{"id":"https://openalex.org/W2013582589","doi":"https://doi.org/10.1186/1752-0509-7-s1-s5","title":"Bioprocess data mining using regularized regression and random forests","display_name":"Bioprocess data mining using regularized regression and random forests","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2013582589","doi":"https://doi.org/10.1186/1752-0509-7-s1-s5","mag":"2013582589","pmid":"https://pubmed.ncbi.nlm.nih.gov/24268049"},"language":"en","primary_location":{"id":"doi:10.1186/1752-0509-7-s1-s5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1752-0509-7-s1-s5","pdf_url":"https://bmcsystbiol.biomedcentral.com/counter/pdf/10.1186/1752-0509-7-S1-S5","source":{"id":"https://openalex.org/S92363890","display_name":"BMC Systems Biology","issn_l":"1752-0509","issn":["1752-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Systems Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://bmcsystbiol.biomedcentral.com/counter/pdf/10.1186/1752-0509-7-S1-S5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067263083","display_name":"Sakira Hassan","orcid":"https://orcid.org/0000-0001-6838-474X"},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Syeda Hassan","raw_affiliation_strings":["Department of Signal Processing, Tampere University of Technology, Tampere, P.O. Box 553, 33101, Finland","[Department of Signal Processing, Tampere University of Technology, Tampere, FINLAND]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Tampere University of Technology, Tampere, P.O. Box 553, 33101, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"[Department of Signal Processing, Tampere University of Technology, Tampere, FINLAND]","institution_ids":["https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075242305","display_name":"Muhammad Farhan","orcid":"https://orcid.org/0000-0002-3649-5717"},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Muhammad Farhan","raw_affiliation_strings":["Department of Signal Processing, Tampere University of Technology, Tampere, P.O. Box 553, 33101, Finland","[Department of Signal Processing, Tampere University of Technology, Tampere, FINLAND]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Tampere University of Technology, Tampere, P.O. Box 553, 33101, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"[Department of Signal Processing, Tampere University of Technology, Tampere, FINLAND]","institution_ids":["https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074636466","display_name":"Rahul Mangayil","orcid":"https://orcid.org/0000-0001-7547-409X"},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Rahul Mangayil","raw_affiliation_strings":["Department of Chemistry and Bioengineering, Tampere University of Technology, Tampere, P.O. Box 541, 33101, Finland","Department of Chemistry and Bioengineering, Tampere University of Technology, Tampere, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry and Bioengineering, Tampere University of Technology, Tampere, P.O. Box 541, 33101, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"Department of Chemistry and Bioengineering, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042399760","display_name":"Heikki Huttunen","orcid":"https://orcid.org/0000-0002-6571-0797"},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Heikki Huttunen","raw_affiliation_strings":["Department of Signal Processing, Tampere University of Technology, Tampere, P.O. Box 553, 33101, Finland","[Department of Signal Processing, Tampere University of Technology, Tampere, FINLAND]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Tampere University of Technology, Tampere, P.O. Box 553, 33101, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"[Department of Signal Processing, Tampere University of Technology, Tampere, FINLAND]","institution_ids":["https://openalex.org/I4210133110"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046641062","display_name":"Tommi Aho","orcid":"https://orcid.org/0000-0003-3818-2623"},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tommi Aho","raw_affiliation_strings":["Department of Chemistry and Bioengineering, Tampere University of Technology, Tampere, P.O. Box 541, 33101, Finland","Department of Chemistry and Bioengineering, Tampere University of Technology, Tampere, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry and Bioengineering, Tampere University of Technology, Tampere, P.O. Box 541, 33101, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"Department of Chemistry and Bioengineering, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5067263083"],"corresponding_institution_ids":["https://openalex.org/I4210133110"],"apc_list":null,"apc_paid":null,"fwci":0.4487,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.65123898,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"7","issue":"Suppl 1","first_page":"S5","last_page":"S5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11663","display_name":"Viral Infectious Diseases and Gene Expression in Insects","score":0.19200000166893005,"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"}},"topics":[{"id":"https://openalex.org/T11663","display_name":"Viral Infectious Diseases and Gene Expression in Insects","score":0.19200000166893005,"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/T10932","display_name":"Microbial Metabolic Engineering and Bioproduction","score":0.15649999678134918,"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/T10864","display_name":"Fluid Dynamics and Mixing","score":0.08659999817609787,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.7022066712379456},{"id":"https://openalex.org/keywords/bioprocess","display_name":"Bioprocess","score":0.5530093312263489},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5034725069999695},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.4266677498817444},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38971370458602905},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3464542627334595},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.324233740568161},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2769675850868225},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24704763293266296},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1706216037273407}],"concepts":[{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.7022066712379456},{"id":"https://openalex.org/C4916135","wikidata":"https://www.wikidata.org/wiki/Q4119055","display_name":"Bioprocess","level":2,"score":0.5530093312263489},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5034725069999695},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4266677498817444},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38971370458602905},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3464542627334595},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.324233740568161},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2769675850868225},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24704763293266296},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1706216037273407},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D012044","descriptor_name":"Regression Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012044","descriptor_name":"Regression Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012044","descriptor_name":"Regression Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/1752-0509-7-s1-s5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1752-0509-7-s1-s5","pdf_url":"https://bmcsystbiol.biomedcentral.com/counter/pdf/10.1186/1752-0509-7-S1-S5","source":{"id":"https://openalex.org/S92363890","display_name":"BMC Systems Biology","issn_l":"1752-0509","issn":["1752-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Systems Biology","raw_type":"journal-article"},{"id":"pmid:24268049","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/24268049","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":"BMC systems biology","raw_type":null},{"id":"pmh:oai:europepmc.org:2744214","is_oa":true,"landing_page_url":"http://europepmc.org/articles/PMC3750505","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:3750505","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3750505","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Syst Biol","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1752-0509-7-s1-s5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1752-0509-7-s1-s5","pdf_url":"https://bmcsystbiol.biomedcentral.com/counter/pdf/10.1186/1752-0509-7-S1-S5","source":{"id":"https://openalex.org/S92363890","display_name":"BMC Systems Biology","issn_l":"1752-0509","issn":["1752-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Systems Biology","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Life in Land","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2013582589.pdf","grobid_xml":"https://content.openalex.org/works/W2013582589.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W322218200","https://openalex.org/W1969423031","https://openalex.org/W2119387367","https://openalex.org/W2133277699","https://openalex.org/W2135046866","https://openalex.org/W2911964244"],"related_works":["https://openalex.org/W2911891560","https://openalex.org/W1518145255","https://openalex.org/W1502859157","https://openalex.org/W3160141509","https://openalex.org/W2048488252","https://openalex.org/W4289884158","https://openalex.org/W4288365262","https://openalex.org/W2940614149","https://openalex.org/W2787485953","https://openalex.org/W3217432596"],"abstract_inverted_index":{"BACKGROUND:":[0],"In":[1,33,119,206,256],"bioprocess":[2,133,265],"development,":[3],"the":[4,35,60,69,95,102,111,122,164,175,179,195,200,209,218,245,251,254],"needs":[5,44],"of":[6,37,59,90,97,104,124,178,199,259,264],"data":[7,15,39,134,152,261],"analysis":[8],"include":[9],"(1)":[10],"getting":[11],"overview":[12],"to":[13,94,109,240],"existing":[14],"sets,":[16],"(2)":[17],"identifying":[18],"primary":[19],"control":[20,26],"parameters,":[21],"(3)":[22],"determining":[23],"a":[24,154,171,260],"useful":[25],"direction,":[27],"and":[28,65,101,128,138,197,220,225,235,244],"(4)":[29],"planning":[30],"future":[31],"experiments.":[32],"particular,":[34],"integration":[36],"multiple":[38,144,189,270],"sets":[40],"causes":[41],"that":[42,52,75,231],"these":[43],"cannot":[45],"be":[46],"properly":[47],"addressed":[48],"by":[49],"regression":[50,64,126,191,234],"models":[51],"assume":[53],"linear":[54,145,190,271],"input-output":[55],"relationship":[56],"or":[57],"unimodality":[58],"response":[61,105],"function.":[62],"Regularized":[63],"random":[66,129,236],"forests,":[67],"on":[68],"other":[70],"hand,":[71],"have":[72],"several":[73],"properties":[74],"may":[76],"appear":[77],"important":[78],"in":[79,86,107,114,132,169,186,204,249,253],"this":[80,120,207,257],"context.":[81],"They":[82],"are":[83],"capable,":[84],"e.g.,":[85],"handling":[87],"small":[88],"number":[89,96],"samples":[91],"with":[92,214],"respect":[93],"variables,":[98],"feature":[99],"selection,":[100],"visualization":[103],"surfaces":[106],"order":[108],"present":[110],"prediction":[112],"results":[113],"an":[115,148],"illustrative":[116],"way.":[117],"RESULTS:":[118],"work,":[121],"applicability":[123],"regularized":[125,233],"(Lasso)":[127],"forests":[130,237],"(RF)":[131],"mining":[135,262],"was":[136,141,211,223,247],"examined,":[137],"their":[139],"performance":[140],"benchmarked":[142],"against":[143],"regression.":[146,272],"As":[147],"example,":[149],"we":[150],"used":[151],"from":[153],"culture":[155,180],"media":[156,181],"optimization":[157,182],"study":[158],"for":[159],"microbial":[160],"hydrogen":[161],"production.":[162],"All":[163],"three":[165],"methods":[166,268],"were":[167,183,202,238],"capable":[168],"providing":[170],"significant":[172],"model":[173],"when":[174,193],"five":[176],"variables":[177,201],"linearly":[184],"included":[185,203],"modeling.":[187,205],"However,":[188],"failed":[192],"also":[194],"multiplications":[196],"squares":[198],"case,":[208],"modeling":[210],"still":[212],"successful":[213],"Lasso":[215],"(correlation":[216],"between":[217],"observed":[219],"predicted":[221],"yield":[222],"0.69)":[224],"RF":[226],"(0.91).":[227],"CONCLUSION:":[228],"We":[229],"found":[230],"both":[232,267],"able":[239],"produce":[241],"feasible":[242],"models,":[243],"latter":[246],"efficient":[248],"capturing":[250],"non-linearity":[252],"data.":[255],"kind":[258],"task":[263],"data,":[266],"outperform":[269]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}