From aff131aac3bd0cb63ee8314e32bcbf5590987fb8 Mon Sep 17 00:00:00 2001 From: gunjanbaid Date: Thu, 11 Apr 2019 16:01:14 -0700 Subject: [PATCH] Update case studies and quickstart doc. PiperOrigin-RevId: 243160494 --- docs/deepvariant-case-study.md | 16 ++++++++-------- docs/deepvariant-exome-case-study.md | 4 ++-- docs/deepvariant-quick-start.md | 8 ++++---- 3 files changed, 14 insertions(+), 14 deletions(-) diff --git a/docs/deepvariant-case-study.md b/docs/deepvariant-case-study.md index 78b8e3a7..675e3541 100644 --- a/docs/deepvariant-case-study.md +++ b/docs/deepvariant-case-study.md @@ -86,17 +86,17 @@ machine, and the `postprocess_variants` step is single-process, single-thread. With the example in [run_wgs_case_study_docker.sh] on a [CPU machine], -Step | Hardware | Wall time ----------------------------------- | ------------------- | --------- -`make_examples` | 64 CPUs | ~ 1h 10m -`call_variants` | 64 CPUs | ~ 2h 45m -`postprocess_variants` (with gVCF) | 1 CPU | ~ 30m +Step | Hardware | Wall time +---------------------------------- | -------- | --------- +`make_examples` | 64 CPUs | ~ 1h 10m +`call_variants` | 64 CPUs | ~ 2h 45m +`postprocess_variants` (with gVCF) | 1 CPU | ~ 35m With the example in [run_wgs_case_study_docker_gpu.sh] on a [GPU machine], Step | Hardware | Wall time ---------------------------------- | ------------------- | --------- -`make_examples` | 16 CPUs | ~ 3h 45m +`make_examples` | 16 CPUs | ~ 3h 25m `call_variants` | 1 P100 GPU, 16 CPUs | ~ 50m `postprocess_variants` (with gVCF) | 1 CPU | ~ 30m @@ -154,8 +154,8 @@ results. Type | # FN | # FP | Recall | Precision | F1\_Score ----- | ---- | ---- | -------- | --------- | --------- -INDEL | 1428 | 924 | 0.996927 | 0.998089 | 0.997508 -SNP | 1328 | 749 | 0.999564 | 0.999754 | 0.999659 +INDEL | 1488 | 944 | 0.996798 | 0.998048 | 0.997423 +SNP | 1576 | 725 | 0.999483 | 0.999762 | 0.999623 [install_nvidia_docker.sh]: https://github.com/google/deepvariant/blob/r0.8/scripts/install_nvidia_docker.sh [run_wgs_case_study_docker.sh]: https://github.com/google/deepvariant/blob/r0.8/scripts/run_wgs_case_study_docker.sh diff --git a/docs/deepvariant-exome-case-study.md b/docs/deepvariant-exome-case-study.md index 8594c918..9a1001f8 100644 --- a/docs/deepvariant-exome-case-study.md +++ b/docs/deepvariant-exome-case-study.md @@ -110,8 +110,8 @@ We evaluate against the capture region: Type | # FN | # FP | Recall | Precision | F1\_Score ----- | ---- | ---- | -------- | --------- | --------- -INDEL | 106 | 49 | 0.959231 | 0.980897 | 0.969943 -SNP | 48 | 16 | 0.998577 | 0.999525 | 0.999051 +INDEL | 117 | 55 | 0.955000 | 0.978507 | 0.966611 +SNP | 37 | 23 | 0.998903 | 0.999318 | 0.999110 [specific machine type]: deepvariant-details.md#commands-for-requesting-machines-used-in-case-studies [install_nvidia_docker.sh]: https://github.com/google/deepvariant/blob/r0.8/scripts/install_nvidia_docker.sh diff --git a/docs/deepvariant-quick-start.md b/docs/deepvariant-quick-start.md index 51d748ab..83e650e1 100644 --- a/docs/deepvariant-quick-start.md +++ b/docs/deepvariant-quick-start.md @@ -171,10 +171,10 @@ You should see output similar to the following. ``` Benchmarking Summary: Type Filter TRUTH.TOTAL TRUTH.TP TRUTH.FN QUERY.TOTAL QUERY.FP QUERY.UNK FP.gt METRIC.Recall METRIC.Precision METRIC.Frac_NA METRIC.F1_Score TRUTH.TOTAL.TiTv_ratio QUERY.TOTAL.TiTv_ratio TRUTH.TOTAL.het_hom_ratio QUERY.TOTAL.het_hom_ratio - INDEL ALL 4 4 0 13 0 9 0 1 1 0.692308 1 NaN NaN 0.333333 1.000000 - INDEL PASS 4 4 0 13 0 9 0 1 1 0.692308 1 NaN NaN 0.333333 1.000000 - SNP ALL 44 44 0 60 0 16 0 1 1 0.266667 1 1.2 1.307692 0.333333 0.363636 - SNP PASS 44 44 0 60 0 16 0 1 1 0.266667 1 1.2 1.307692 0.333333 0.363636 + INDEL ALL 4 4 0 13 0 9 0 1.000000 1 0.692308 1.000000 NaN NaN 0.333333 1.000000 + INDEL PASS 4 4 0 13 0 9 0 1.000000 1 0.692308 1.000000 NaN NaN 0.333333 1.000000 + SNP ALL 44 43 1 59 0 16 0 0.977273 1 0.271186 0.988506 1.2 1.36 0.333333 0.340909 + SNP PASS 44 43 1 59 0 16 0 0.977273 1 0.271186 0.988506 1.2 1.36 0.333333 0.340909 ``` [BAM]: http://genome.sph.umich.edu/wiki/BAM