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
–arXiv.org Artificial Intelligence
Inverse protein folding generates valid amino acid sequences that can fold into a desired protein structure, with recent deep-learning advances showing significant potential and competitive performance. However, challenges remain in predicting highly uncertain regions, such as those with loops and disorders. To tackle such low-confidence residue prediction, we propose a \textbf{Ma}sk \textbf{p}rior-guided denoising \textbf{Diff}usion (\textbf{MapDiff}) framework that accurately captures both structural 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 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 improve uncertainty estimation. Evaluation on four challenging sequence design benchmarks shows that MapDiff significantly 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.
arXiv.org Artificial Intelligence
Dec-10-2024
- Country:
- North America > United States
- New York > New York County > New York City (0.04)
- Europe
- United Kingdom > England
- South Yorkshire > Sheffield (0.04)
- Hampshire > Southampton (0.04)
- Cambridgeshire > Cambridge (0.04)
- Sweden > Vaestra Goetaland
- Gothenburg (0.04)
- United Kingdom > England
- North America > United States
- Genre:
- Research Report > New Finding (0.93)
- Industry:
- Technology: