Saved in:
Bibliographic Details
Main Authors: Bai, Peizhen, Miljković, Filip, Liu, Xianyuan, De Maria, Leonardo, Croasdale-Wood, Rebecca, Rackham, Owen, Lu, Haiping
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.07815
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911077907824640
author Bai, Peizhen
Miljković, Filip
Liu, Xianyuan
De Maria, Leonardo
Croasdale-Wood, Rebecca
Rackham, Owen
Lu, Haiping
author_facet Bai, Peizhen
Miljković, Filip
Liu, Xianyuan
De Maria, Leonardo
Croasdale-Wood, Rebecca
Rackham, Owen
Lu, Haiping
contents Inverse protein folding generates valid amino acid sequences that can fold into a desired protein structure, with recent deep-learning advances showing strong potential and competitive performance. However, challenges remain, such as predicting elements with high structural uncertainty, including disordered regions. To tackle such low-confidence residue prediction, we propose a Mask-prior-guided denoising Diffusion (MapDiff) framework that accurately captures both structural information and residue interactions for inverse protein folding. MapDiff is a discrete diffusion probabilistic model that iteratively generates amino acid sequences with reduced noise, conditioned on a given protein backbone. To incorporate structural information and residue interactions, we develop a graph-based denoising network with a mask-prior pre-training strategy. Moreover, in the generative process, we combine the denoising diffusion implicit model with Monte-Carlo dropout to reduce uncertainty. Evaluation on four challenging sequence design benchmarks shows that MapDiff substantially outperforms state-of-the-art methods. Furthermore, the in silico sequences generated by MapDiff closely resemble the physico-chemical and structural characteristics of native proteins across different protein families and architectures.
format Preprint
id arxiv_https___arxiv_org_abs_2412_07815
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Mask prior-guided denoising diffusion improves inverse protein folding
Bai, Peizhen
Miljković, Filip
Liu, Xianyuan
De Maria, Leonardo
Croasdale-Wood, Rebecca
Rackham, Owen
Lu, Haiping
Biomolecules
Machine Learning
Inverse protein folding generates valid amino acid sequences that can fold into a desired protein structure, with recent deep-learning advances showing strong potential and competitive performance. However, challenges remain, such as predicting elements with high structural uncertainty, including disordered regions. To tackle such low-confidence residue prediction, we propose a Mask-prior-guided denoising Diffusion (MapDiff) framework that accurately captures both structural information and residue interactions for inverse protein folding. MapDiff is a discrete diffusion probabilistic model that iteratively generates amino acid sequences with reduced noise, conditioned on a given protein backbone. To incorporate structural information and residue interactions, we develop a graph-based denoising network with a mask-prior pre-training strategy. Moreover, in the generative process, we combine the denoising diffusion implicit model with Monte-Carlo dropout to reduce uncertainty. Evaluation on four challenging sequence design benchmarks shows that MapDiff substantially outperforms state-of-the-art methods. Furthermore, the in silico sequences generated by MapDiff closely resemble the physico-chemical and structural characteristics of native proteins across different protein families and architectures.
title Mask prior-guided denoising diffusion improves inverse protein folding
topic Biomolecules
Machine Learning
url https://arxiv.org/abs/2412.07815