Approaching Optimal pH Enzyme Prediction with Large Language Models
Abstract
Enzymes are widely used in biotechnology due to their ability to catalyze chemical reactions: food making, laundry, pharmaceutics, textile, brewing─all these areas benefit from utilizing various enzymes. Proton concentration (pH) is one of the key factors that define the enzyme functioning and efficiency. Usually there is only a narrow range of pH values where the enzyme is active. This is a common problem in biotechnology to design an enzyme with optimal activity in a given pH range. A large part of this task can be completed in silico, by predicting the optimal pH of designed candidates. The success of such computational methods critically depends on the available data. In this study, we developed a language-model-based approach to predict the optimal pH range from the enzyme sequence. We used different splitting strategies based on sequence similarity, protein family annotation, and enzyme classification to validate the robustness of the proposed approach. The derived machine-learning models demonstrated high accuracy across proteins from different protein families and proteins with lower sequence similarities compared with the training set. The proposed method is fast enough for the high-throughput virtual exploration of protein space for the search for sequences with desired optimal pH levels.
Main Authors
Format
Articles
Research article
Published
2024
Series
Subjects
Publication in research information system
Publisher
American Chemical Society
The permanent address of the publication
https://urn.fi/URN:NBN:fi:jyu-202409115903Use this for linking
Review status
Peer reviewed
ISSN
2161-5063
DOI
https://doi.org/10.1021/acssynbio.4c00465
Language
English
Published in
ACS Synthetic Biology
Citation
- Zaretckii, M., Buslaev, P., Kozlovskii, I., Morozov, A., & Popov, P. (2024). Approaching Optimal pH Enzyme Prediction with Large Language Models. ACS Synthetic Biology, Early online. https://doi.org/10.1021/acssynbio.4c00465
Funder(s)
Research Council of Finland
Funding program(s)
Postdoctoral Researcher, AoF
Tutkijatohtori, SA

Additional information about funding
P.B. was supported by the Academy of Finland (grant 342908). A.M. was supported by the Russian Science Foundation (RSF-22–74–10098).
Copyright© The Authors. Published by American Chemical Society