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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Khurana, Mridul, Daw, Arka, Maruf, M., Uyeda, Josef C., Dahdul, Wasila, Charpentier, Caleb, Bakış, Yasin, Bart Jr., Henry L., Mabee, Paula M., Lapp, Hilmar, Balhoff, James P., Chao, Wei-Lun, Stewart, Charles, Berger-Wolf, Tanya, Karpatne, Anuj
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914894682521600
author Khurana, Mridul
Daw, Arka
Maruf, M.
Uyeda, Josef C.
Dahdul, Wasila
Charpentier, Caleb
Bakış, Yasin
Bart Jr., Henry L.
Mabee, Paula M.
Lapp, Hilmar
Balhoff, James P.
Chao, Wei-Lun
Stewart, Charles
Berger-Wolf, Tanya
Karpatne, Anuj
author_facet Khurana, Mridul
Daw, Arka
Maruf, M.
Uyeda, Josef C.
Dahdul, Wasila
Charpentier, Caleb
Bakış, Yasin
Bart Jr., Henry L.
Mabee, Paula M.
Lapp, Hilmar
Balhoff, James P.
Chao, Wei-Lun
Stewart, Charles
Berger-Wolf, Tanya
Karpatne, Anuj
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_00160
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Hierarchical Conditioning of Diffusion Models Using Tree-of-Life for Studying Species Evolution
Khurana, Mridul
Daw, Arka
Maruf, M.
Uyeda, Josef C.
Dahdul, Wasila
Charpentier, Caleb
Bakış, Yasin
Bart Jr., Henry L.
Mabee, Paula M.
Lapp, Hilmar
Balhoff, James P.
Chao, Wei-Lun
Stewart, Charles
Berger-Wolf, Tanya
Karpatne, Anuj
Populations and Evolution
Computer Vision and Pattern Recognition
Machine Learning
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.
title Hierarchical Conditioning of Diffusion Models Using Tree-of-Life for Studying Species Evolution
topic Populations and Evolution
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2408.00160