Welcome to molearn’s documentation!

molearn is a Python package streamlining the implementation of machine learning models dedicated to the generation of protein conformations from example data obtained via experiment or molecular simulation.

molearn provides tools to load protein conformational ensemble data, build a model handling this data, define a loss function for this model to train against, define a training protocol, and analyse the resulting trained model.

Contents:

• Data Loading
  • PDBData
• Loss Functions
• FoldingNet Model
• CNN model
• Trainers
• Scoring
• Analysis
• Frequently Asked Questions
  • I cannot install openmmtorchplugin
  • I get an IndexError when I try loading a multiPDB
  • The GUI freezes when I use it/does not work as expected

Please see molearn’s Github page for installation instructions and examples scripts.

Indices and tables

• Index

• Module Index

• Search Page