search

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
3.25k stars 728 forks source link

Very slow performave for make_example #903

Closed Lionward closed 3 weeks ago

Lionward commented 3 weeks ago

I am running deepvariant using singularity:

I already tested it on the provided test files.

singularity run --bind $bam_PATH/:/bam --bind $REFPATH:/ref deepvariant_1.6.1.sif \ /opt/deepvariant/bin/run_deepvariant --model_type=PACBIO --reads=/bam/HG002.SequelII.merged_15kb_20kb.pbmm2.GRCh38.haplotag.10x.bam --ref=/ref/GCA_000001405.15_GRCh38_no_alt_analysis_set.fa \ --output_vcf variants_HG002.vcf.gz --logging_dir calls/deepvariant/GRCh38/NA12886_HG002/ --num_shards 10 &

I was wondering what is the expected time for deepvariant on CCS reads?

kishwarshafin commented 3 weeks ago

Please see https://github.com/google/deepvariant/blob/r1.6.1/docs/metrics.md page for details on expected runtime. The runtimes reported here are on n2-standard-64 GCP instances with 64 vCPUs.

Lionward commented 3 weeks ago

Thanks for the fast reply! That answers my question.