https://github.com/smrfeld/phys_dbd

Physics-based machine learning with dynamic Boltzmann distributions
https://github.com/smrfeld/phys_dbd

machine-learning physics physics-informed-learning physics-informed-ml physics-informed-neural-networks reaction-diffusion tensorflow

Last synced: 7 days ago
JSON representation

Physics-based machine learning with dynamic Boltzmann distributions

• Host: GitHub
• URL: https://github.com/smrfeld/phys_dbd
• Owner: smrfeld
• License: mit
• Created: 2021-06-13T20:52:41.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2022-01-11T05:44:27.000Z (almost 3 years ago)
• Last Synced: 2024-12-15T17:21:31.923Z (16 days ago)
• Topics: machine-learning, physics, physics-informed-learning, physics-informed-ml, physics-informed-neural-networks, reaction-diffusion, tensorflow
• Language: Jupyter Notebook
• Homepage: https://smrfeld.github.io/phys_dbd
• Size: 19.3 MB
• Stars: 2
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Physics-based dynamic PCA for modeling stochastic reaction networks with TensorFlow

[![docs](https://github.com/smrfeld/phys_dbd/actions/workflows/docs.yml/badge.svg)](https://github.com/smrfeld/phys_dbd/actions/workflows/docs.yml)

This is the source repo. for the `physDBD` Python package. It allows the creation of physics-based machine learning models in `TensorFlow` for modeling stochastic reaction networks.



## Quickstart

1. Install:

    ```

    pip install physDBD

    ```

2. See the [example notebook](example/main.ipynb).

3. Read the [documentation](https://smrfeld.github.io/phys_dbd).

## About

This repo. implements a TensorFlow package for modeling stochastic reaction networks with a dynamic PCA model. [Please see this paper for technical details](https://arxiv.org/abs/2109.05053):

```

O. K. Ernst, T. Bartol, T. Sejnowski and E. Mjolsness. Physics-based machine learning for modeling stochastic IP3-dependent calcium dynamics. arXiv:2109.05053

```

The original implementation in the paper is written in Mathematica and can be found [here](https://github.com/smrfeld/physics-based-ml-reaction-networks). The Python package developed here translates these methods to `TensorFlow`.

The only current supported probability distribution is the Gaussian distribution defined by PCA; more general Gaussian distributions are a work in progress.

## Requirements

* `TensorFlow 2.5.0` or later. *Note: later versions not tested.*

* `Python 3.7.4` or later.

## Installation

Use `pip`:

```

pip install physDBD

```

Alternatively, clone this repo. and use the provided `setup.py`:

```

python setup.py install

```

## Documentation

See the dedicated [documentation page](https://smrfeld.github.io/phys_dbd).

## Example

See the notebook in the [example notebook](example/main.ipynb).

## Tests

Tests are run using `pytest` and are located in [tests](tests/).

## Citing

[Please cite this paper:](https://arxiv.org/abs/2109.05053):

```

O. K. Ernst, T. Bartol, T. Sejnowski and E. Mjolsness. Physics-based machine learning for modeling stochastic IP3-dependent calcium dynamics. arXiv:2109.05053

```