Elastic net-based prediction of IFN-β treatment response of patients with multiple sclerosis using time series microarray gene expression profiles

INF-β has been widely used to treat patients with multiple sclerosis (MS) in relapse. Accurate prediction of treatment response is important for effective personalization of treatment. Microarray data have been frequently used to discover new genes and to predict treatment responses. However, conventional analytical methods suffer from three difficulties: high-dimensionality of datasets; high degree of multi-collinearity; and achieving gene identification in time-course data. The use of Elastic net, a sparse modelling method, would decrease the first two issues; however, Elastic net is currently unable to solve these three issues simultaneously. Here, we improved Elastic net to accommodate time-course data analyses. Numerical experiments were conducted using two time-course microarray datasets derived from peripheral blood mononuclear cells collected from patients with MS. The proposed methods successfully identified genes showing a high predictive ability for INF-β treatment response. Bootstrap sampling resulted in an 81% and 78% accuracy for each dataset, which was significantly higher than the 71% and 73% accuracy obtained using conventional methods. Our methods selected genes showing consistent differentiation throughout all time-courses. These genes are expected to provide new predictive biomarkers that can influence INF-β treatment for MS patients.

[1]  A. Bertolotto,et al.  Biological markers of interferon-beta therapy: comparison among interferon-stimulated genes MxA, TRAIL and XAF-1 , 2006, Multiple sclerosis.

[2]  A. Bertolotto,et al.  A gene expression study denies the ability of 25 candidate biomarkers to predict the interferon-beta treatment response in multiple sclerosis patients , 2016, Journal of Neuroimmunology.

[3]  Chin-Teng Lin,et al.  Discovering monotonic stemness marker genes from time-series stem cell microarray data , 2015, BMC Genomics.

[4]  Seunggeun Lee,et al.  An efficient resampling method for calibrating single and gene-based rare variant association analysis in case-control studies. , 2016, Biostatistics.

[5]  N. Meinshausen,et al.  Stability selection , 2008, 0809.2932.

[6]  D. Arnold,et al.  B-cell depletion with rituximab in relapsing-remitting multiple sclerosis. , 2008, The New England journal of medicine.

[7]  Shengwu Xiong,et al.  InDel marker detection by integration of multiple softwares using machine learning techniques , 2016, BMC Bioinformatics.

[8]  Dao-Qing Dai,et al.  Regularized logistic regression with network-based pairwise interaction for biomarker identification in breast cancer , 2016, BMC Bioinformatics.

[9]  Claudio Cobelli,et al.  Significance analysis of microarray transcript levels in time series experiments , 2007, BMC Bioinformatics.

[10]  P. Bühlmann,et al.  The group lasso for logistic regression , 2008 .

[11]  Tso-Jung Yen,et al.  Discussion on "Stability Selection" by Meinshausen and Buhlmann , 2010 .

[12]  J. Epstein,et al.  Peripherally Induced Tolerance Depends on Peripheral Regulatory T Cells That Require Hopx To Inhibit Intrinsic IL-2 Expression , 2015, The Journal of Immunology.

[13]  M. Hecker,et al.  Reassessment of Blood Gene Expression Markers for the Prognosis of Relapsing-Remitting Multiple Sclerosis , 2011, PloS one.

[14]  H. Hartung,et al.  New concepts in the immunopathogenesis of multiple sclerosis , 2002, Nature Reviews Neuroscience.

[15]  Yu Shyr,et al.  The prediction of interferon treatment effects based on time series microarray gene expression profiles , 2008, Journal of Translational Medicine.

[16]  Jieping Ye,et al.  Sparse learning and stability selection for predicting MCI to AD conversion using baseline ADNI data , 2012, BMC Neurology.

[17]  A. E. Hoerl,et al.  Ridge Regression: Applications to Nonorthogonal Problems , 1970 .

[18]  B. Weinshenker,et al.  Epidemiology of multiple sclerosis. , 1996, Neurologic clinics.

[19]  Dirk Koczan,et al.  Elevated type I interferon-like activity in a subset of multiple sclerosis patients: molecular basis and clinical relevance , 2012, Journal of Neuroinflammation.

[20]  A. E. Hoerl,et al.  Ridge regression: biased estimation for nonorthogonal problems , 2000 .

[21]  Kazuyuki Aihara,et al.  Predicting disease progression from short biomarker series using expert advice algorithm , 2015, Scientific Reports.

[22]  S. Chung,et al.  No effect of recumbency duration on the occurrence of post-lumbar puncture headache with a 22G cutting needle , 2012, BMC Neurology.

[23]  J. Shao,et al.  Elevated expressions of survivin and VEGF protein are strong independent predictors of survival in advanced nasopharyngeal carcinoma , 2008, Journal of Translational Medicine.

[24]  Holger Fröhlich,et al.  Modeling ERBB receptor-regulated G1/S transition to find novel targets for de novo trastuzumab resistance , 2009, BMC Systems Biology.

[25]  Jianqing Fan,et al.  Sure independence screening for ultrahigh dimensional feature space , 2006, math/0612857.

[26]  Atul J Butte,et al.  Robust meta-analysis of gene expression using the elastic net , 2015, Nucleic acids research.

[27]  W Y Zhang,et al.  Discussion on `Sure independence screening for ultra-high dimensional feature space' by Fan, J and Lv, J. , 2008 .

[28]  R. Rudick,et al.  Excessive Biologic Response to IFNβ Is Associated with Poor Treatment Response in Patients with Multiple Sclerosis , 2011, PloS one.

[29]  Benno Schwikowski,et al.  Analysis of Time-Resolved Gene Expression Measurements across Individuals , 2013, PloS one.

[30]  R Guthke,et al.  Network analysis of transcriptional regulation in response to intramuscular interferon-β-1a multiple sclerosis treatment , 2010, The Pharmacogenomics Journal.

[31]  Trevor Hastie,et al.  Regularization Paths for Generalized Linear Models via Coordinate Descent. , 2010, Journal of statistical software.

[32]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[33]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[34]  L. Greller,et al.  Transcription-Based Prediction of Response to IFNβ Using Supervised Computational Methods , 2004, PLoS biology.

[35]  Chun-Nan Hsu,et al.  Weakly supervised learning of biomedical information extraction from curated data , 2016, BMC Bioinformatics.

[36]  D. Hawiger,et al.  Peripherally Induced Regulatory T Cells: Recruited Protectors of the Central Nervous System against Autoimmune Neuroinflammation , 2017, Front. Immunol..

[37]  T. Myers,et al.  PLZF Regulates CCR6 and Is Critical for the Acquisition and Maintenance of the Th17 Phenotype in Human Cells , 2015, The Journal of Immunology.

[38]  Hans-Georg Müller,et al.  Classification using functional data analysis for temporal gene expression data , 2006, Bioinform..

[39]  X. Montalban,et al.  Defining the response to interferon‐β in relapsing‐remitting multiple sclerosis patients , 2006, Annals of neurology.

[40]  Satoru Miyano,et al.  Gene set differential analysis of time course expression profiles via sparse estimation in functional logistic model with application to time-dependent biomarker detection. , 2016, Biostatistics.

[41]  I. Simon,et al.  Studying and modelling dynamic biological processes using time-series gene expression data , 2012, Nature Reviews Genetics.

[42]  Masao Nagasaki,et al.  Recursive regularization for inferring gene networks from time-course gene expression profiles , 2009, BMC Systems Biology.

[43]  Vincenzo Lagani,et al.  Feature selection for high-dimensional temporal data , 2018, BMC Bioinformatics.

[44]  K. Conant,et al.  Matrix metalloproteinase activity stimulates N-cadherin shedding and the soluble N-cadherin ectodomain promotes classical microglial activation , 2017, Journal of Neuroinflammation.

[45]  Ramil N. Nurtdinov,et al.  Search for Specific Biomarkers of IFNβ Bioactivity in Patients with Multiple Sclerosis , 2011, PloS one.

[46]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[47]  Dirk Koczan,et al.  Long-term genome-wide blood RNA expression profiles yield novel molecular response candidates for IFN-beta-1b treatment in relapsing remitting MS. , 2010, Pharmacogenomics.

[48]  Richard Reynolds,et al.  Innate Immunity in multiple sclerosis white matter lesions: expression of natural cytotoxicity triggering receptor 1 (NCR1) , 2012, Journal of Neuroinflammation.

[49]  May D. Wang,et al.  Estimating Classification Error to Identify Biomarkers in Time Series Expression Data , 2007, 2007 IEEE 7th International Symposium on BioInformatics and BioEngineering.

[50]  W. A. LaFramboise,et al.  Gene expression changes in peripheral blood mononuclear cells from multiple sclerosis patients undergoing β-interferon therapy , 2007, Journal of the Neurological Sciences.