ok.. _home:
Neuro-MINE Documentation
Neuro-MINE (Model Identification of Neural Encoding) is a tool for analyzing neural response data and making statistical inferences.
Neuro-MINE allows users to train a flexible, convolutional neural network (CNN) to analyze experimental datasets containing neural activity and corresponding predictors (e.g., behavioral responses).
It also allows for predictions of neural responses from a previously fit model for hypothesis generation.
Quick Start
Create conda environment:
conda create -n mine python=3.12
Activate environment
conda activate mine
Install/upgrade Neuro-MINE from PyPi
pip install -U neuro_mine
Links
Source code: https://github.com/matovic5/neuro_mine
Release notes: https://github.com/matovic5/neuro_mine/releases
Issue tracker: https://github.com/matovic5/neuro_mine/issues
About the Project
Neuro-MINE was created for neuroscientists by neuroscientists.
If you use this package in your research, please consider citing the associated protocol:
Matovic D, Haesemeyer M. Protocol for Neuro-MINE: A machine learning pipeline for time-series neural response data analysis. STAR Protocols. 2026 Dec 18;7(4). doi: 10.1016/j.xpro.2026.104913. https://doi.org/10.1016/j.xpro.2026.104913
or the original publication:
Costabile JD, Balakrishnan KA, Schwinn S, Haesemeyer M. Model discovery to link neural activity to behavioral tasks. Elife. 2023 Jun 6;12:e83289. doi: 10.7554/eLife.83289. PMID: 37278516; PMCID: PMC10310322. https://elifesciences.org/articles/83289
Note
This documentation is a work in progress. Contributions and feedback are welcome.