postprocess_variants step is erroring out in quickstart example

[sushruta]

Have you checked the FAQ? https://github.com/google/deepvariant/blob/r1.6.1/docs/FAQ.md:
Yes

Describe the issue:
(A clear and concise description of what the issue is.)
run_deepvariant is erroring out in the postprocess_variants step.

Setup

• Operating system: Running inside docker image - google/deepvariant:1.6.0-gpu
• DeepVariant version: 1.6.0
• Installation method (Docker, built from source, etc.): Docker image - google/deepvariant:1.6.0-gpu
• Type of data: (sequencing instrument, reference genome, anything special that is unlike the case studies?)

Steps to reproduce:

• Command: Running the quickstart cmd --

/opt/deepvariant/bin/run_deepvariant --model_type=WGS --ref=/opt/deepvariant/quickstart-testdata/ucsc.hg19.chr20.unittest.fasta --reads=/opt/deepvariant/quickstart-testdata/NA12878_S1.chr20.10_10p1mb.bam --regions "chr20:10,000,000-10,010,000" --output_vcf=/opt/deepvariant/quickstart-output/output.vcf.gz --output_gvcf=/opt/deepvariant/quickstart-output/output.g.vcf.gz --intermediate_results_dir /opt/deepvariant/quickstart-output/intermediate_results_dir --num_shards=1 --verbosity=2

• Error trace: (if applicable) In the postprocess_variants step

***** Running the command:*****
time /opt/deepvariant/bin/postprocess_variants --ref "/opt/deepvariant/quickstart-testdata/ucsc.hg19.chr20.unittest.fasta" --infile "/opt/deepvariant/quickstart-output/intermediate_results_dir/call_variants_output.tfrecord.gz" --outfile "/opt/deepvariant/quickstart-output/output.vcf.gz" --cpus "1" --gvcf_outfile "/opt/deepvariant/quickstart-output/output.g.vcf.gz" --nonvariant_site_tfrecord_path "/opt/deepvariant/quickstart-output/intermediate_results_dir/gvcf.tfrecord@1.gz"

2024-10-31 20:36:34.101345: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libcublas.so.12: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64
2024-10-31 20:36:34.101375: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
2024-10-31 20:36:35.010025: W tensorflow/core/common_runtime/gpu/gpu_device.cc:2027] TensorFlow was not built with CUDA kernel binaries compatible with compute capability 9.0. CUDA kernels will be jit-compiled from PTX, which could take 30 minutes or longer.
I1031 20:36:35.011695 132485076334400 postprocess_variants.py:1211] Using sample name from call_variants output. Sample name: NA12878
I1031 20:36:35.013445 132485076334400 postprocess_variants.py:1313] CVO sorting took 1.1885166168212891e-05 minutes
I1031 20:36:35.013573 132485076334400 postprocess_variants.py:1316] Transforming call_variants_output to variants.
I1031 20:36:35.014770 132485076334400 postprocess_variants.py:1211] Using sample name from call_variants output. Sample name: NA12878
Traceback (most recent call last):
  File "/tmp/Bazel.runfiles_in6znu90/runfiles/com_google_deepvariant/deepvariant/postprocess_variants.py", line 1419, in <module>
    app.run(main)
  File "/tmp/Bazel.runfiles_in6znu90/runfiles/absl_py/absl/app.py", line 312, in run
    _run_main(main, args)
  File "/tmp/Bazel.runfiles_in6znu90/runfiles/absl_py/absl/app.py", line 258, in _run_main
    sys.exit(main(argv))
  File "/tmp/Bazel.runfiles_in6znu90/runfiles/com_google_deepvariant/deepvariant/postprocess_variants.py", line 1385, in main
    tmp_variant_file = dump_variants_to_temp_file(variant_generator)
  File "/tmp/Bazel.runfiles_in6znu90/runfiles/com_google_deepvariant/deepvariant/postprocess_variants.py", line 1067, in dump_variants_to_temp_file
    tfrecord.write_tfrecords(variant_protos, temp.name)
  File "/tmp/Bazel.runfiles_in6znu90/runfiles/com_google_deepvariant/third_party/nucleus/io/tfrecord.py", line 190, in write_tfrecords
    for proto in protos:
  File "/tmp/Bazel.runfiles_in6znu90/runfiles/com_google_deepvariant/deepvariant/haplotypes.py", line 91, in maybe_resolve_conflicting_variants
    for overlapping_candidates in _group_overlapping_variants(sorted_variants):
  File "/tmp/Bazel.runfiles_in6znu90/runfiles/com_google_deepvariant/deepvariant/haplotypes.py", line 111, in _group_overlapping_variants
    for variant in sorted_variants:
  File "/tmp/Bazel.runfiles_in6znu90/runfiles/com_google_deepvariant/deepvariant/postprocess_variants.py", line 1062, in _transform_call_variants_output_to_variants
    yield _transform_call_variant_group_to_output_variant(**cvo_group_kwargs)
  File "/tmp/Bazel.runfiles_in6znu90/runfiles/com_google_deepvariant/deepvariant/postprocess_variants.py", line 1036, in _transform_call_variant_group_to_output_variant
    return add_call_to_variant(
  File "/tmp/Bazel.runfiles_in6znu90/runfiles/com_google_deepvariant/deepvariant/postprocess_variants.py", line 434, in add_call_to_variant
    gq, variant.quality = compute_quals(predictions, index)
  File "/tmp/Bazel.runfiles_in6znu90/runfiles/com_google_deepvariant/deepvariant/postprocess_variants.py", line 469, in compute_quals
    genomics_math.ptrue_to_bounded_phred(predictions[prediction_index])
  File "/tmp/Bazel.runfiles_in6znu90/runfiles/com_google_deepvariant/third_party/nucleus/util/genomics_math.py", line 143, in ptrue_to_bounded_phred
    raise ValueError('ptrue must be between zero and one: {}'.format(ptrue))
ValueError: ptrue must be between zero and one: nan

Does the quick start test work on your system?
Please test with https://github.com/google/deepvariant/blob/r1.6/docs/deepvariant-quick-start.md.
Is there any way to reproduce the issue by using the quick start?

Any additional context:

I'm running this code on an H100 GPU running nvidia driver - 535.183.06 and CUDA version is 12.2

[kishwarshafin]

@sushruta can you please post the full command you are running?

[sushruta]

Here's the full command --

/opt/deepvariant/bin/run_deepvariant --model_type=WGS \
  --ref=/opt/deepvariant/quickstart-testdata/ucsc.hg19.chr20.unittest.fasta \
  --reads=/opt/deepvariant/quickstart-testdata/NA12878_S1.chr20.10_10p1mb.bam \
  --regions "chr20:10,000,000-10,010,000" \
  --output_vcf=/opt/deepvariant/quickstart-output/output.vcf.gz \
  --output_gvcf=/opt/deepvariant/quickstart-output/output.g.vcf.gz \
  --intermediate_results_dir /opt/deepvariant/quickstart-output/intermediate_results_dir \
  --num_shards=1 --verbosity=2

[pichuan]

Hi @sushruta ,
I wonder if this could related to #849

If so, the best solution might be to wait for our next release, which should hopefully be out not too long from now.