Mimetic Neural Networks: A Unified Framework for Protein Design and Folding

• DOI: 10.3389/fbinf.2022.715006
• Publication Date: 2022-05-05T05:52:00Z
• Authors: Moshe Eliasof; Tue Boesen; Eldad Haber; Chen Keasar; Eran Treister
• Keywords: Folding (DSP implementation)

Recent advancements in machine learning techniques for protein structure prediction motivate better results 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 reversible architecture solves the design problems tandem, allowing improve backbone when estimated. We use ProteinNet data set state of art can be met even improved, given recent architectures folding.