Metadata-Version: 2.1
Name: pyErmine
Version: 0.1.2
Summary: Estimate Reaction-rates by Markov-based Investigation of Nanoscopy Experiments (ermine) using Python.
Home-page: https://github.com/SMLMS/pyErmine
Author: Sebastian Malkusch
Author-email: malkusch@med.uni-frankfurt.de
License: GNU General Public License v3 (GPLv3)
Keywords: hidden markov model,unsupervised learning,single particle tracking,biophysics
Platform: UNKNOWN
Classifier: Intended Audience :: Science/Research
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: MacOS :: MacOS X
Classifier: Operating System :: Microsoft :: Windows
Classifier: Operating System :: POSIX :: Linux
Requires-Python: >=3.5
Description-Content-Type: text/markdown
Requires-Dist: hmmlearn (>=0.2.4)
Requires-Dist: numpy (>=1.19.2)
Requires-Dist: pandas (>=1.1.5)
Requires-Dist: scikit-learn (>=0.23.2)

# pyErmine
Estimate Reaction-rates by Markov-based Investigation of Nanoscopy Experiments (ermine) using Python.

## Author
Sebastian Malkusch  

Data Science | Clinical Pharmacology  
Institute for clinical pharmacology  
Goethe-University-Hospital  
Frankfurt am Main  
Germany

## Abstarct
The python package pyErmine analyzes the mobility of laterally diffusing molecules, such as membrane receptors, using hidden Markov models. It maps the movements of individual receptors to discrete diffusion states, all of which are Brownian in nature. The model is trained with single-particle tracking data.

## Requirements
* hmmlearn >= 0.2.4
* numpy >= 1.19.2
* pandas >= 1.1.5
* scikit-learn >= 0.23.2

## Reference
Publication in progress.

## Tutorial
A tutorial including a test data set can be found on Github at the following repository: https://github.com/SMLMS/ermine-tutorial



