A grand challenge in biology is to discover evolutionary traits, which are features of organisms common to a group of species with a shared ancestor in the Tree of Life (also referred to as phylogenetic tree). With the recent availability of large-scale image repositories in biology and advances in the field of explainable machine learning (ML) such as ProtoPNet and other prototype-based methods, there is a tremendous opportunity to discover evolutionary traits directly from images in the form of a hierarchy of prototypes learned at internal nodes of the phylogenetic tree. However, current prototype-based methods are mostly designed to operate over a flat structure of classes and face several challenges in discovering hierarchical prototypes on a tree, including the problem of learning over-specific features at internal nodes in the tree. To overcome these challenges, we introduce the framework of Hierarchy aligned Commonality through Prototypical Networks (HComP-Net), which learns common features shared by all descendant species of an internal node and avoids the learning of over-specific prototypes. We empirically show that HComP-Net learns prototypes that are of high accuracy, semantically consistent, and generalizable to unseen species in comparison to baselines. While we focus on the biological problem of discovering evolutionary traits, our work can be applied to any domain involving a hierarchy of classes. / Master of Science / A phylogenetic tree (also called as tree of life) shows how different species or groups of living things are related to each other through evolution. Scientists use phylogenetic trees to trace the evolutionary history of species, helping them understand how life on Earth is connected and how different species have changed over time. Each branch of the tree represents a group of species that share a common ancestor, and the point where branches split shows when they began to evolve into different species. Although the species have evolved separately they continue to share some traits due to their common ancestry in the phylogeny. Such traits are referred to as synapomorphies. In our work, we focus on identifying such traits from images in the form of prototypes (representative image patches) by incorporating the knowledge of phylogenetic tree. We learn prototypes at each internal node of the phylogenetic tree, such that the prototypes learned at each node represents the common traits that are shared between all the species that are under the node. By learning such prototypes we can identify and localize the regions (or image patches) of the image that contains such common traits.
| Identifer | oai:union.ndltd.org:VTETD/oai:vtechworks.lib.vt.edu:10919/121329 |
| Date | 11 October 2024 |
| Creators | Manogaran, Harish Babu |
| Contributors | Electrical and Computer Engineering, Abbott, Amos L., Karpatne, Anuj, Jones, Creed Farris |
| Publisher | Virginia Tech |
| Source Sets | Virginia Tech Theses and Dissertation |
| Language | English |
| Detected Language | English |
| Type | Thesis |
| Format | ETD, application/pdf |
| Rights | In Copyright, http://rightsstatements.org/vocab/InC/1.0/ |
Page generated in 0.0021 seconds