Design of metalloproteins and novel protein folds using variational autoencoders

Abstract

The design of novel proteins has many applications but remains an attritional process with success in isolated cases. Meanwhile, deep learning technologies have exploded in popularity in recent years and are increasingly applicable to biology due to the rise in available data. We attempt to link protein design and deep learning by using variational autoencoders to generate protein sequences conditioned on desired properties. Potential copper and calcium binding sites are added to non-metal binding proteins without human intervention and compared to a hidden Markov model. In another use case, a grammar of protein structures is developed and used to produce sequences for a novel protein topology. One candidate structure is found to be stable by molecular dynamics simulation. The ability of our model to confine the vast search space of protein sequences and to scale easily has the potential to assist in a variety of protein design tasks.

arXiv commentJGG and LM contributed equally to the work

References in corpus (8)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Automatic chemical design using a data-driven continuous representation of molecules
• Conditional Image Generation with PixelCNN Decoders
• Pixel Recurrent Neural Networks
• ProtVec: A Continuous Distributed Representation of Biological Sequences
• Computational Protein Design with Deep Learning Neural Networks
• Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space
• Variational auto-encoding of protein sequences

Cited by in corpus (11)

• Learning from Protein Structure with Geometric Vector Perceptrons
• Protein sequence design with deep generative models
• Efficient generative modeling of protein sequences using simple autoregressive models
• Fast differentiable DNA and protein sequence optimization for molecular design
• ProGen: Language Modeling for Protein Generation
• Deep Learning in Protein Structural Modeling and Design
• A primer on model-guided exploration of fitness landscapes for biological sequence design
• Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design
• Lattice protein design using Bayesian learning
• Learning to Design RNA
• Combination of digital signal processing and assembled predictive models facilitates the rational design of proteins