Large-scale design and refinement of stable proteins using sequence-only models

Singer, Jedediah M.; Novotney, Scott; Strickland, Devin; Haddox, Hugh K.; Leiby, Nicholas; Rocklin, Gabriel J.; Chow, Cameron M.; Roy, Anindya; Bera, Asim K.; Motta, Francis C.; Cao, Longxing; Strauch, Eva-Maria; Chidyausiku, Tamuka M.; Ford, Alex; Ho, Ethan; Mackenzie, Craig O.; Eramian, Hamed; DiMaio, Frank; Grigoryan, Gevorg; Vaughn, Matthew; Stewart, Lance J.; Baker, David; Klavins, Eric

Engineered proteins generally must possess a stable structure in order to achieve their designed function. Stable designs, however, are astronomically rare within the space of all possible amino acid sequences. As a consequence, many designs must be tested computationally and experimentally in order to find stable ones, which is expensive in terms of time and resources. Here we report a neural network model that predicts protein stability based only on sequences of amino acids, and demonstrate its performance by evaluating the stability of almost 200,000 novel proteins. These include a wide range of sequence perturbations, providing a baseline for future work in the field. We also report a second neural network model that is able to generate novel stable proteins. Finally, we show that the predictive model can be used to substantially increase the stability of both expert-designed and model-generated proteins.