» Articles » PMID: 39251570

A Conditional Protein Diffusion Model Generates Artificial Programmable Endonuclease Sequences with Enhanced Activity

Overview
Journal Cell Discov
Date 2024 Sep 9
PMID 39251570
Authors
Affiliations
Soon will be listed here.
Abstract

Deep learning-based methods for generating functional proteins address the growing need for novel biocatalysts, allowing for precise tailoring of functionalities to meet specific requirements. This advancement leads to the development of highly efficient and specialized proteins with diverse applications across scientific, technological, and biomedical fields. This study establishes a pipeline for protein sequence generation with a conditional protein diffusion model, namely CPDiffusion, to create diverse sequences of proteins with enhanced functions. CPDiffusion accommodates protein-specific conditions, such as secondary structures and highly conserved amino acids. Without relying on extensive training data, CPDiffusion effectively captures highly conserved residues and sequence features for specific protein families. We applied CPDiffusion to generate artificial sequences of Argonaute (Ago) proteins based on the backbone structures of wild-type (WT) Kurthia massiliensis Ago (KmAgo) and Pyrococcus furiosus Ago (PfAgo), which are complex multi-domain programmable endonucleases. The generated sequences deviate by up to nearly 400 amino acids from their WT templates. Experimental tests demonstrated that the majority of the generated proteins for both KmAgo and PfAgo show unambiguous activity in DNA cleavage, with many of them exhibiting superior activity as compared to the WT. These findings underscore CPDiffusion's remarkable success rate in generating novel sequences for proteins with complex structures and functions in a single step, leading to enhanced activity. This approach facilitates the design of enzymes with multi-domain molecular structures and intricate functions through in silico generation and screening, all accomplished without the need for supervision from labeled data.

Citing Articles

Protein engineering in the deep learning era.

Zhou B, Tan Y, Hu Y, Zheng L, Zhong B, Hong L mLife. 2025; 3(4):477-491.

PMID: 39744096 PMC: 11685842. DOI: 10.1002/mlf2.12157.


Sifting through the noise: A survey of diffusion probabilistic models and their applications to biomolecules.

Norton T, Bhattacharya D J Mol Biol. 2024; 437(6):168818.

PMID: 39389290 PMC: 11885034. DOI: 10.1016/j.jmb.2024.168818.

References
1.
Huang P, Boyken S, Baker D . The coming of age of de novo protein design. Nature. 2016; 537(7620):320-7. DOI: 10.1038/nature19946. View

2.
Watson J, Juergens D, Bennett N, Trippe B, Yim J, Eisenach H . De novo design of protein structure and function with RFdiffusion. Nature. 2023; 620(7976):1089-1100. PMC: 10468394. DOI: 10.1038/s41586-023-06415-8. View

3.
Hegge J, Swarts D, Chandradoss S, Cui T, Kneppers J, Jinek M . DNA-guided DNA cleavage at moderate temperatures by Clostridium butyricum Argonaute. Nucleic Acids Res. 2019; 47(11):5809-5821. PMC: 6582352. DOI: 10.1093/nar/gkz306. View

4.
Xun G, Liu Q, Chong Y, Guo X, Li Z, Li Y . Argonaute with stepwise endonuclease activity promotes specific and multiplex nucleic acid detection. Bioresour Bioprocess. 2024; 8(1):46. PMC: 10991114. DOI: 10.1186/s40643-021-00401-6. View

5.
Zheng L, Lu H, Zan B, Li S, Liu H, Liu Z . Loosely-packed dynamical structures with partially-melted surface being the key for thermophilic argonaute proteins achieving high DNA-cleavage activity. Nucleic Acids Res. 2022; 50(13):7529-7544. PMC: 9303296. DOI: 10.1093/nar/gkac565. View