Skip to content

GenNet 2.0

Latest
Compare
Choose a tag to compare
@ArnovanHilten ArnovanHilten released this 27 Feb 13:08
· 14 commits to master since this release

What's Changed

  • GenNet interpret: adds the interpretation module with six interpretation methods
    • get_weight_scores: uses the weights to calculate the importance of each feature and node
    • DeepExplain: uses the gradient (see DeepExplain) to calculate the importance
    • RLIPP: uses logistic regression with signals to and from the node to calculate a measure of non-linearity for all nodes
    • NID: Finds interacting features based on the features with the strongest weights
    • DFIM: perturbs each input (or N inputs in the order of importance), and tracks which other features change importance to find interacting features
    • PathExplain: Uses the Expected Hessian to find interacting features
  • Bugfixes for converting plink2 files
  • Script for converting toplogy to npz matrices
  • Add one-hot encoding support
  • Adds multiple filters. LocallyDirected1D now supports multiple filters akin to channels or feature maps in CNNs