SVM-RFE: selection and visualization of the most relevant features through non-linear kernels

Background Support vector machines (SVM) are a powerful tool to analyze data with a number of predictors approximately equal or larger than the number of observations. However, originally, application of SVM to analyze biomedical data was limited because SVM was not designed to evaluate importance o...

Full description

Saved in:
Bibliographic Details
Published inBMC bioinformatics Vol. 19; no. 1; pp. 432 - 18
Main Authors Sanz, Hector, Valim, Clarissa, Vegas, Esteban, Oller, Josep M., Reverter, Ferran
Format Journal Article
LanguageEnglish
Published London BioMed Central 19.11.2018
BioMed Central Ltd
BMC
Subjects
Online AccessGet full text
ISSN1471-2105
1471-2105
DOI10.1186/s12859-018-2451-4

Cover

Abstract Background Support vector machines (SVM) are a powerful tool to analyze data with a number of predictors approximately equal or larger than the number of observations. However, originally, application of SVM to analyze biomedical data was limited because SVM was not designed to evaluate importance of predictor variables. Creating predictor models based on only the most relevant variables is essential in biomedical research. Currently, substantial work has been done to allow assessment of variable importance in SVM models but this work has focused on SVM implemented with linear kernels. The power of SVM as a prediction model is associated with the flexibility generated by use of non-linear kernels. Moreover, SVM has been extended to model survival outcomes. This paper extends the Recursive Feature Elimination (RFE) algorithm by proposing three approaches to rank variables based on non-linear SVM and SVM for survival analysis. Results The proposed algorithms allows visualization of each one the RFE iterations, and hence, identification of the most relevant predictors of the response variable. Using simulation studies based on time-to-event outcomes and three real datasets, we evaluate the three methods, based on pseudo-samples and kernel principal component analysis, and compare them with the original SVM-RFE algorithm for non-linear kernels. The three algorithms we proposed performed generally better than the gold standard RFE for non-linear kernels, when comparing the truly most relevant variables with the variable ranks produced by each algorithm in simulation studies. Generally, the RFE-pseudo-samples outperformed the other three methods, even when variables were assumed to be correlated in all tested scenarios. Conclusions The proposed approaches can be implemented with accuracy to select variables and assess direction and strength of associations in analysis of biomedical data using SVM for categorical or time-to-event responses. Conducting variable selection and interpreting direction and strength of associations between predictors and outcomes with the proposed approaches, particularly with the RFE-pseudo-samples approach can be implemented with accuracy when analyzing biomedical data. These approaches, perform better than the classical RFE of Guyon for realistic scenarios about the structure of biomedical data.
AbstractList Support vector machines (SVM) are a powerful tool to analyze data with a number of predictors approximately equal or larger than the number of observations. However, originally, application of SVM to analyze biomedical data was limited because SVM was not designed to evaluate importance of predictor variables. Creating predictor models based on only the most relevant variables is essential in biomedical research. Currently, substantial work has been done to allow assessment of variable importance in SVM models but this work has focused on SVM implemented with linear kernels. The power of SVM as a prediction model is associated with the flexibility generated by use of non-linear kernels. Moreover, SVM has been extended to model survival outcomes. This paper extends the Recursive Feature Elimination (RFE) algorithm by proposing three approaches to rank variables based on non-linear SVM and SVM for survival analysis. The proposed algorithms allows visualization of each one the RFE iterations, and hence, identification of the most relevant predictors of the response variable. Using simulation studies based on time-to-event outcomes and three real datasets, we evaluate the three methods, based on pseudo-samples and kernel principal component analysis, and compare them with the original SVM-RFE algorithm for non-linear kernels. The three algorithms we proposed performed generally better than the gold standard RFE for non-linear kernels, when comparing the truly most relevant variables with the variable ranks produced by each algorithm in simulation studies. Generally, the RFE-pseudo-samples outperformed the other three methods, even when variables were assumed to be correlated in all tested scenarios. The proposed approaches can be implemented with accuracy to select variables and assess direction and strength of associations in analysis of biomedical data using SVM for categorical or time-to-event responses. Conducting variable selection and interpreting direction and strength of associations between predictors and outcomes with the proposed approaches, particularly with the RFE-pseudo-samples approach can be implemented with accuracy when analyzing biomedical data. These approaches, perform better than the classical RFE of Guyon for realistic scenarios about the structure of biomedical data.
Background Support vector machines (SVM) are a powerful tool to analyze data with a number of predictors approximately equal or larger than the number of observations. However, originally, application of SVM to analyze biomedical data was limited because SVM was not designed to evaluate importance of predictor variables. Creating predictor models based on only the most relevant variables is essential in biomedical research. Currently, substantial work has been done to allow assessment of variable importance in SVM models but this work has focused on SVM implemented with linear kernels. The power of SVM as a prediction model is associated with the flexibility generated by use of non-linear kernels. Moreover, SVM has been extended to model survival outcomes. This paper extends the Recursive Feature Elimination (RFE) algorithm by proposing three approaches to rank variables based on non-linear SVM and SVM for survival analysis. Results The proposed algorithms allows visualization of each one the RFE iterations, and hence, identification of the most relevant predictors of the response variable. Using simulation studies based on time-to-event outcomes and three real datasets, we evaluate the three methods, based on pseudo-samples and kernel principal component analysis, and compare them with the original SVM-RFE algorithm for non-linear kernels. The three algorithms we proposed performed generally better than the gold standard RFE for non-linear kernels, when comparing the truly most relevant variables with the variable ranks produced by each algorithm in simulation studies. Generally, the RFE-pseudo-samples outperformed the other three methods, even when variables were assumed to be correlated in all tested scenarios. Conclusions The proposed approaches can be implemented with accuracy to select variables and assess direction and strength of associations in analysis of biomedical data using SVM for categorical or time-to-event responses. Conducting variable selection and interpreting direction and strength of associations between predictors and outcomes with the proposed approaches, particularly with the RFE-pseudo-samples approach can be implemented with accuracy when analyzing biomedical data. These approaches, perform better than the classical RFE of Guyon for realistic scenarios about the structure of biomedical data.
Support vector machines (SVM) are a powerful tool to analyze data with a number of predictors approximately equal or larger than the number of observations. However, originally, application of SVM to analyze biomedical data was limited because SVM was not designed to evaluate importance of predictor variables. Creating predictor models based on only the most relevant variables is essential in biomedical research. Currently, substantial work has been done to allow assessment of variable importance in SVM models but this work has focused on SVM implemented with linear kernels. The power of SVM as a prediction model is associated with the flexibility generated by use of non-linear kernels. Moreover, SVM has been extended to model survival outcomes. This paper extends the Recursive Feature Elimination (RFE) algorithm by proposing three approaches to rank variables based on non-linear SVM and SVM for survival analysis.BACKGROUNDSupport vector machines (SVM) are a powerful tool to analyze data with a number of predictors approximately equal or larger than the number of observations. However, originally, application of SVM to analyze biomedical data was limited because SVM was not designed to evaluate importance of predictor variables. Creating predictor models based on only the most relevant variables is essential in biomedical research. Currently, substantial work has been done to allow assessment of variable importance in SVM models but this work has focused on SVM implemented with linear kernels. The power of SVM as a prediction model is associated with the flexibility generated by use of non-linear kernels. Moreover, SVM has been extended to model survival outcomes. This paper extends the Recursive Feature Elimination (RFE) algorithm by proposing three approaches to rank variables based on non-linear SVM and SVM for survival analysis.The proposed algorithms allows visualization of each one the RFE iterations, and hence, identification of the most relevant predictors of the response variable. Using simulation studies based on time-to-event outcomes and three real datasets, we evaluate the three methods, based on pseudo-samples and kernel principal component analysis, and compare them with the original SVM-RFE algorithm for non-linear kernels. The three algorithms we proposed performed generally better than the gold standard RFE for non-linear kernels, when comparing the truly most relevant variables with the variable ranks produced by each algorithm in simulation studies. Generally, the RFE-pseudo-samples outperformed the other three methods, even when variables were assumed to be correlated in all tested scenarios.RESULTSThe proposed algorithms allows visualization of each one the RFE iterations, and hence, identification of the most relevant predictors of the response variable. Using simulation studies based on time-to-event outcomes and three real datasets, we evaluate the three methods, based on pseudo-samples and kernel principal component analysis, and compare them with the original SVM-RFE algorithm for non-linear kernels. The three algorithms we proposed performed generally better than the gold standard RFE for non-linear kernels, when comparing the truly most relevant variables with the variable ranks produced by each algorithm in simulation studies. Generally, the RFE-pseudo-samples outperformed the other three methods, even when variables were assumed to be correlated in all tested scenarios.The proposed approaches can be implemented with accuracy to select variables and assess direction and strength of associations in analysis of biomedical data using SVM for categorical or time-to-event responses. Conducting variable selection and interpreting direction and strength of associations between predictors and outcomes with the proposed approaches, particularly with the RFE-pseudo-samples approach can be implemented with accuracy when analyzing biomedical data. These approaches, perform better than the classical RFE of Guyon for realistic scenarios about the structure of biomedical data.CONCLUSIONSThe proposed approaches can be implemented with accuracy to select variables and assess direction and strength of associations in analysis of biomedical data using SVM for categorical or time-to-event responses. Conducting variable selection and interpreting direction and strength of associations between predictors and outcomes with the proposed approaches, particularly with the RFE-pseudo-samples approach can be implemented with accuracy when analyzing biomedical data. These approaches, perform better than the classical RFE of Guyon for realistic scenarios about the structure of biomedical data.
Support vector machines (SVM) are a powerful tool to analyze data with a number of predictors approximately equal or larger than the number of observations. However, originally, application of SVM to analyze biomedical data was limited because SVM was not designed to evaluate importance of predictor variables. Creating predictor models based on only the most relevant variables is essential in biomedical research. Currently, substantial work has been done to allow assessment of variable importance in SVM models but this work has focused on SVM implemented with linear kernels. The power of SVM as a prediction model is associated with the flexibility generated by use of non-linear kernels. Moreover, SVM has been extended to model survival outcomes. This paper extends the Recursive Feature Elimination (RFE) algorithm by proposing three approaches to rank variables based on non-linear SVM and SVM for survival analysis. The proposed algorithms allows visualization of each one the RFE iterations, and hence, identification of the most relevant predictors of the response variable. Using simulation studies based on time-to-event outcomes and three real datasets, we evaluate the three methods, based on pseudo-samples and kernel principal component analysis, and compare them with the original SVM-RFE algorithm for non-linear kernels. The three algorithms we proposed performed generally better than the gold standard RFE for non-linear kernels, when comparing the truly most relevant variables with the variable ranks produced by each algorithm in simulation studies. Generally, the RFE-pseudo-samples outperformed the other three methods, even when variables were assumed to be correlated in all tested scenarios. The proposed approaches can be implemented with accuracy to select variables and assess direction and strength of associations in analysis of biomedical data using SVM for categorical or time-to-event responses. Conducting variable selection and interpreting direction and strength of associations between predictors and outcomes with the proposed approaches, particularly with the RFE-pseudo-samples approach can be implemented with accuracy when analyzing biomedical data. These approaches, perform better than the classical RFE of Guyon for realistic scenarios about the structure of biomedical data.
Background Support vector machines (SVM) are a powerful tool to analyze data with a number of predictors approximately equal or larger than the number of observations. However, originally, application of SVM to analyze biomedical data was limited because SVM was not designed to evaluate importance of predictor variables. Creating predictor models based on only the most relevant variables is essential in biomedical research. Currently, substantial work has been done to allow assessment of variable importance in SVM models but this work has focused on SVM implemented with linear kernels. The power of SVM as a prediction model is associated with the flexibility generated by use of non-linear kernels. Moreover, SVM has been extended to model survival outcomes. This paper extends the Recursive Feature Elimination (RFE) algorithm by proposing three approaches to rank variables based on non-linear SVM and SVM for survival analysis. Results The proposed algorithms allows visualization of each one the RFE iterations, and hence, identification of the most relevant predictors of the response variable. Using simulation studies based on time-to-event outcomes and three real datasets, we evaluate the three methods, based on pseudo-samples and kernel principal component analysis, and compare them with the original SVM-RFE algorithm for non-linear kernels. The three algorithms we proposed performed generally better than the gold standard RFE for non-linear kernels, when comparing the truly most relevant variables with the variable ranks produced by each algorithm in simulation studies. Generally, the RFE-pseudo-samples outperformed the other three methods, even when variables were assumed to be correlated in all tested scenarios. Conclusions The proposed approaches can be implemented with accuracy to select variables and assess direction and strength of associations in analysis of biomedical data using SVM for categorical or time-to-event responses. Conducting variable selection and interpreting direction and strength of associations between predictors and outcomes with the proposed approaches, particularly with the RFE-pseudo-samples approach can be implemented with accuracy when analyzing biomedical data. These approaches, perform better than the classical RFE of Guyon for realistic scenarios about the structure of biomedical data. Keywords: Support vector machines, Relevant variables, Recursive feature elimination, Kernel methods
Abstract Background Support vector machines (SVM) are a powerful tool to analyze data with a number of predictors approximately equal or larger than the number of observations. However, originally, application of SVM to analyze biomedical data was limited because SVM was not designed to evaluate importance of predictor variables. Creating predictor models based on only the most relevant variables is essential in biomedical research. Currently, substantial work has been done to allow assessment of variable importance in SVM models but this work has focused on SVM implemented with linear kernels. The power of SVM as a prediction model is associated with the flexibility generated by use of non-linear kernels. Moreover, SVM has been extended to model survival outcomes. This paper extends the Recursive Feature Elimination (RFE) algorithm by proposing three approaches to rank variables based on non-linear SVM and SVM for survival analysis. Results The proposed algorithms allows visualization of each one the RFE iterations, and hence, identification of the most relevant predictors of the response variable. Using simulation studies based on time-to-event outcomes and three real datasets, we evaluate the three methods, based on pseudo-samples and kernel principal component analysis, and compare them with the original SVM-RFE algorithm for non-linear kernels. The three algorithms we proposed performed generally better than the gold standard RFE for non-linear kernels, when comparing the truly most relevant variables with the variable ranks produced by each algorithm in simulation studies. Generally, the RFE-pseudo-samples outperformed the other three methods, even when variables were assumed to be correlated in all tested scenarios. Conclusions The proposed approaches can be implemented with accuracy to select variables and assess direction and strength of associations in analysis of biomedical data using SVM for categorical or time-to-event responses. Conducting variable selection and interpreting direction and strength of associations between predictors and outcomes with the proposed approaches, particularly with the RFE-pseudo-samples approach can be implemented with accuracy when analyzing biomedical data. These approaches, perform better than the classical RFE of Guyon for realistic scenarios about the structure of biomedical data.
Background Support vector machines (SVM) are a powerful tool to analyze data with a number of predictors approximately equal or larger than the number of observations. However, originally, application of SVM to analyze biomedical data was limited because SVM was not designed to evaluate importance of predictor variables. Creating predictor models based on only the most relevant variables is essential in biomedical research. Currently, substantial work has been done to allow assessment of variable importance in SVM models but this work has focused on SVM implemented with linear kernels. The power of SVM as a prediction model is associated with the flexibility generated by use of non-linear kernels. Moreover, SVM has been extended to model survival outcomes. This paper extends the Recursive Feature Elimination (RFE) algorithm by proposing three approaches to rank variables based on non-linear SVM and SVM for survival analysis. Results The proposed algorithms allows visualization of each one the RFE iterations, and hence, identification of the most relevant predictors of the response variable. Using simulation studies based on time-to-event outcomes and three real datasets, we evaluate the three methods, based on pseudo-samples and kernel principal component analysis, and compare them with the original SVM-RFE algorithm for non-linear kernels. The three algorithms we proposed performed generally better than the gold standard RFE for non-linear kernels, when comparing the truly most relevant variables with the variable ranks produced by each algorithm in simulation studies. Generally, the RFE-pseudo-samples outperformed the other three methods, even when variables were assumed to be correlated in all tested scenarios. Conclusions The proposed approaches can be implemented with accuracy to select variables and assess direction and strength of associations in analysis of biomedical data using SVM for categorical or time-to-event responses. Conducting variable selection and interpreting direction and strength of associations between predictors and outcomes with the proposed approaches, particularly with the RFE-pseudo-samples approach can be implemented with accuracy when analyzing biomedical data. These approaches, perform better than the classical RFE of Guyon for realistic scenarios about the structure of biomedical data.
ArticleNumber 432
Audience Academic
Author Reverter, Ferran
Vegas, Esteban
Oller, Josep M.
Valim, Clarissa
Sanz, Hector
Author_xml – sequence: 1
  givenname: Hector
  orcidid: 0000-0001-6540-8427
  surname: Sanz
  fullname: Sanz, Hector
  email: hsrodenas@gmail.com
  organization: Department of Genetics, Microbiology and Statistics, Faculty of Biology, Universitat de Barcelona
– sequence: 2
  givenname: Clarissa
  surname: Valim
  fullname: Valim, Clarissa
  organization: Department of Osteopathic Medical Specialties, Michigan State University, Department of Immunology and Infectious Diseases, Harvard T.H. Chen School of Public Health
– sequence: 3
  givenname: Esteban
  surname: Vegas
  fullname: Vegas, Esteban
  organization: Department of Genetics, Microbiology and Statistics, Faculty of Biology, Universitat de Barcelona
– sequence: 4
  givenname: Josep M.
  surname: Oller
  fullname: Oller, Josep M.
  organization: Department of Genetics, Microbiology and Statistics, Faculty of Biology, Universitat de Barcelona
– sequence: 5
  givenname: Ferran
  surname: Reverter
  fullname: Reverter, Ferran
  organization: Department of Genetics, Microbiology and Statistics, Faculty of Biology, Universitat de Barcelona, Centre for Genomic Regulation (CRG), The Barcelona Institute for Science and Technology
BackLink https://www.ncbi.nlm.nih.gov/pubmed/30453885$$D View this record in MEDLINE/PubMed
BookMark eNqNUl1v0zAUjdAQ-4AfwAuKxAs8ZNjOhxMekKZpg0pDSNvEG7JunOvWJbU72ymMX4_TjqpFaEKRleT6nHOPj-9xcmCswSR5SckppXX1zlNWl01GaJ2xoqRZ8SQ5ogWnGaOkPNj5PkyOvZ8TQnlNymfJYU6KMq_r8ij5dvP1c3Z9efE-9dijDNqaFEyXrrQfoNe_YF2xKg0zTBfWh9RF3ApMSBVCGBz6uOXsMJ2l0V3Wa4Pg0u_oDPb-efJUQe_xxcP7JLm9vLg9_5Rdffk4OT-7yiSnPGRQ8Q7iKZSCpiI1SlIAQgs5Y0XFFVSMdihZThvGQBW0UI1UwCDviGwU5CfJZCPbWZiLpdMLcPfCghbrgnVTAS5o2aNoSdvWVUFRlrygtGjbllVVxfIOeWxTRC220RrMEu5_QN9vBSkRY-xiE7uIhsUYuxhJHzak5dAusJNogoN-z8n-jtEzMbUrUUWBhpEoQDcC0g9SOJToJIQ1cfszLkY4E3nJWc0j581DU2fvBvRBLLSX2Pdg0A5eMJpXpOQ5HaGvN9ApxAy0UTa6kCNcnJUVq1kTDxNRp_9AxafDhZZx9JSO9T3C2z1CxAT8GaYweC8mN9f72Fe7EW2z-TOKOxE4671D9V-58784Uof1yEbnun-U-XDNPnYxU3Ribgdn4pA-QvoNHQsQPg
CitedBy_id crossref_primary_10_3389_fgene_2023_1154839
crossref_primary_10_1016_j_intimp_2024_112766
crossref_primary_10_2147_PRBM_S460283
crossref_primary_10_1007_s42979_022_01500_7
crossref_primary_10_3389_fnagi_2023_1169620
crossref_primary_10_3390_diagnostics11030574
crossref_primary_10_1097_MD_0000000000038917
crossref_primary_10_3390_diagnostics12071771
crossref_primary_10_3724_abbs_2024014
crossref_primary_10_1109_TCBB_2024_3421228
crossref_primary_10_1038_s41598_020_76334_5
crossref_primary_10_1017_dce_2024_60
crossref_primary_10_3389_fimmu_2023_1158379
crossref_primary_10_1155_2022_3439010
crossref_primary_10_1007_s00432_023_04903_y
crossref_primary_10_1007_s10142_023_01270_2
crossref_primary_10_1016_j_waojou_2024_100964
crossref_primary_10_3389_fonc_2023_1179897
crossref_primary_10_3389_fmicb_2023_1191004
crossref_primary_10_1016_j_diii_2020_10_004
crossref_primary_10_1016_j_eswa_2025_126612
crossref_primary_10_1109_ACCESS_2020_3043715
crossref_primary_10_1109_JSTARS_2024_3357520
crossref_primary_10_3389_fimmu_2022_974935
crossref_primary_10_1177_03000605231213781
crossref_primary_10_3389_fgene_2021_622683
crossref_primary_10_3389_fimmu_2025_1486961
crossref_primary_10_1016_j_agrformet_2021_108698
crossref_primary_10_1016_j_foodchem_2023_137940
crossref_primary_10_1007_s12035_024_04461_5
crossref_primary_10_1186_s12967_024_05934_w
crossref_primary_10_4103_1673_5374_391306
crossref_primary_10_1016_j_cor_2023_106485
crossref_primary_10_3390_jimaging11030086
crossref_primary_10_1038_s41598_024_72979_8
crossref_primary_10_1186_s12891_021_04109_8
crossref_primary_10_1016_j_heliyon_2025_e41831
crossref_primary_10_3389_fendo_2022_957010
crossref_primary_10_1080_07391102_2021_1970628
crossref_primary_10_3389_fmed_2024_1309510
crossref_primary_10_3390_biom13010039
crossref_primary_10_1007_s11165_019_9835_y
crossref_primary_10_3389_fendo_2022_955630
crossref_primary_10_3389_fmicb_2024_1349374
crossref_primary_10_1155_2022_5475313
crossref_primary_10_1016_j_acra_2024_12_041
crossref_primary_10_1080_07391102_2024_2440651
crossref_primary_10_3389_fonc_2022_1030335
crossref_primary_10_1016_j_bbrc_2023_149180
crossref_primary_10_1109_TLT_2023_3281056
crossref_primary_10_1109_ACCESS_2022_3232307
crossref_primary_10_3390_math10091480
crossref_primary_10_3389_fmicb_2025_1528865
crossref_primary_10_1007_s10753_023_01851_0
crossref_primary_10_1007_s12672_025_01869_w
crossref_primary_10_1155_2022_2373694
crossref_primary_10_1155_2022_6732780
crossref_primary_10_1007_s11064_025_04352_8
crossref_primary_10_1093_bioinformatics_btab074
crossref_primary_10_3389_fmed_2023_1158166
crossref_primary_10_1016_j_heliyon_2024_e35511
crossref_primary_10_3389_fendo_2024_1372221
crossref_primary_10_47992_IJMTS_2581_6012_0206
crossref_primary_10_3389_fneur_2024_1354062
crossref_primary_10_1080_21655979_2021_1933743
crossref_primary_10_1038_s41598_024_81844_7
crossref_primary_10_3390_biom14010013
crossref_primary_10_1186_s13018_024_04590_6
crossref_primary_10_1016_j_jmoldx_2024_03_003
crossref_primary_10_1038_s41598_024_74409_1
crossref_primary_10_1016_j_eswa_2024_125126
crossref_primary_10_1016_j_cellsig_2025_111705
crossref_primary_10_3389_fmed_2024_1382004
crossref_primary_10_3389_fgene_2022_1078790
crossref_primary_10_3389_fimmu_2022_906889
crossref_primary_10_3389_fimmu_2024_1388690
crossref_primary_10_1093_bfgp_elac025
crossref_primary_10_3389_fimmu_2024_1424259
crossref_primary_10_3390_rs14133153
crossref_primary_10_3389_fimmu_2024_1374465
crossref_primary_10_1016_j_heliyon_2024_e35408
crossref_primary_10_1016_j_comptc_2024_114551
crossref_primary_10_1016_j_heliyon_2023_e21071
crossref_primary_10_3389_fonc_2024_1411214
crossref_primary_10_3389_fphar_2022_865624
crossref_primary_10_1016_j_atmosenv_2020_117971
crossref_primary_10_1109_ACCESS_2024_3412655
crossref_primary_10_3389_fimmu_2024_1429817
crossref_primary_10_1007_s00262_022_03343_w
crossref_primary_10_17537_2020_15_4
crossref_primary_10_1186_s40001_024_01988_0
crossref_primary_10_3389_fendo_2023_1203120
crossref_primary_10_3389_fmicb_2023_1261889
crossref_primary_10_1038_s41598_025_90578_z
crossref_primary_10_1016_j_intimp_2025_114220
crossref_primary_10_1007_s00262_022_03221_5
crossref_primary_10_1080_10255842_2023_2236744
crossref_primary_10_3389_fimmu_2024_1329009
crossref_primary_10_3389_fmed_2023_1132676
crossref_primary_10_1016_j_bbrc_2024_150674
crossref_primary_10_1097_CIN_0000000000000765
crossref_primary_10_1186_s13019_024_03199_4
crossref_primary_10_18632_aging_203962
crossref_primary_10_3892_etm_2024_12695
crossref_primary_10_1111_cns_13196
crossref_primary_10_1016_j_heliyon_2024_e30209
crossref_primary_10_1016_j_acra_2024_08_038
crossref_primary_10_3892_etm_2022_11500
crossref_primary_10_1155_2023_5199810
crossref_primary_10_1007_s10278_024_01231_6
crossref_primary_10_1155_2022_4407541
crossref_primary_10_1002_hbm_26395
crossref_primary_10_1007_s11042_023_17825_1
crossref_primary_10_3389_fgene_2021_758103
crossref_primary_10_1007_s00432_023_05287_9
crossref_primary_10_1007_s10115_023_01915_5
crossref_primary_10_1007_s00430_023_00767_8
crossref_primary_10_2174_18741207_v16_e2208300
crossref_primary_10_3389_fcvm_2023_1268675
crossref_primary_10_32604_biocell_2023_043864
crossref_primary_10_1007_s10462_021_10088_y
crossref_primary_10_3389_fimmu_2023_1305025
crossref_primary_10_1111_andr_13238
crossref_primary_10_2147_JIR_S452608
crossref_primary_10_1080_0886022X_2022_2081579
crossref_primary_10_1186_s41065_024_00354_8
crossref_primary_10_1016_j_molimm_2024_07_015
crossref_primary_10_1038_s41598_022_26345_1
crossref_primary_10_2147_IJGM_S351168
crossref_primary_10_3390_ph17040429
crossref_primary_10_1007_s12672_025_01955_z
crossref_primary_10_1016_j_heliyon_2024_e38022
crossref_primary_10_1007_s00382_022_06646_x
crossref_primary_10_1016_j_heliyon_2024_e28935
crossref_primary_10_1016_j_imbio_2024_152841
crossref_primary_10_3389_fimmu_2023_1142215
crossref_primary_10_1002_hbm_25095
crossref_primary_10_1016_j_heliyon_2025_e41872
crossref_primary_10_4037_ajcc2025349
crossref_primary_10_3389_fmolb_2024_1425143
crossref_primary_10_3390_jcm11092310
crossref_primary_10_1007_s00170_020_06129_5
crossref_primary_10_3389_fcvm_2022_848840
crossref_primary_10_1038_s41598_025_91376_3
crossref_primary_10_1111_jog_15720
crossref_primary_10_3390_su12187365
crossref_primary_10_1016_j_heliyon_2024_e37612
crossref_primary_10_1186_s12891_025_08528_9
crossref_primary_10_1016_j_heliyon_2025_e42956
crossref_primary_10_1007_s00011_023_01849_2
crossref_primary_10_3389_fcell_2024_1486170
crossref_primary_10_3389_fendo_2022_1056310
crossref_primary_10_3389_fimmu_2022_952708
crossref_primary_10_3389_fimmu_2023_1286203
crossref_primary_10_3389_fimmu_2024_1416297
crossref_primary_10_1080_21691401_2025_2471762
crossref_primary_10_1016_j_ajpath_2024_03_013
crossref_primary_10_1038_s41598_024_74862_y
crossref_primary_10_3389_fimmu_2023_1304165
crossref_primary_10_3233_IDT_210227
crossref_primary_10_2147_IJGM_S478146
crossref_primary_10_3389_fendo_2023_1134325
crossref_primary_10_3389_fimmu_2022_1007326
crossref_primary_10_1007_s12033_023_01026_0
crossref_primary_10_1016_j_euf_2021_05_005
crossref_primary_10_1016_j_intimp_2023_110968
crossref_primary_10_1186_s12931_024_02845_8
crossref_primary_10_1002_jsp2_70050
crossref_primary_10_1186_s12887_024_04555_y
crossref_primary_10_1016_j_energy_2021_121543
crossref_primary_10_1186_s12891_023_06303_2
crossref_primary_10_1186_s13048_024_01375_7
crossref_primary_10_1186_s12865_023_00581_0
crossref_primary_10_18632_aging_202713
crossref_primary_10_2147_VHRM_S429535
crossref_primary_10_3389_fimmu_2023_1251750
crossref_primary_10_2174_0115672050339307241108101528
crossref_primary_10_7717_peerj_17011
crossref_primary_10_1038_s41598_023_48990_w
crossref_primary_10_1016_j_arabjc_2023_105485
crossref_primary_10_1016_j_jocn_2021_05_015
crossref_primary_10_1515_jib_2019_0110
crossref_primary_10_1016_j_procs_2024_10_127
crossref_primary_10_1080_15412555_2024_2379811
crossref_primary_10_1155_2022_2069756
crossref_primary_10_3389_fonc_2023_1047377
crossref_primary_10_2147_JIR_S493889
crossref_primary_10_3389_fmed_2024_1322102
crossref_primary_10_1109_TAFFC_2019_2943551
crossref_primary_10_1109_ACCESS_2023_3275967
crossref_primary_10_1016_j_humgen_2024_201258
crossref_primary_10_1016_j_ygeno_2020_06_014
crossref_primary_10_3389_fendo_2024_1440436
crossref_primary_10_3233_IDT_220077
crossref_primary_10_3390_genes13101916
crossref_primary_10_1016_j_bspc_2024_106503
crossref_primary_10_1089_omi_2023_0015
crossref_primary_10_18632_aging_203378
crossref_primary_10_1038_s41598_024_68890_x
crossref_primary_10_1016_j_ijbiomac_2025_140793
crossref_primary_10_1186_s41065_025_00390_y
crossref_primary_10_2147_IJGM_S352330
crossref_primary_10_1007_s11042_024_18793_w
crossref_primary_10_1080_21655979_2021_1950258
crossref_primary_10_1093_sexmed_qfae090
crossref_primary_10_1093_rheumatology_keaf134
crossref_primary_10_1109_JBHI_2022_3221639
crossref_primary_10_1016_j_geoderma_2024_117026
crossref_primary_10_2147_JIR_S489847
crossref_primary_10_3390_diagnostics13061203
crossref_primary_10_1186_s40001_025_02454_1
crossref_primary_10_3389_fdmed_2024_1480346
crossref_primary_10_1111_iwj_14815
crossref_primary_10_3390_app13148289
crossref_primary_10_31083_j_fbl2812343
crossref_primary_10_1002_jcb_29376
crossref_primary_10_1016_j_compbiomed_2022_106413
crossref_primary_10_3389_fimmu_2024_1396221
crossref_primary_10_3390_app131810076
crossref_primary_10_1155_2021_6633563
crossref_primary_10_3389_fimmu_2024_1460431
crossref_primary_10_4018_IJSI_303582
crossref_primary_10_1007_s10528_023_10449_y
crossref_primary_10_1186_s40164_022_00335_5
crossref_primary_10_1016_j_patrec_2022_11_013
crossref_primary_10_3389_fonc_2021_757111
crossref_primary_10_1155_2022_3140370
crossref_primary_10_1186_s12885_022_09540_1
crossref_primary_10_3389_fimmu_2022_1015436
crossref_primary_10_1016_j_asoc_2019_105538
crossref_primary_10_1016_j_compbiomed_2023_107220
crossref_primary_10_3389_fcvm_2024_1478827
crossref_primary_10_1016_j_intimp_2024_111809
crossref_primary_10_12998_wjcc_v12_i20_4091
crossref_primary_10_1038_s41598_024_73441_5
crossref_primary_10_3389_fgene_2022_814264
crossref_primary_10_3389_fonc_2022_889833
crossref_primary_10_3389_fimmu_2023_1177968
crossref_primary_10_1007_s12035_024_04647_x
crossref_primary_10_1115_1_4066923
crossref_primary_10_1016_j_heliyon_2024_e40151
crossref_primary_10_1038_s41598_024_77409_3
crossref_primary_10_7717_peerj_18310
crossref_primary_10_1109_ACCESS_2025_3547813
crossref_primary_10_1002_iid3_70137
crossref_primary_10_3389_fgene_2022_1037520
crossref_primary_10_1186_s12859_023_05404_y
crossref_primary_10_3389_fimmu_2023_1164667
crossref_primary_10_1186_s41065_024_00350_y
crossref_primary_10_3389_fsurg_2022_891984
crossref_primary_10_3390_antiox12010186
crossref_primary_10_2147_JIR_S459819
crossref_primary_10_3390_mi14112047
crossref_primary_10_1155_2022_9043300
crossref_primary_10_1186_s40659_021_00334_6
crossref_primary_10_1016_j_lfs_2020_118248
crossref_primary_10_1186_s41065_024_00335_x
crossref_primary_10_1186_s13287_025_04247_z
crossref_primary_10_3389_fgene_2021_762136
crossref_primary_10_1016_j_ijbiomac_2025_142277
crossref_primary_10_3389_fpls_2021_777028
crossref_primary_10_3934_mbe_2022402
crossref_primary_10_1016_j_burns_2025_107413
crossref_primary_10_1186_s13048_023_01338_4
crossref_primary_10_1109_ACCESS_2025_3538278
crossref_primary_10_3389_fimmu_2022_1042484
crossref_primary_10_3389_fimmu_2022_1053819
crossref_primary_10_3390_buildings14051471
crossref_primary_10_15212_CVIA_2024_0011
crossref_primary_10_1016_j_intimp_2024_113256
crossref_primary_10_1097_MD_0000000000034918
crossref_primary_10_3389_fneur_2024_1387477
crossref_primary_10_2174_1874120702115010001
crossref_primary_10_1016_j_heliyon_2024_e28997
crossref_primary_10_3389_fimmu_2024_1456083
crossref_primary_10_3390_brainsci12101349
crossref_primary_10_1007_s10142_024_01415_x
crossref_primary_10_1038_s41598_022_19027_5
crossref_primary_10_3389_fimmu_2023_1114870
crossref_primary_10_1097_MD_0000000000038721
crossref_primary_10_1155_2021_5582920
crossref_primary_10_3389_fgene_2021_720888
crossref_primary_10_1186_s12859_024_05899_z
crossref_primary_10_1109_ACCESS_2019_2926377
crossref_primary_10_1002_cam4_70016
crossref_primary_10_1016_j_ygyno_2021_07_015
crossref_primary_10_1038_s41598_023_31797_0
crossref_primary_10_3389_fgene_2022_1010361
crossref_primary_10_3389_fendo_2022_957742
crossref_primary_10_1186_s41065_023_00295_8
crossref_primary_10_12677_acm_2024_1472093
crossref_primary_10_1155_2022_1425032
crossref_primary_10_1186_s12958_019_0556_x
crossref_primary_10_1016_j_compbiomed_2023_107818
crossref_primary_10_1111_exsy_70002
crossref_primary_10_2147_DMSO_S445341
crossref_primary_10_3389_fimmu_2024_1370647
crossref_primary_10_1016_j_ijbiomac_2025_139775
crossref_primary_10_1111_jcmm_70323
crossref_primary_10_1038_s41598_024_77033_1
crossref_primary_10_1002_jmv_28706
crossref_primary_10_3389_fgene_2022_1032010
crossref_primary_10_1080_07391102_2023_2233021
crossref_primary_10_3233_JAD_201254
crossref_primary_10_1016_j_jad_2025_03_057
crossref_primary_10_3389_fendo_2025_1512503
crossref_primary_10_1016_j_chbr_2022_100267
crossref_primary_10_18632_aging_205875
crossref_primary_10_3389_fmolb_2025_1506961
crossref_primary_10_3390_cimb46090619
crossref_primary_10_3390_ijms21197271
crossref_primary_10_1155_2022_6934744
crossref_primary_10_1038_s41598_024_81681_8
crossref_primary_10_1016_j_csbj_2024_04_024
crossref_primary_10_1371_journal_pone_0259475
crossref_primary_10_1016_j_heliyon_2024_e36158
crossref_primary_10_1007_s10044_025_01411_2
crossref_primary_10_1186_s13062_024_00461_6
crossref_primary_10_1007_s00477_022_02330_y
crossref_primary_10_18632_aging_205199
crossref_primary_10_1186_s13020_024_01018_5
crossref_primary_10_2174_1386207323666200428120310
crossref_primary_10_1016_j_aca_2021_339352
crossref_primary_10_1097_MD_0000000000034371
crossref_primary_10_1007_s00261_024_04641_w
crossref_primary_10_1038_s41598_024_77642_w
crossref_primary_10_1038_s41598_024_59907_6
crossref_primary_10_3390_genes15060676
crossref_primary_10_3389_fimmu_2023_1147501
crossref_primary_10_1016_j_eti_2024_103998
crossref_primary_10_1186_s13062_024_00529_3
crossref_primary_10_3389_fimmu_2022_905921
crossref_primary_10_1080_07853890_2024_2397572
crossref_primary_10_1186_s12888_025_06542_8
crossref_primary_10_1093_gigascience_giad083
crossref_primary_10_1111_jcmm_70107
crossref_primary_10_1016_j_heliyon_2024_e30269
crossref_primary_10_1186_s12883_024_03533_2
crossref_primary_10_18632_aging_205961
crossref_primary_10_1016_j_heliyon_2024_e29860
crossref_primary_10_1186_s40001_023_01622_5
crossref_primary_10_2147_NDT_S511671
crossref_primary_10_1002_iid3_1058
crossref_primary_10_1186_s13036_024_00466_9
crossref_primary_10_1186_s12859_019_2754_0
crossref_primary_10_3390_diagnostics11020347
crossref_primary_10_1007_s12665_022_10578_4
crossref_primary_10_3389_fcvm_2022_1053697
crossref_primary_10_3389_fgene_2022_1065297
crossref_primary_10_1038_s41598_024_52094_4
crossref_primary_10_1186_s40360_025_00844_z
crossref_primary_10_3390_metabo12111058
crossref_primary_10_1016_j_heliyon_2023_e17454
crossref_primary_10_1007_s12035_025_04819_3
crossref_primary_10_1016_j_jocs_2020_101238
crossref_primary_10_3389_fgene_2023_1136783
crossref_primary_10_1002_iid3_70059
crossref_primary_10_1007_s00330_022_08830_3
crossref_primary_10_3389_fgene_2023_1264873
crossref_primary_10_1016_j_ejphar_2023_175568
crossref_primary_10_3389_fcell_2022_901207
crossref_primary_10_3389_fimmu_2022_1001070
crossref_primary_10_1016_j_ejro_2024_100615
crossref_primary_10_1097_MD_0000000000037862
crossref_primary_10_3389_fcvm_2023_1058834
crossref_primary_10_7717_peerj_18591
crossref_primary_10_1002_iid3_70170
crossref_primary_10_1038_s41598_025_89252_1
crossref_primary_10_1016_j_heliyon_2024_e28085
crossref_primary_10_1038_s41598_024_81129_z
Cites_doi 10.1007/978-3-540-35488-8_13
10.1016/j.eswa.2011.08.051
10.1016/j.ins.2009.02.014
10.1007/978-1-4419-7787-8
10.7551/mitpress/4175.001.0001
10.1186/1471-2105-12-138
10.1093/bioinformatics/btp286
10.1002/sim.2059
10.1023/A:1012487302797
10.1007/BF01386316
10.1109/72.788641
10.1007/s10462-011-9205-2
10.1016/j.jesp.2013.03.013
10.1093/bioinformatics/btm344
10.1021/ac101338y
10.1186/1752-0509-8-S2-S6
10.1016/j.ejor.2015.01.006
10.1016/j.aca.2011.04.025
ContentType Journal Article
Contributor Universitat de Barcelona
Contributor_xml – sequence: 1
  fullname: Universitat de Barcelona
Copyright The Author(s). 2018
COPYRIGHT 2018 BioMed Central Ltd.
cc-by (c) Sanz, Hector et al., 2018 info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by/3.0/es
Copyright_xml – notice: The Author(s). 2018
– notice: COPYRIGHT 2018 BioMed Central Ltd.
– notice: cc-by (c) Sanz, Hector et al., 2018 info:eu-repo/semantics/openAccess <a href="http://creativecommons.org/licenses/by/3.0/es">http://creativecommons.org/licenses/by/3.0/es</a>
DBID C6C
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
ISR
7X8
XX2
5PM
ADTOC
UNPAY
DOA
DOI 10.1186/s12859-018-2451-4
DatabaseName Springer Nature OA Free Journals
CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
Gale In Context: Science
MEDLINE - Academic
Recercat
PubMed Central (Full Participant titles)
Unpaywall for CDI: Periodical Content
Unpaywall
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE

MEDLINE - Academic





Database_xml – sequence: 1
  dbid: C6C
  name: Springer Open Access
  url: http://www.springeropen.com/
  sourceTypes: Publisher
– sequence: 2
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 3
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 4
  dbid: EIF
  name: MEDLINE
  url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search
  sourceTypes: Index Database
– sequence: 5
  dbid: UNPAY
  name: Unpaywall
  url: https://proxy.k.utb.cz/login?url=https://unpaywall.org/
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Biology
EISSN 1471-2105
EndPage 18
ExternalDocumentID oai_doaj_org_article_b0bb8641ec574114bbb266623de76214
10.1186/s12859-018-2451-4
PMC6245920
oai_recercat_cat_2072_357287
A562829018
30453885
10_1186_s12859_018_2451_4
Genre Journal Article
GrantInformation_xml – fundername: MINECO/FEDER
  grantid: MTM2015-64465-C2-1-R; MTM2015-64465-C2-1-R
– fundername: MINECO/FEDER
  grantid: MTM2015-64465-C2-1-R
– fundername: ;
  grantid: MTM2015-64465-C2-1-R; MTM2015-64465-C2-1-R
GroupedDBID ---
0R~
23N
2WC
53G
5VS
6J9
7X7
88E
8AO
8FE
8FG
8FH
8FI
8FJ
AAFWJ
AAJSJ
AAKPC
AASML
ABDBF
ABUWG
ACGFO
ACGFS
ACIHN
ACIWK
ACPRK
ACUHS
ADBBV
ADMLS
ADRAZ
ADUKV
AEAQA
AENEX
AEUYN
AFKRA
AFPKN
AFRAH
AHBYD
AHMBA
AHYZX
ALMA_UNASSIGNED_HOLDINGS
AMKLP
AMTXH
AOIJS
ARAPS
AZQEC
BAPOH
BAWUL
BBNVY
BCNDV
BENPR
BFQNJ
BGLVJ
BHPHI
BMC
BPHCQ
BVXVI
C6C
CCPQU
CS3
DIK
DU5
DWQXO
E3Z
EAD
EAP
EAS
EBD
EBLON
EBS
EJD
EMB
EMK
EMOBN
ESX
F5P
FYUFA
GNUQQ
GROUPED_DOAJ
GX1
H13
HCIFZ
HMCUK
HYE
IAO
ICD
IHR
INH
INR
ISR
ITC
K6V
K7-
KQ8
LK8
M1P
M48
M7P
MK~
ML0
M~E
O5R
O5S
OK1
OVT
P2P
P62
PGMZT
PHGZM
PHGZT
PIMPY
PJZUB
PPXIY
PQGLB
PQQKQ
PROAC
PSQYO
PUEGO
RBZ
RNS
ROL
RPM
RSV
SBL
SOJ
SV3
TR2
TUS
UKHRP
W2D
WOQ
WOW
XH6
XSB
AAYXX
CITATION
-A0
3V.
ACRMQ
ADINQ
ALIPV
C24
CGR
CUY
CVF
ECM
EIF
M0N
NPM
7X8
XX2
5PM
123
2VQ
4.4
ADTOC
AFFHD
AHSBF
C1A
IPNFZ
RIG
UNPAY
ID FETCH-LOGICAL-c717t-a67da018ffa9608ec04aeaba322467fa621dec231922af414f9cfa2a3d0c9fa3
IEDL.DBID M48
ISSN 1471-2105
IngestDate Fri Oct 03 12:33:43 EDT 2025
Wed Oct 29 12:03:38 EDT 2025
Tue Sep 30 16:41:21 EDT 2025
Sat Oct 18 15:20:05 EDT 2025
Thu Sep 04 20:31:19 EDT 2025
Mon Oct 20 21:58:02 EDT 2025
Mon Oct 20 16:29:40 EDT 2025
Thu Oct 16 14:21:26 EDT 2025
Wed Feb 19 02:36:33 EST 2025
Wed Oct 01 04:15:31 EDT 2025
Thu Apr 24 23:07:06 EDT 2025
Sat Sep 06 07:27:15 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Keywords Support vector machines
Kernel methods
Recursive feature elimination
Relevant variables
Language English
License Open AccessThis article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated.
cc-by
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c717t-a67da018ffa9608ec04aeaba322467fa621dec231922af414f9cfa2a3d0c9fa3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0001-6540-8427
OpenAccessLink http://journals.scholarsportal.info/openUrl.xqy?doi=10.1186/s12859-018-2451-4
PMID 30453885
PQID 2136057317
PQPubID 23479
PageCount 18
ParticipantIDs doaj_primary_oai_doaj_org_article_b0bb8641ec574114bbb266623de76214
unpaywall_primary_10_1186_s12859_018_2451_4
pubmedcentral_primary_oai_pubmedcentral_nih_gov_6245920
csuc_recercat_oai_recercat_cat_2072_357287
proquest_miscellaneous_2136057317
gale_infotracmisc_A562829018
gale_infotracacademiconefile_A562829018
gale_incontextgauss_ISR_A562829018
pubmed_primary_30453885
crossref_primary_10_1186_s12859_018_2451_4
crossref_citationtrail_10_1186_s12859_018_2451_4
springer_journals_10_1186_s12859_018_2451_4
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2018-11-19
PublicationDateYYYYMMDD 2018-11-19
PublicationDate_xml – month: 11
  year: 2018
  text: 2018-11-19
  day: 19
PublicationDecade 2010
PublicationPlace London
PublicationPlace_xml – name: London
– name: England
PublicationTitle BMC bioinformatics
PublicationTitleAbbrev BMC Bioinformatics
PublicationTitleAlternate BMC Bioinformatics
PublicationYear 2018
Publisher BioMed Central
BioMed Central Ltd
BMC
Publisher_xml – name: BioMed Central
– name: BioMed Central Ltd
– name: BMC
References N Becker (2451_CR8) 2011; 12
JF Benders (2451_CR6) 1962; 4
F Reverter (2451_CR16) 2014; 8
H-T Shiao (2451_CR20) 2013
PWT Krooshof (2451_CR12) 2010; 82
2451_CR17
S Maldonado (2451_CR3) 2009; 179
2451_CR5
2451_CR2
I Guyon (2451_CR1) 2002; 46
H Aytug (2451_CR4) 2015; 244
Q Liu (2451_CR10) 2011; 36
E Niaf (2451_CR21) 2011
GJ Postma (2451_CR13) 2011; 705
Y Saeys (2451_CR9) 2007; 23
B Scholkopf (2451_CR18) 1999; 10
F Alonso-Atienza (2451_CR11) 2012; 39
N Becker (2451_CR7) 2009; 25
C Leys (2451_CR15) 2013; 49
R Bender (2451_CR19) 2005; 24
David Ruppert (2451_CR14) 2011
References_xml – ident: 2451_CR2
  doi: 10.1007/978-3-540-35488-8_13
– volume: 39
  start-page: 1956
  year: 2012
  ident: 2451_CR11
  publication-title: Expert Syst Appl
  doi: 10.1016/j.eswa.2011.08.051
– volume: 179
  start-page: 2208
  year: 2009
  ident: 2451_CR3
  publication-title: Inf Sci
  doi: 10.1016/j.ins.2009.02.014
– volume-title: Statistics and Data Analysis for Financial Engineering
  year: 2011
  ident: 2451_CR14
  doi: 10.1007/978-1-4419-7787-8
– ident: 2451_CR17
  doi: 10.7551/mitpress/4175.001.0001
– volume: 12
  start-page: 138
  issue: 1
  year: 2011
  ident: 2451_CR8
  publication-title: BMC Bioinformatics
  doi: 10.1186/1471-2105-12-138
– volume: 25
  start-page: 1711
  year: 2009
  ident: 2451_CR7
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/btp286
– volume: 24
  start-page: 1713
  year: 2005
  ident: 2451_CR19
  publication-title: Stat Med
  doi: 10.1002/sim.2059
– start-page: 1
  volume-title: In Proceedings of the International Conference on Data Mining (DMIN)
  year: 2013
  ident: 2451_CR20
– ident: 2451_CR5
– volume: 46
  start-page: 389
  year: 2002
  ident: 2451_CR1
  publication-title: Mach Learn
  doi: 10.1023/A:1012487302797
– volume: 4
  start-page: 238
  year: 1962
  ident: 2451_CR6
  publication-title: Numer Math
  doi: 10.1007/BF01386316
– volume: 10
  start-page: 1000
  year: 1999
  ident: 2451_CR18
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/72.788641
– volume: 36
  start-page: 99
  year: 2011
  ident: 2451_CR10
  publication-title: Artif Intell Rev
  doi: 10.1007/s10462-011-9205-2
– volume: 49
  start-page: 764
  year: 2013
  ident: 2451_CR15
  publication-title: J Exp Soc Psychol
  doi: 10.1016/j.jesp.2013.03.013
– volume: 23
  start-page: 2507
  year: 2007
  ident: 2451_CR9
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/btm344
– volume: 82
  start-page: 7000
  year: 2010
  ident: 2451_CR12
  publication-title: Anal Chem
  doi: 10.1021/ac101338y
– volume: 8
  start-page: S6
  issue: 2
  year: 2014
  ident: 2451_CR16
  publication-title: BMC Syst Biol
  doi: 10.1186/1752-0509-8-S2-S6
– start-page: 757
  volume-title: Statistical Signal Processing Workshop (SSP)
  year: 2011
  ident: 2451_CR21
– volume: 244
  start-page: 210
  year: 2015
  ident: 2451_CR4
  publication-title: Eur J Oper Res
  doi: 10.1016/j.ejor.2015.01.006
– volume: 705
  start-page: 123
  year: 2011
  ident: 2451_CR13
  publication-title: Anal Chim Acta
  doi: 10.1016/j.aca.2011.04.025
SSID ssj0017805
Score 2.6891632
Snippet Background Support vector machines (SVM) are a powerful tool to analyze data with a number of predictors approximately equal or larger than the number of...
Support vector machines (SVM) are a powerful tool to analyze data with a number of predictors approximately equal or larger than the number of observations....
Background Support vector machines (SVM) are a powerful tool to analyze data with a number of predictors approximately equal or larger than the number of...
Abstract Background Support vector machines (SVM) are a powerful tool to analyze data with a number of predictors approximately equal or larger than the number...
SourceID doaj
unpaywall
pubmedcentral
csuc
proquest
gale
pubmed
crossref
springer
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 432
SubjectTerms Algorismes
Algorithms
Analysis
Anàlisi vectorial
Bioinformatics
Biomarkers, Tumor - genetics
Biomedical and Life Sciences
Biometria
Biometry
Computational Biology/Bioinformatics
Computer Appl. in Life Sciences
Computer Graphics
Humans
Imports
Kernel methods
Knowledge-based analysis
Laws, regulations, etc
Life Sciences
Liver Cirrhosis, Biliary - genetics
Liver Cirrhosis, Biliary - mortality
Lung Neoplasms - genetics
Lung Neoplasms - mortality
Lymphoma, Large B-Cell, Diffuse - genetics
Lymphoma, Large B-Cell, Diffuse - mortality
Methodology
Methodology Article
Methods
Microarrays
Recursive feature elimination
Recursive functions
Relevant variables
Support Vector Machine
Support vector machines
Survival Rate
Vector analysis
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3da9RAEF_kQNSH4rfRKqsIgiU0m2ySjW9VelShPrRV-iLLfmrxmpRLTul_70yyFy4K7YsP93C3e5fbmdmd3zA7vyHkNQMQaoUrYl8xG3POK2zzwmINUKLIUm9tjsXJh5-Lgy_802l-utHqC--EDfTAg-B2daK1KDhzJgfnx7jWGnwKOG3rYB_3LazTRFTrYCrkD5CpP-QwmSh2W4Y8bRA2g1XwHIKmiReamXZlAmf_vyfzhmv6-9rkmDu9Q26t6gt1-VstFhvuaX6XbAVcSfeG9dwjN1x9n9wcOk1ePiDfjr8exkfz_Xe07RvfgDaoqi39ddZiVeVQi0kbTwEP0vOm7Sg2UwGU3VHveu7PloaWPrRu6hjBqVrSn25Zg3N9SE7m-ycfDuLQWSE2EL51sSpKq0Aa3iuIYIQzCVdOaZUhvVzpFQjWOgPQr0pT5TnjvjJepSqziam8yh6RGTzLPSEUfT4zxnBTWA5QUwMgcBrLTlQudJlFJFkLWprAOo7NLxayjz5EIQfdSPg3EnUjeUTejl-5GCg3rp4M2pPgHtzSqE4iXfb4Bl9pUqYyy0sIDSPyHnU8_irO7T8Ag5PB4OR1BheRV2ghEskzaryd812t2lZ-PD6SewAm-8S0iMibMMk3sFyjQrEDCA35tiYztyczYXebyfDLtSFKHMIrcbVrVq1MWVYgmyWDZT0eDHNcGKa_MyHyiJQTk52sfDpSn_3oycULkGuVJhHZWRu3DKdae5UWdkb7v15nT_-HGp6R2ynuZ7yRWW2TWbdcueeADzv9oj8K_gCRlFzE
  priority: 102
  providerName: Directory of Open Access Journals
– databaseName: Springer Nature OA Free Journals
  dbid: C6C
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fb9MwELagCAEPiN8EBjIICYkpIk4cJ-FtTKsG0njYBtoLsmzHhomSTHUK2n_PXeJGDaAhHvrQ-pLUvnPuO53vO0JeMAChdWlF7CpWx5zzCtu8sFgDlBBZ6uo6x-Lkgw9i_yN_f5KfBLJorIXZzN-zUrz2DBnWIOAFffIcwp3L5Ar4KNHnZcXumDBAav6QtPzrZRO3MzN-ZQJJ_5-v4g1f9Ps5yTFZeoNcWzVn6vynWiw2_NH8FrkZgCTdGTR_m1yyzR1ydWgteX6XfD76dBAfzvfeUN93uoHlp6qp6Y9Tj2WUQ_ElbR0FAEi_t76j2D0FYHVHne3JPj0NPXxo0zYxolG1pN_ssgFveo8cz_eOd_fj0EohNhCvdbESRa1gNZxTELKU1iRcWaVVhnxyhVMiZbU1gPWqNFWOM-4q41SqsjoxlVPZfTKDZ9mHhKKTZ8YYbkTNAVtqQABWY52JyktdZBFJ1gstTaAZx24XC9mHG6WQg24k_BuJupE8Iq_GS84Gjo2LhUF7EvyBXRrVSeTHHr_gJ02KVGZ5AbFgRN6ijse7omz_A5iYDFtT6kTrUnBmTQ7winGtNaAWgIW1BU_B4InP0UIksmU0eBzni1p5L98dHcodQI99JrqMyMsg5FqYrlGhugEWDQm2JpJbE0nYzmYy_GxtiBKH8AxcY9uVlynLBNJXMpjWg8Ewx4lhvjsryzwixcRkJzOfjjSnX3s2cQHrWqVJRLbXxi3Da8xfpIXt0f7_rbNH_3Xvx-R6ihsXz1pWW2TWLVf2CSC_Tj_t9_wvkqlNgw
  priority: 102
  providerName: Springer Nature
– databaseName: Unpaywall
  dbid: UNPAY
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3rb9MwELdGJwR84P0oDGQQEhJTujhxXnwraNNA2kB7oPEBWbZjj6pdUjUJaPz13CVp1Aw0hMSHSm19edi-8_1O9v2OkJcMQGgam9CxCUsdznmCZV6YowBKhL5n0zTA5OS9_XD3mH84CU7WyMdlLow602qSt6ShSFQ8Wk1Dn9VrN3zR0615ahuTj8OtgiEPG4TFMOs8gKDoClkPAwDnA7J-vP9p_KXOMYqYAwFO0O5t_vG6nnca6KLSLZf_7yv2isu6eJyy21O9Qa5V2Vye_5Cz2Yrb2rlF5ssON6dVpqOqVCP98wIX5H8ckdvkZgtx6bjRyTtkzWR3ydWm6OX5PfL18POec7Cz_YYWdQ0eUAwqs5R-nxSY4NmkhdLcUoCm9CwvSop1XQDwl9Samoa0oG11IZrlmYM4WS7o1Cwy8PP3ydHO9tG7Xact8uBoiCRLR4ZRKuE1rZUwX7HRLpdGKukj011kZeix1GhAoYnnScsZt4m20pN-6urESv8BGcCzzCNCEX4wrTXXYcoB9SrAJkZhBowMYhX5Q-Iu51bolgAd63DMRB0IxaFoBk3A2wgcNMGH5HV3ybxh_7hcGBRGgKcyCy1Lgczd3Q_8eG7kCT-IIEodkreoVt1dUbb-I1-cinbREMpVKg45MzoA4Me4UgrwFADW1IAPY_DEF6iUAnk8MjwodCqrohDvDw_EGHBtvUceD8mrVsjmqCeyzbuAQUPqr57kRk8SFhrda36-1H2BTXg6LzN5VQiP-SESazLo1sPGFrqO4U68H8fBkEQ9K-n1vN-STb7VPOchjGviuUOyubQn0S6wxWWzsNmZ3N_n7PE_ST8h1z20KDwFmmyQQbmozFPApKV61q4zvwDp6IP5
  priority: 102
  providerName: Unpaywall
Title SVM-RFE: selection and visualization of the most relevant features through non-linear kernels
URI https://link.springer.com/article/10.1186/s12859-018-2451-4
https://www.ncbi.nlm.nih.gov/pubmed/30453885
https://www.proquest.com/docview/2136057317
https://recercat.cat/handle/2072/357287
https://pubmed.ncbi.nlm.nih.gov/PMC6245920
https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-018-2451-4
https://doaj.org/article/b0bb8641ec574114bbb266623de76214
UnpaywallVersion publishedVersion
Volume 19
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVADU
  databaseName: BioMedCentral
  customDbUrl:
  eissn: 1471-2105
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017805
  issn: 1471-2105
  databaseCode: RBZ
  dateStart: 20000101
  isFulltext: true
  titleUrlDefault: https://www.biomedcentral.com/search/
  providerName: BioMedCentral
– providerCode: PRVAFT
  databaseName: Open Access Digital Library
  customDbUrl:
  eissn: 1471-2105
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017805
  issn: 1471-2105
  databaseCode: KQ8
  dateStart: 20000101
  isFulltext: true
  titleUrlDefault: http://grweb.coalliance.org/oadl/oadl.html
  providerName: Colorado Alliance of Research Libraries
– providerCode: PRVAFT
  databaseName: Open Access Digital Library
  customDbUrl:
  eissn: 1471-2105
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017805
  issn: 1471-2105
  databaseCode: KQ8
  dateStart: 20000701
  isFulltext: true
  titleUrlDefault: http://grweb.coalliance.org/oadl/oadl.html
  providerName: Colorado Alliance of Research Libraries
– providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 1471-2105
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017805
  issn: 1471-2105
  databaseCode: DOA
  dateStart: 20000101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVEBS
  databaseName: EBSCOhost Academic Search Ultimate
  customDbUrl: https://search.ebscohost.com/login.aspx?authtype=ip,shib&custid=s3936755&profile=ehost&defaultdb=asn
  eissn: 1471-2105
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017805
  issn: 1471-2105
  databaseCode: ABDBF
  dateStart: 20000101
  isFulltext: true
  titleUrlDefault: https://search.ebscohost.com/direct.asp?db=asn
  providerName: EBSCOhost
– providerCode: PRVEBS
  databaseName: Inspec with Full Text
  customDbUrl:
  eissn: 1471-2105
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017805
  issn: 1471-2105
  databaseCode: ADMLS
  dateStart: 20000101
  isFulltext: true
  titleUrlDefault: https://www.ebsco.com/products/research-databases/inspec-full-text
  providerName: EBSCOhost
– providerCode: PRVBFR
  databaseName: Free Medical Journals - Free Access to All
  customDbUrl:
  eissn: 1471-2105
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017805
  issn: 1471-2105
  databaseCode: DIK
  dateStart: 20000101
  isFulltext: true
  titleUrlDefault: http://www.freemedicaljournals.com
  providerName: Flying Publisher
– providerCode: PRVFQY
  databaseName: GFMER Free Medical Journals
  customDbUrl:
  eissn: 1471-2105
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017805
  issn: 1471-2105
  databaseCode: GX1
  dateStart: 0
  isFulltext: true
  titleUrlDefault: http://www.gfmer.ch/Medical_journals/Free_medical.php
  providerName: Geneva Foundation for Medical Education and Research
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 1471-2105
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017805
  issn: 1471-2105
  databaseCode: M~E
  dateStart: 20000101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVAQN
  databaseName: PubMed Central
  customDbUrl:
  eissn: 1471-2105
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017805
  issn: 1471-2105
  databaseCode: RPM
  dateStart: 20000101
  isFulltext: true
  titleUrlDefault: https://www.ncbi.nlm.nih.gov/pmc/
  providerName: National Library of Medicine
– providerCode: PRVPQU
  databaseName: Health & Medical Collection (Proquest)
  customDbUrl:
  eissn: 1471-2105
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017805
  issn: 1471-2105
  databaseCode: 7X7
  dateStart: 20090101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/healthcomplete
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest One Academic
  customDbUrl: http://www.proquest.com/pqcentral?accountid=15518
  eissn: 1471-2105
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017805
  issn: 1471-2105
  databaseCode: BENPR
  dateStart: 20090101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Technology Collection
  customDbUrl:
  eissn: 1471-2105
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017805
  issn: 1471-2105
  databaseCode: 8FG
  dateStart: 20090101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/technologycollection1
  providerName: ProQuest
– providerCode: PRVFZP
  databaseName: Scholars Portal Journals: Open Access
  customDbUrl:
  eissn: 1471-2105
  dateEnd: 20250131
  omitProxy: true
  ssIdentifier: ssj0017805
  issn: 1471-2105
  databaseCode: M48
  dateStart: 20000701
  isFulltext: true
  titleUrlDefault: http://journals.scholarsportal.info
  providerName: Scholars Portal
– providerCode: PRVAVX
  databaseName: HAS SpringerNature Open Access 2022
  customDbUrl:
  eissn: 1471-2105
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017805
  issn: 1471-2105
  databaseCode: AAJSJ
  dateStart: 20001201
  isFulltext: true
  titleUrlDefault: https://www.springernature.com
  providerName: Springer Nature
– providerCode: PRVAVX
  databaseName: Springer Open Access
  customDbUrl:
  eissn: 1471-2105
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017805
  issn: 1471-2105
  databaseCode: C6C
  dateStart: 20000112
  isFulltext: true
  titleUrlDefault: http://www.springeropen.com/
  providerName: Springer Nature
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1tb9MwELa2Tgj4gHinMCqDkJCYAnHivCEh1FUto1Krqd1Q-YAsx3HGRElGkgL999wlaVhgGnxoq8ZOUvvucs_VvucIecYAhEa-do04YJHBOQ-wzAszQoASrm3FUeRgcvJk6h4c8_HCWWyRTXmregLzC0M7rCd1nC1f_vy2fgsG_6Y0eN99lTNkYYOgGGTOHQiJtskOOKoAKzlM-O9FBaTvL5ONPGZApOPUi5wXXqLlpjoqX6ma1P_vR_c53_XnvspmcfU6ubpKzuT6h1wuz_mv0U1yowaetF9pyi2ypZPb5EpVinJ9h3yaf5gYs9HwNc3LyjggLiqTiH4_zTHtskrWpGlMATDSr2leUKy2AjC8oLEuyUFzWtf8oUmaGIheZUa_6CwB73uXHI2GR4MDoy69YCiI7wpDul4kYTbiWEKI42tlcqllKG3kn_Ni6Vos0gqwYWBZMuaMx4GKpSXtyFRBLO17pAP30g8IRVDAlFJcuREHLBoCYtAh5qVIxw89u0vMzUQLVdOSY3WMpSjDE98VlWwE_BqBshG8S140p5xVnByXdwbpCfAfOlOyEMin3XzBl2V6lrAdD2LHLtlHGTdXxb7lgTQ7EbUpi9AMQ9_lTCsH4BjjYRgCygEYGWnwLAzu-BQ1RCC7RoLbd07kKs_F-_lM9AFtlivXfpc8rzvFKQxXyTobAiYNCblaPXdbPcH8Vav5yUYRBTbhnrlEp6tcWMx2ke6SwbDuV4rZDAzXx23fd7rEa6lsa-TtluT0c8k-7sK8BpbZJXsb5RYbq71MCnuN_v9bZg__e3IekWsWGi3uywx2SafIVvoxoMQi7JFtb-HBuz961yM7_f54PobP_eH0cAZHB-6gV_7_0iufEdByPD3sf_wFMAVmaQ
linkProvider Scholars Portal
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3db9MwELegExo8IL4JDDAICYkpIk6cL94KWtWVdQ9rQXuZLNuxx0RJpiYF7b_nLnWjBdAQD31o4yS17-z7ne7ud4S8ZgBCi8wkvs1Z4XPOc2zzwnwFUCKJQlsUMRYnTw-T8Wc-OY6PXR13vcl234Qk25O63dZZ8q5myLUGri9Ilsfg-FwnW5hjBbtxaziczCZd8ABp-l0A86839kzQQNcr7Qj7_zyWL9ml33Mmu8DpLbK9Ks_lxU-5WFyyTaM75LYDlXS41oK75Jop75Eb6zaTF_fJyezL1D8a7b2nddv1BkRBZVnQH2c1llSuCzFpZSmAQfq9qhuKnVQAYjfUmpb4s6aunw8tq9JHZCqX9JtZlmBZH5D5aG_-cey7tgq-Bt-t8WWSFhJWw1oJ7ktmdMClkUpGyC2XWpmErDAacF8ehtJyxm2urQxlVAQ6tzJ6SAbwLvOYUDT4TGvNdVJwwJkK0IBRWHMi40ylkUeCzUIL7SjHsfPFQrSuR5aItWwE_BuBshHcI2-7W87XfBtXDwbpCbANZqllI5Aru_uCnzBIQxHFKfiFHvmAMu6eimPbH6rlqXDbVKhAqSzhzOgYoBbjSilAMAARCwNWg8EbX6GGCGTOKDE151Su6lrsz47EEJBkG5XOPPLGDbIVTFdLV-kAi4ZkW72RO72RsLV17_LLjSIKvIT5cKWpVrUIWZQglSWDaT1aK2Y3MYx9R1kWeyTtqWxv5v0r5dnXllk8gXXNw8AjuxvlFu5Iq6-Swm6n__-W2ZP_evYLsj2eTw_Ewf7hp6fkZoibGHMw8x0yaJYr8wwQYaOeuxPgF6o9Vdw
linkToPdf http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3db9MwELegiK8HxDeBAQYhITFFixPHSXgbZdUGbELbQHtBlu3YY6IkVZKC9t9zl6TRAmiIhz60dpLad879Tnf3O0JeMACheWqF7zKW-5zzDNu8MF8DlBBR6PI8xuLk3T2x_Ym_O4qP-j6n9SrbfRWS7GoakKWpaDYWueuOeCo2aoa8a-AGg5R5DE7QRXKJg3HDFgZTMR3CCEjY34cy_3rZyBhNTL00PXX_ny_oMxbq9-zJIYR6nVxdFgt1-lPN52es1OwmudHDS7rZ6cMtcsEWt8nlruHk6R3y5eDzrr8_23pN67b_DQiFqiKnP05qLK7sSjJp6SjAQvq9rBuKPVUAbDfU2ZYCtKZ9Zx9alIWPGFVV9JutCrCxd8nhbOtwuu33DRZ8A15c4yuR5Ap2wzkFjkxqTcCVVVpFyDKXOCVCllsDCDALQ-U44y4zToUqygOTORXdIxN4ln1AKJp-ZozhRuQcEKcGXGA1Vp-oONVJ5JFgtdHS9OTj2ANjLlsnJBWyk42EfyNRNpJ75NVwyaJj3jh_MkhPgpWwlVGNRNbs4Qt-wiAJZRQn4CF65A3KeLgrzm1_KKtj2R9YqQOtU8GZNTGALsa11oBlACzmFuwHgyc-Rw2RyKFRYJLOsVrWtdw52JebgCnb-HTqkZf9JFfCco3qax5g05B2azRzbTQTDrkZDT9bKaLEIcyMK2y5rGXIIoGklgyWdb9TzGFhGAWP0jT2SDJS2dHKxyPFydeWY1zAvmZh4JH1lXLL_uVWnyeF9UH__y2zh_9176fkyse3M_lhZ-_9I3ItxDOMyZjZGpk01dI-BmjY6Cft8f8F4opYuQ
linkToUnpaywall http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3rb9MwELdGJwR84P0oDGQQEhJTujhxXnwraNNA2kB7oPEBWbZjj6pdUjUJaPz13CVp1Aw0hMSHSm19edi-8_1O9v2OkJcMQGgam9CxCUsdznmCZV6YowBKhL5n0zTA5OS9_XD3mH84CU7WyMdlLow602qSt6ShSFQ8Wk1Dn9VrN3zR0615ahuTj8OtgiEPG4TFMOs8gKDoClkPAwDnA7J-vP9p_KXOMYqYAwFO0O5t_vG6nnca6KLSLZf_7yv2isu6eJyy21O9Qa5V2Vye_5Cz2Yrb2rlF5ssON6dVpqOqVCP98wIX5H8ckdvkZgtx6bjRyTtkzWR3ydWm6OX5PfL18POec7Cz_YYWdQ0eUAwqs5R-nxSY4NmkhdLcUoCm9CwvSop1XQDwl9Samoa0oG11IZrlmYM4WS7o1Cwy8PP3ydHO9tG7Xact8uBoiCRLR4ZRKuE1rZUwX7HRLpdGKukj011kZeix1GhAoYnnScsZt4m20pN-6urESv8BGcCzzCNCEX4wrTXXYcoB9SrAJkZhBowMYhX5Q-Iu51bolgAd63DMRB0IxaFoBk3A2wgcNMGH5HV3ybxh_7hcGBRGgKcyCy1Lgczd3Q_8eG7kCT-IIEodkreoVt1dUbb-I1-cinbREMpVKg45MzoA4Me4UgrwFADW1IAPY_DEF6iUAnk8MjwodCqrohDvDw_EGHBtvUceD8mrVsjmqCeyzbuAQUPqr57kRk8SFhrda36-1H2BTXg6LzN5VQiP-SESazLo1sPGFrqO4U68H8fBkEQ9K-n1vN-STb7VPOchjGviuUOyubQn0S6wxWWzsNmZ3N_n7PE_ST8h1z20KDwFmmyQQbmozFPApKV61q4zvwDp6IP5
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=SVM-RFE%3A+selection+and+visualization+of+the+most+relevant+features+through+non-linear+kernels&rft.jtitle=BMC+bioinformatics&rft.au=Sanz%2C+Hector&rft.au=Valim%2C+Clarissa&rft.au=Vegas%2C+Esteban&rft.au=Oller%2C+Josep+M&rft.date=2018-11-19&rft.pub=BioMed+Central+Ltd&rft.issn=1471-2105&rft.eissn=1471-2105&rft.volume=19&rft.issue=1&rft_id=info:doi/10.1186%2Fs12859-018-2451-4&rft.externalDocID=A562829018
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1471-2105&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1471-2105&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1471-2105&client=summon