warnings in the output of DeepVariant command

[AlirezaShokrollahi]

Dear DeepVariant team,

I run DeepVariant command based on DeepVariant quick start. I saw some warnings and I am not sure about these warnings.

Could you guild me about this warnings?

Best regards,
Alireza.

(base) bear@bear:~/alireza/deepvariant$ sudo docker run
-v "${INPUT_DIR}":"/input"
-v "${OUTPUT_DIR}":"/output"
google/deepvariant:"${BIN_VERSION}"
/opt/deepvariant/bin/run_deepvariant
--model_type=WGS
--vcf_stats_report=true
--ref=/input/ucsc.hg19.chr20.unittest.fasta
--reads=/input/NA12878_S1.chr20.10_10p1mb.bam
--regions "chr20:10,000,000-10,010,000"
--output_vcf=/output/output.vcf.gz
--output_gvcf=/output/output.g.vcf.gz
--intermediate_results_dir /output/intermediate_results_dir
--num_shards=1
[sudo] password for bear:
2024-12-28 16:10:45.473731: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 AVX512F AVX512_VNNI AVX512_BF16 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2024-12-28 16:10:45.540276: I tensorflow/core/util/port.cc:104] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable TF_ENABLE_ONEDNN_OPTS=0.
2024-12-28 16:10:45.542603: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
2024-12-28 16:10:45.542613: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
2024-12-28 16:10:46.010168: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory
2024-12-28 16:10:46.010228: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory
2024-12-28 16:10:46.010233: 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.
2024-12-28 16:10:46.699474: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory
2024-12-28 16:10:46.699493: W tensorflow/compiler/xla/stream_executor/cuda/cuda_driver.cc:265] failed call to cuInit: UNKNOWN ERROR (303)
2024-12-28 16:10:46.699507: I tensorflow/compiler/xla/stream_executor/cuda/cuda_diagnostics.cc:163] no NVIDIA GPU device is present: /dev/nvidia0 does not exist
I1228 16:10:46.699570 127594862972928 run_deepvariant.py:643] Creating a directory for intermediate results in /output/intermediate_results_dir

***** Intermediate results will be written to /output/intermediate_results_dir in docker. ****

***** Running the command:*****
time seq 0 0 | parallel -q --halt 2 --line-buffer /opt/deepvariant/bin/make_examples --mode calling --ref "/input/ucsc.hg19.chr20.unittest.fasta" --reads "/input/NA12878_S1.chr20.10_10p1mb.bam" --examples "/output/intermediate_results_dir/[email protected]" --checkpoint "/opt/models/wgs" --call_small_model_examples --gvcf "/output/intermediate_results_dir/[email protected]" --regions "chr20:10,000,000-10,010,000" --small_model_indel_gq_threshold "30" --small_model_snp_gq_threshold "25" --small_model_vaf_context_window_size "51" --trained_small_model_path "/opt/smallmodels/wgs" --task {}

I1228 16:10:46.699922 127594862972928 run_deepvariant.py:847] env = {'HOSTNAME': '11a3b8cb1891', 'PYTHON_VERSION': '3.10', 'DV_GPU_BUILD': '0', 'PWD': '/opt/deepvariant', 'TF_ENABLE_ONEDNN_OPTS': '1', 'HOME': '/root', 'SHLVL': '1', 'PATH': '/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/conda/bin:/opt/conda/envs/bio/bin:/opt/deepvariant/bin', 'VERSION': '1.8.0', '_': '/usr/bin/python3', 'LC_CTYPE': 'C.UTF-8', 'TPU_ML_PLATFORM': 'Tensorflow', 'TF2_BEHAVIOR': '1', 'TF_CPP_MIN_LOG_LEVEL': '1'}
2024-12-28 16:10:47.252359: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
2024-12-28 16:10:47.548985: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory
2024-12-28 16:10:47.549017: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory
2024-12-28 16:10:47.549020: 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.
/usr/local/lib/python3.10/dist-packages/tensorflow_addons/utils/tfa_eol_msg.py:23: UserWarning:

TensorFlow Addons (TFA) has ended development and introduction of new features.
TFA has entered a minimal maintenance and release mode until a planned end of life in May 2024.
Please modify downstream libraries to take dependencies from other repositories in our TensorFlow community (e.g. Keras, Keras-CV, and Keras-NLP).

For more information see: tensorflow/addons#2807

warnings.warn(
2024-12-28 16:10:48.250534: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory
2024-12-28 16:10:48.250546: W tensorflow/compiler/xla/stream_executor/cuda/cuda_driver.cc:265] failed call to cuInit: UNKNOWN ERROR (303)
I1228 16:10:48.250900 136107432939520 genomics_reader.py:223] Reading /input/NA12878_S1.chr20.10_10p1mb.bam with NativeSamReader
I1228 16:10:48.251638 136107432939520 dv_utils.py:325] From /opt/models/wgs/example_info.json: Shape of input examples: [100, 221, 7], Channels of input examples: [1, 2, 3, 4, 5, 6, 19].
I1228 16:10:48.254233 136107432939520 make_examples_core.py:322] Preparing inputs
I1228 16:10:48.254390 136107432939520 genomics_reader.py:223] Reading /input/NA12878_S1.chr20.10_10p1mb.bam with NativeSamReader
I1228 16:10:48.254612 136107432939520 make_examples_core.py:322] Common contigs are ['chr20']
I1228 16:10:48.493595 136107432939520 make_examples_core.py:322] Starting from v0.9.0, --use_ref_for_cram is default to true. If you are using CRAM input, note that we will decode CRAM using the reference you passed in with --ref
I1228 16:10:48.495226 136107432939520 genomics_reader.py:223] Reading /input/NA12878_S1.chr20.10_10p1mb.bam with NativeSamReader
I1228 16:10:48.560587 136107432939520 genomics_reader.py:223] Reading /input/NA12878_S1.chr20.10_10p1mb.bam with NativeSamReader
I1228 16:10:48.560690 136107432939520 make_examples_core.py:322] Writing gvcf records to /output/intermediate_results_dir/gvcf.tfrecord-00000-of-00001.gz
I1228 16:10:48.561406 136107432939520 make_examples_core.py:322] Writing examples to /output/intermediate_results_dir/make_examples.tfrecord-00000-of-00001.gz
I1228 16:10:48.561437 136107432939520 make_examples_core.py:322] Overhead for preparing inputs: 0 seconds
I1228 16:10:48.656072 136107432939520 make_examples_core.py:322] 6 candidates (1 examples) [0.09s elapsed]
I1228 16:10:49.193665 136107432939520 make_examples_core.py:322] Writing example info to /output/intermediate_results_dir/make_examples.tfrecord-00000-of-00001.gz.example_info.json
I1228 16:10:49.193746 136107432939520 make_examples_core.py:3175] example_shape = [100, 221, 7]
I1228 16:10:49.193766 136107432939520 make_examples_core.py:3176] example_channels = [1, 2, 3, 4, 5, 6, 19]
I1228 16:10:49.193965 136107432939520 make_examples_core.py:322] Found 78 candidate variants
I1228 16:10:49.193990 136107432939520 make_examples_core.py:322] Created 22 examples
I1228 16:10:49.194005 136107432939520 make_examples_core.py:322] Created 0 small model examples
I1228 16:10:49.194018 136107432939520 make_examples_core.py:322] Small Model called 62 candidates

real 0m2.822s
user 0m4.502s
sys 0m2.088s

***** Running the command:*****
time /opt/deepvariant/bin/call_variants --outfile "/output/intermediate_results_dir/call_variants_output.tfrecord.gz" --examples "/output/intermediate_results_dir/[email protected]" --checkpoint "/opt/models/wgs"

2024-12-28 16:10:49.816191: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
2024-12-28 16:10:50.194286: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory
2024-12-28 16:10:50.194322: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory
2024-12-28 16:10:50.194325: 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.
/usr/local/lib/python3.10/dist-packages/tensorflow_addons/utils/tfa_eol_msg.py:23: UserWarning:

TensorFlow Addons (TFA) has ended development and introduction of new features.
TFA has entered a minimal maintenance and release mode until a planned end of life in May 2024.
Please modify downstream libraries to take dependencies from other repositories in our TensorFlow community (e.g. Keras, Keras-CV, and Keras-NLP).

For more information see: tensorflow/addons#2807

warnings.warn(
2024-12-28 16:10:51.056151: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory
2024-12-28 16:10:51.056166: W tensorflow/compiler/xla/stream_executor/cuda/cuda_driver.cc:265] failed call to cuInit: UNKNOWN ERROR (303)
I1228 16:10:51.056234 139675775700992 call_variants.py:918] call_variants: env = {'HOSTNAME': '11a3b8cb1891', 'PYTHON_VERSION': '3.10', 'TF_CPP_MIN_LOG_LEVEL': '1', 'DV_GPU_BUILD': '0', 'PWD': '/opt/deepvariant', 'TF_ENABLE_ONEDNN_OPTS': '1', '_': '/usr/bin/python3', 'HOME': '/root', 'TPU_ML_PLATFORM': 'Tensorflow', 'SHLVL': '3', 'LC_CTYPE': 'C.UTF-8', 'PATH': '/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/conda/bin:/opt/conda/envs/bio/bin:/opt/deepvariant/bin', 'TF2_BEHAVIOR': '1', 'VERSION': '1.8.0', 'PYTHONPATH': '/tmp/Bazel.runfiles_lv2eh_r1/runfiles:/tmp/Bazel.runfiles_lv2eh_r1/runfiles/com_google_protobuf/python:/tmp/Bazel.runfiles_lv2eh_r1/runfiles/absl_py:/tmp/Bazel.runfiles_lv2eh_r1/runfiles/bazel_tools:/tmp/Bazel.runfiles_lv2eh_r1/runfiles/com_google_deepvariant:/tmp/Bazel.runfiles_lv2eh_r1/runfiles/com_google_protobuf:/tmp/Bazel.runfiles_lv2eh_r1/runfiles/six_archive', 'RUNFILES_DIR': '/tmp/Bazel.runfiles_lv2eh_r1/runfiles'}
I1228 16:10:51.064217 139675775700992 call_variants.py:785] Total 1 writing processes started.
I1228 16:10:51.065089 139675775700992 call_variants.py:796] Use saved model: True
I1228 16:10:51.065470 139675775700992 dv_utils.py:325] From /output/intermediate_results_dir/make_examples.tfrecord-00000-of-00001.gz.example_info.json: Shape of input examples: [100, 221, 7], Channels of input examples: [1, 2, 3, 4, 5, 6, 19].
I1228 16:10:53.779392 139675775700992 dv_utils.py:325] From /opt/models/wgs/example_info.json: Shape of input examples: [100, 221, 7], Channels of input examples: [1, 2, 3, 4, 5, 6, 19].
I1228 16:10:53.779490 139675775700992 call_variants.py:814] example_shape: [100, 221, 7]
I1228 16:10:54.350414 139675775700992 call_variants.py:891] Predicted 22 examples in 1 batches [1.253 sec per 100].
I1228 16:10:54.396512 139675775700992 call_variants.py:967] Complete: call_variants.

real 0m5.543s
user 0m7.714s
sys 0m2.230s

***** Running the command:*****
time /opt/deepvariant/bin/postprocess_variants --ref "/input/ucsc.hg19.chr20.unittest.fasta" --infile "/output/intermediate_results_dir/call_variants_output.tfrecord.gz" --outfile "/output/output.vcf.gz" --cpus "1" --small_model_cvo_records "/output/intermediate_results_dir/[email protected]" --gvcf_outfile "/output/output.g.vcf.gz" --nonvariant_site_tfrecord_path "/output/intermediate_results_dir/[email protected]" --regions "chr20:10,000,000-10,010,000"

2024-12-28 16:10:55.368256: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
2024-12-28 16:10:55.743046: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory
2024-12-28 16:10:55.743091: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory
2024-12-28 16:10:55.743095: 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.
2024-12-28 16:10:56.406978: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory
2024-12-28 16:10:56.406993: W tensorflow/compiler/xla/stream_executor/cuda/cuda_driver.cc:265] failed call to cuInit: UNKNOWN ERROR (303)
I1228 16:10:56.407692 137050720653312 postprocess_variants.py:1445] Using sample name from call_variants output. Sample name: NA12878
I1228 16:10:56.408358 137050720653312 postprocess_variants.py:1318] CVO sorting took 4.8836072285970054e-06 minutes
I1228 16:10:56.408421 137050720653312 postprocess_variants.py:1322] Transforming call_variants_output to variants.
I1228 16:10:56.408440 137050720653312 postprocess_variants.py:1330] Processed 84 variants.
I1228 16:10:56.408485 137050720653312 postprocess_variants.py:1533] Processing variants (and writing to temporary files) took 7.092952728271484e-06 minutes
I1228 16:10:56.665696 137050720653312 postprocess_variants.py:1568] VCF and gVCF creation took 0.004286126295725504 minutes.
I1228 16:10:56.676080 137050720653312 postprocess_variants.py:1723] Indexing VCF and gVCF took 0.00017061233520507813 minutes.

real 0m1.890s
user 0m3.615s
sys 0m1.947s

***** Running the command:*****
time /opt/deepvariant/bin/vcf_stats_report --input_vcf "/output/output.vcf.gz" --outfile_base "/output/output"

2024-12-28 16:10:57.196252: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
2024-12-28 16:10:57.627780: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory
2024-12-28 16:10:57.627816: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory
2024-12-28 16:10:57.627819: 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.
2024-12-28 16:10:58.318505: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory
2024-12-28 16:10:58.318520: W tensorflow/compiler/xla/stream_executor/cuda/cuda_driver.cc:265] failed call to cuInit: UNKNOWN ERROR (303)
I1228 16:10:58.318864 130550458163200 genomics_reader.py:223] Reading /output/output.vcf.gz with NativeVcfReader

real 0m1.784s
user 0m3.572s
sys 0m1.909s

[kishwarshafin]

hi @AlirezaShokrollahi ,

The warnings are from different APIs that DeepVariant uses and can happen depending on what system you are using. Your run seem to have finished successfully, you can safely ignore the warnings.

[AlirezaShokrollahi]

Hi,

Thank you.