Generative AI illuminates enzyme secrets using sequences evolved in nature

Generative AI illuminates enzyme secrets using sequences evolved in nature
Comparative illustration of generative models utilized for protein sequence modeling. (A) MaxEnt model: This model aims to delineate both the conservation of individual amino acids and their pairwise interactions, while concurrently making minimal assumptions by maximizing sequence information entropy. (B) VAE: A neural network that learns to encode data into a lower-dimensional latent space and then decode it back; after training, it can effectively generate new data that resemble the training set. (C) Language model: A masked language model employs a prediction-based mechanism that strives to accurately forecast the masked amino acid, thus learning the distribution of a corpus of protein sequences. (D) GAN: A framework utilizes two neural networks operating in tandem—a generator that creates new protein sequences, and a discriminator that evaluates them for authenticity. Credit: National Science Review (2023). DOI: 10.1093/nsr/nwad331

Enzymes, nature’s remarkable biocatalysts, play an integral role in various aspects of daily life. Consider the awe-inspiring sight of fireflies lighting up a summer night. Their captivating glow serves not just to enchant observers but also plays a role in communication and mating. This natural spectacle is powered by an enzyme known as luciferase.

Zooming into the molecular scale, enzymes are intricate networks of amino acids. Luciferase, a prime example, exhibits a fascinating diversity among different species. However, these homologs exhibit specific evolutionary patterns, crucial for advancing the prediction of protein structures. A key question emerges: how do these patterns relate to the function of enzymes?

Dr. Xie and Dr. Warshel aim to decipher this intricate relationship. They approach proteins as a language of amino acid ‘letters’ and are developing generative AI tools akin to the principles behind the widely used ChatGPT.

Their AI tool quantifies the likelihood of certain sequences or mutations appearing in nature. Fascinatingly, they discovered that this probability is primarily linked to enzyme catalytic activity when mutations occur near the substrate. Conversely, mutations in the enzyme’s scaffold mainly correlate with protein stability. These insights have enabled the successful engineering of several proteins, including luciferase.

Dr. Warshel said, “The relationship between evolutionary information and diverse enzyme functions suggests that enzymes are indeed multi-scale objects. This study has the potential to revolutionize our understanding of enzyme catalysis and evolution.”

This research, now published in the journal National Science Review, not only offers new perspectives on enzyme catalysis but also holds promise for practical applications in biotechnology and beyond.

More information:
Wen Jun Xie et al, Harnessing generative AI to decode enzyme catalysis and evolution for enhanced engineering, National Science Review (2023). DOI: 10.1093/nsr/nwad331

Provided by
Science China Press


Citation:
Generative AI illuminates enzyme secrets using sequences evolved in nature (2024, March 20)
retrieved 20 March 2024
from https://phys.org/news/2024-03-generative-ai-illuminates-enzyme-secrets.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.

Source link

Denial of responsibility! NewsConcerns is an automatic aggregator of the all world’s media. In each content, the hyperlink to the primary source is specified. All trademarks belong to their rightful owners, all materials to their authors. If you are the owner of the content and do not want us to publish your materials, please contact us by email – [email protected]. The content will be deleted within 24 hours.

Leave a Comment