Hi, there
When I tried to run pbrun deepvariant with the official sample dataset, I got the following error.
$ pbrun deepvariant --ref parabricks_sample/Ref/Homo_sapiens_assembly38.fasta \
> --in-bam output.bam \
> --out-variants output.vcf \
> --x3
Please visit https://docs.nvidia.com/clara/#parabricks for detailed documentation
docker run --gpus all -u=1000:1000 --rm -w=/uploads/workspace --net=host -v /opt/parabricks:/INSTALL/ -v /uploads/workspace/DUUWMSRM:/uploads/workspace/DUUWMSRM -v /uploads/workspace:/uploads/workspace -v /uploads/workspace/parabricks_sample/Ref:/uploads/workspace/parabricks_sample/Ref parabricks/release:v3.5.0 deepvariant --ref parabricks_sample/Ref/Homo_sapiens_assembly38.fasta --in-bam output.bam --out-variants output.vcf --x3 --tmp-dir /uploads/workspace/DUUWMSRM
PARABRICKS Starting...
CUDA Device Query (Runtime API) version (CUDART static linking)
Detected 1 CUDA Capable device(s), considering 1 device(s)
CUDA Driver Version / Runtime Version 11.3 / 10.1
Device 0: "NVIDIA Tesla P100-PCIE-16GB"
CUDA Capability Major/Minor version number: 6.0
Total amount of global memory: 16281 MBytes (17071734784 bytes)
(56) Multiprocessors, ( 64) CUDA Cores/MP: 3584 CUDA Cores
GPU Max Clock rate: 1329 MHz (1.33 GHz)
Memory Clock rate: 715 Mhz
Memory Bus Width: 4096-bit
L2 Cache Size: 4194304 bytes
Maximum Texture Dimension Size (x,y,z) 1D=(131072), 2D=(131072, 65536), 3D=(16384, 16384, 16384)
Maximum Layered 1D Texture Size, (num) layers 1D=(32768), 2048 layers
Maximum Layered 2D Texture Size, (num) layers 2D=(32768, 32768), 2048 layers
Total amount of constant memory: 65536 bytes
Total amount of shared memory per block: 49152 bytes
Total number of registers available per block: 65536
Warp size: 32
Maximum number of threads per multiprocessor: 2048
Maximum number of threads per block: 1024
Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
Max dimension size of a grid size (x,y,z): (2147483647, 65535, 65535)
Maximum memory pitch: 2147483647 bytes
Texture alignment: 512 bytes
Concurrent copy and kernel execution: Yes with 2 copy engine(s)
Run time limit on kernels: No
Integrated GPU sharing Host Memory: No
Support host page-locked memory mapping: Yes
Alignment requirement for Surfaces: Yes
Device has ECC support: Enabled
Device supports Unified Addressing (UVA): Yes
Device supports Compute Preemption: Yes
Supports Cooperative Kernel Launch: Yes
Supports MultiDevice Co-op Kernel Launch: Yes
Device PCI Domain ID / Bus ID / location ID: 1 / 0 / 0
Compute Mode:
< Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >
deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 11.3, CUDA Runtime Version = 10.1, NumDevs = 1
Using model for CUDA Capability Major/Minor version number: 60
Please visit https://docs.nvidia.com/clara/#parabricks for detailed documentation
/usr/local/cuda/.pb/binaries//bin/deepvariant /uploads/workspace/parabricks_sample/Ref/Homo_sapiens_assembly38.fasta /uploads/workspace/output.bam 1 -o /uploads/workspace/output.vcf --model /usr/local/cuda/.pb/binaries//model/60/shortread/deepvariant.eng -n 4 --vsc_min_count_snps 2 --vsc_min_count_indels 2 --vsc_min_fraction_snps 0.12 --min_mapping_quality 5 --min_base_quality 10 --alt_aligned_pileup none --variant_caller VERY_SENSITIVE_CALLER
------------------------------------------------------------------------------
|| Parabricks accelerated Genomics Pipeline ||
|| Version v3.5.0 ||
|| deepvariant ||
|| Contact: Parabricks-Support@nvidia.com ||
------------------------------------------------------------------------------
Invalid modelFileName /usr/local/cuda/.pb/binaries//model/60/shortread/deepvariant.eng. Exiting...
Please contact Parabricks-Support@nvidia.com for any questions
There is a forum for Q&A as well at https://forums.developer.nvidia.com/c/healthcare/Parabricks/290
Exiting...
Could not run deepvariant
Exiting pbrun ...
where the error is:
Invalid modelFileName /usr/local/cuda/.pb/binaries//model/60/shortread/deepvariant.eng. Exiting…
But it is fine to run pbrun germline (with HaplotypeCaller) or the single standalone tool pbrun haplotypecaller.
$ pbrun haplotypecaller --ref parabricks_sample/Ref/Homo_sapiens_assembly38.fasta \
> --in-bam output.bam \
> --in-recal-file report.txt \
> --out-variants output.vcf
Please visit https://docs.nvidia.com/clara/#parabricks for detailed documentation
------------------------------------------------------------------------------
|| Parabricks accelerated Genomics Pipeline ||
|| Version v3.5.0 ||
|| GPU-GATK4 HaplotypeCaller ||
|| Contact: Parabricks-Support@nvidia.com ||
------------------------------------------------------------------------------
ProgressMeter - Current-Locus Elapsed-Minutes Regions-Processed Regions/Minute
0 /uploads/workspace/output.bam /uploads/workspace/output.vcf
[03:58:29] chr1:23827075 0.2 99611 597666
[03:58:39] chr1:58579359 0.3 248439 745317
[03:58:49] chr1:103487401 0.5 437443 874886
[03:58:59] chr1:156993568 0.7 573674 860511
[03:59:09] chr1:198172788 0.8 747203 896643
[03:59:19] chr1:235333645 1.0 903616 903616
...
...
[04:09:29] chr22:46147131 11.2 11232255 1005873
[04:09:39] chrX:85146967 11.3 11560850 1020075
[04:09:49] chrY:13803548 11.5 11865157 1031752
Total time taken: 701.162
------------------------------------------------------------------------------
|| Program: GPU-GATK4 HaplotypeCaller ||
|| Version: v3.5.0 ||
|| Start Time: Fri Jun 25 03:57:00 2021 ||
|| End Time: Fri Jun 25 04:10:00 2021 ||
|| Total Time: 13 minutes 0 seconds ||
------------------------------------------------------------------------------
Please visit https://docs.nvidia.com/clara/#parabricks for detailed documentation
nvidia-smi info
How can I resolve the deepvariant error?