Interpretable per Case Weighted Ensemble Method for Cancer Associations

Abstract

Motivation: Molecular measurements from cancer patients such as gene expression and DNA methylation are usually very noisy. Furthermore, cancer types can be very heterogeneous. Therefore, one of the main assumptions for machine learning, that the underlying unknown distribution is the same for all samples, might not be completely fullfilled. We introduce a method, that can estimate this bias on a per-feature level and incorporate calculated feature confidences into a weighted combination of classifiers with disjoint feature sets. Results: The new method achieves state-of-the-art performance on many different cancer data sets with measured DNA methylation or gene expression. Moreover, we show how to visualize the learned classifiers to find interesting associations with the target label. Applied to a leukemia data set we find several ribosomal proteins associated with leukemia's risk group that might be interesting targets for follow-up studies and support the hypothesis that the ribosomes are a new frontier in gene regulation. Availability: The method is available under GPLv3+ License at https: //github.com/adrinjalali/Network-Classifier.