Diffusion on language model encodings for protein sequence generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Meshchaninov, Viacheslav, Strashnov, Pavel, Shevtsov, Andrey, Nikolaev, Fedor, Ivanisenko, Nikita, Kardymon, Olga, Vetrov, Dmitry
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914024723054592
author Meshchaninov, Viacheslav
Strashnov, Pavel
Shevtsov, Andrey
Nikolaev, Fedor
Ivanisenko, Nikita
Kardymon, Olga
Vetrov, Dmitry
author_facet Meshchaninov, Viacheslav
Strashnov, Pavel
Shevtsov, Andrey
Nikolaev, Fedor
Ivanisenko, Nikita
Kardymon, Olga
Vetrov, Dmitry
contents Protein sequence design has seen significant advances through discrete diffusion and autoregressive approaches, yet the potential of continuous diffusion remains underexplored. Here, we present DiMA, a latent diffusion framework that operates on protein language model representations. Through systematic exploration of architectural choices and diffusion components, we develop a robust methodology that generalizes across multiple protein encoders ranging from 8M to 3B parameters. We demonstrate that our framework achieves consistently high performance across sequence-only (ESM-2, ESMc), dual-decodable (CHEAP), and multimodal (SaProt) representations using the same architecture and training approach. We extensively evaluate existing methods alongside DiMA using multiple metrics across two protein modalities, covering quality, diversity, novelty, and distribution matching of generated proteins. DiMA consistently produces novel, high-quality and diverse protein sequences and achieves strong results compared to baselines such as autoregressive, discrete diffusion and flow matching language models. The model demonstrates versatile functionality, supporting conditional generation tasks including protein family-generation, motif scaffolding and infilling, and fold-specific sequence design. This work provides a universal continuous diffusion framework for protein sequence generation, offering both architectural insights and practical applicability across various protein design scenarios. Code is released at \href{https://github.com/MeshchaninovViacheslav/DiMA}{GitHub}.
format Preprint
id arxiv_https___arxiv_org_abs_2403_03726
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Diffusion on language model encodings for protein sequence generation
Meshchaninov, Viacheslav
Strashnov, Pavel
Shevtsov, Andrey
Nikolaev, Fedor
Ivanisenko, Nikita
Kardymon, Olga
Vetrov, Dmitry
Machine Learning
Artificial Intelligence
Biomolecules
Protein sequence design has seen significant advances through discrete diffusion and autoregressive approaches, yet the potential of continuous diffusion remains underexplored. Here, we present DiMA, a latent diffusion framework that operates on protein language model representations. Through systematic exploration of architectural choices and diffusion components, we develop a robust methodology that generalizes across multiple protein encoders ranging from 8M to 3B parameters. We demonstrate that our framework achieves consistently high performance across sequence-only (ESM-2, ESMc), dual-decodable (CHEAP), and multimodal (SaProt) representations using the same architecture and training approach. We extensively evaluate existing methods alongside DiMA using multiple metrics across two protein modalities, covering quality, diversity, novelty, and distribution matching of generated proteins. DiMA consistently produces novel, high-quality and diverse protein sequences and achieves strong results compared to baselines such as autoregressive, discrete diffusion and flow matching language models. The model demonstrates versatile functionality, supporting conditional generation tasks including protein family-generation, motif scaffolding and infilling, and fold-specific sequence design. This work provides a universal continuous diffusion framework for protein sequence generation, offering both architectural insights and practical applicability across various protein design scenarios. Code is released at \href{https://github.com/MeshchaninovViacheslav/DiMA}{GitHub}.
title Diffusion on language model encodings for protein sequence generation
topic Machine Learning
Artificial Intelligence
Biomolecules
url https://arxiv.org/abs/2403.03726