A deep learning approach to programmable RNA switches
| Autor: | Alexander S. Garruss, James J. Collins, Nicolaas M. Angenent-Mari, George M. Church, Luis R. Soenksen |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
0301 basic medicine
Riboswitch Computer science Science Datasets as Topic General Physics and Astronomy Genome Viral Computational biology Article General Biochemistry Genetics and Molecular Biology 03 medical and health sciences Synthetic biology Deep Learning 0302 clinical medicine Machine learning Humans lcsh:Science Multidisciplinary business.industry Deep learning Computational science RNA General Chemistry Small molecule Kinetics 030104 developmental biology Pattern recognition (psychology) Nucleic acid Thermodynamics Synthetic Biology lcsh:Q Artificial intelligence Genetic Engineering business 030217 neurology & neurosurgery Function (biology) Transcription Factors |
| Zdroj: | Nature Communications, Vol 11, Iss 1, Pp 1-12 (2020) Nature Communications |
| ISSN: | 2041-1723 |
| DOI: | 10.1038/s41467-020-18677-1 |
| Popis: | 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 (R2 = 0.43–0.70) previous state-of-the-art thermodynamic and kinetic models (R2 = 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. RNA can be used as a programmable tool for detection of biological analytes. Here the authors use deep neural networks to predict toehold switch functionality in synthetic biology applications. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|