database","display_name":"Reference database","score":0.35429999232292175},{"id":"https://openalex.org/keywords/database-search-engine","display_name":"Database search engine","score":0.3285999894142151}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7838000059127808},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.654699981212616},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.527400016784668},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5045999884605408},{"id":"https://openalex.org/C2984968299","wikidata":"https://www.wikidata.org/wiki/Q1077784","display_name":"Software tool","level":3,"score":0.3776000142097473},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C2984717058","wikidata":"https://www.wikidata.org/wiki/Q1789476","display_name":"Reference database","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3515999913215637},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3301999866962433},{"id":"https://openalex.org/C48000682","wikidata":"https://www.wikidata.org/wiki/Q5227411","display_name":"Database search engine","level":3,"score":0.3285999894142151},{"id":"https://openalex.org/C59276292","wikidata":"https://www.wikidata.org/wiki/Q580427","display_name":"Database index","level":3,"score":0.321399986743927},{"id":"https://openalex.org/C41584329","wikidata":"https://www.wikidata.org/wiki/Q175902","display_name":"Sequence database","level":3,"score":0.30090001225471497},{"id":"https://openalex.org/C20901353","wikidata":"https://www.wikidata.org/wiki/Q4117139","display_name":"Biological database","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2750000059604645},{"id":"https://openalex.org/C2779281246","wikidata":"https://www.wikidata.org/wiki/Q172847","display_name":"Peptide","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.2556000053882599}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btag134","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag134","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41863347","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41863347","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":null}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btag134","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag134","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2342708510","display_name":null,"funder_award_id":"MU 4430/2-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W752259472","https://openalex.org/W1996701734","https://openalex.org/W2020973783","https://openalex.org/W2028673251","https://openalex.org/W2045204781","https://openalex.org/W2092276439","https://openalex.org/W2099078041","https://openalex.org/W2123845384","https://openalex.org/W2143210482","https://openalex.org/W2154139219","https://openalex.org/W2173732482","https://openalex.org/W2562943845","https://openalex.org/W2592902329","https://openalex.org/W2603081759","https://openalex.org/W2732361594","https://openalex.org/W2809112422","https://openalex.org/W2809649683","https://openalex.org/W2888985586","https://openalex.org/W2903819617","https://openalex.org/W2944891442","https://openalex.org/W2949700480","https://openalex.org/W2998893621","https://openalex.org/W3008735661","https://openalex.org/W3011946280","https://openalex.org/W3084210196","https://openalex.org/W3134672249","https://openalex.org/W3136924813","https://openalex.org/W3157859266","https://openalex.org/W3176125632","https://openalex.org/W3188077199","https://openalex.org/W4212959738","https://openalex.org/W4226494615","https://openalex.org/W4312095560","https://openalex.org/W4313456710","https://openalex.org/W4376279030","https://openalex.org/W4402735200","https://openalex.org/W4403353371"],"related_works":[],"abstract_inverted_index":{"MOTIVATION:":[0],"A":[1,52],"central":[2],"problem":[3],"for":[4,112,147],"metaproteomic":[5],"analysis":[6],"is":[7,61],"the":[8,13,20,34,95,140,180],"often-unknown":[9],"taxonomic":[10,136],"composition":[11],"of":[12,26,98,142,182],"analyzed":[14],"microbiomes.":[15],"Using":[16],"a":[17,110,126,135,175,198],"database":[18,37,58],"search,":[19],"standard":[21],"approach":[22,133],"requires":[23],"prior":[24],"knowledge":[25],"which":[27,44],"proteins":[28],"and":[29,47,91,102,170],"taxa":[30],"to":[31,39,55,82,158],"include":[32],"in":[33,49,174],"protein":[35,121],"reference":[36,145,192],"or":[38],"use":[40,196],"tailored":[41],"metagenome-derived":[42],"databases,":[43,193],"are":[45,68],"expensive":[46],"error-prone":[48],"their":[50],"generation.":[51],"possible":[53],"strategy":[54],"circumvent":[56],"this":[57],"search":[59],"issue":[60],"de":[62,115],"novo":[63,116],"sequencing,":[64],"where":[65],"peptide":[66,117],"sequences":[67,76,118],"directly":[69],"identified":[70],"from":[71],"mass":[72],"spectra.":[73],"However,":[74],"these":[75],"must":[77],"still":[78],"be":[79],"mapped":[80],"back":[81],"potentially":[83],"extensive":[84,191],"databases.":[85,122],"Here,":[86],"alignment-based":[87],"approaches":[88],"enable":[89],"robust":[90],"precise":[92],"results,":[93],"with":[94,139],"potential":[96,181],"drawback":[97],"high":[99],"memory":[100],"usage":[101],"long":[103],"run":[104],"times.":[105],"RESULTS:":[106],"We":[107,178],"present":[108],"MegaPX,":[109],"software":[111],"rapidly":[113],"classifying":[114],"against":[119,190],"large":[120,172],"MegaPX":[123,183],"implemented":[124],"as":[125,134,197],"C++-based":[127],"tool,":[128],"uses":[129,151],"an":[130],"alignment-free,":[131],"k-mer":[132],"classification":[137],"method":[138],"possibility":[141],"generating":[143],"mutated":[144],"databases":[146,173],"error-tolerant":[148],"searching.":[149],"It":[150],"various":[152],"algorithms,":[153],"including":[154,188],"interleaved":[155],"Bloom":[156],"filters,":[157],"efficiently":[159],"compute":[160],"approximate":[161],"membership":[162],"queries,":[163],"ensuring":[164],"fast":[165,199],"processing":[166],"times":[167],"while":[168],"querying":[169],"indexing":[171],"multi-indexing":[176],"fashion.":[177],"demonstrate":[179],"by":[184],"analyzing":[185],"different":[186],"samples,":[187],"metaproteomics,":[189],"highlighting":[194],"its":[195],"screening":[200],"tool.":[201]},"counts_by_year":[],"updated_date":"2026-07-12T07:33:03.550515","created_date":"2026-03-22T00:00:00"}