Class CNNVariantTrain

java.lang.Object
org.broadinstitute.hellbender.cmdline.CommandLineProgram
org.broadinstitute.hellbender.tools.walkers.vqsr.CNNVariantTrain
All Implemented Interfaces:
org.broadinstitute.barclay.argparser.CommandLinePluginProvider

@DocumentedFeature @ExperimentalFeature public class CNNVariantTrain extends CommandLineProgram
Train a Convolutional Neural Network (CNN) for filtering variants. This tool expects requires training data generated by CNNVariantWriteTensors.

Inputs

  • data-dir The training data created by CNNVariantWriteTensors.
  • The --tensor-type argument determines what types of tensors the model will expect. Set it to "reference" for 1D tensors or "read_tensor" for 2D tensors.

Outputs

  • output-dir The model weights file and semantic configuration json are saved here. This default to the current working directory.
  • model-name The name for your model.

Usage example

Train a 1D CNN on Reference Tensors

 gatk CNNVariantTrain \
   -tensor-type reference \
   -input-tensor-dir my_tensor_folder \
   -model-name my_1d_model
 

Train a 2D CNN on Read Tensors

 gatk CNNVariantTrain \
   -input-tensor-dir my_tensor_folder \
   -tensor-type read-tensor \
   -model-name my_2d_model
 
  • Constructor Details

    • CNNVariantTrain

      public CNNVariantTrain()
  • Method Details

    • onStartup

      protected void onStartup()
      Description copied from class: CommandLineProgram
      Perform initialization/setup after command-line argument parsing but before doWork() is invoked. Default implementation does nothing. Subclasses can override to perform initialization.
      Overrides:
      onStartup in class CommandLineProgram
    • doWork

      protected Object doWork()
      Description copied from class: CommandLineProgram
      Do the work after command line has been parsed. RuntimeException may be thrown by this method, and are reported appropriately.
      Specified by:
      doWork in class CommandLineProgram
      Returns:
      the return value or null is there is none.