Cell Maps VNN (Cell Maps Visible Neural Network)

The Cell Maps VNN Tool allows to create an interpretable neural network-based model that predicts cell response to a drug. The tool uses hierarchy in HCX format generated by cellmaps_generate_hierarchy tool to create visible neural network that incorporates given input features. Then the tools allows training the model and perform predictions of cell response to a drug.

The tool creates an output directory (for both training and prediction) where results are stored and registered within Research Object Crates (RO-Crate) using the FAIRSCAPE-cli.

Warning

Interpretation and Visualization are not implemented in the current version. As for today, the tool allows to perform training and predictions using data for NeST VNN project.

Overview of Cell Maps VNN Flow

• Free software: MIT license

• Source code: https://github.com/idekerlab/cellmaps_vnn

Contents:

• Installation
  • Stable release
  • From sources
• Usage
  • In a project
  • On the command line
  • Via Docker
  • Example Usage for NeST VNN
• Inputs
  • General
  • NeST VNN
• Outputs
  • Training
  • Prediction
  • Annotation
  • Logs and Metadata
• Reference
  • cellmaps_vnn package
• Developer Topics
  • Contributing
  • Development Process
  • Creating a new release
  • Expected configuration for .pypirc file
  • Integration testing
  • Versioning Scheme
• Credits
  • Development Lead
  • Contributors
• History
  • 0.1.0 (2024-02-01)

Indices and tables

• Index

• Module Index

• Search Page