feat: NGS-bits SampleAncestry (#3502)

<!-- 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
-->

<!-- Add a description of your PR here-->
This PR adds a second tool from
[ngs-bits](https://github.com/imgag/ngs-bits/blob/master/doc/tools/SampleAncestry/index.md).

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

* [X] I confirm that I have followed the [documentation for contributing
to
`snakemake-wrappers`](https://snakemake-wrappers.readthedocs.io/en/stable/contributing.html).

While the contributions guidelines are more extensive, please
particularly ensure that:
* [X] `test.py` was updated to call any added or updated example rules
in a `Snakefile`
* [X] `input:` and `output:` file paths in the rules can be chosen
arbitrarily
* [X] wherever possible, command line arguments are inferred and set
automatically (e.g. based on file extensions in `input:` or `output:`)
* [X] 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
* [X] the `meta.yaml` contains a link to the documentation of the
respective tool or command under `url:`
* [X] conda environments use a minimal amount of channels and packages,
in recommended ordering


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

- **New Features**
- Introduced `environment.linux-64.pin.txt` and `environment.yaml` files
for easy environment setup on Linux.
- Added a new tool, `NGS-bits SampleAncestry`, to estimate sample
ancestry based on genetic variants.
- Implemented a Snakemake wrapper for executing the `SampleAncestry`
command.
- Created a sample VCF file for testing the ancestry estimation
functionality.

- **Bug Fixes**
- Enhanced test coverage with new test functions for `SampleAncestry`
and `autoindex` workflows.

- **Documentation**
- Added comprehensive metadata for the `NGS-bits SampleAncestry` tool,
detailing its functionality and requirements.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

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/ngsbits/sampleancestry/environment.yaml

@@ -0,0 +1,6 @@
+channels:
+  - conda-forge
+  - bioconda
+  - nodefaults
+dependencies:
+  - ngs-bits=2024_11

bio/ngsbits/sampleancestry/meta.yaml

@@ -0,0 +1,13 @@
+name: NGS-bits SampleAncestry
+url: https://github.com/imgag/ngs-bits/blob/master/doc/tools/SampleAncestry/index.md
+description: Estimates the ancestry of a sample based on variants.
+authors:
+  - Thibault Dayris
+input:
+  - Path to one or multiple VCF file(s).
+output:
+  - Path to results table (TSV)
+params:
+  - extra: Optional parameters besides IO
+notes: |
+  To estimate ancestry, the input VCF file must have enough variants AND variants that overlaps known human variants ancestry.

bio/ngsbits/sampleancestry/test/Snakefile

@@ -0,0 +1,13 @@
+rule test_ngsbits_sampleancestry:
+    input:
+        # Either a single VCF or a list of VCF files
+        "sample.vcf",
+    output:
+        "ancestry.tsv",
+    threads: 1
+    log:
+        "ancestry.log",
+    params:
+        extra="-min_snps 4 -build hg19",
+    wrapper:
+        "master/bio/ngsbits/sampleancestry"

bio/ngsbits/sampleancestry/test/sample.vcf

@@ -0,0 +1,11 @@
+##fileformat=VCFv4.0
+##INFO=<ID=AF_AFR,Number=1,Type=String,Description="no description available">
+##INFO=<ID=AF_EAS,Number=1,Type=String,Description="no description available">
+##INFO=<ID=AF_EUR,Number=1,Type=String,Description="no description available">
+##INFO=<ID=AF_SAS,Number=1,Type=String,Description="no description available">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	Sample1
+chr1	69270	.	A	G	.	.	AF_AFR=0.360;AF_EAS=0.998;AF_EUR=0.911;AF_SAS=0.902	GT	1/1
+chr1	69897	.	T	C	.	.	AF_AFR=0.312;AF_EAS=0.777;AF_EUR=0.844;AF_SAS=0.805	GT	0/1
+chr1	325155	.	C	A	.	.	AF_AFR=0.653;AF_EAS=0.971;AF_EUR=0.769;AF_SAS=0.497	GT	1/1
+chr1	881627	.	G	A	.	.	AF_AFR=0.130;AF_EAS=0.658;AF_EUR=0.636;AF_SAS=0.565	GT	0/1
+chr1	914852	.	G	C	.	.	AF_AFR=0.249;AF_EAS=0.722;AF_EUR=0.596;AF_SAS=0.622	GT	1/1

bio/ngsbits/sampleancestry/wrapper.py

@@ -0,0 +1,23 @@
+# coding: utf-8
+
+"""Snakemake wrapper for NGS-bits SampleAncestry"""
+
+__author__ = "Thibault Dayris"
+__copyright__ = "Copyright 2024, Thibault Dayris"
+__email__ = "thibault.dayris@gustaveroussy.fr"
+__license__ = "MIT"
+
+from snakemake.shell import shell
+
+log = snakemake.log_fmt_shell(
+    stdout=False,
+    stderr=True,
+)
+extra = snakemake.params.get("extra", "")
+
+shell(
+    "SampleAncestry {extra}"
+    " -in {snakemake.input}"
+    " -out {snakemake.output:q}"
+    " {log}"
+)

test_wrappers.py

@@ -3579,6 +3579,20 @@ def test_nanosim_metagenome(run):
     )
 
 
+def test_ngsbits_sampleancestry(run):
+    run(
+        "bio/ngsbits/sampleancestry",
+        [
+            "snakemake",
+            "--cores",
+            "1",
+            "--use-conda",
+            "-F",
+            "ancestry.tsv",
+        ],
+    )
+
+
 def test_ngsderive(run):
     run(
         "bio/ngsderive",
@@ -5959,12 +5973,14 @@ def test_vg_autoindex_giraffe(run):
         ["snakemake", "--cores", "1", "resources/genome.dist", "--use-conda", "-F"],
     )
 
+
 def test_vg_autoindex_map(run):
     run(
         "bio/vg/autoindex",
         ["snakemake", "--cores", "1", "resources/genome.xg", "--use-conda", "-F"],
     )
 
+
 def test_vg_construct(run):
     run(
         "bio/vg/construct",