Parabricks
Purpose
Use this skill to discover the right NVIDIA Parabricks pbrun command, assess
runtime readiness, and generate version-aware command guidance for individual
tools and pipelines.
Do not use this skill for whole-workflow inspection, acceleration planning,
or wiring optional GPU branches. For pipeline-level work, use
genomics-workflow-acceleration.
When to Use This Skill
- Which
pbrun tool fits the user's data and goal
- GPU, driver, Docker, container, storage, or installation readiness
- Command shape, flags, and validation for a specific Parabricks tool
- Troubleshooting a single Parabricks command or tool family
Prerequisites
Ask for input data type, sequencing technology, reference build, sample
structure, desired output, target Parabricks version/container tag, and runtime
target before recommending commands.
If the user is unsure which tool applies, read
tool-index.md first, then load the matching
references/pbrun-<tool>.md file.
Limitations
This skill routes and guides Parabricks commands. It does not install
Parabricks, infer missing sample metadata, guarantee output parity, provide
clinical interpretation, or promise exact runtime without benchmark data.
Workflow
- Confirm the Parabricks version or container tag. Verify the current NVIDIA
docs when the user asks for the latest tool list or version-sensitive flags.
- Classify the request:
- Runtime → runtime-environment.md
- Tool discovery → tool-index.md
- Specific command → matching
references/pbrun-<tool>.md
- Collect missing biological and filesystem context before generating commands.
- Generate conservative Docker commands with explicit mounts, workdir, and
placeholders. Validate paths, indexes, and outputs after command generation.
Tool Reference Index
Load only the reference file for the selected tool.
| Tool |
Reference |
Use when |
applybqsr |
pbrun-applybqsr.md |
Apply BQSR table to aligned BAM |
bam2fq |
pbrun-bam2fq.md |
BAM → FASTQ conversion |
bamsort |
pbrun-bamsort.md |
Standalone BAM sort |
bqsr |
pbrun-bqsr.md |
Generate BQSR recalibration table |
fq2bam |
pbrun-fq2bam.md |
Short-read DNA paired FASTQ → BAM/CRAM |
fq2bam_meth |
pbrun-fq2bam_meth.md |
Bisulfite/methylation FASTQ → BAM/CRAM |
giraffe |
pbrun-giraffe.md |
Pangenome graph alignment |
markdup |
pbrun-markdup.md |
Standalone duplicate marking |
minimap2 |
pbrun-minimap2.md |
Long-read FASTQ alignment |
rna_fq2bam |
pbrun-rna_fq2bam.md |
RNA-seq FASTQ(s) → splice-aware BAM (STAR alignment) |
starfusion |
pbrun-starfusion.md |
Fusion detection from chimeric junction input + STAR-Fusion genome library |
germline |
pbrun-germline.md |
GATK-style germline pipeline from FASTQ |
deepvariant_germline |
pbrun-deepvariant_germline.md |
DeepVariant germline pipeline from FASTQ |
haplotypecaller |
pbrun-haplotypecaller.md |
Standalone HaplotypeCaller from BAM/CRAM |
deepvariant |
pbrun-deepvariant.md |
Standalone DeepVariant from BAM/CRAM |
somatic |
pbrun-somatic.md |
Tumor-normal somatic pipeline |
mutectcaller |
pbrun-mutectcaller.md |
Mutect2-compatible somatic calling |
deepsomatic |
pbrun-deepsomatic.md |
DeepSomatic-based somatic calling |
pacbio_germline |
pbrun-pacbio_germline.md |
PacBio long-read germline |
ont_germline |
pbrun-ont_germline.md |
Oxford Nanopore long-read germline |
pangenome_germline |
pbrun-pangenome_germline.md |
Pangenome-aware germline |
pangenome_aware_deepvariant |
pbrun-pangenome_aware_deepvariant.md |
Pangenome-aware DeepVariant |
prepon |
pbrun-prepon.md |
Pangenome-aware preprocessing |
postpon |
pbrun-postpon.md |
Pangenome-aware post-processing |
bammetrics |
pbrun-bammetrics.md |
Whole-genome coverage/depth metrics |
collectmultiplemetrics |
pbrun-collectmultiplemetrics.md |
Multiple Picard/GATK-style alignment metrics |
genotypegvcf |
pbrun-genotypegvcf.md |
Joint-genotype GVCF input(s) into VCF |
indexgvcf |
pbrun-indexgvcf.md |
Index GVCF input |
dbsnp |
pbrun-dbsnp.md |
dbSNP annotation on variant files |
For routing heuristics when multiple tools could apply, see
tool-index.md.
Runtime Readiness
For GPU, driver, Docker, container, storage, or installation questions, read
runtime-environment.md and prefer:
python3 skills/parabricks/scripts/check_parabricks_runtime.py
Add --path <dir> for known input/output/tmp paths. Run container probes only
with user consent.
Command Shape
docker run --rm --gpus all \
--volume /host/input:/workdir \
--volume /host/output:/outputdir \
--workdir /workdir \
nvcr.io/nvidia/clara/clara-parabricks:<version> \
pbrun <selected-tool> \
<tool-specific-options>
Check the version-specific tool reference before finalizing flags.
Troubleshooting
| Error |
Cause |
Solution |
| Multiple plausible tools |
Data type or goal underspecified |
Ask for assay, inputs, caller preference, desired output; use tool-index |
| Exact flag requested |
Options are version-sensitive |
Check the selected tool reference and NVIDIA docs |
| Runtime question |
GPU, Docker, drivers, or storage |
Use runtime-environment reference and diagnostic script |
| Wrong tool family |
Assay or input type unclear |
Confirm DNA/RNA/methylation/long-read/pangenome before routing |
| CUDA or memory failure |
Runtime not ready or GPU memory constrained |
Assess runtime before tuning command flags |
Guardrails
- Treat command availability and options as version-sensitive.
- Do not infer exact flags from command names alone.
- Do not collapse standalone tools and full pipelines when explaining tradeoffs.
- Do not substitute DNA
fq2bam for RNA, or germline for somatic callers.
- Do not invent sample names, read groups, reference builds, known-sites files,
model files, graph resources, container tags, or output paths.
- Do not install, upgrade, or modify packages. Label setup commands as user-run.
- Do not claim CPU execution of Parabricks tools.
- Do not claim biological or VCF parity without a comparison run.
- Prefer official NVIDIA docs for exact command syntax and option defaults.
Key References
1---2name: parabricks3description: Route NVIDIA Parabricks pbrun tools, assess GPU/runtime readiness, and provide version-aware command guidance for FASTQ/BAM processing, RNA-seq, variant calling, BAM QC, and GVCF workflows. Do NOT use for inspecting or accelerating whole pipelines — use genomics-workflow-acceleration.4license: CC-BY-4.0 AND Apache-2.05---67# Parabricks89## Purpose1011Use this skill to discover the right NVIDIA Parabricks `pbrun` command, assess12runtime readiness, and generate version-aware command guidance for individual13tools and pipelines.1415Do **not** use this skill for whole-workflow inspection, acceleration planning,16or wiring optional GPU branches. For pipeline-level work, use17`genomics-workflow-acceleration`.1819## When to Use This Skill2021- Which `pbrun` tool fits the user's data and goal22- GPU, driver, Docker, container, storage, or installation readiness23- Command shape, flags, and validation for a specific Parabricks tool24- Troubleshooting a single Parabricks command or tool family2526## Prerequisites2728Ask for input data type, sequencing technology, reference build, sample29structure, desired output, target Parabricks version/container tag, and runtime30target before recommending commands.3132If the user is unsure which tool applies, read33[tool-index.md](references/tool-index.md) first, then load the matching34`references/pbrun-<tool>.md` file.3536## Limitations3738This skill routes and guides Parabricks commands. It does not install39Parabricks, infer missing sample metadata, guarantee output parity, provide40clinical interpretation, or promise exact runtime without benchmark data.4142## Workflow43441. Confirm the Parabricks version or container tag. Verify the current NVIDIA45 docs when the user asks for the latest tool list or version-sensitive flags.462. Classify the request:47 - **Runtime** → [runtime-environment.md](references/runtime-environment.md)48 - **Tool discovery** → [tool-index.md](references/tool-index.md)49 - **Specific command** → matching `references/pbrun-<tool>.md`503. Collect missing biological and filesystem context before generating commands.514. Generate conservative Docker commands with explicit mounts, workdir, and52 placeholders. Validate paths, indexes, and outputs after command generation.5354## Tool Reference Index5556Load only the reference file for the selected tool.5758| Tool | Reference | Use when |59|------|-----------|----------|60| `applybqsr` | [pbrun-applybqsr.md](references/pbrun-applybqsr.md) | Apply BQSR table to aligned BAM |61| `bam2fq` | [pbrun-bam2fq.md](references/pbrun-bam2fq.md) | BAM → FASTQ conversion |62| `bamsort` | [pbrun-bamsort.md](references/pbrun-bamsort.md) | Standalone BAM sort |63| `bqsr` | [pbrun-bqsr.md](references/pbrun-bqsr.md) | Generate BQSR recalibration table |64| `fq2bam` | [pbrun-fq2bam.md](references/pbrun-fq2bam.md) | Short-read DNA paired FASTQ → BAM/CRAM |65| `fq2bam_meth` | [pbrun-fq2bam_meth.md](references/pbrun-fq2bam_meth.md) | Bisulfite/methylation FASTQ → BAM/CRAM |66| `giraffe` | [pbrun-giraffe.md](references/pbrun-giraffe.md) | Pangenome graph alignment |67| `markdup` | [pbrun-markdup.md](references/pbrun-markdup.md) | Standalone duplicate marking |68| `minimap2` | [pbrun-minimap2.md](references/pbrun-minimap2.md) | Long-read FASTQ alignment |69| `rna_fq2bam` | [pbrun-rna_fq2bam.md](references/pbrun-rna_fq2bam.md) | RNA-seq FASTQ(s) → splice-aware BAM (STAR alignment) |70| `starfusion` | [pbrun-starfusion.md](references/pbrun-starfusion.md) | Fusion detection from chimeric junction input + STAR-Fusion genome library |71| `germline` | [pbrun-germline.md](references/pbrun-germline.md) | GATK-style germline pipeline from FASTQ |72| `deepvariant_germline` | [pbrun-deepvariant_germline.md](references/pbrun-deepvariant_germline.md) | DeepVariant germline pipeline from FASTQ |73| `haplotypecaller` | [pbrun-haplotypecaller.md](references/pbrun-haplotypecaller.md) | Standalone HaplotypeCaller from BAM/CRAM |74| `deepvariant` | [pbrun-deepvariant.md](references/pbrun-deepvariant.md) | Standalone DeepVariant from BAM/CRAM |75| `somatic` | [pbrun-somatic.md](references/pbrun-somatic.md) | Tumor-normal somatic pipeline |76| `mutectcaller` | [pbrun-mutectcaller.md](references/pbrun-mutectcaller.md) | Mutect2-compatible somatic calling |77| `deepsomatic` | [pbrun-deepsomatic.md](references/pbrun-deepsomatic.md) | DeepSomatic-based somatic calling |78| `pacbio_germline` | [pbrun-pacbio_germline.md](references/pbrun-pacbio_germline.md) | PacBio long-read germline |79| `ont_germline` | [pbrun-ont_germline.md](references/pbrun-ont_germline.md) | Oxford Nanopore long-read germline |80| `pangenome_germline` | [pbrun-pangenome_germline.md](references/pbrun-pangenome_germline.md) | Pangenome-aware germline |81| `pangenome_aware_deepvariant` | [pbrun-pangenome_aware_deepvariant.md](references/pbrun-pangenome_aware_deepvariant.md) | Pangenome-aware DeepVariant |82| `prepon` | [pbrun-prepon.md](references/pbrun-prepon.md) | Pangenome-aware preprocessing |83| `postpon` | [pbrun-postpon.md](references/pbrun-postpon.md) | Pangenome-aware post-processing |84| `bammetrics` | [pbrun-bammetrics.md](references/pbrun-bammetrics.md) | Whole-genome coverage/depth metrics |85| `collectmultiplemetrics` | [pbrun-collectmultiplemetrics.md](references/pbrun-collectmultiplemetrics.md) | Multiple Picard/GATK-style alignment metrics |86| `genotypegvcf` | [pbrun-genotypegvcf.md](references/pbrun-genotypegvcf.md) | Joint-genotype GVCF input(s) into VCF |87| `indexgvcf` | [pbrun-indexgvcf.md](references/pbrun-indexgvcf.md) | Index GVCF input |88| `dbsnp` | [pbrun-dbsnp.md](references/pbrun-dbsnp.md) | dbSNP annotation on variant files |8990For routing heuristics when multiple tools could apply, see91[tool-index.md](references/tool-index.md).9293## Runtime Readiness9495For GPU, driver, Docker, container, storage, or installation questions, read96[runtime-environment.md](references/runtime-environment.md) and prefer:9798```bash99python3 skills/parabricks/scripts/check_parabricks_runtime.py100```101102Add `--path <dir>` for known input/output/tmp paths. Run container probes only103with user consent.104105## Command Shape106107```bash108docker run --rm --gpus all \109 --volume /host/input:/workdir \110 --volume /host/output:/outputdir \111 --workdir /workdir \112 nvcr.io/nvidia/clara/clara-parabricks:<version> \113 pbrun <selected-tool> \114 <tool-specific-options>115```116117Check the version-specific tool reference before finalizing flags.118119## Troubleshooting120121| Error | Cause | Solution |122|-------|-------|----------|123| Multiple plausible tools | Data type or goal underspecified | Ask for assay, inputs, caller preference, desired output; use tool-index |124| Exact flag requested | Options are version-sensitive | Check the selected tool reference and NVIDIA docs |125| Runtime question | GPU, Docker, drivers, or storage | Use runtime-environment reference and diagnostic script |126| Wrong tool family | Assay or input type unclear | Confirm DNA/RNA/methylation/long-read/pangenome before routing |127| CUDA or memory failure | Runtime not ready or GPU memory constrained | Assess runtime before tuning command flags |128129## Guardrails130131- Treat command availability and options as version-sensitive.132- Do not infer exact flags from command names alone.133- Do not collapse standalone tools and full pipelines when explaining tradeoffs.134- Do not substitute DNA `fq2bam` for RNA, or germline for somatic callers.135- Do not invent sample names, read groups, reference builds, known-sites files,136 model files, graph resources, container tags, or output paths.137- Do not install, upgrade, or modify packages. Label setup commands as user-run.138- Do not claim CPU execution of Parabricks tools.139- Do not claim biological or VCF parity without a comparison run.140- Prefer official NVIDIA docs for exact command syntax and option defaults.141142## Key References143144- Parabricks tool index:145 <https://docs.nvidia.com/clara/parabricks/latest/toolreference.html>146- Output accuracy and compatible CPU software versions:147 <https://docs.nvidia.com/clara/parabricks/latest/documentation/tooldocs/outputaccuracyandcompatiblecpusoftwareversions.html>148- Getting started:149 <https://docs.nvidia.com/clara/parabricks/latest/gettingstarted.html>150- Overview:151 <https://docs.nvidia.com/clara/parabricks/latest/overview.html>
nvidia-bionemo