Pre-trained architecture for CNNScoreVariants and non-human data

Answered

Follow

mk

• March 11, 2020 00:39

Thank you for this great tool. I was wondering if the pre-trained architecture would be suitable for non-human data, or would it be better to stick to hard filtering?

0

• Official comment

  

  Genevieve Brandt (she/her)

  • March 30, 2021 17:33
  • Edited

  We would not recommend using the pre-trained CNN (CNNScoreVariants) for non-human samples. The training script is available by running CNNWriteTensors and CNNVariantTrain.

  Comment actions Permalink
• 

  Bhanu Gandham

  • March 13, 2020 17:44

  Hi ,

  The GATK support team is focused on resolving questions about GATK tool-specific errors and abnormal results from the tools. For all other questions, such as this one, we are building a backlog to work through when we have the capacity.

  Please continue to post your questions because we will be mining them for improvements to documentation, resources, and tools.

  We cannot guarantee a reply, however, we ask other community members to help out if you know the answer.

  For context, check out our support policy.

   

  0

  Comment actions Permalink

Please sign in to leave a comment.