A Comprehensive Evaluation Framework for Benchmarking Multi-Objective Feature Selection in Omics-Based Biomarker Discovery

Machine learning algorithms have been extensively used for accurate classification of cancer subtypes driven by gene expression-based biomarkers. However, biomarker models combining multiple gene expression signatures are often not reproducible in external validation datasets and their feature set s...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE/ACM transactions on computational biology and bioinformatics Jg. 21; H. 6; S. 2432 - 2446
Hauptverfasser:	Cattelani, Luca, Ghosh, Arindam, Rintala, Teemu J., Fortino, Vittorio
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States IEEE 01.11.2024
Schlagworte:	Accuracy Algorithms Benchmark testing Benchmarking Biological system modeling biology and genetics Biomarkers, Tumor - analysis Biomarkers, Tumor - genetics Biomarkers, Tumor - metabolism Cancer Classification algorithms Computational Biology - methods Databases, Genetic evolutionary computing and genetic algorithms Feature extraction Gene Expression Profiling - methods Genetic algorithms Humans Machine Learning Measurement Neoplasms - genetics Neoplasms - metabolism Prediction algorithms Training Transcriptome - genetics
ISSN:	1545-5963, 1557-9964, 1557-9964
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Machine learning algorithms have been extensively used for accurate classification of cancer subtypes driven by gene expression-based biomarkers. However, biomarker models combining multiple gene expression signatures are often not reproducible in external validation datasets and their feature set size is often not optimized, jeopardizing their translatability into cost-effective clinical tools. We investigated how to solve the multi-objective problem of finding the best trade-offs between classification performance and set size applying seven algorithms for machine learning-driven feature subset selection and analyse how they perform in a benchmark with eight large-scale transcriptome datasets of cancer, covering both training and external validation sets. The benchmark includes evaluation metrics assessing the performance of the individual biomarkers and the solution sets, according to their accuracy, diversity, and stability of the composing genes. Moreover, a new evaluation metric for cross-validation studies is proposed that generalizes the hypervolume, which is commonly used to assess the performance of multi-objective optimization algorithms. Biomarkers exhibiting 0.8 of balanced accuracy on the external dataset for breast, kidney and ovarian cancer using respectively 4, 2 and 7 features, were obtained. Genetic algorithms often provided better performance than other considered algorithms, and the recently proposed NSGA2-CH and NSGA2-CHS were the best performing methods in most cases.
AbstractList	Machine learning algorithms have been extensively used for accurate classification of cancer subtypes driven by gene expression-based biomarkers. However, biomarker models combining multiple gene expression signatures are often not reproducible in external validation datasets and their feature set size is often not optimized, jeopardizing their translatability into cost-effective clinical tools. We investigated how to solve the multi-objective problem of finding the best trade-offs between classification performance and set size applying seven algorithms for machine learning-driven feature subset selection and analyse how they perform in a benchmark with eight large-scale transcriptome datasets of cancer, covering both training and external validation sets. The benchmark includes evaluation metrics assessing the performance of the individual biomarkers and the solution sets, according to their accuracy, diversity, and stability of the composing genes. Moreover, a new evaluation metric for cross-validation studies is proposed that generalizes the hypervolume, which is commonly used to assess the performance of multi-objective optimization algorithms. Biomarkers exhibiting 0.8 of balanced accuracy on the external dataset for breast, kidney and ovarian cancer using respectively 4, 2 and 7 features, were obtained. Genetic algorithms often provided better performance than other considered algorithms, and the recently proposed NSGA2-CH and NSGA2-CHS were the best performing methods in most cases. Machine learning algorithms have been extensively used for accurate classification of cancer subtypes driven by gene expression-based biomarkers. However, biomarker models combining multiple gene expression signatures are often not reproducible in external validation datasets and their feature set size is often not optimized, jeopardizing their translatability into cost-effective clinical tools. We investigated how to solve the multi-objective problem of finding the best trade-offs between classification performance and set size applying seven algorithms for machine learning-driven feature subset selection and analyse how they perform in a benchmark with eight large-scale transcriptome datasets of cancer, covering both training and external validation sets. The benchmark includes evaluation metrics assessing the performance of the individual biomarkers and the solution sets, according to their accuracy, diversity, and stability of the composing genes. Moreover, a new evaluation metric for cross-validation studies is proposed that generalizes the hypervolume, which is commonly used to assess the performance of multi-objective optimization algorithms. Biomarkers exhibiting 0.8 of balanced accuracy on the external dataset for breast, kidney and ovarian cancer using respectively 4, 2 and 7 features, were obtained. Genetic algorithms often provided better performance than other considered algorithms, and the recently proposed NSGA2-CH and NSGA2-CHS were the best performing methods in most cases.Machine learning algorithms have been extensively used for accurate classification of cancer subtypes driven by gene expression-based biomarkers. However, biomarker models combining multiple gene expression signatures are often not reproducible in external validation datasets and their feature set size is often not optimized, jeopardizing their translatability into cost-effective clinical tools. We investigated how to solve the multi-objective problem of finding the best trade-offs between classification performance and set size applying seven algorithms for machine learning-driven feature subset selection and analyse how they perform in a benchmark with eight large-scale transcriptome datasets of cancer, covering both training and external validation sets. The benchmark includes evaluation metrics assessing the performance of the individual biomarkers and the solution sets, according to their accuracy, diversity, and stability of the composing genes. Moreover, a new evaluation metric for cross-validation studies is proposed that generalizes the hypervolume, which is commonly used to assess the performance of multi-objective optimization algorithms. Biomarkers exhibiting 0.8 of balanced accuracy on the external dataset for breast, kidney and ovarian cancer using respectively 4, 2 and 7 features, were obtained. Genetic algorithms often provided better performance than other considered algorithms, and the recently proposed NSGA2-CH and NSGA2-CHS were the best performing methods in most cases.
Author	Rintala, Teemu J. Fortino, Vittorio Ghosh, Arindam Cattelani, Luca
Author_xml	– sequence: 1 givenname: Luca orcidid: 0000-0003-4852-2310 surname: Cattelani fullname: Cattelani, Luca email: luca.cattelani@uef.fi organization: Institute of Biomedicine, School of Medicine, University of Eastern Finland, Kuopio, Finland – sequence: 2 givenname: Arindam orcidid: 0000-0002-8779-0986 surname: Ghosh fullname: Ghosh, Arindam email: arindam.ghosh@uef.fi organization: Institute of Biomedicine, School of Medicine, University of Eastern Finland, Kuopio, Finland – sequence: 3 givenname: Teemu J. orcidid: 0000-0003-1849-235X surname: Rintala fullname: Rintala, Teemu J. email: teemu.rintala@uef.fi organization: Institute of Biomedicine, School of Medicine, University of Eastern Finland, Kuopio, Finland – sequence: 4 givenname: Vittorio orcidid: 0000-0001-8693-5285 surname: Fortino fullname: Fortino, Vittorio email: vittorio.fortino@uef.fi organization: Institute of Biomedicine, School of Medicine, University of Eastern Finland, Kuopio, Finland
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/39401114$$D View this record in MEDLINE/PubMed
BookMark	eNp9kc1u1DAUhS1URH_gAZAQ8pJNBt_4L142Q6cgFc2Cso4c54a6TeLBTgaVp2_CDAixYOUr6_vsq3POyckQBiTkNbAVADPvb9dlucpZLlZcFAwke0bOQEqdGaPEyTILmUmj-Ck5T-mezaRh4gU55UYwABBn5OclXYd-F_EOh-T3SK_2tpvs6MNAN9H2-CPEB9qGSEsc3F1v44MfvtHPUzf6bFvfoxsXa4N2nCLSL9gtN7PsB7rtvUtZaRM2tPRhcTHSDz65sMf4-JI8b22X8NXxvCBfN1e364_Zzfb60_ryJnNcyTFDRIbcSC1ZnmPbaOd0LlpWg27qQmrIUeWmqAs0QjScCetANQKaQlmnLecX5N3h3V0M3ydMY9XPK2DX2QHDlCoOoJSWHPSMvj2iU91jU-2in7d-rH7nNQNwAFwMKUVs_yDAqqWTaumkWjqpjp3Mjv7HcX78lfAYre_-a745mH4O4a-fNCguOX8CKSyZ9A
CODEN	ITCBCY
CitedBy_id	crossref_primary_10_1093_bib_bbae674 crossref_primary_10_3390_biomedinformatics5030034
Cites_doi	10.1007/978-1-4614-6940-7_15 10.1016/j.compbiomed.2023.106854 10.1073/pnas.2009192117 10.1016/j.ress.2005.11.018 10.4137/CMO.S18006 10.1111/j.2517-6161.1996.tb02080.x 10.1093/jnci/dju249 10.1093/bioadv/vbac074 10.2166/hydro.2014.116 10.1200/CCI.19.00119 10.1016/j.cmpb.2019.06.029 10.1016/j.crmeth.2023.100461 10.1186/s41241-020-00089-8 10.1038/s41746-024-01043-6 10.1007/s12032-022-01711-1 10.1016/j.bbe.2019.10.001 10.1109/4235.996017 10.1016/S1672-0229(08)60050-9 10.3389/fonc.2022.932689 10.1038/sj.bjc.6600776 10.1109/TSMCB.2012.2227469 10.1109/TEVC.2013.2281535 10.1007/978-0-85729-652-8_1 10.1038/s41467-022-31609-5 10.4111/kju.2014.55.4.239 10.1093/bioinformatics/btz521 10.1038/s41586-021-04278-5 10.1145/3300148 10.1093/bioinformatics/btaa144 10.1016/j.asoc.2024.112332 10.1056/NEJMoa041588 10.1007/978-3-540-70928-2_64 10.1007/s10549-017-4619-4 10.21037/tlcr-22-151 10.1038/s41540-018-0056-1 10.1158/0008-5472.CAN-12-3232 10.1007/978-981-99-4749-2_61 10.1016/j.heliyon.2019.e02826 10.1186/1741-7015-10-87 10.1093/bioinformatics/btac463 10.1109/MCI.2006.1597059 10.1373/clinchem.2016.254649 10.1186/s13046-021-02026-1 10.1093/ckj/sfaa188 10.1109/TEVC.2015.2504420 10.1002/jcb.29620 10.1038/onc.2017.48
ContentType	Journal Article
DBID	97E ESBDL RIA RIE AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8
DOI	10.1109/TCBB.2024.3480150
DatabaseName	IEEE Xplore (IEEE) IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic MEDLINE
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Biology
EISSN	1557-9964
EndPage	2446
ExternalDocumentID	39401114 10_1109_TCBB_2024_3480150 10716353
Genre	orig-research Research Support, Non-U.S. Gov't Journal Article
GrantInformation_xml	– fundername: Jane and Aatos Erkko Foundation grantid: 210026 – fundername: Academy of Finland grantid: 336275; 332510; 358037 funderid: 10.13039/501100002341
GroupedDBID	0R~ 29I 4.4 53G 5GY 5VS 6IK 8US 97E AAJGR AAKMM AALFJ AARMG AASAJ AAWTH AAWTV ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACM ACPRK ADBCU ADL AEBYY AEFXT AEJOY AENEX AENSD AETIX AFRAH AFWIH AFWXC AGQYO AGSQL AHBIQ AIBXA AIKLT AKJIK AKQYR AKRVB ALMA_UNASSIGNED_HOLDINGS ASPBG ATWAV AVWKF BDXCO BEFXN BFFAM BGNUA BKEBE BPEOZ CCLIF CS3 DU5 EBS EJD ESBDL FEDTE GUFHI HGAVV HZ~ I07 IEDLZ IFIPE IPLJI JAVBF LAI LHSKQ M43 O9- OCL P1C P2P PQQKQ RIA RIE RNI RNS ROL RZB TN5 XOL AAYXX CITATION CGR CUY CVF ECM EIF NPM RIG 7X8
ID	FETCH-LOGICAL-c365t-eee0e39575022efd7cc724f0b17db85712e6298b8e944d304ac16d41d86ac7a33
IEDL.DBID	RIE
ISICitedReferencesCount	1
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001375732400037&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1545-5963 1557-9964
IngestDate	Sun Sep 28 16:13:24 EDT 2025 Wed Aug 06 16:36:18 EDT 2025 Tue Nov 18 22:16:48 EST 2025 Sat Nov 29 01:52:07 EST 2025 Wed Aug 27 02:33:19 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	6
Language	English
License	https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c365t-eee0e39575022efd7cc724f0b17db85712e6298b8e944d304ac16d41d86ac7a33
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ORCID	0000-0002-8779-0986 0000-0003-4852-2310 0000-0003-1849-235X 0000-0001-8693-5285
OpenAccessLink	https://ieeexplore.ieee.org/document/10716353
PMID	39401114
PQID	3116675317
PQPubID	23479
PageCount	15
ParticipantIDs	proquest_miscellaneous_3116675317 pubmed_primary_39401114 crossref_primary_10_1109_TCBB_2024_3480150 ieee_primary_10716353 crossref_citationtrail_10_1109_TCBB_2024_3480150
PublicationCentury	2000
PublicationDate	2024-11-01
PublicationDateYYYYMMDD	2024-11-01
PublicationDate_xml	– month: 11 year: 2024 text: 2024-11-01 day: 01
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States
PublicationTitle	IEEE/ACM transactions on computational biology and bioinformatics
PublicationTitleAbbrev	TCBB
PublicationTitleAlternate	IEEE/ACM Trans Comput Biol Bioinform
PublicationYear	2024
Publisher	IEEE
Publisher_xml	– name: IEEE
References	ref13 ref15 ref14 ref11 ref10 ref17 ref16 ref19 ref18 Stahlecker (ref44) 2000; 20 ref50 ref46 ref45 ref48 ref42 ref41 ref43 Guyon (ref12) 2002 ref49 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 ref35 ref34 ref37 ref36 Zhan (ref47) 2015; 7 ref31 ref30 ref33 ref32 ref2 ref1 ref39 ref38 ref24 ref23 ref26 ref25 ref20 ref22 ref21 ref28 ref27 ref29
References_xml	– ident: ref11 doi: 10.1007/978-1-4614-6940-7_15 – ident: ref23 doi: 10.1016/j.compbiomed.2023.106854 – volume: 7 start-page: 1398 issue: 8 year: 2015 ident: ref47 article-title: Identification of immunohistochemical markers for distinguishing lung adenocarcinoma from squamous cell carcinoma publication-title: J. Thoracic Dis. – ident: ref5 doi: 10.1073/pnas.2009192117 – ident: ref29 doi: 10.1016/j.ress.2005.11.018 – ident: ref42 doi: 10.4137/CMO.S18006 – volume-title: Gene Selectionfor Cancer Classification Using Support Vector Machines year: 2002 ident: ref12 – ident: ref31 doi: 10.1111/j.2517-6161.1996.tb02080.x – ident: ref49 doi: 10.1093/jnci/dju249 – ident: ref6 doi: 10.1093/bioadv/vbac074 – ident: ref21 doi: 10.2166/hydro.2014.116 – ident: ref39 doi: 10.1200/CCI.19.00119 – ident: ref17 doi: 10.1016/j.cmpb.2019.06.029 – ident: ref7 doi: 10.1016/j.crmeth.2023.100461 – ident: ref37 doi: 10.1186/s41241-020-00089-8 – ident: ref3 doi: 10.1038/s41746-024-01043-6 – ident: ref1 doi: 10.1007/s12032-022-01711-1 – volume: 20 start-page: 5041 issue: 6D year: 2000 ident: ref44 article-title: MIA as a reliable tumor marker in the serum of patients with malignant melanoma publication-title: Anticancer Res. – ident: ref18 doi: 10.1016/j.bbe.2019.10.001 – ident: ref15 doi: 10.1109/4235.996017 – ident: ref24 doi: 10.1016/S1672-0229(08)60050-9 – ident: ref50 doi: 10.3389/fonc.2022.932689 – ident: ref41 doi: 10.1038/sj.bjc.6600776 – ident: ref22 doi: 10.1109/TSMCB.2012.2227469 – ident: ref27 doi: 10.1109/TEVC.2013.2281535 – ident: ref30 doi: 10.1007/978-0-85729-652-8_1 – ident: ref19 doi: 10.1038/s41467-022-31609-5 – ident: ref46 doi: 10.4111/kju.2014.55.4.239 – ident: ref20 doi: 10.1093/bioinformatics/btz521 – ident: ref2 doi: 10.1038/s41586-021-04278-5 – ident: ref33 doi: 10.1145/3300148 – ident: ref4 doi: 10.1093/bioinformatics/btaa144 – ident: ref26 doi: 10.1016/j.asoc.2024.112332 – ident: ref34 doi: 10.1056/NEJMoa041588 – ident: ref25 doi: 10.1007/978-3-540-70928-2_64 – ident: ref35 doi: 10.1007/s10549-017-4619-4 – ident: ref48 doi: 10.21037/tlcr-22-151 – ident: ref16 doi: 10.1038/s41540-018-0056-1 – ident: ref9 doi: 10.1158/0008-5472.CAN-12-3232 – ident: ref14 doi: 10.1007/978-981-99-4749-2_61 – ident: ref38 doi: 10.1016/j.heliyon.2019.e02826 – ident: ref10 doi: 10.1186/1741-7015-10-87 – ident: ref13 doi: 10.1093/bioinformatics/btac463 – ident: ref28 doi: 10.1109/MCI.2006.1597059 – ident: ref8 doi: 10.1373/clinchem.2016.254649 – ident: ref36 doi: 10.1186/s13046-021-02026-1 – ident: ref40 doi: 10.1093/ckj/sfaa188 – ident: ref32 doi: 10.1109/TEVC.2015.2504420 – ident: ref45 doi: 10.1002/jcb.29620 – ident: ref43 doi: 10.1038/onc.2017.48
SSID	ssj0024904
Score	2.395192
Snippet	Machine learning algorithms have been extensively used for accurate classification of cancer subtypes driven by gene expression-based biomarkers. However,...
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	2432
SubjectTerms	Accuracy Algorithms Benchmark testing Benchmarking Biological system modeling biology and genetics Biomarkers, Tumor - analysis Biomarkers, Tumor - genetics Biomarkers, Tumor - metabolism Cancer Classification algorithms Computational Biology - methods Databases, Genetic evolutionary computing and genetic algorithms Feature extraction Gene Expression Profiling - methods Genetic algorithms Humans Machine Learning Measurement Neoplasms - genetics Neoplasms - metabolism Prediction algorithms Training Transcriptome - genetics
Title	A Comprehensive Evaluation Framework for Benchmarking Multi-Objective Feature Selection in Omics-Based Biomarker Discovery
URI	https://ieeexplore.ieee.org/document/10716353 https://www.ncbi.nlm.nih.gov/pubmed/39401114 https://www.proquest.com/docview/3116675317
Volume	21
WOSCitedRecordID	wos001375732400037&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1557-9964 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0024904 issn: 1545-5963 databaseCode: RIE dateStart: 20040101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3db9MwED-xCSRe2IABHTAZiSekDCexY-dx3VbxtCExpL5FsX3VOrEUpS3S-Ou5s9MCD0PiLQ--ONHd-e58Hz-A96Ylp0CjptgETaZmQWeuLrgCYGYdoleylRFswlxc2Om0_jw0q8deGESMxWd4zI8xlx8Wfs1XZaTh5N2XutyBHWOq1Kz1e7BeHbEC2SXINInVkMLMZf3x6nQ8plCwUMclT0vRDP_GiOCk5-ovexQBVu73NaPNmez959fuw5PBuRQnSRqewgPsnsGjBDd59xx-nghW_x6vU9W6ON-O-haTTZGWIC9WjEl2r2_beI8uYo9udulu0tko2Gtc9yi-RAgdJp534vJ27pfZmGxiELQh02IvzuZLzzWidwfwdXJ-dfopG7AXMl9WepXR30jkHJ4mI4-zYLw3hZpJl5vgrDZ5gVVRW2exViqUUrU-r4LKg61ab9qyfAG73aLDVyAwON3aoK0LloJB6Ug4TB48HR2uKqQZgdxwoPHDYHLGx_jWxABF1g3zr2H-NQP_RvBhS_I9TeX41-IDZs4fCxNfRvBuw-eGdIoTJW2Hi_WyKfO8okCKXKsRvEwCsKXeyM3hPW99DY9589Su-AZ2V_0a38JD_2M1X_ZHJLhTexQF9xdb0Oci
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB5BAcGFZ4GlPIzECSnFSezYOXZLV0WULRKL1FsU27PqIppF2V2k9td3xsku5VAkbjnYiaMZe77xPD6Ad6YmUKBRk2-CJlHToBNXZpwBMLUO0StZy0g2YcZje3JSfu2L1WMtDCLG5DPc5ccYyw9zv-KrMtrhhO5znd-EW0yd1Zdr_WmtV0a2QAYFiSbF6oOYqSw_TPaHQ3IGM7Wbc78UzQRwzAlOO139ZZEixcr1aDNandGD_1zvQ7jfw0ux1-nDI7iBzWO40xFOnj-Biz3BB0CLp13eujjYNPsWo3WaliAcK4akvadndbxJF7FKNzl2P7rTUTBuXLUovkUSHZ48a8Tx2cwvkiFZxSDogzwXW_FxtvCcJXq-Dd9HB5P9w6RnX0h8XuhlQn8jkaN4msw8ToPx3mRqKl1qgrPapBkWWWmdxVKpkEtV-7QIKg22qL2p8_wpbDXzBp-DwOB0bYO2LlhyB6Uj9TBp8HR4uCKTZgByLYHK963JmSHjZxVdFFlWLL-K5Vf18hvA-82UX11fjn8N3mbhXBnYyWUAb9dyrmhXcaikbnC-WlR5mhbkShG4GsCzTgE2s9d68-Kat76Bu4eTL0fV0afx5x24xwvpihdfwtayXeEruO1_L2eL9nVU30sbEOmD
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+Comprehensive+Evaluation+Framework+for+Benchmarking+Multi-Objective+Feature+Selection+in+Omics-Based+Biomarker+Discovery&rft.jtitle=IEEE%2FACM+transactions+on+computational+biology+and+bioinformatics&rft.au=Cattelani%2C+Luca&rft.au=Ghosh%2C+Arindam&rft.au=Rintala%2C+Teemu+J.&rft.au=Fortino%2C+Vittorio&rft.date=2024-11-01&rft.pub=IEEE&rft.issn=1545-5963&rft.volume=21&rft.issue=6&rft.spage=2432&rft.epage=2446&rft_id=info:doi/10.1109%2FTCBB.2024.3480150&rft_id=info%3Apmid%2F39401114&rft.externalDocID=10716353
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1545-5963&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1545-5963&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1545-5963&client=summon