🧬
Research in Computational Biochemistry
Utilized natural language processing (NLP) and large language models (LLMs) to computationally generate and validate Cas9 proteins for their use in CRISPR-Cas9 gene editing systems in silico. Sub-par fidelity of Cas9 proteins results in off-target effects, compromising the safety of gene therapies. Conventional laboratory protein engineering has improved, however, the rise in computational design of endonuclease proteins and peptide-based binders with machine learning has presented a more efficient avenue for developing novel therapeutics using protein-based large language models (LLMs).
2024