Author:
Eliasof Moshe,Boesen Tue,Haber Eldad,Keasar Chen,Treister Eran
Abstract
Recent advancements in machine learning techniques for protein structure prediction 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 backbone 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 met and even improved, given recent architectures for protein folding.
Cited by
4 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. DRIP: deep regularizers for inverse problems;Inverse Problems;2023-12-01
2. Estimating a Potential Without the Agony of the Partition Function;SIAM Journal on Mathematics of Data Science;2023-11-16
3. Protein Design Using Physics Informed Neural Networks;Biomolecules;2023-03-01
4. Graph machine learning in drug discovery;Cheminformatics, QSAR and Machine Learning Applications for Novel Drug Development;2023