{"id":"https://openalex.org/W2912228103","doi":"https://doi.org/10.1093/bioinformatics/btz054","title":"Predicting runtimes of bioinformatics tools based on historical data: five years of Galaxy usage","display_name":"Predicting runtimes of bioinformatics tools based on historical data: five years of Galaxy usage","publication_year":2019,"publication_date":"2019-01-26","ids":{"openalex":"https://openalex.org/W2912228103","doi":"https://doi.org/10.1093/bioinformatics/btz054","mag":"2912228103","pmid":"https://pubmed.ncbi.nlm.nih.gov/30698642"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btz054","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz054","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://www.ncbi.nlm.nih.gov/pmc/articles/6931352","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083053860","display_name":"Anastasia Tyryshkina","orcid":"https://orcid.org/0000-0001-8710-5590"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anastasia Tyryshkina","raw_affiliation_strings":["Huck Institute of Life Sciences, Neuroscience Program, The Pennsylvania State University, University Park , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huck Institute of Life Sciences, Neuroscience Program, The Pennsylvania State University, University Park , USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030446017","display_name":"Nate Coraor","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nate Coraor","raw_affiliation_strings":["Department of Biochemistry and Molecular Biology, The Pennsylvania State University, University Park , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, The Pennsylvania State University, University Park , USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065292926","display_name":"Anton Nekrutenko","orcid":"https://orcid.org/0000-0002-5987-8032"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anton Nekrutenko","raw_affiliation_strings":["Department of Biochemistry and Molecular Biology, The Pennsylvania State University, University Park , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, The Pennsylvania State University, University Park , USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065292926"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":5.7638,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.96707442,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"35","issue":"18","first_page":"3453","last_page":"3460"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.2547000050544739,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.2547000050544739,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.10459999740123749,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.06300000101327896,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6937803626060486},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5170515179634094},{"id":"https://openalex.org/keywords/galaxy","display_name":"Galaxy","score":0.43888571858406067},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3802414536476135},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3300839066505432},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2190619707107544},{"id":"https://openalex.org/keywords/astronomy","display_name":"Astronomy","score":0.09713733196258545}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6937803626060486},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5170515179634094},{"id":"https://openalex.org/C98444146","wikidata":"https://www.wikidata.org/wiki/Q318","display_name":"Galaxy","level":2,"score":0.43888571858406067},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3802414536476135},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3300839066505432},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2190619707107544},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.09713733196258545},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","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":"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":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btz054","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz054","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:30698642","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30698642","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},{"id":"pmh:oai:pubmedcentral.nih.gov:6931352","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6931352","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:6931352","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6931352","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G2940291979","display_name":null,"funder_award_id":"1661497","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3448084246","display_name":null,"funder_award_id":"R01 AI134384-01","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7609855956","display_name":null,"funder_award_id":"U41 HG006620","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310419","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231"},{"id":"https://openalex.org/F4320324004","display_name":"Forskningsr\u00e5det om H\u00e4lsa, Arbetsliv och V\u00e4lf\u00e4rd","ror":"https://ror.org/02d290r06"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1518866231","https://openalex.org/W1548150408","https://openalex.org/W1573647811","https://openalex.org/W1583240815","https://openalex.org/W1678356000","https://openalex.org/W1956666728","https://openalex.org/W2056132907","https://openalex.org/W2101234009","https://openalex.org/W2119438912","https://openalex.org/W2136482257","https://openalex.org/W2346143774","https://openalex.org/W2485414348","https://openalex.org/W2911964244","https://openalex.org/W2917207851","https://openalex.org/W2964281761","https://openalex.org/W4247606021","https://openalex.org/W6634147026","https://openalex.org/W6675354045"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"MOTIVATION:":[0],"One":[1],"of":[2,20,34,75,87,113,153,180,186,209,221,231],"the":[3,17,80,85,99,111,123,127,132,144,171,178,181,184,187,207,210,222,228,237],"many":[4],"technical":[5],"challenges":[6],"that":[7,41,138,216,220,226],"arises":[8],"when":[9],"scheduling":[10],"bioinformatics":[11,76],"analyses":[12,55,77],"at":[13,267,278],"scale":[14],"is":[15,217,234],"determining":[16],"appropriate":[18],"amount":[19],"memory":[21,62,229],"and":[22,27,53,104,131,136,169,192],"processing":[23],"resources.":[24],"Both":[25],"over-":[26],"under-allocation":[28],"leads":[29],"to":[30,56,83,173,219],"an":[31,88,214],"inefficient":[32],"use":[33],"computational":[35],"infrastructure.":[36],"Over":[37],"allocation":[38],"locks":[39],"resources":[40],"could":[42],"otherwise":[43],"be":[44,57,194,254],"used":[45],"for":[46,91,156,257],"other":[47],"analyses.":[48],"Under-allocation":[49],"causes":[50],"job":[51,101,233],"failure":[52],"requires":[54],"repeated":[58],"with":[59,213],"a":[60,72,232],"larger":[61],"or":[63],"runtime":[64,145],"allowance.":[65],"We":[66,117,148,224],"address":[67,200],"this":[68,201],"challenge":[69],"by":[70,176,203],"using":[71,236],"historical":[73],"dataset":[74,103],"run":[78,102],"on":[79,110],"Galaxy":[81,100],"platform":[82],"demonstrate":[84],"feasibility":[86],"online":[89],"service":[90],"resource":[92,114,259],"requirement":[93],"estimation.":[94],"RESULTS:":[95],"Here":[96],"we":[97,244],"introduced":[98],"tested":[105],"popular":[106,120],"machine":[107],"learning":[108],"models":[109],"task":[112],"usage":[115],"prediction.":[116],"include":[118],"three":[119],"forest":[121,134,198],"models:":[122],"extra":[124],"trees":[125],"regressor,":[126,135],"gradient":[128],"boosting":[129],"regressor":[130],"random":[133,139],"find":[137],"forests":[140,162],"perform":[141],"best":[142],"in":[143,166,270],"prediction":[146,211],"task.":[147],"also":[149],"present":[150],"two":[151],"methods":[152],"choosing":[154],"walltimes":[155],"previously":[157],"unseen":[158],"jobs.":[159],"Quantile":[160],"regression":[161],"are":[163,190,276],"more":[164],"accurate":[165,258],"their":[167],"predictions,":[168],"grant":[170],"ability":[172],"improve":[174],"performance":[175],"changing":[177],"confidence":[179,188],"estimates.":[182],"However,":[183],"sizes":[185],"intervals":[189,212],"variable":[191],"cannot":[193],"absolutely":[195],"constrained.":[196],"Random":[197],"classifiers":[199],"problem":[202],"providing":[204],"control":[205],"over":[206],"size":[208],"accuracy":[215],"comparable":[218],"regressor.":[223],"show":[225],"estimating":[227],"requirements":[230],"possible":[235],"same":[238],"methods,":[239],"which":[240],"as":[241,243],"far":[242],"know,":[245],"has":[246],"not":[247],"been":[248],"done":[249],"before.":[250],"Such":[251],"estimation":[252],"can":[253],"highly":[255],"beneficial":[256],"allocation.":[260],"AVAILABILITY":[261],"AND":[262],"IMPLEMENTATION:":[263],"Source":[264],"code":[265],"available":[266,277],"https://github.com/atyryshkina/algorithm-performance-analysis,":[268],"implemented":[269],"Python.":[271],"SUPPLEMENTARY":[272],"INFORMATION:":[273],"Supplementary":[274],"data":[275],"Bioinformatics":[279],"online.":[280]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}