Journal Article
. 2017 Aug; 9(1):217-245.
doi: 10.1007/s12561-016-9169-5.

Prediction-Oriented Marker Selection (PROMISE): With Application to High-Dimensional Regression

Soyeon Kim 1 Veerabhadran Baladandayuthapani 2 J Jack Lee 2 
  • PMID: 28785367
  •     24 References
  •     3 citations


In personalized medicine, biomarkers are used to select therapies with the highest likelihood of success based on an individual patient's biomarker/genomic profile. Two goals are to choose important biomarkers that accurately predict treatment outcomes and to cull unimportant biomarkers to reduce the cost of biological and clinical verifications. These goals are challenging due to the high dimensionality of genomic data. Variable selection methods based on penalized regression (e.g., the lasso and elastic net) have yielded promising results. However, selecting the right amount of penalization is critical to simultaneously achieving these two goals. Standard approaches based on cross-validation (CV) typically provide high prediction accuracy with high true positive rates but at the cost of too many false positives. Alternatively, stability selection (SS) controls the number of false positives, but at the cost of yielding too few true positives. To circumvent these issues, we propose prediction-oriented marker selection (PROMISE), which combines SS with CV to conflate the advantages of both methods. Our application of PROMISE with the lasso and elastic net in data analysis shows that, compared to CV, PROMISE produces sparse solutions, few false positives, and small type I + type II error, and maintains good prediction accuracy, with a marginal decrease in the true positive rates. Compared to SS, PROMISE offers better prediction accuracy and true positive rates. In summary, PROMISE can be applied in many fields to select regularization parameters when the goals are to minimize false positives and maximize prediction accuracy.

Keywords: Cross-validation; Lasso; Personalized medicine; Predictive marker; Stability Selection; Variable Selection.

Effects of GM-CSF and M-CSF on tumor progression of lung cancer: roles of MEK1/ERK and AKT/PKB pathways.
Yoshiki Uemura, Makoto Kobayashi, +4 authors, Hirokuni Taguchi.
Int J Mol Med, 2006 Jul 06; 18(2). PMID: 16820947
Clinical, pathological and molecular prognostic factors in prostate cancer decision-making process.
Dario Pugliese, Giuseppe Palermo, +2 authors, Francesco Pinto.
Urologia, 2016 Feb 27; 83(1). PMID: 26917215
Predictive and prognostic molecular markers for cancer medicine.
Sunali Mehta, Andrew Shelling, +4 authors, Cristin Print.
Ther Adv Med Oncol, 2010 Mar 01; 2(2). PMID: 21789130    Free PMC article.
Regularization Paths for Generalized Linear Models via Coordinate Descent.
Jerome Friedman, Trevor Hastie, Rob Tibshirani.
J Stat Softw, 2010 Sep 03; 33(1). PMID: 20808728    Free PMC article.
Highly Cited.
Incorporating group correlations in genome-wide association studies using smoothed group Lasso.
Jin Liu, Jian Huang, Shuangge Ma, Kai Wang.
Biostatistics, 2012 Sep 19; 14(2). PMID: 22988281    Free PMC article.
Regression approaches for microarray data analysis.
Mark R Segal, Kam D Dahlquist, Bruce R Conklin.
J Comput Biol, 2004 Feb 26; 10(6). PMID: 14980020
Down-regulation of Gadd45 expression is associated with tumor differentiation in non-small cell lung cancer.
Hiroshi Higashi, Daniel Vallböhmer, +9 authors, Paul M Schneider.
Anticancer Res, 2006 Jul 11; 26(3A). PMID: 16827157
The BATTLE trial: personalizing therapy for lung cancer.
Edward S Kim, Roy S Herbst, +21 authors, Waun K Hong.
Cancer Discov, 2012 May 16; 1(1). PMID: 22586319    Free PMC article.
Highly Cited.
Aryl hydrocarbon receptor and lung cancer.
Junchieh J Tsay, Kam-Meng Tchou-Wong, +2 authors, William N Rom.
Anticancer Res, 2013 Apr 09; 33(4). PMID: 23564762    Free PMC article.
Adaptive clinical trial designs in oncology.
Yong Zang, J Jack Lee.
Chin Clin Oncol, 2015 Mar 27; 3(4). PMID: 25811018    Free PMC article.
Inhibition of glutathione disulfide reductase by glutathione.
P M Chung, R E Cappel, H F Gilbert.
Arch Biochem Biophys, 1991 Jul 01; 288(1). PMID: 1898023
Cancer/testis antigen expression in human mesenchymal stem cells: down-regulation of SSX impairs cell migration and matrix metalloproteinase 2 expression.
Garth Cronwright, Katarina Le Blanc, +3 authors, Bertha Brodin.
Cancer Res, 2005 Mar 23; 65(6). PMID: 15781633
Somatic EGFR mutation and gene copy gain as predictive biomarkers for response to tyrosine kinase inhibitors in non-small cell lung cancer.
Issa J Dahabreh, Helena Linardou, +3 authors, Samuel Murray.
Clin Cancer Res, 2009 Dec 24; 16(1). PMID: 20028749
Systematic Review.
Discussion of "Sure Independence Screening for Ultra-High Dimensional Feature Space.
Hao Helen Zhang.
J R Stat Soc Series B Stat Methodol, 2008 Jan 01; 70(5). PMID: 19603084    Free PMC article.
Highly Cited.
Bayesian two-step Lasso strategy for biomarker selection in personalized medicine development for time-to-event endpoints.
Xuemin Gu, Guosheng Yin, J Jack Lee.
Contemp Clin Trials, 2013 Oct 01; 36(2). PMID: 24075829    Free PMC article.
Stability selection for genome-wide association.
David H Alexander, Kenneth Lange.
Genet Epidemiol, 2011 Oct 20; 35(7). PMID: 22009793
Wnt signaling pathway in non-small cell lung cancer.
David J Stewart.
J Natl Cancer Inst, 2013 Dec 07; 106(1). PMID: 24309006
Highly Cited. Review.
Reporting disease control rates or clinical benefit rates in early clinical trials of anticancer agents: useful endpoint or hype?
Mario Sznol.
Curr Opin Investig Drugs, 2011 Jan 28; 11(12). PMID: 21268434
Cancer genomics: from discovery science to personalized medicine.
Lynda Chin, Jannik N Andersen, P Andrew Futreal.
Nat Med, 2011 Mar 09; 17(3). PMID: 21383744
Highly Cited.
Vitamin D receptor expression in normal, premalignant, and malignant human lung tissue.
Ravi J Menezes, Richard T Cheney, +7 authors, Mary E Reid.
Cancer Epidemiol Biomarkers Prev, 2008 May 17; 17(5). PMID: 18483332    Free PMC article.
Companion diagnostic testing for targeted cancer therapies: an overview.
Yao-Shan Fan.
Genet Test Mol Biomarkers, 2013 Apr 12; 17(7). PMID: 23574530
Bayesian adaptive randomization designs for targeted agent development.
J Jack Lee, Xuemin Gu, Suyu Liu.
Clin Trials, 2010 Jun 24; 7(5). PMID: 20571130    Free PMC article.
The role of glutathione in cancer.
Ganesaratnam K Balendiran, Rajesh Dabur, Deborah Fraser.
Cell Biochem Funct, 2004 Sep 24; 22(6). PMID: 15386533
Highly Cited. Review.
Expression of the neutral amino acids transporter ASCT1 in esophageal carcinomas.
M Younes, M Pathak, +3 authors, M R Schwartz.
Anticancer Res, 2001 Mar 28; 20(5C). PMID: 11268453
Germinal Immunogenetics predict treatment outcome for PD-1/PD-L1 checkpoint inhibitors.
Sadal Refae, Jocelyn Gal, +7 authors, Esma Saada-Bouzid.
Invest New Drugs, 2019 Aug 14; 38(1). PMID: 31402427
Collective effects of long-range DNA methylations predict gene expressions and estimate phenotypes in cancer.
Soyeon Kim, Hyun Jung Park, Xiangqin Cui, Degui Zhi.
Sci Rep, 2020 Mar 05; 10(1). PMID: 32127627    Free PMC article.
3' UTR shortening represses tumor-suppressor genes in trans by disrupting ceRNA crosstalk.
Hyun Jung Park, Ping Ji, +12 authors, Wei Li.
Nat Genet, 2018 May 23; 50(6). PMID: 29785014    Free PMC article.
Highly Cited.