Skip to main content

Automated analysis of MEA datasets

Project description

autoMEA

autoMEA (Automated analysis of MEA datasets) is a open-source Python package for the analysis of Micro-Electrode Array (MEA) datasets.

How does autoMEA work?

Bursts are detected using the Max Interval Method. Users can manually set Max Interval Parameters, or can use a machine learning model that dynamically predicts optimal parameters for specific recording times. Several models are distributed with automea, and users are free to fine-tune the existing models for their specific needs, or upload new models completely.

The machine-learning-based burst detection routine is explained in the paper accompanying the package.

Tutorials and documentation can be found on readthedocs.

Installation

The preferred way of installing autoMEA is to use pip:

pip install automea

Reproducibility

All the data used to train and evaluate the machine learning models distributed with autoMEA can be found on zenodo.

Citing

If you have used autoMEA for work that has led to a scientific publication, please cite it as

@article {Hernandes2024.05.08.593078,
	author = {Hernandes, Vinicius and Heuvelmans, Anouk M. and Gualtieri, Valentina and Meijer, Dimphna H. and van Woerden, Geeske M. and Greplova, Eliska},
	title = {autoMEA: Machine learning-based burst detection for multi-electrode array datasets},
	elocation-id = {2024.05.08.593078},
	year = {2024},
	doi = {10.1101/2024.05.08.593078},
	publisher = {Cold Spring Harbor Laboratory},
	URL = {https://www.biorxiv.org/content/early/2024/05/08/2024.05.08.593078},
	journal = {bioRxiv}
}

@dataset{hernandes_2024_12685150,
  author       = {Hernandes, Vinicius and
                  Heuvelmans, Anouk M. and
                  Gualtieri, Valentina and
                  Meijer, Dimphna H. and
                  van Woerden, Geeske M. and
                  Greplova, Eliska},
  title        = {{Data and scripts used in: "autoMEA: Machine 
                   learning-based burst detection for multi-electrode
                   array datasets"}},
  month        = jul,
  year         = 2024,
  publisher    = {Zenodo},
  doi          = {10.1101/2024.05.08.593078},
  url          = {https://doi.org/10.1101/2024.05.08.593078}
}

Authors

Here is a list of authors who have contributed to this project:

  • Vinicius Hernandes
  • Anouk M. Heuvelmans
  • Valentina Gualtieri
  • Dimphna H. Meijer
  • Geeske M. van Woerden
  • Eliska Greplova

Contributing

autoMEA is an open source package, and we invite you to contribute! You contribute by opening issues, fixing them, and spreading the word about autoMEA.

License

This work is licensed under a MIT License

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

automea-0.0.16.tar.gz (53.2 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

automea-0.0.16-py3-none-any.whl (53.2 MB view details)

Uploaded Python 3

File details

Details for the file automea-0.0.16.tar.gz.

File metadata

  • Download URL: automea-0.0.16.tar.gz
  • Upload date:
  • Size: 53.2 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.9.13

File hashes

Hashes for automea-0.0.16.tar.gz
Algorithm Hash digest
SHA256 bc87a6a7505e066532b99d647f4596afeb98609f5d89b49ddd418a0e5ad30364
MD5 b8e869c53a5022b0f9d941d96431d425
BLAKE2b-256 970ecc15bbdd75d915830315e7255db4a02d334a6a7dca086ad7b45163ea2b78

See more details on using hashes here.

File details

Details for the file automea-0.0.16-py3-none-any.whl.

File metadata

  • Download URL: automea-0.0.16-py3-none-any.whl
  • Upload date:
  • Size: 53.2 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.9.13

File hashes

Hashes for automea-0.0.16-py3-none-any.whl
Algorithm Hash digest
SHA256 9bcc2ff6c90767a6e6724635a58d79773eeec1c22967a390871ccf1008d11fa8
MD5 76d03471e83f116f908b3e694646c2a9
BLAKE2b-256 32da14af06658b4880e6efd4007d2bb033edb1aaa98a9e21a4e6d54e899a9851

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page