Predictive computational phenotyping and biomarker discovery using reference-free genome comparisons.
Department of Computer Science and Software Engineering, Université Laval, Québec, Canada. email@example.com.
The identification of genomic biomarkers is a key step towards improving diagnostic tests and therapies. We present a reference-free method for this task that relies on a k-mer representation of genomes and a machine learning algorithm that produces intelligible models. The method is computationally scalable and well-suited for whole genome sequencing studies.
BMC Genomics 2016;17(1):754.
Pubmed ID: 27671088