Data clustering and classification are fundamental problems in data science, with applications in almost every field of study. In this talk, we present prototype software that applies a data science approach to identifying groups of closely related species and possible species complexes.

We will present our prototype software, which implements a pipeline that queries the GenBank and BOLD databases for genetic data, uses sequence alignment to generate measures of genetic similarity, and augments these measures with morphological data. Similarity relationships are visualized as network graphs, allowing users to identify and propose potential species groupings for further investigation.

This ongoing project has been jointly funded by Okanagan College’s Grants-in-Aid Fund and the College’s Department of Applied Science.