The increasing availability of enzyme turnover number measurements from experiments and of turnover number predictions from deep learning models prompts the use of these enzyme parameters in precise metabolic engineering or selection of plant genotypes with desired traits. Here, we present the findings from two data-driven modeling approaches that allow the prediction of metabolic engineering strategies relying on modification of turnover numbers to improve plant metabolic traits of interest. The first approach is rooted in genomic prediction of enzyme parameters estimated by fitting measured photosynthesis-related traits to kinetic models of photosynthesis. We demonstrate that this approach can be used to predict photosynthesis-related traits for unseen environments and genotypes. The second is a constraint-based modelling approach that relies on enzyme-constrained metabolic models to predict in silico strategies to modulate metabolic traits of interest (e.g. photosynthetic efficiency, respiration rate, production of chemicals). It facilitates the usage of the available compendia of turnover numbers in the design of precise metabolic engineering strategies. We show that this approach can be used in the design of precise metabolic engineering strategies that couple enzyme optimization with modulation of enzyme abundance. The resulting metabolic strategies make use of the latest development of enzyme-constrained plant metabolic models, and pave the way for systematic investigation of synthetic designs to modify plant metabolism.