Sequence-to-function deep learning frameworks for engineered riboregulators
| Autor: | Miguel A. Alcantar, Katherine M. Collins, Diogo M. Camacho, Timothy K. Lu, Pradeep Ramesh, Jacqueline A. Valeri, Bianca Lepe |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
0301 basic medicine
Computer science media_common.quotation_subject Science General Physics and Astronomy Datasets as Topic Genome Viral General Biochemistry Genetics and Molecular Biology Bottleneck Article 03 medical and health sciences Synthetic biology Structure-Activity Relationship 0302 clinical medicine Deep Learning Machine learning Humans Computer Simulation lcsh:Science Function (engineering) media_common Electronic circuit Natural Language Processing Sequence Multidisciplinary Base Sequence Models Genetic business.industry Genome Human Deep learning General Chemistry Construct (python library) 030104 developmental biology Template Computer architecture Mutagenesis Riboswitch lcsh:Q Synthetic Biology Artificial intelligence business Genetic Engineering 030217 neurology & neurosurgery Biotechnology |
| Zdroj: | Nature Communications, Vol 11, Iss 1, Pp 1-14 (2020) Nature Communications |
| ISSN: | 2041-1723 |
| Popis: | While synthetic biology has revolutionized our approaches to medicine, agriculture, and energy, the design of completely novel biological circuit components beyond naturally-derived templates remains challenging due to poorly understood design rules. Toehold switches, which are programmable nucleic acid sensors, face an analogous design bottleneck; our limited understanding of how sequence impacts functionality often necessitates expensive, time-consuming screens to identify effective switches. Here, we introduce Sequence-based Toehold Optimization and Redesign Model (STORM) and Nucleic-Acid Speech (NuSpeak), two orthogonal and synergistic deep learning architectures to characterize and optimize toeholds. Applying techniques from computer vision and natural language processing, we ‘un-box’ our models using convolutional filters, attention maps, and in silico mutagenesis. Through transfer-learning, we redesign sub-optimal toehold sensors, even with sparse training data, experimentally validating their improved performance. This work provides sequence-to-function deep learning frameworks for toehold selection and design, augmenting our ability to construct potent biological circuit components and precision diagnostics. The design of synthetic biology circuits remains challenging due to poorly understood design rules. Here the authors introduce STORM and NuSpeak, two deep-learning architectures to characterize and optimize toehold switches. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|