SE(3)-Stochastic Flow Matching for Protein Backbone Generation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Bose, Avishek Joey, Akhound-Sadegh, Tara, Huguet, Guillaume, Fatras, Kilian, Rector-Brooks, Jarrid, Liu, Cheng-Hao, Nica, Andrei Cristian, Korablyov, Maksym, Bronstein, Michael, Tong, Alexander
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929310053433344
author Bose, Avishek Joey
Akhound-Sadegh, Tara
Huguet, Guillaume
Fatras, Kilian
Rector-Brooks, Jarrid
Liu, Cheng-Hao
Nica, Andrei Cristian
Korablyov, Maksym
Bronstein, Michael
Tong, Alexander
author_facet Bose, Avishek Joey
Akhound-Sadegh, Tara
Huguet, Guillaume
Fatras, Kilian
Rector-Brooks, Jarrid
Liu, Cheng-Hao
Nica, Andrei Cristian
Korablyov, Maksym
Bronstein, Michael
Tong, Alexander
contents The computational design of novel protein structures has the potential to impact numerous scientific disciplines greatly. Toward this goal, we introduce FoldFlow, a series of novel generative models of increasing modeling power based on the flow-matching paradigm over $3\mathrm{D}$ rigid motions -- i.e. the group $\text{SE}(3)$ -- enabling accurate modeling of protein backbones. We first introduce FoldFlow-Base, a simulation-free approach to learning deterministic continuous-time dynamics and matching invariant target distributions on $\text{SE}(3)$. We next accelerate training by incorporating Riemannian optimal transport to create FoldFlow-OT, leading to the construction of both more simple and stable flows. Finally, we design FoldFlow-SFM, coupling both Riemannian OT and simulation-free training to learn stochastic continuous-time dynamics over $\text{SE}(3)$. Our family of FoldFlow, generative models offers several key advantages over previous approaches to the generative modeling of proteins: they are more stable and faster to train than diffusion-based approaches, and our models enjoy the ability to map any invariant source distribution to any invariant target distribution over $\text{SE}(3)$. Empirically, we validate FoldFlow, on protein backbone generation of up to $300$ amino acids leading to high-quality designable, diverse, and novel samples.
format Preprint
id arxiv_https___arxiv_org_abs_2310_02391
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle SE(3)-Stochastic Flow Matching for Protein Backbone Generation
Bose, Avishek Joey
Akhound-Sadegh, Tara
Huguet, Guillaume
Fatras, Kilian
Rector-Brooks, Jarrid
Liu, Cheng-Hao
Nica, Andrei Cristian
Korablyov, Maksym
Bronstein, Michael
Tong, Alexander
Machine Learning
Artificial Intelligence
The computational design of novel protein structures has the potential to impact numerous scientific disciplines greatly. Toward this goal, we introduce FoldFlow, a series of novel generative models of increasing modeling power based on the flow-matching paradigm over $3\mathrm{D}$ rigid motions -- i.e. the group $\text{SE}(3)$ -- enabling accurate modeling of protein backbones. We first introduce FoldFlow-Base, a simulation-free approach to learning deterministic continuous-time dynamics and matching invariant target distributions on $\text{SE}(3)$. We next accelerate training by incorporating Riemannian optimal transport to create FoldFlow-OT, leading to the construction of both more simple and stable flows. Finally, we design FoldFlow-SFM, coupling both Riemannian OT and simulation-free training to learn stochastic continuous-time dynamics over $\text{SE}(3)$. Our family of FoldFlow, generative models offers several key advantages over previous approaches to the generative modeling of proteins: they are more stable and faster to train than diffusion-based approaches, and our models enjoy the ability to map any invariant source distribution to any invariant target distribution over $\text{SE}(3)$. Empirically, we validate FoldFlow, on protein backbone generation of up to $300$ amino acids leading to high-quality designable, diverse, and novel samples.
title SE(3)-Stochastic Flow Matching for Protein Backbone Generation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2310.02391