Co-founder and VP of Development at eXoZymes, Dr. Paul Opgenorth, states:

"The Large Language Models (LLMs) actually got to learn our vocabulary by breaking down the English language to its core constituents - the 26 letters of the alphabet. Then the LLM identifies patterns and stitches the letters together in order to coherently answer the questions we give it. Conversely, you can think of enzymes in the same way. Enzymes are made up of 20 amino acids and LLMs can make the same correlations between these amino acids to get to stable structures. We can use these stable structures to make better enzymes and even select for properties that would up-classify them to exozymes."

Full story:

https://exozymes.com/blog/alphafold-to-exozymes

#enzymes #exozymes #biomade #alphafold #proteinstructure