How to get list of variants after make_examples step?

[sophienguyen01]

Hi,

Is it possible to get a list of variants in files ***.tfrecord-?????-of-000??.gz ( the output of make_examples step)?

One thing I can think of is to call show_examples command which will generate images for each variant from the file, but is there other faster way to get the list of variants?

Thank you

[pichuan]

Hi @sophienguyen01 You can try https://github.com/google/deepvariant/blob/r1.6.1/deepvariant/labeler/labeled_examples_to_vcf.py This is more experimental and not officially documented yet. But you can find in our Docker: https://github.com/google/deepvariant/blob/r1.6.1/Dockerfile#L152

For now, please read the code and use the flags there. As mentioned, this is experimental and we have not officially supported it yet, so I can't say it'll work for the specific use case that you want. But you can at least look at the code and see whether you can adapt it.

Another more typical approach is to run through the rest of the steps (call_variants, postprocess_variants) and get the list of variants that way.