Empirical Dynamic Modeling for Systems Biology with Machine Learning
Kevin Siswandi
May 2020
https://github.com/Physicist91/systems-identification
- Deep Learning Framework: TensorFlow 2.0
- Numerics Framework: NodePy, SymPy
- Scientific Computing Stack: SciPy, NumPy
The primary materials I consult are
The motivation of this project is derived from
- Villaverde, A. F. & Banga, J. R. Reverse engineering and identification in systems biology: strategies, perspectives and challenges. J. R. Soc. Interface 11, 20130505 (2013).
- Universal Differential Equations for Scientific Machine Learning
Keywords:
- Dynamical Systems
- Systems Biology
- Machine Learning
- Neural Network
This project is very close to the state-of-the-art research currently being conducted in the field. Traditionally, the method of discovering dynamics from data was known as system identification before machine learning libraries were made open-source commodity. However, systems identification is recognized as a hard problem in the physical sciences. Here, I want to show that a machine learning approach can help accelerate and transform how dynamic modeling is done in the sciences.