A deep learning approach to programmable RNA switches
Name
s41467-020-18677-1.pdf
Description
Published version
Size
4.97 MB
Format
Adobe PDF
Checksum (MD5)
d7abd18846c57719ca3fa43d8851034f
Author(s)
Angenent-Mari, Nicolaas M
Garruss, Alexander S
Soenksen, Luis R
Church, George
Collins, James J
Date Issued
2020
Journal
Nature Communications
Publisher
Springer Science and Business Media LLC
Version
Final published version
Abstract
Engineered RNA elements are programmable tools capable of detecting small molecules, proteins, and nucleic acids. Predicting the behavior of these synthetic biology components remains a challenge, a situation that could be addressed through enhanced pattern recognition from deep learning. Here, we investigate Deep Neural Networks (DNN) to predict toehold switch function as a canonical riboswitch model in synthetic biology. To facilitate DNN training, we synthesize and characterize in vivo a dataset of 91,534 toehold switches spanning 23 viral genomes and 906 human transcription factors. DNNs trained on nucleotide sequences outperform (R = 0.43–0.70) previous state-of-the-art thermodynamic and kinetic models (R = 0.04–0.15) and allow for human-understandable attention-visualizations (VIS4Map) to identify success and failure modes. This work shows that deep learning approaches can be used for functionality predictions and insight generation in RNA synthetic biology. 2 2
MIT Department
Massachusetts Institute of Technology. Department of Biological Engineering
Massachusetts Institute of Technology. Institute for Medical Engineering & Science
Massachusetts Institute of Technology. Department of Mechanical Engineering
Harvard University--MIT Division of Health Sciences and Technology
Terms of Use
Creative Commons Attribution 4.0 International license
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1038/S41467-020-18677-1
