feat: Add GATK LeftAlignAndTrimVariants (#993)

<!-- Ensure that the PR title follows conventional commit style (<type>:
<description>)-->
<!-- Possible types are here:
https://github.com/commitizen/conventional-commit-types/blob/master/index.json
-->

### Description

<!-- Add a description of your PR here-->
Add GATK LeftAlignAndTrimVariants wrapper

### QC
<!-- Make sure that you can tick the boxes below. -->

* [x] I confirm that:

For all wrappers added by this PR, 

* there is a test case which covers any introduced changes,
* `input:` and `output:` file paths in the resulting rule can be changed
arbitrarily,
* either the wrapper can only use a single core, or the example rule
contains a `threads: x` statement with `x` being a reasonable default,
* rule names in the test case are in
[snake_case](https://en.wikipedia.org/wiki/Snake_case) and somehow tell
what the rule is about or match the tools purpose or name (e.g.,
`map_reads` for a step that maps reads),
* all `environment.yaml` specifications follow [the respective best
practices](https://stackoverflow.com/a/64594513/2352071),
* wherever possible, command line arguments are inferred and set
automatically (e.g. based on file extensions in `input:` or `output:`),
* all fields of the example rules in the `Snakefile`s and their entries
are explained via comments (`input:`/`output:`/`params:` etc.),
* `stderr` and/or `stdout` are logged correctly (`log:`), depending on
the wrapped tool,
* temporary files are either written to a unique hidden folder in the
working directory, or (better) stored where the Python function
`tempfile.gettempdir()` points to (see
[here](https://docs.python.org/3/library/tempfile.html#tempfile.gettempdir);
this also means that using any Python `tempfile` default behavior
works),
* the `meta.yaml` contains a link to the documentation of the respective
tool or command,
* `Snakefile`s pass the linting (`snakemake --lint`),
* `Snakefile`s are formatted with
[snakefmt](https://github.com/snakemake/snakefmt),
* Python wrapper scripts are formatted with
[black](https://black.readthedocs.io).
* Conda environments use a minimal amount of channels, in recommended
ordering. E.g. for bioconda, use (conda-forge, bioconda, nodefaults, as
conda-forge should have highest priority and defaults channels are
usually not needed because most packages are in conda-forge nowadays).

bio/gatk/leftalignandtrimvariants/environment.yaml

@@ -0,0 +1,7 @@
+channels:
+  - conda-forge
+  - bioconda
+  - nodefaults
+dependencies:
+  - gatk4 =4.3.0.0
+  - snakemake-wrapper-utils =0.5.0

bio/gatk/leftalignandtrimvariants/meta.yaml

@@ -0,0 +1,13 @@
+name: gatk LeftAlignAndTrimVariants
+url: https://gatk.broadinstitute.org/hc/en-us/articles/360037225872-LeftAlignAndTrimVariants
+description: |
+  Run gatk LeftAlignAndTrimVariants
+authors:
+  - Dmitry Bespiatykh
+input:
+  - A variant call set to left-align and trim
+output:
+  - A left-aligned VCF
+notes: |
+  * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. `-XX:ParallelGCThreads=10` (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically).
+  * The `extra` param allows for additional program arguments.

bio/gatk/leftalignandtrimvariants/test/Homo_sapiens_assembly38.chrM.dict

@@ -0,0 +1,2 @@
+@HD	VN:1.6
+@SQ	SN:chrM	LN:16569	M5:c68f52674c9fb33aef52dcf399755519	UR:file:Homo_sapiens_assembly38.chrM.fasta

bio/gatk/leftalignandtrimvariants/test/Homo_sapiens_assembly38.chrM.fasta.fai

@@ -0,0 +1 @@
+chrM	16569	122	70	71

bio/gatk/leftalignandtrimvariants/test/Snakefile

@@ -0,0 +1,18 @@
+rule gatk_leftalignandtrimvariants:
+    input:
+        vcf="calls/test_split_with_AS_filters.vcf",
+        ref="Homo_sapiens_assembly38.chrM.fasta",
+        fai="Homo_sapiens_assembly38.chrM.fasta.fai",
+        dict="Homo_sapiens_assembly38.chrM.dict",
+#       intervals="intervals.bed", # optional
+    output:
+        vcf="calls/split_multiallelics.vcf",
+    log:
+        "logs/gatk/leftalignandtrimvariants.log",
+    params:
+        extra="--split-multi-allelics", # optional
+        java_opts="",  # optional
+    resources:
+        mem_mb=1024,
+    wrapper:
+        "master/bio/gatk/leftalignandtrimvariants"

bio/gatk/leftalignandtrimvariants/wrapper.py

@@ -0,0 +1,34 @@
+"""Snakemake wrapper for GATK LeftAlignAndTrimVariants"""
+
+__author__ = "Dmitry Bespiatykh"
+__copyright__ = "Copyright 2023, Dmitry Bespiatykh"
+__license__ = "MIT"
+
+
+import tempfile
+from snakemake.shell import shell
+from snakemake_wrapper_utils.java import get_java_opts
+
+extra = snakemake.params.get("extra", "")
+java_opts = get_java_opts(snakemake)
+log = snakemake.log_fmt_shell(stdout=True, stderr=True)
+
+
+intervals = snakemake.input.get("intervals", "")
+if not intervals:
+    intervals = snakemake.params.get("intervals", "")
+if intervals:
+    intervals = "--intervals {}".format(intervals)
+
+
+with tempfile.TemporaryDirectory() as tmpdir:
+    shell(
+        "gatk --java-options '{java_opts}' LeftAlignAndTrimVariants"
+        " --variant {snakemake.input.vcf}"
+        " --reference {snakemake.input.ref}"
+        " {intervals}"
+        " {extra}"
+        " --tmp-dir {tmpdir}"
+        " --output {snakemake.output.vcf}"
+        " {log}"
+    )

test.py

@@ -3959,6 +3959,13 @@ def test_gatk_learn_read_orientation():
         ["snakemake", "--cores", "1", "--use-conda"]
     )
 
+@skip_if_not_modified
+def test_gatk_leftalignandtrimvariants():
+    run(
+        "bio/gatk/leftalignandtrimvariants",
+        ["snakemake", "--cores", "1", "calls/split_multiallelics.vcf", "--use-conda", "-F"],
+    )
+
 
 @skip_if_not_modified
 def test_gatk_getpileupsummaries():