An Improved Systematic Method for Constructing ecGEMs using a Protein-Chemical Transformer

Enzyme-constrained genome-scale metabolic models (ecGEMs) have improved Flux Balance Analysis (FBA) by incorporating enzyme turnover numbers (kcats). Since in-vivo kcat data is costly to obtain and therefore scarce, we present a novel multi-modal transformer-based approach with cross-attention to predict kcat values for Escherichia coli using enzyme amino acid sequences and SMILES annotations of reaction substrates. For heteromeric enzymes, we evaluate multiple subunit kcat aggregation strategies. We benchmark ecGEMs constructed with these strategies against current state-of-the-art models using experimental growth rates, 13C fluxes, and enzyme abundances, and prior to any calibration outperform or match existing methods. We also devise a new calibration method using flux control coefficients (derivatives of log flux with respect to log kcat), which we show to be identical to enzyme cost at the FBA optimum. Using these coefficients, we identify 8 key kcat values to recalibrate using experimental data, subsequently achieving superior performance to the current state-of-the-art with 81% fewer calibrations.