Team:Toronto/drylab
Dry Lab
Bioreactor
In order to fit PETase into current infrastructure, the development of an industrial application of PETase was required. By creating a bioreactor model, we bridged a thermally stable enzyme with greater catalyic activity and the public's current habits. Our bioreactor model extracted terephthalic acid (TPA) and ethylene glycol (EG) for reuse. We also created an enzyme kinetic model to describe the production of TPA and EG for downstream applications. Through three tanks and a distillation column, we modelled the extraction process for TPA and EG recycling.
Protein Engineering
To achieve higher catalytic activity and thermostability of our enzyme, we pursued different protein engineering approaches. Genetic algorithms, rational design, transfer learning, and a program called CRAUT helped generate various variants of PETase that we could test in the lab. The results demonstrated different advantages of each approach.
Software
We present a generalizable and automated pipeline for protein design. Our model can be applied to the optimization of any protein class, even those with scarce data. We first train an AdaBoost regressor that is able to predict a protein property from sequence alone. We then train a recurrent neural network (RNN) that is able to generate novel protein sequences. Generated sequences are evaluated by the regressor and those that pass a specified threshold are added in the training set for the RNN to be retrained. This iterative process continues until convergence or experimental validation.
