Back to Search
Start Over
Using deep learning to model the hierarchical structure and function of a cell
- Source :
- Nature methods
- Publication Year :
- 2018
-
Abstract
- Although artificial neural networks simulate a variety of human functions, their internal structures are hard to interpret. In the life sciences, extensive knowledge of cell biology provides an opportunity to design visible neural networks (VNNs) which couple the model’s inner workings to those of real systems. Here we develop DCell, a VNN embedded in the hierarchical structure of 2526 subsystems comprising a eukaryotic cell (http://d-cell.ucsd.edu/). Trained on several million genotypes, DCell simulates cellular growth nearly as accurately as laboratory observations. During simulation, genotypes induce patterns of subsystem activities, enabling in-silico investigations of the molecular mechanisms underlying genotype-phenotype associations. These mechanisms can be validated and many are unexpected; some are governed by Boolean logic. Cumulatively, 80% of the importance for growth prediction is captured by 484 subsystems (21%), reflecting the emergence of a complex phenotype. DCell provides a foundation for decoding the genetics of disease, drug resistance, and synthetic life.
- Subjects :
- 0301 basic medicine
Time Factors
Genotype
Computer science
In silico
Diving
Biochemistry
Article
Cell Physiological Phenomena
03 medical and health sciences
Deep Learning
Humans
Computer Simulation
Molecular Biology
Eukaryotic cell
Structure (mathematical logic)
Artificial neural network
Real systems
business.industry
Deep learning
Cell Biology
Structure and function
030104 developmental biology
Gene Expression Regulation
Artificial intelligence
Neural Networks, Computer
business
Decoding methods
Biotechnology
Subjects
Details
- Language :
- English
- ISSN :
- 15487105 and 15487091
- Volume :
- 15
- Issue :
- 4
- Database :
- OpenAIRE
- Journal :
- Nature methods
- Accession number :
- edsair.doi.dedup.....f8abc4453019b11bbd0988f278730f74