Publication — IRIC

Predictive computational phenotyping and biomarker discovery using reference-free genome comparisons.

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.

Publication date
September 26, 2016
Principal Investigators
Drouin A, Giguère S, Déraspe M, Marchand M, Tyers M, Loo VG, Bourgault AM, Laviolette F, Corbeil J
PubMed reference
BMC Genomics 2016;17(1):754
PubMed ID
Department of Computer Science and Software Engineering, Université Laval, Québec, Canada.