Structure‐ and Data‐Driven Protein Engineering of Transaminases for Improving Activity and Stereoselectivity

Amine transaminases (ATAs) are powerful biocatalysts for the stereoselective synthesis of chiral amines. Machine learning provides a promising approach for protein engineering, but activity prediction models for ATAs remain elusive due to the difficulty of obtaining high‐quality training data. Thus,...

Full description

Saved in:
Bibliographic Details
Published in:Angewandte Chemie International Edition 2023-06, Vol.62 (23), p.e202301660-n/a
Main Authors: Ao, Yu‐Fei, Pei, Shuxin, Xiang, Chao, Menke, Marian J., Shen, Lin, Sun, Chenghai, Dörr, Mark, Born, Stefan, Höhne, Matthias, Bornscheuer, Uwe T.
Format: Article
Language:English
Subjects:
Amines
Amines - chemistry
Biocatalysis
Biocatalysts
Catalytic Activity
Design optimization
Machine Learning
Prediction models
Protein Engineering
Protein structure
Proteins
Regression analysis
Stereoselectivity
Substrate Specificity
Substrates
Transaminases
Transaminases - metabolism
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Amine transaminases (ATAs) are powerful biocatalysts for the stereoselective synthesis of chiral amines. Machine learning provides a promising approach for protein engineering, but activity prediction models for ATAs remain elusive due to the difficulty of obtaining high‐quality training data. Thus, we first created variants of the ATA from Ruegeria sp. (3FCR) with improved catalytic activity (up to 2000‐fold) as well as reversed stereoselectivity by a structure‐dependent rational design and collected a high‐quality dataset in this process. Subsequently, we designed a modified one‐hot code to describe steric and electronic effects of substrates and residues within ATAs. Finally, we built a gradient boosting regression tree predictor for catalytic activity and stereoselectivity, and applied this for the data‐driven design of optimized variants which then showed improved activity (up to 3‐fold compared to the best variants previously identified). We also demonstrated that the model can predict the catalytic activity for ATA variants of another origin by retraining with a small set of additional data. Using structure‐dependent protein engineering of transaminases, a high‐quality catalytic activity and stereoselectivity dataset was collected. A machine learning predictor was built based on this dataset and successfully applied in the data‐driven protein engineering resulting in enzyme variants with significantly improved activity, higher and even inversed stereoselectivity.
ISSN:1433-7851
1521-3773
DOI:10.1002/anie.202301660