Mimetic Neural Networks: A unified framework for Protein Design and Folding
This work aims to improve protein design for researchers in structural biology and drug discovery by integrating it with protein folding.
This paper introduces MimNet, a graph mimetic neural network, to address protein design and folding simultaneously. It demonstrates that a reversible architecture can improve protein design by leveraging better structure estimations from recent protein folding architectures, achieving state-of-the-art results on the ProteinNet dataset.
Recent advancements in machine learning techniques for protein folding motivate better results in its inverse problem -- protein design. In this work we introduce a new graph mimetic neural network, MimNet, and show that it is possible to build a reversible architecture that solves the structure and design problems in tandem, allowing to improve protein design when the structure is better estimated. We use the ProteinNet data set and show that the state of the art results in protein design can be improved, given recent architectures for protein folding.