Computer scientists pioneer method to determine taxonomic relationships

Researchers in the Cheriton School of Computer Science are using unsupervised machine learning to determine taxonomic relationships between organisms.

The new method, called Deep Learning for Unsupervised Clustering of DNA Sequences, or DeLUCS for short, was pioneered by Lila Kari, professor of computer science, her PhD students Pablo Millán Arias and Fatemeh Alipour and her colleague Professor Kathleen Hill at Western University’s Department of Biology.

“The evolutionary relationships that DeLUCS determines match true taxonomic groups with very high accuracy, ranging from 77 per cent right up to 100 per cent across a range of genetic datasets from organisms as diverse as vertebrates, bacteria and viruses,” Kari says.

Learn more about DeLUCS in the feature article on the Cheriton School of Computer Science website.