> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/clara/parabricks/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/clara/parabricks/_mcp/server.

# 4.3.1-1 Release Notes

**Highlights:**

* New tool, [deepsomatic](/tool-reference/tools/deepsomatic) for somatic variant calling.
* The latest Parabricks toolkit (v4.3.1) is now fully supported on Grace Hopper, refer to [NVIDIA Grace CPU Platforms](/get-started/nvidia-grace-cpu-platforms).
* [deepvariant](/tool-reference/tools/deepvariant) version 1.6.1 updated, new option added.
* [haplotypecaller](/tool-reference/tools/haplotypecaller) bug fixes and 3 new options added.
* [mutectcaller](/tool-reference/tools/mutectcaller) a few bug fixes.
* [rna\_fq2bam](/tool-reference/tools/rna-fq-2-bam) bug fixes and feature added in wrapper.
* [minimap2](/tool-reference/tools/minimap-2) bug fixes, version update, and improved support for ONT data.
* fq2bamfast and [fq2bam](/tool-reference/tools/fq-2-bam-bwa-mem-gatk): Bug fixes and performance improvements. Additional option to monitor approximate CPU utilization and host memory usage during execution (`--monitor-usage`).

## New Tools

With Parabricks 4.3.1 we are releasing an accelerated deepsomatic tool.  DeepSomatic builds on the deep learning-based variant
caller DeepVariant. It processes aligned reads from tumor and normal samples
(in BAM or CRAM format), generates pileup image tensors, classifies these
tensors using a convolutional neural network, and outputs somatic variants in
standard VCF or gVCF files.

## Improvements

### Tool Updates

[haplotypecaller](/tool-reference/tools/haplotypecaller):

* Adds the following new options:

  * `--minimum-mapping-quality`
  * `--mapping-quality-threshold-for-genotyping`
  * `--enable-dynamic-read-disqualification-for-genotyping`

* Improved performance by leveraging AVX512 instructions for CPU-based PairHMM computation.

[mutectcaller](/tool-reference/tools/mutectcaller):

* Improved performance by leveraging AVX512 instructions for CPU-based PairHMM computation.

[deepvariant](/tool-reference/tools/deepvariant):

* Updates to match the baseline version v1.6.1.
* Adds the new option `--haploid-contigs`
* Improved performance for short-read mode through increased GPU utilization and kernel optimizations.

[rna\_fq2bam](/tool-reference/tools/rna-fq-2-bam):

* Supports passing `--out-chim-type` multiple times.

fq2bamfast

* Improved alignment performance on Hopper GPUs through increased use of [DPX instructions](https://developer.nvidia.com/blog/boosting-dynamic-programming-performance-using-nvidia-hopper-gpu-dpx-instructions/).
* Improved performance on multi-GPU runs; for example, on [DGX H100](https://www.nvidia.com/en-us/data-center/dgx-h100/).
* Improved error detection for improper FASTQ inputs through `--in-fq` or `--in-se-fq`. Previously recorded a utf-8 decode error.
* Additional option to monitor approximate CPU utilization and host memory usage during execution (`--monitor-usage`).

[fq2bam](/tool-reference/tools/fq-2-bam-bwa-mem-gatk):

* Improved error detection for improper FASTQ inputs through `--in-fq` or `--in-se-fq`. Previously recorded a utf-8 decode error.
* Additional option to monitor approximate CPU utilization and host memory usage during execution (`--monitor-usage`).

[minimap2](/tool-reference/tools/minimap-2):

* Updated map-pbmm2 preset to match the updated versions of minimap2 (v2.26) and pbmm2 (v1.13.0).

## Bug Fixes

* [mutectcaller](/tool-reference/tools/mutectcaller) and [haplotypecaller](/tool-reference/tools/haplotypecaller): Fixed a wrong alignment offset value in smith-waterman algorithm.
* [mutectcaller](/tool-reference/tools/mutectcaller) and [haplotypecaller](/tool-reference/tools/haplotypecaller): Fixed a crash on GPU when running in low memory mode.
* [mutectcaller](/tool-reference/tools/mutectcaller): Fixed the wrong active probability value when the pileup size is 0.
* [mutectcaller](/tool-reference/tools/mutectcaller): Fixed a max coverage overflow bug.
* [rna\_fq2bam](/tool-reference/tools/rna-fq-2-bam): Fixed an error when passing "WithinBAM\_SoftClip" or "WithinBAM\_HardClip" to `--out-chim-type`.
* [minimap2](/tool-reference/tools/minimap-2): Fixed support for Oxford Nanopore Technologies (ONT) data with minimap2.
* fq2bamfast : Fix rare erroneous assertion (`Workspace not big enough, expected desiredSize <= cubWorkspaceSize, exiting`). Case will now be handled correctly and fall back to CPU recovery if needed.
* [deepvariant](/tool-reference/tools/deepvariant): Fixed bug related to Smith-Waterman computation on CPU.

For further information refer to the
[Parabricks datasheet](https://resources.nvidia.com/en-us-hc-genomics/healthcare-genomics).