Prediction of Acquired Taxane Resistance Using a Personalized Pathway-Based Machine Learning Method
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Purpose This study was conducted to develop and validate an individualized prediction model for automated detection of acquired taxane resistance (ATR). Materials and Methods Penalized regression, combined with an individualized pathway score algorithm, was applied to construct a predictive model using publically available genomic cohorts of ATR and intrinsic taxane resistance (ITR). To develop a model with enhanced generalizability, we merged multiple ATR studies then updated the learning parameter via robust cross-study validation. Results For internal cross-study validation, the ATR model produced a perfect performance with an overall area under the receiver operating curve (AUROC) of 1.000 with an area under the precision-recall curve (AUPRC) of 1.000, a Brier score of 0.007, a sensitivity and a specificity of 100%. The model showed an excellent performance on two independent blind ATR cohorts (overall AUROC of 0.940, AUPRC of 0.940, a Brier score of 0.127). When we applied our algorithm to two large-scale pharmacogenomic resources for ITR, the Cancer Genome Project (CGP) and the Cancer Cell Line Encyclopedia (CCLE), an overall ITR cross-study AUROC was 0.70, which is a far better accuracy than an almost random level reported by previous studies. Furthermore, this model had a high transferability on blind ATR cohorts with an AUROC of 0.69, suggesting that general predictive features may be at work across both ITR and ATR. Conclusion We successfully constructed a multi-study–derived personalized prediction model for ATR with excellent accuracy, generalizability, and transferability.
Abstract
Purpose This study was conducted to develop and validate an individualized prediction model for automated detection of acquired taxane resistance (ATR). Materials and Methods Penalized regression, combined with an individualized pathway score algorithm, was applied to construct a predictive model using publically available genomic cohorts of ATR and intrinsic taxane resistance (ITR). To develop a model with enhanced generalizability, we merged multiple ATR studies then updated the learning parameter via robust cross-study validation. Results For internal cross-study validation, the ATR model produced a perfect performance with an overall area under the receiver operating curve (AUROC) of 1.000 with an area under the precision-recall curve (AUPRC) of 1.000, a Brier score of 0.007, a sensitivity and a specificity of 100%. The model showed an excellent performance on two independent blind ATR cohorts (overall AUROC of 0.940, AUPRC of 0.940, a Brier score of 0.127). When we applied our algorithm to two large-scale pharmacogenomic resources for ITR, the Cancer Genome Project (CGP) and the Cancer Cell Line Encyclopedia (CCLE), an overall ITR cross-study AUROC was 0.70, which is a far better accuracy than an almost random level reported by previous studies. Furthermore, this model had a high transferability on blind ATR cohorts with an AUROC of 0.69, suggesting that general predictive features may be at work across both ITR and ATR. Conclusion We successfully constructed a multi-study–derived personalized prediction model for ATR with excellent accuracy, generalizability, and transferability.
참고문헌 (26)
- Nussbaumer S, "Analysis of anticancer drugs : a review", Talanta, 85, pp.2265~2289 (2011)
- Haibe-Kains B, "Inconsistency in large pharmacogenomic studies", Nature, 504, pp.389~393 (2013)
- Bouhaddou M, "Drug response consistency in CCLE and CGP", Nature, 540, pp.E9~E10 (2016)
- Domingo-Domenech J, "Suppression of acquired docetaxel resistance in prostate cancer through depletion of notch- and hedgehog-dependent tumorinitiating cells", Cancer Cell, 22, pp.373~388 (2012)
- "Gene expression data of sensitive, Docetaxel resistant and paclitaxel resistant MDA-MB-231 cells. GEO DataSets. Series GSE28784" (2011)[URL]
- Landen CN Jr, "Targeting aldehyde dehydrogenase cancer stem cells in ovarian cancer", Mol Cancer Ther, 9, pp.3186~3199 (2010)
- Luo W, "Identification of polymorphisms associated with hypertriglyceridemia and prolonged survival induced by bexarotene in treating non-small cell lung cancer", Anticancer Res, 31, pp.2303~2311 (2011)
- Marin-Aguilera M, "Identification of docetaxel resistance genes in castration-resistant prostate cancer", Mol Cancer Ther, 11, pp.329~339 (2012)
- Hughey JJ, "Robust meta-analysis of gene expression using the elastic net", Nucleic Acids Res, 43, pp.e79~ (2015)
- Irizarry RA, "Exploration, normalization, and summaries of high density oligonucleotide array probe level data", Biostatistics, 4, pp.249~264 (2003)
- Troyanskaya O, "Missing value estimation methods for DNA microarrays", Bioinformatics, 17, pp.520~525 (2001)
- Johnson WE, "Adjusting batch effects in microarray expression data using empirical Bayes methods", Biostatistics, 8, pp.118~127 (2007)
- Drier Y, "Pathway-based personalized analysis of cancer", Proc Natl Acad Sci U S A, 110, pp.6388~6393 (2013)
- Hastie T, "Principal curves", J Am Stat Assoc, 84, pp.502~516 (1989)
- Friedman J, "Regularization paths for generalized linear models via coordinate descent", J Stat Softw, 33, pp.1~22 (2010)
- Zou H, "Regularization and variable selection via the elastic net", J R Stat Soc Series B Stat Methodol, 67, pp.301~320 (2005)
- Sill M, "c060 : extended inference with Lasso and elastic-net regularized Cox and generalized linear models", J Stat Softw, 62, pp.1~22 (2014)
- Kuhn M, "Building predictive models in R using the caret package", J Stat Softw, 28, pp.1~26 (2008)
- Kanehisa M, "KEGG : Kyoto Encyclopedia of Genes and Genomes", Nucleic Acids Res, 28, pp.27~30 (2000)
- Schaefer CF, "PID: the pathway interaction database", Nucleic Acids Res, 37, pp.D674~D679 (2009)
- Nishimura D, "BioCarta", Biotech Softw Internet Rep, 2, pp.117~120 (2001)
- Dong Z, "Anticancer drug sensitivity prediction in cell lines from baseline gene expression through recursive feature selection", BMC Cancer, 15, pp.489~ (2015)
- Greenberger LM, "Cancer drug resistance", pp.329~358 (2006), Humana Press
- Zeng L, "Hypoxia inducible factor-1 influences sensitivity to paclitaxel of human lung cancer cell lines under normoxic conditions", Cancer Sci, 98, pp.1394~1401 (2007)
- Szakacs G, "Targeting multidrug resistance in cancer", Nat Rev Drug Discov, 5, pp.219~234 (2006)
- Seguin L, "Integrins and cancer : regulators of cancer stemness, metastasis, and drug resistance", Trends Cell Biol, 25, pp.234~240 (2015)