The identification of aggregation-prone regions in proteins and their suppression through mutations is a powerful strategy to enhance protein solubility and yield, expanding their potential applications. Here, the authors identify miss-annotations on widespread aggregation databases and apply a deep neural network-based predictor that generates a residue-level aggregation profile for protein sequences (AggreProt) to identify aggregation-prone regions in the LinB enzyme and design mutations to suppress aggregation in its exposed regions.
- Vojtech Cima
- Antonin Kunka
- Jan Martinovic