Whole-genome sequencing has revolutionized biosciences by providing tools for constructing complete DNA sequences of individuals.
With entire genomes at hand, scientists can pinpoint DNA fragments responsible for different cancers and predict patient responses to cancer treatments. However, the sheer volume of whole-genome data makes it difficult to encode the characteristics of genomic variants as features for machine learning algorithms.
We present three feature extraction methods that facilitate classifier learning from distributions of genomic variants. The proposed approaches use binning, clustering, and kernel density estimation to produce features that discriminate between two groups of patients. Experiments on genomes of 219 ovarian, 61 lung, and 929 breast cancer patients show that the proposed approaches automatically identify genomic biomarkers associated with cancer subtypes and clinical response to oncological treatment. Finally, we show that the extracted features can be used alongside unsupervised learning methods to analyze genomic samples.