Search

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. [ABSTRACT FROM AUTHOR]

Accurately modeling the protein fitness landscapes holds great importance for protein engineering. Pre-trained protein language models have achieved state-of-the-art performance in predicting protein fitness without wet-lab experimental data, but their accuracy and interpretability remain limited. On the other hand, traditional supervised deep learning models require abundant labeled training examples for performance improvements, posing a practical barrier. In this work, we introduce FSFP, a training strategy that can effectively optimize protein language models under extreme data scarcity for fitness prediction. By combining meta-transfer learning, learning to rank, and parameter-efficient fine-tuning, FSFP can significantly boost the performance of various protein language models using merely tens of labeled single-site mutants from the target protein. In silico benchmarks across 87 deep mutational scanning datasets demonstrate FSFP's superiority over both unsupervised and supervised baselines. Furthermore, we successfully apply FSFP to engineer the Phi29 DNA polymerase through wet-lab experiments, achieving a 25% increase in the positive rate. These results underscore the potential of our approach in aiding AI-guided protein engineering. In this work, the authors proposed a few-shot learning approach that can efficiently optimize protein language models for fitness prediction. It combines the techniques of meta-transfer learning, learning to rank, and parameter-efficient fine-tuning. [ABSTRACT FROM AUTHOR]

Streptomyces mobaraensis transglutaminase (smTG) has been widely used in the food processing industry for protein crosslinking. However, its poor thermostability becomes a major obstacle to further applications. It is significant to develop a feasible strategy to improve the thermostability of smTG. Here, we developed a computational model based on the Siamese graph neural network framework to identify residues critical to the thermostability of smTG by predicting changes in folding free energy (ΔΔG) between the wild type and mutants. Four candidate residues were selected for mutation experiments, and the single mutant H44C exhibited 2.7 U mg−1 residual enzyme activity after 10 min incubation at 60 °C, twice as much as the wild type. Mutants Q74F and E87W also exhibited 3- and 2.3-times greater activity after 20 min. Molecular dynamics (MD) simulations revealed that smTG mutants (H44C, Q74F, and E87W) improved thermostability by enhancing hydrogen bond interactions, increasing additional residue interactions, and reducing loop flexibility. The MM-GBSA calculation demonstrated that mutants H44C and Q74F enhanced binding affinity with the substrate, and six residues crucial for substrate binding were identified. This study combines computational analysis with mutation assays for the rational design of smTG and offers a facile and efficient strategy to understand and improve the thermostability of proteins for industrial applications. [ABSTRACT FROM AUTHOR]

The protein dynamical transition at ~200 K, where the biomolecule transforms from a harmonic, non-functional form to an anharmonic, functional state, has been thought to be slaved to the thermal activation of dynamics in its surface hydration water. Here, by selectively probing the dynamics of protein and hydration water using elastic neutron scattering and isotopic labeling, we found that the onset of anharmonicity in the two components around 200 K is decoupled. The one in protein is an intrinsic transition, whose characteristic temperature is independent of the instrumental resolution time, but varies with the biomolecular structure and the amount of hydration, while the one of water is merely a resolution effect., Competing Interests: LZ, BZ, BW, YT, JH, MT, VG, TY, HO, QZ, LH No competing interests declared, (© 2024, Zheng, Zhou, Wu et al.)

Prokaryotic Argonaute (pAgo) proteins, a class of DNA/RNA-guided programmable endonucleases, have been extensively utilized in nucleic acid-based biosensors. The specific binding and cleavage of nucleic acids by pAgo proteins, which are crucial processes for their applications, are dependent on the presence of Mn 2+ bound in the pockets, as verified through X-ray crystallography. However, a comprehensive understanding of how dissociated Mn 2+ in the solvent affects the catalytic cycle, and its underlying regulatory role in this structure-function relationship, remains underdetermined. By combining experimental and computational methods, this study reveals that unbound Mn 2+ in solution enhances the flexibility of diverse pAgo proteins. This increase in flexibility through decreasing the number of hydrogen bonds, induced by Mn 2+ , leads to higher affinity for substrates, thus facilitating cleavage. More importantly, Mn 2+ -induced structural flexibility increases the mismatch tolerance between guide-target pairs by increasing the conformational states, thereby enhancing the cleavage of mismatches. Further simulations indicate that the enhanced flexibility in linkers triggers conformational changes in the PAZ domain for recognizing various lengths of nucleic acids. Additionally, Mn 2+ -induced dynamic alterations of the protein cause a conformational shift in the N domain and catalytic sites towards their functional form, resulting in a decreased energy penalty for target release and cleavage. These findings demonstrate that the dynamic conformations of pAgo proteins, resulting from the presence of the unbound Mn 2+ in solution, significantly promote the catalytic cycle of endonucleases and the tolerance of cleavage to mismatches. This flexibility enhancement mechanism serves as a general strategy employed by Ago proteins from diverse prokaryotes to accomplish their catalytic functions and provide useful information for Ago-based precise molecular diagnostics., Competing Interests: The authors declare no competing financial interests., (This journal is © The Royal Society of Chemistry.)