google / deepvariant

DeepVariant is an analysis pipeline that uses a deep neural network to call genetic variants from next-generation DNA sequencing data.
BSD 3-Clause "New" or "Revised" License
3.24k stars 729 forks source link

Question about intermediate_results #887

Closed 0809zheng closed 1 month ago

0809zheng commented 2 months ago

Hello,

I have learned that DeepVariant is three steps at runtime. To better understand DeepVariant, I want to know if there is a way to parse the output file of call_variants like the output file of make_examples (Visualizing DeepVariant examples), so that it becomes human readable instead of a binary string like below.

tf.Tensor(b'\nc2\x01T:\x01AZQ\x12\n\n\x02DP\x12\x04\n\x028\x1c\x12\x0e\n\x02AD\x12\x08\n\x028\x15\n\x028\x04\x12\x12\n\x03VAF\x12\x0b\n\t\x11\x92$I\x92$I\xc2?:\x14\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01\xff\xff\xff\xff\xff\xff\xff\xff\xff\x01J\tHG001_10Xh\xf7Nr\x011\x80\x01\xf6N\x12\x03\n\x01\x00\x1a\x18\x00\x00\x00\x00\xb6\xf8\xef?\x00\x00\x00@\x9e\x0fH?]F\xb5\xb9\x86a$?', shape=(), dtype=string)

Sorry for the interruption!

kishwarshafin commented 1 month ago

Hi @0809zheng ,

Currently, there is not solution provided by us to look at call variants output. However, call variants output go to postprocess variants and that converts the calls into a VCF which you can look into.

0809zheng commented 1 month ago

Thank you very much for your comment, I will close this issue.