feat: allow for specifying multiple chromosomes in ensembl reference …

…dna sequence download wrapper (#2376)

This will concatenate multiple chromosomes in the order in which they
are listed under `params: chromosome:`.

<!-- 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-->

### 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/reference/ensembl-sequence/test/Snakefile

@@ -13,15 +13,31 @@ rule get_genome:
         "master/bio/reference/ensembl-sequence"
 
 
-rule get_chromosome:
+rule get_single_chromosome:
     output:
-        "refs/chr1.fasta",
+        "refs/chr2.fasta",
     params:
         species="saccharomyces_cerevisiae",
         datatype="dna",
         build="R64-1-1",
         release="101",
-        chromosome="I",  # optional: restrict to chromosome
+        chromosome="II",  # optional: restrict to one or multiple chromosomes, for multiple see below
+        # branch="plants",  # optional: specify branch
+    log:
+        "logs/get_genome.log",
+    cache: "omit-software"  # save space and time with between workflow caching (see docs)
+    wrapper:
+        "master/bio/reference/ensembl-sequence"
+
+rule get_multiple_chromosome:
+    output:
+        "refs/chr1_and_chr2.fasta",
+    params:
+        species="saccharomyces_cerevisiae",
+        datatype="dna",
+        build="R64-1-1",
+        release="101",
+        chromosome=["I", "II"],  # optional: restrict to one or multiple chromosomes
         # branch="plants",  # optional: specify branch
     log:
         "logs/get_genome.log",

bio/reference/ensembl-sequence/wrapper.py

@@ -30,7 +30,7 @@
 chromosome = snakemake.params.get("chromosome", "")
 if datatype == "dna":
     if chromosome:
-        suffixes = ["dna.chromosome.{}.fa.gz".format(chromosome)]
+        suffixes = [f"dna.chromosome.{chrom}.fa.gz" for chrom in chromosome]
     else:
         suffixes = ["dna.primary_assembly.fa.gz", "dna.toplevel.fa.gz"]
 elif datatype == "cdna":
@@ -62,7 +62,7 @@
     except sp.CalledProcessError:
         continue
 
-    shell("(curl -L {url} | gzip -d > {snakemake.output[0]}) {log}")
+    shell("(curl -L {url} | gzip -d >> {snakemake.output[0]}) {log}")
     success = True
     break
 

test.py

@@ -5321,7 +5321,14 @@ def test_ensembl_sequence_old_release():
 def test_ensembl_sequence_chromosome():
     run(
         "bio/reference/ensembl-sequence",
-        ["snakemake", "--cores", "1", "refs/chr1.fasta", "--use-conda", "-F"],
+        ["snakemake", "--cores", "1", "refs/chr2.fasta", "--use-conda", "-F"],
+    )
+
+
+def test_ensembl_sequence_chromosomes():
+    run(
+        "bio/reference/ensembl-sequence",
+        ["snakemake", "--cores", "1", "refs/chr1_and_chr2.fasta", "--use-conda", "-F"],
     )