RamaNet: Computational De Novo Helical Protein Backbone Design using a Long Short-Term Memory Generative Neural Network

Abstract

The ability to perform de novo protein design will allow researchers to expand the variety of available proteins. By designing synthetic structures computationally, they can utilise more structures than those available in the Protein Data Bank, design structures that are not found in nature, or direct the design of proteins to acquire a specific desired structure. While some researchers attempt to design proteins from first physical and thermodynamic principals, we decided to attempt to test whether it is possible to perform de novo helical protein design of just the backbone statistically using machine learning by building a model that uses a long short-term memory (LSTM) architecture. The LSTM model used only the{phi} and{psi} angles of each residue from an augmented dataset of only helical protein structures. Though the networks generated backbone structures were not perfect, they were idealised and evaluated post generation where the non-ideal structures were filtered out and the adequate structures kept. The results were successful in developing a logical, rigid, compact, helical protein backbone topology. This paper is a proof of concept that shows it is possible to generate a novel helical backbone topology using an LSTM neural network architecture using only the{phi} and{psi} angles as features. The next step is to attempt to use these backbone topologies and sequence design them to form complete protein structures. Author summaryThis research project stemmed from the desire to expand the pool of protein structures that can be used as scaffolds in computational vaccine development, since the number of structures available from the Protein Data Bank was not sufficient to allow for great diversity and increase the probability of grafting a target motif onto a protein scaffold. Since a protein structures backbone can be defined by the{phi} and{psi} angles of each amino acid in the polypeptide and can effectively translate a proteins 3D structure into a table of numbers, and since protein structures are not random, this numerical representation of protein structures can be used to train a neural network to mathematically generalise what a protein structure is, and therefore generate new a protein backbone. Instead of using all proteins in the Protein Data Bank a curated dataset was used encompassing protein structures with specific characteristics that will, theoretically, allow them to be evaluated computationally. This paper details how a trained neural network was able to successfully generate helical protein backbones.