Enzymes have evolved for millions of years to adapt to various conditions such as temperatures well above boiling all the way to near freezing. To be able to adapt enzymes in silico to new conditions have been a long standing goal in biotechnology. Existing methods have focused on leveraging the evolutionary data in orthologous groups that include the target properties. These methods are dependent on the existence of orthologous groups with the desired property. However, new methods in AI research have proved that style transfer can be implemented with unpaired data sets in the domains of computer vision. We now want to adopt these methods to transfer properties between enzymes.