mouse_connectivity_models is a Python module for constructing and testing mesoscale connectivity models using data from the Allen Institute for Brain Science.

It provides models written in Scikit-Learn estimator style, and has been used in the following publications:

• High resolution data-driven model of the mouse connectome

Download: http://download.alleninstitute.org/publications/A_high_resolution_data-driven_model_of_the_mouse_connectome/

Website: http://mouse-connectivity-models.readthedocs.io/en/latest/

mouse_connectivity_models requires:

• Python (>=2.7 or >= 3.4)
• scikit-learn (>= 0.22.1)
• allensdk (>= 2.10.1)

For running the examples Matplotlib >= 1.3.1 is required.

We have only tested and used this package on Linux.

We use Git for our version control and Github for hosting our main repository.

You can check out the latest sources and install using pip:

$ git clone https://github.com/AllenInstitute/mouse_connectivity_models.git
$ cd mouse_connectivity_models
$ pip install .

We are not currently supporting this code, but simply releasing it to the community AS IS but are not able to provide any guarantees of support. The community is welcome to submit issues, but you should not expect an active response.

We encourage the community to contribute! Please first review the Allen Institute Contributing Agreement, then refer to the contributing guide.

Use pipenv to install the dev dependencies. If you do not have pipenv currently installed

$ pip install pipenv

Then install dev dependencies

$ pipenv install --dev

This will create a virtual environment on your machine for this project. To activate the virtual environment (to develop)

$ pipenv shell

After installation, you can launch the test suite from outside the source directory (mcmodels) using pytest

$ pytest mcmodels

The documentation that supports mouse_connectivity_models can be found at the Website.