Computational Protein Design with Deep Learning Neural Networks

Abstract

Computational protein design has a wide variety of applications. Despite its remarkable success, designing a protein for a given structure and function is still a challenging task. On the other hand, the number of solved protein structures is rapidly increasing while the number of unique protein folds has reached a steady number, suggesting more structural information is being accumulated on each fold. Deep learning neural network is a powerful method to learn such big data set and has shown superior performance in many machine learning fields. In this study, we applied the deep learning neural network approach to computational protein design for predicting the probability of 20 natural amino acids on each residue in a protein. A large set of protein structures was collected and a multi-layer neural network was constructed. A number of structural properties were extracted as input features and the best network achieved an accuracy of 38.3%. Using the network output as residue type restraints was able to improve the average sequence identity in designing three natural proteins using Rosetta. Moreover, the predictions from our network show ~3% higher sequence identity than a previous method. Results from this study may benefit further development of computational protein design methods.

arXiv comment16 pages, 5 figures, 3 tables

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model
• Protein-Ligand Scoring with Convolutional Neural Networks
• Protein Secondary Structure Prediction Using Cascaded Convolutional and Recurrent Neural Networks
• Protein Secondary Structure Prediction with Long Short Term Memory Networks
• Toxicity Prediction using Deep Learning
• Deep Learning for Computational Chemistry
• Protein Secondary Structure Prediction Using Deep Multi-scale Convolutional Neural Networks and Next-Step Conditioning

Cited by in corpus (13)

• Learning from Protein Structure with Geometric Vector Perceptrons
• Design of metalloproteins and novel protein folds using variational autoencoders
• Generative Discovery of Novel Chemical Designs using Diffusion Modeling and Transformer Deep Neural Networks with Application to Deep Eutectic Solvents
• Controllable Data Generation by Deep Learning: A Review
• Deep Learning in Protein Structural Modeling and Design
• Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design
• MLIMC: Machine learning-based implicit-solvent Monte Carlo
• Energy-based models for atomic-resolution protein conformations
• Lattice protein design using Bayesian learning
• Accurate Protein Structure Prediction by Embeddings and Deep Learning Representations
• ForceGen: End-to-end de novo protein generation based on nonlinear mechanical unfolding responses using a protein language diffusion model
• Generate Novel Molecules With Target Properties Using Conditional Generative Models
• Functional bottlenecks can emerge from non-epistatic underlying traits