EncoderMap#
Encodermap is a neural-network autoencoder based approach to dimensionality reduction. For a quick intro have a look at the following video:
Interactive Tutorials#
You can access interactive versions of EncoderMap tutorials online on BinderHub or Google Colab:
Start with the tutorials#
You can access all EncoderMap tutorials online on mybinder.org:


Documentation#
This is the main page of EncoderMap’s documentation. Click on one of the cards below to look at specific parts of EncoderMap’s documentation
The getting started with EncoderMap guide contains the most crucial information to get you started with EncoderMap.
Have a look at static copies of EncoderMap’s introductory notebooks. Each notebook contains a link to Google Colab to run the notebook interactively.
The user guide provides an overview of the basic concepts and top-level implementations of EncoderMap.
The API section contains the complete documentation generated by Sphinx’ autodoc. The User Guide and the API reference each other.
The results of the tests.
The current code coverage.
Results from the MyPy static type checker.
A link to CHANGELOG.md.
Guides to allow you to make contributions to EncoderMap.
Citations
#
You can find more information in these two articles. Please cite one or both if you use EncoderMap in your project. [LP19] and [LBJP19]
Tobias Lemke, Andrej Berg, Alok Jain, and Christine Peter. Encodermap (ii): visualizing important molecular motions with improved generation of protein conformations. Journal of Chemical Information and Modeling, 59(11):4550–4560, 2019.
Tobias Lemke and Christine Peter. Encodermap: dimensionality reduction and generation of molecule conformations. Journal of chemical theory and computation, 15(2):1209–1215, 2019.