Hierarchical Conditioning of Diffusion Models Using Tree-of-Life for Studying Species Evolution

TL;DR

This paper introduces Phylo-Diffusion, a diffusion model conditioned on phylogenetic knowledge to study species evolution through images, enabling visualization of evolutionary traits and insights into biological mechanisms.

Contribution

It presents a novel hierarchical embedding approach for conditioning diffusion models with phylogenetic data, advancing generative modeling in evolutionary biology.

Findings

Successfully captures meaningful trait variations in fishes and birds.

Reveals new insights into evolutionary mechanisms.

Introduces trait masking and swapping experiments for embedding perturbation.

Abstract

A central problem in biology is to understand how organisms evolve and adapt to their environment by acquiring variations in the observable characteristics or traits of species across the tree of life. With the growing availability of large-scale image repositories in biology and recent advances in generative modeling, there is an opportunity to accelerate the discovery of evolutionary traits automatically from images. Toward this goal, we introduce Phylo-Diffusion, a novel framework for conditioning diffusion models with phylogenetic knowledge represented in the form of HIERarchical Embeddings (HIER-Embeds). We also propose two new experiments for perturbing the embedding space of Phylo-Diffusion: trait masking and trait swapping, inspired by counterpart experiments of gene knockout and gene editing/swapping. Our work represents a novel methodological advance in generative modeling to structure the embedding space of diffusion models using tree-based knowledge. Our work also opens a new chapter of research in evolutionary biology by using generative models to visualize evolutionary changes directly from images. We empirically demonstrate the usefulness of Phylo-Diffusion in capturing meaningful trait variations for fishes and birds, revealing novel insights about the biological mechanisms of their evolution.