Discovering Novel Biological Traits From Images Using Phylogeny-Guided Neural Networks

TL;DR

This paper introduces Phylo-NN, a neural network method that discovers evolutionary traits from organism images by encoding phylogenetic signals without requiring trait labels, aiding biological understanding and image-based tasks.

Contribution

The paper presents a novel label-free approach, Phylo-NN, that encodes phylogenetic information from images into sequences of feature vectors for trait discovery.

Findings

Effective in identifying biologically meaningful traits

Improves species image generation and translation tasks

Operates without trait labels, reducing manual effort

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.