Computational Protein Design with Deep Learning Neural Networks

By Jingxue Wang, Huali Cao, J. H. Zhang, Yifei Qi. 2018

179 citations recorded by the source corpus.

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 improves 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.

Subfields: Molecular Biology, Generative Models, Computational Biology & Bioinformatics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

In Generative Models

In Computational Biology & Bioinformatics

Citations in the corpus

Learning inverse folding from millions of predicted structures (2022, methodology): “More recently, convolution-based deep learning methods have also been applied to predict amino acid propensities given the surrounding local structural environments (Anand-Achim et al., 2021; Boomsma & Frellsen, 2017; Shroff et al., 2020; Li et al., 2020; Qi & Zhang, 2020; Zhang et al., 2020; Chen e”
Protein sequence design with a learned potential (2022, methodology): “…learning methods for design thus far have focused on mutation prediction 25 – 30 , rotamer repacking of native sequences 31 , or amino acid sequence design without modeling side-chain conformers 32 – 35 , with some experimental validation including circular dichroism data 33 and ﬂ uorescence 26 .”
Learning from Protein Structure with Geometric Vector Perceptrons (2020, methodology): “Therefore, the proxy metric of native sequence recovery — inferring native sequences given their experimentally determined structures—is often used (Li et al., 2014; O’Connell et al., 2018; Wang et al., 2018).”
Energy-based models for atomic-resolution protein conformations (2020, methodology): “These methods have also been explored for protein design (Wang et al., 2018).”
A structure-based deep learning framework for protein engineering (2019, result): “Taken together, these data confirm our model classifies wild-type amino acids with unprecedented accuracy compared to previously reported deep learning approaches 9, 12-14 .”
Recent developments in deep learning applied to protein structure prediction (2019, background): “learning is also starting to show a lot of promise in the area of protein design.(11,12) This article is not intended to be a detailed exposition of every”
AlphaDesign: A graph protein design method and benchmark on AlphaFoldDB (2022, methodology): “The MLP methods have a high inference speed, but their accuracy is relatively low due to the partial considering of structural information.”
Generative Models for Graph-Based Protein Design (2019, methodology): “By composing multiple layers of this structured self-attention, our model can effectively capture higher-order, interaction-based dependencies between sequence and structure, in contrast to previous parameteric approaches [8, 9] that are limited to only the first-order effects.”
A general-purpose protein design framework based on mining sequence–structure relationships in known protein structures (2018, background): “More recently, Qi and coworkers applied deep-learning neural networks to CPD by expressing it as the problem of predicting the amino-acid identity at a position given its structural neighborhood (55).”
Artificial intelligence in clinical and genomic diagnostics (2019, methodology): “When applied to genomic sequence data, AI time series algorithms appear to be especially effective at detecting functional DNA sequence elements that are indicative of gene splicing [26, 27], large-scale regulatory elements [28], and gene function [29].”
Using AlphaFold for Rapid and Accurate Fixed Backbone Protein Design (2021, background): “…deep learning include ﬁxed backbone design (O’Connell et al., 2018; Ingraham et al., 2019; Qi and Zhang, 2020; Norn et al., 2021), antibody design (Wang et al., 2018; Saka et al., 2021; Shin et al., 2021), de novo design (Anishchenko et al., 2020; Moffat and Jones, 2021), and the prediction of…”
Protein sequence design with a learned potential (2020, background): “Other studies that attempt to leverage machine learning for the structure-guided sequence design task include using neural networks to individually predict residues in a sequence [80, 81], building a variational autoencoder conditioned on protein topology to generate designs [82], and framing protei”