ePrints

Predicting plant Rubisco kinetics from RbcL sequence data using machine learning

Lookup NU author(s): Dr Wasim Iqbal, Dr Maxim KapralovORCiD

Downloads

• Published version [.pdf]

Licence

This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).

Abstract

Ribulose-1,5-bisphosphate carboxylase/oxygenase (Rubisco) is responsible for the conversion of atmospheric CO₂ to organic carbon during photosynthesis, and often acts as a rate limiting step in the later process. Screening the natural diversity of Rubisco kinetics is the main strategy used to find better Rubisco enzymes for crop engineering efforts. Here, we demonstrate the use of Gaussian processes (GPs), a family of Bayesian models, coupled with protein encoding schemes, for predicting Rubisco kinetics from Rubisco large subunit (RbcL) sequence data. GPs trained on published experimentally obtained Rubisco kinetic datasets were applied to over 9000 sequences encoding RbcL to predict Rubisco kinetic parameters. Notably, our predicted kinetic values were in agreement with known trends, e.g. higher carboxylation turnover rates (Kcat) for Rubisco enzymes from C₄ or crassulacean acid metabolism (CAM) species, compared with those found in C₃ species. This is the first study demonstrating machine learning approaches as a tool for screening and predicting Rubisco kinetics, which could be applied to other enzymes.

Publication metadata

Author(s): Iqbal WA, Lisitsa A, Kapralov MV

Publication type: Article

Publication status: Published

Journal: Journal of Experimental Botany

Year: 2023

Volume: 74

Issue: 2

Pages: 638-650

Print publication date: 11/01/2023

Online publication date: 12/09/2022

Acceptance date: 12/09/2022

Date deposited: 13/07/2023

ISSN (print): 0022-0957

ISSN (electronic): 1460-2431

Publisher: Oxford University Press

URL: https://doi.org/10.1093/jxb/erac368

DOI: 10.1093/jxb/erac368

Altmetrics

Funding

Share