feat: Gatk calculate contamination (#1547)

<!-- 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

This PR add [GATK Calculate
Contamination](https://gatk.broadinstitute.org/hc/en-us/articles/360036888972-CalculateContamination)
in the list of available wrappers

### 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).

---------

Co-authored-by: tdayris <tdayris@gustaveroussy.fr>
Co-authored-by: tdayris <thibault.dayris@gustaveroussy.fr>
Co-authored-by: Johannes Köster <johannes.koester@uni-due.de>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: snakedeploy-bot[bot] <115615832+snakedeploy-bot[bot]@users.noreply.github.com>
Co-authored-by: Felix Mölder <felix.moelder@uni-due.de>
Co-authored-by: Christopher Schröder <christopher.schroeder@tu-dortmund.de>
Co-authored-by: Filipe G. Vieira <1151762+fgvieira@users.noreply.github.com>

bio/gatk/calculatecontamination/environment.yaml

@@ -0,0 +1,7 @@
+channels:
+  - conda-forge
+  - bioconda
+  - nodefaults
+dependencies:
+  - gatk4 =4.4.0.0
+  - snakemake-wrapper-utils =0.6.2

bio/gatk/calculatecontamination/meta.yaml

@@ -0,0 +1,14 @@
+name: gatk CalculateContamination
+url: https://gatk.broadinstitute.org/hc/en-us/articles/360036888972-CalculateContamination
+description: |
+  Calculate the fraction of reads coming from cross-sample contamination
+authors:
+  - Thibault Dayris
+input:
+  - tumor: Path to pileup table from GATK GetPileupSummaries
+  - normal: Optional path to noram pileup table
+output:
+  - Path to contamination table
+params:
+  - 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).
+  - extra: param allows for additional program arguments.

bio/gatk/calculatecontamination/test/Snakefile

@@ -0,0 +1,15 @@
+rule test_gatk_calculate_contamination:
+    input:
+        tumor="pileups.table",
+        # normal="normal.pileups.table",
+    output:
+        "contamination.table",
+    threads: 1
+    resources:
+        mem_mb=1024,
+    log:
+        "logs/gatk/contamination.log",
+    params:
+        extra="",
+    wrapper:
+        "master/bio/gatk/calculatecontamination"

bio/gatk/calculatecontamination/test/pileups.table

@@ -0,0 +1,2 @@
+#<METADATA>SAMPLE=mysample
+contig	position	ref_count	alt_count	other_alt_count	allele_frequency

bio/gatk/calculatecontamination/wrapper.py

@@ -0,0 +1,26 @@
+__author__ = "Thibault Dayris"
+__copyright__ = "Copyright 2023, Thibault Dayris"
+__email__ = "thibault.dayris@gustaveroussy.fr"
+__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)
+
+if snakemake.input.get("normal"):
+    extra += f" --matched-normal {snakemake.input.normal}"
+
+with tempfile.TemporaryDirectory() as tmpdir:
+    shell(
+        "gatk --java-options '{java_opts}' CalculateContamination"
+        " --input {snakemake.input.tumor}"
+        " {extra}"
+        " --tmp-dir {tmpdir}"
+        " --output {snakemake.output}"
+        " {log}"
+    )

test.py

@@ -4219,6 +4219,14 @@ def test_gatk_callcopyrationsegments():
     )
 
 
+@skip_if_not_modified
+def test_gatk_calculatecontamination():
+    run(
+        "bio/gatk/calculatecontamination",
+        ["snakemake", "--cores", "1", "contamination.table", "--use-conda", "-F"],
+    )
+
+
 @skip_if_not_modified
 def test_gatk_scatterintervalsbyns():
     run(