Computational Protein Design with Deep Learning Neural Networks

TL;DR

This paper demonstrates that deep learning neural networks can predict amino acid probabilities in proteins, improving design accuracy and sequence identity over previous methods, thus advancing computational protein design techniques.

Contribution

The study introduces a deep learning approach for protein design that leverages structural data to enhance prediction accuracy and sequence identity in protein engineering.

Findings

Achieved 38.3% prediction accuracy for amino acid probabilities.

Improved average sequence identity in protein design by using network outputs.

Predictions showed ~3% higher sequence identity than previous methods.

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.