Discovering Novel Biological Traits From Images Using Phylogeny-Guided Neural Networks
Abstract
Discovering evolutionary traits that are heritable across species on the tree of life (also referred to as a phylogenetic tree) is of great interest to biologists to understand how organisms diversify and evolve. However, the measurement of traits is often a subjective and labor-intensive process, making trait discovery a highly label-scarce problem. We present a novel approach for discovering evolutionary traits directly from images without relying on trait labels. Our proposed approach, Phylo-NN, encodes the image of an organism into a sequence of quantized feature vectors -- or codes -- where different segments of the sequence capture evolutionary signals at varying ancestry levels in the phylogeny. We demonstrate the effectiveness of our approach in producing biologically meaningful results in a number of downstream tasks including species image generation and species-to-species image translation, using fish species as a target example.
Keywords
Cite
@article{arxiv.2306.03228,
title = {Discovering Novel Biological Traits From Images Using Phylogeny-Guided Neural Networks},
author = {Mohannad Elhamod and Mridul Khurana and Harish Babu Manogaran and Josef C. Uyeda and Meghan A. Balk and Wasila Dahdul and Yasin Bakış and Henry L. Bart and Paula M. Mabee and Hilmar Lapp and James P. Balhoff and Caleb Charpentier and David Carlyn and Wei-Lun Chao and Charles V. Stewart and Daniel I. Rubenstein and Tanya Berger-Wolf and Anuj Karpatne},
journal= {arXiv preprint arXiv:2306.03228},
year = {2023}
}