Sonification based de novo protein design using artificial intelligence, structure prediction, and analysis using molecular modeling.

Chi-Hua Yu,Markus J Buehler

doi:10.1063/1.5133026

Abstract

We report the use of a deep learning model to design de novo proteins, based on the interplay of elementary building blocks via hierarchical patterns. The deep neural network model is based on translating protein sequences and structural information into a musical score that features different pitches for each of the amino acids, and variations in note length and note volume reflecting secondary structure information and information about the chain length and distinct protein molecules. We train a deep learning model whose architecture is composed of several long short-term memory units from data consisting of musical representations of proteins classified by certain features, focused here on alpha-helix rich proteins. Using the deep learning model, we then generate de novo musical scores and translate the pitch information and chain lengths into sequences of amino acids. We use a Basic Local Alignment Search Tool to compare the predicted amino acid sequences against known proteins, and estimate folded protein structures using the Optimized protein fold RecognitION method (ORION) and MODELLER. We find that the method proposed here can be used to design de novo proteins that do not exist yet, and that the designed proteins fold into specified secondary structures. We validate the newly predicted protein by molecular dynamics equilibration in explicit water and subsequent characterization using a normal mode analysis. The method provides a tool to design novel protein materials that could find useful applications as materials in biology, medicine, and engineering.

Highlights

The design of hierarchical materials represents one of the frontiers in materials science.1–3 In spite of nature’s extensive examples of material designs, from silk, to bone, to cells and many others, we are yet to have access to methods that can automatically extract design features from such materials and implement them in new materials that do not yet exist in nature
We review the results of a variety of amino acid sequence predictions and the resulting protein structures
We note that in the mapping from the musical score back to the amino acid sequence, we solely map the amino acid sequence, and do not capture any secondary or higher-order structural information. This serves as a control mechanism to confirm that the predicted secondary structure, obtained through an analysis of the musical score, agrees with the predicted protein structures

Summary

Introduction

The design of hierarchical materials represents one of the frontiers in materials science. In spite of nature’s extensive examples of material designs, from silk, to bone, to cells and many others, we are yet to have access to methods that can automatically extract design features from such materials and implement them in new materials that do not yet exist in nature. The design of hierarchical materials represents one of the frontiers in materials science.. In spite of nature’s extensive examples of material designs, from silk, to bone, to cells and many others, we are yet to have access to methods that can automatically extract design features from such materials and implement them in new materials that do not yet exist in nature. Proteins consist of 20 naturally occurring amino acid building blocks that are assembled into hierarchical structures across many length-scales.. Examples for protein materials with a structural (e.g., mechanical) function include hair, silk, and tendon.

Methods

Results

Conclusion