Linda J. Broadbelt

This paper develops reaction rules informed by enzyme mechanisms to predict viable novel enzymatic reactions, achieving high coverage and precise atom identification.

RC-GNN predicts enzyme-reaction pairs using amino acid sequences and reaction stoichiometry, achieving high ROC-AUC scores on diverse datasets.

BioPKS Pipeline automates the design of chimeric type I polyketide synthases and enzymatic pathways to synthesize target chemicals, achieving exact designs for 93 of 155 tested molecules and proposing routes for complex natural products.

This paper develops a dynamic kinetic model of cell-free metabolism to optimize butanol production, identifying aldehyde/alcohol dehydrogenase as a key bottleneck.

The paper identifies signaling interactions and transcription factors involved in ovarian follicle development using protein interaction networks and public microarray data.

This paper uses Bayesian inference with linear-logarithmic kinetics to efficiently estimate parameter uncertainty in metabolic models from multiomics data.