{"id":"https://openalex.org/W3126778191","doi":"https://doi.org/10.3390/a14020059","title":"An Investigation of Alternatives to Transform Protein Sequence Databases to a Columnar Index Schema","display_name":"An Investigation of Alternatives to Transform Protein Sequence Databases to a Columnar Index Schema","publication_year":2021,"publication_date":"2021-02-11","ids":{"openalex":"https://openalex.org/W3126778191","doi":"https://doi.org/10.3390/a14020059","mag":"3126778191"},"language":"en","primary_location":{"id":"doi:10.3390/a14020059","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a14020059","pdf_url":"https://www.mdpi.com/1999-4893/14/2/59/pdf?version=1614236295","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/14/2/59/pdf?version=1614236295","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061275415","display_name":"Roman Zoun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roman Zoun","raw_affiliation_strings":["Line of Business Life Science, Adesso Schweiz AG, 8048 Z\u00fcrich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Line of Business Life Science, Adesso Schweiz AG, 8048 Z\u00fcrich, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035808388","display_name":"Kay Schallert","orcid":"https://orcid.org/0000-0002-1683-7222"},"institutions":[{"id":"https://openalex.org/I4210138551","display_name":"University Hospital Magdeburg","ror":"https://ror.org/03m04df46","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210138551"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kay Schallert","raw_affiliation_strings":["Bioprocess Engineering, University of Magdeburg, 39106 Magdeburg, Germany"],"affiliations":[{"raw_affiliation_string":"Bioprocess Engineering, University of Magdeburg, 39106 Magdeburg, Germany","institution_ids":["https://openalex.org/I4210138551"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061367729","display_name":"David Broneske","orcid":"https://orcid.org/0000-0002-9580-740X"},"institutions":[{"id":"https://openalex.org/I4210138551","display_name":"University Hospital Magdeburg","ror":"https://ror.org/03m04df46","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210138551"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"David Broneske","raw_affiliation_strings":["Databases and Software Engineering, University of Magdeburg, 39106 Magdeburg, Germany"],"affiliations":[{"raw_affiliation_string":"Databases and Software Engineering, University of Magdeburg, 39106 Magdeburg, Germany","institution_ids":["https://openalex.org/I4210138551"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024223749","display_name":"Ivayla Trifonova","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivayla Trifonova","raw_affiliation_strings":["Line of Business Life Science, Adesso Schweiz AG, 8048 Z\u00fcrich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Line of Business Life Science, Adesso Schweiz AG, 8048 Z\u00fcrich, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101628480","display_name":"Xiao Chen","orcid":"https://orcid.org/0000-0003-4073-6170"},"institutions":[{"id":"https://openalex.org/I4210138551","display_name":"University Hospital Magdeburg","ror":"https://ror.org/03m04df46","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210138551"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Xiao Chen","raw_affiliation_strings":["Databases and Software Engineering, University of Magdeburg, 39106 Magdeburg, Germany"],"affiliations":[{"raw_affiliation_string":"Databases and Software Engineering, University of Magdeburg, 39106 Magdeburg, Germany","institution_ids":["https://openalex.org/I4210138551"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054797839","display_name":"Robert Heyer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138551","display_name":"University Hospital Magdeburg","ror":"https://ror.org/03m04df46","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210138551"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Robert Heyer","raw_affiliation_strings":["Bioprocess Engineering, University of Magdeburg, 39106 Magdeburg, Germany","Databases and Software Engineering, University of Magdeburg, 39106 Magdeburg, Germany"],"affiliations":[{"raw_affiliation_string":"Bioprocess Engineering, University of Magdeburg, 39106 Magdeburg, Germany","institution_ids":["https://openalex.org/I4210138551"]},{"raw_affiliation_string":"Databases and Software Engineering, University of Magdeburg, 39106 Magdeburg, Germany","institution_ids":["https://openalex.org/I4210138551"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005911295","display_name":"Dirk Benndorf","orcid":"https://orcid.org/0000-0003-4021-8525"},"institutions":[{"id":"https://openalex.org/I4210138551","display_name":"University Hospital Magdeburg","ror":"https://ror.org/03m04df46","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210138551"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dirk Benndorf","raw_affiliation_strings":["Bioprocess Engineering, University of Magdeburg, 39106 Magdeburg, Germany"],"affiliations":[{"raw_affiliation_string":"Bioprocess Engineering, University of Magdeburg, 39106 Magdeburg, Germany","institution_ids":["https://openalex.org/I4210138551"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042946019","display_name":"Gunter Saake","orcid":"https://orcid.org/0000-0001-9576-8474"},"institutions":[{"id":"https://openalex.org/I4210138551","display_name":"University Hospital Magdeburg","ror":"https://ror.org/03m04df46","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210138551"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gunter Saake","raw_affiliation_strings":["Databases and Software Engineering, University of Magdeburg, 39106 Magdeburg, Germany"],"affiliations":[{"raw_affiliation_string":"Databases and Software Engineering, University of Magdeburg, 39106 Magdeburg, Germany","institution_ids":["https://openalex.org/I4210138551"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5061367729"],"corresponding_institution_ids":["https://openalex.org/I4210138551"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.008983,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":"2","first_page":"59","last_page":"59"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9965999722480774,"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":0.9965999722480774,"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":0.9907000064849854,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9898999929428101,"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/computer-science","display_name":"Computer science","score":0.7720820903778076},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.6345112323760986},{"id":"https://openalex.org/keywords/sequence-database","display_name":"Sequence database","score":0.5515124201774597},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5453431606292725},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5207869410514832},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5180009007453918},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.4879695773124695},{"id":"https://openalex.org/keywords/standardization","display_name":"Standardization","score":0.4356464147567749},{"id":"https://openalex.org/keywords/database-schema","display_name":"Database schema","score":0.4176381528377533},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.29738664627075195},{"id":"https://openalex.org/keywords/database-design","display_name":"Database design","score":0.1936037838459015},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09032213687896729}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7720820903778076},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6345112323760986},{"id":"https://openalex.org/C41584329","wikidata":"https://www.wikidata.org/wiki/Q175902","display_name":"Sequence database","level":3,"score":0.5515124201774597},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5453431606292725},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5207869410514832},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5180009007453918},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.4879695773124695},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.4356464147567749},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.4176381528377533},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29738664627075195},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.1936037838459015},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09032213687896729},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/a14020059","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a14020059","pdf_url":"https://www.mdpi.com/1999-4893/14/2/59/pdf?version=1614236295","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b1437ecd47274ad78e2d48ba92a12ec6","is_oa":true,"landing_page_url":"https://doaj.org/article/b1437ecd47274ad78e2d48ba92a12ec6","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms, Vol 14, Iss 2, p 59 (2021)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1999-4893/14/2/59/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/a14020059","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Algorithms; Volume 14; Issue 2; Pages: 59","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/a14020059","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a14020059","pdf_url":"https://www.mdpi.com/1999-4893/14/2/59/pdf?version=1614236295","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2012584104","display_name":null,"funder_award_id":"031L0103","funder_id":"https://openalex.org/F4320330124","funder_display_name":"German Network for Bioinformatics Infrastructure"},{"id":"https://openalex.org/G7171533173","display_name":null,"funder_award_id":"11.000sz00.00.0 17 114347 0","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G8242277598","display_name":null,"funder_award_id":"22404015","funder_id":"https://openalex.org/F4320323499","funder_display_name":"Bundesministerium f\u00fcr Ern\u00e4hrung und Landwirtschaft"}],"funders":[{"id":"https://openalex.org/F4320323499","display_name":"Bundesministerium f\u00fcr Ern\u00e4hrung und Landwirtschaft","ror":"https://ror.org/04jw21793"},{"id":"https://openalex.org/F4320330124","display_name":"German Network for Bioinformatics Infrastructure","ror":null},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3126778191.pdf","grobid_xml":"https://content.openalex.org/works/W3126778191.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1982904104","https://openalex.org/W2016995838","https://openalex.org/W2023096047","https://openalex.org/W2030062409","https://openalex.org/W2036321220","https://openalex.org/W2073201322","https://openalex.org/W2101607266","https://openalex.org/W2110768797","https://openalex.org/W2113416763","https://openalex.org/W2113746559","https://openalex.org/W2132811240","https://openalex.org/W2142759233","https://openalex.org/W2580517875","https://openalex.org/W2885262286","https://openalex.org/W2889069416","https://openalex.org/W2938809374","https://openalex.org/W2940571671","https://openalex.org/W2946733097","https://openalex.org/W2967445719","https://openalex.org/W3045239073","https://openalex.org/W6677006021","https://openalex.org/W6889564412"],"related_works":["https://openalex.org/W2031508292","https://openalex.org/W2098175815","https://openalex.org/W2079588361","https://openalex.org/W2460926837","https://openalex.org/W52829598","https://openalex.org/W2774489303","https://openalex.org/W2336519490","https://openalex.org/W2748090995","https://openalex.org/W223556604","https://openalex.org/W2356754926"],"abstract_inverted_index":{"Mass":[0],"spectrometers":[1],"enable":[2],"identifying":[3],"proteins":[4],"in":[5,53],"biological":[6,12],"samples":[7],"leading":[8],"to":[9,37,70,76,85,100],"biomarkers":[10],"for":[11,48,60,90,146],"process":[13],"parameters":[14],"and":[15,29,40,113,117,135],"diseases.":[16],"However,":[17],"bioinformatic":[18],"evaluation":[19],"of":[20],"the":[21,33,92,97,101,138,151],"mass":[22],"spectrometer":[23],"data":[24,95,144],"needs":[25],"a":[26,45,58,67,78,87,142],"standardized":[27],"workflow":[28],"system":[30],"that":[31,124],"stores":[32],"protein":[34,50,93,148],"sequences.":[35,51],"Due":[36],"its":[38],"standardization":[39],"maturity,":[41],"relational":[42],"systems":[43,65],"are":[44],"great":[46],"fit":[47],"storing":[49],"Hence,":[52,137],"this":[54],"work,":[55],"we":[56,105],"present":[57],"schema":[59],"distributed":[61],"column-based":[62],"database":[63,111],"management":[64],"using":[66],"column-oriented":[68],"index":[69],"store":[71],"sequence":[72,94],"data.":[73],"In":[74],"order":[75],"achieve":[77],"high":[79],"storage":[80],"performance,":[81],"it":[82],"was":[83],"necessary":[84],"choose":[86],"well-performing":[88],"strategy":[89],"transforming":[91,147],"from":[96],"FASTA":[98],"format":[99],"new":[102],"schema.":[103,153],"Therefore,":[104],"applied":[106],"an":[107],"in-memory":[108],"map,":[109],"HDDmap,":[110],"engine,":[112],"extended":[114,127],"radix":[115,128,139],"tree":[116,129,140],"evaluated":[118],"their":[119],"performance.":[120],"The":[121],"results":[122],"show":[123],"our":[125],"proposed":[126],"performs":[130],"best":[131],"regarding":[132],"memory":[133],"consumption":[134],"runtime.":[136],"is":[141],"suitable":[143],"structure":[145],"sequences":[149],"into":[150],"indexed":[152]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2021-02-15T00:00:00"}
