feat: Genepred to bed (#2726)

<!-- 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 UCSC genePredToBed to the list of available wrappers.

While UCSC tools have a very simple and common CLI, each of them has its
own conda package. So I did not merge all of them into a single
multi-command wrapper like XSV or SeqKit.

### 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),
* the `environment.yaml` pinning has been updated by running
`snakedeploy pin-conda-envs environment.yaml` on a linux machine,
* 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>

bio/ucsc/genePredToBed/environment.yaml

@@ -0,0 +1,6 @@
+channels:
+  - conda-forge
+  - bioconda
+  - nodefaults
+dependencies:
+  - ucsc-genepredtobed=447

bio/ucsc/genePredToBed/meta.yaml

@@ -0,0 +1,11 @@
+name: genePredToBed
+description: Convert from genePred to bed format. Does not yet handle genePredExt
+url: https://hgdownload.cse.ucsc.edu/admin/exe/
+authors:
+  - "Thibault Dayris"
+input:
+  - Path to a genePred file
+output:
+  - Path to the output bed12 file
+params:
+  - extra: Optional parameters for `genePredToBed`

bio/ucsc/genePredToBed/test/Snakefile

@@ -0,0 +1,11 @@
+rule test_genePredToBed:
+    input:
+        "annotation.genePred",
+    output:
+        "annotation.bed",
+    params:
+        extra="",
+    log:
+        "ucsc.log",
+    wrapper:
+        "master/bio/ucsc/genePredToBed"

bio/ucsc/genePredToBed/test/annotation.genePred

@@ -0,0 +1,19 @@
+ENST00000456328.2	chr1	+	11868	14409	14409	14409	3	11868,12612,13220,	12227,12721,14409,
+ENST00000450305.2	chr1	+	12009	13670	13670	13670	6	12009,12178,12612,12974,13220,13452,	12057,12227,12697,13052,13374,13670,
+ENST00000488147.1	chr1	-	14403	29570	29570	29570	11	14403,15004,15795,16606,16857,17232,17605,17914,18267,24737,29533,	14501,15038,15947,16765,17055,17368,17742,18061,18366,24891,29570,
+ENST00000619216.1	chr1	-	17368	17436	17436	17436	1	17368,	17436,
+ENST00000473358.1	chr1	+	29553	31097	31097	31097	3	29553,30563,30975,	30039,30667,31097,
+ENST00000469289.1	chr1	+	30266	31109	31109	31109	2	30266,30975,	30667,31109,
+ENST00000607096.1	chr1	+	30365	30503	30503	30503	1	30365,	30503,
+ENST00000417324.1	chr1	-	34553	36081	36081	36081	3	34553,35276,35720,	35174,35481,36081,
+ENST00000461467.1	chr1	-	35244	36073	36073	36073	2	35244,35720,	35481,36073,
+ENST00000606857.1	chr1	+	52472	53312	53312	53312	1	52472,	53312,
+ENST00000642116.1	chr1	+	57597	64116	64116	64116	3	57597,58699,62915,	57653,58856,64116,
+ENST00000492842.2	chr1	+	62948	63887	63887	63887	1	62948,	63887,
+ENST00000641515.1	chr1	+	65418	71585	69090	70008	3	65418,65519,69036,	65433,65573,71585,
+ENST00000335137.4	chr1	+	69054	70108	69090	70008	1	69054,	70108,
+ENST00000466430.5	chr1	-	89294	120932	120932	120932	4	89294,92090,112699,120774,	91629,92240,112804,120932,
+ENST00000477740.5	chr1	-	92229	129217	129217	129217	4	92229,112699,120720,129054,	92240,112804,120932,129217,
+ENST00000471248.1	chr1	-	110952	129173	129173	129173	3	110952,112699,129054,	111357,112804,129173,
+ENST00000610542.1	chr1	-	120724	133723	133723	133723	4	120724,120873,129054,133373,	120869,120932,129223,133723,
+ENST00000453576.2	chr1	-	129080	133566	133566	133566	2	129080,133373,	129223,133566,

bio/ucsc/genePredToBed/wrapper.py

@@ -0,0 +1,13 @@
+# coding: utf-8
+
+__author__ = "Thibault Dayris"
+__mail__ = "thibault.dayris@gustaveroussy.fr"
+__copyright__ = "Copyright 2024, Thibault Dayris"
+__license__ = "MIT"
+
+from snakemake import shell
+
+extra = snakemake.params.get("extra", "")
+log = snakemake.log_fmt_shell(stdout=True, stderr=True)
+
+shell("genePredToBed {extra} {snakemake.input} {snakemake.output} {log}")

test.py

@@ -5309,6 +5309,13 @@ def test_ucsc_bedgraphtobigwig():
     )
 
 
+@skip_if_not_modified
+def test_ucsc_genepredtobed():
+    run(
+        "bio/ucsc/genePredToBed",
+        ["snakemake", "--cores", "1", "annotation.bed", "--use-conda", "-F"],
+    )
+
 @skip_if_not_modified
 def test_ucsc_fatotwobit():
     run(