Beyond Natural Antibodies: Scaffold-Based Generation of Novel Anti-3CLpro Nanobody Nb01
Zhan, Z.; Luo, C.; Xiong, J.; Jiang, Y.; Li, Y.; Huang, F.; Cai, Y.; Liu, J.
Show abstract
In the post-pandemic era, continuous mutations and persistent infections of Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) pose a significant threat to global health, making the normalization of preventive measures imperative. Due to its high conservation, the 3CLpro is relatively stable across all these variants without significant changes, suggesting that drugs targeting this enzyme could be effective against all variant viruses. And compared to traditional antibodies, nanobodies show significant advantages against SARS-CoV-2 and its variants. Traditional antibodies often lose their inhibitory activity due to viral mutation. Nanobodies are characterised by their small size, high stability, high affinity for antigen binding, and high water solubility, which enable them to capture viruses quickly and effectively address the continuous mutations and persistent infections of SARS-CoV-2. In this research, we devised a strategy to produce nanobodies by utilizing a fragment-generating large language model, resulting in the identification of a nanobody named Nb01. Nb01 exhibits potent and broad-spectrum neutralizing activity against numerous SARS-CoV-2 variants. The nanobody Nb01, directed against the SARS-CoV-2 3CLpro, demonstrated efficacy against the majority of prevalent SARS-CoV-2 variants. Notably, it has a higher affinity than the current best performing nanobodies (S43, bn03, R14, and 3-2A2-4) for most of the variants, including the Alpha (27.5%), Gamma (29.7%), Omicron BA.2 (32.2%), BA.4/5 (81.2%), BF.7 (64.2%) and XBB (5.5%) variants. For other variants, Nb01 displayed affinities that were on par with these benchmark nanobodies. In summary, the exceptional specificity, low toxicity, robust stability, and extensive spectrum of Nb01 indicate its potential to be developed as a nanobody therapeutic for the management of SARS-CoV-2 infections and its diverse variants.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- A method for predicting linear and conformational B-cell epitopes in an antigen from its primary sequence 94%
- AE-LGBM: Sequence-Based Novel Approach To Detect Interacting Protein Pairs via Ensemble of Autoencoder and LightGBM. 94%
- In Silico Identification of Potential Inhibitors of Mycobacterium tuberculosis DNA Gyrase from Phytoconstituents of Indian Medicinal Plants 94%
Similar papers in this journal
- Elucidation of Genome-wide Understudied Proteins targeted by PROTAC-induced degradation using Interpretable Machine Learning 96%
- Pathfinder: protein folding pathway prediction based on conformational sampling 96%
- Protein Domain-Based Prediction of Compound-Target Interactions and Experimental Validation on LIM Kinases 94%
Similar papers in this journal
- E2EDA: Protein domain assembly based on end-to-end deep learning 95%
- Pred-AHCP: Robust feature selection enabled Sequence Specific Prediction of Anti-Hepatitis C Peptides via Machine Learning 94%
- To Improve Protein Sequence Profile Prediction through Image Captioning on Pairwise Residue Distance Map 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.