Mutation Clusters from Cancer Exome
Genes 8(8) (2017) 201
84 Pages Posted: 4 Apr 2017 Last revised: 16 Aug 2017
Date Written: March 31, 2017
We apply our statistically deterministic machine learning/clustering algorithm *K-means (recently developed in http://ssrn.com/abstract=2908286) to 10,656 published exome samples for 32 cancer types. A majority of cancer types exhibit mutation clustering structure. Our results are in-sample stable. They are also out-of-sample stable when applied to 1,389 published genome samples across 14 cancer types. In contrast, we find in- and out-of-sample instabilities in cancer signatures extracted from exome samples via nonnegative matrix factorization (NMF), a computationally costly and non-deterministic method. Extracting stable mutation structures from exome data could have important implications for speed and cost, which are critical for early-stage cancer diagnostics such as novel blood-test methods currently in development.
Keywords: Clustering, K-Means, Nonnegative Matrix Factorization, Somatic Mutation, Cancer Signatures, Genome, Exome, DNA, eRank, Correlation, Covariance, Machine Learning, Sample, Matrix, Source Code, Quantitative Finance, Statistical Risk Model, Industry Classification
JEL Classification: G00
Suggested Citation: Suggested Citation