feat: move pindel region bed files to input (#594)

### Description

Recently I discovered that if you pass a non-existent bed file as a
value for the command line parameters `-j/--include` or `-J/--exclude`
in pindel, the program behaves as if empty files are being passed. Since
these are supplied in `params.extra`, no checks are done on them.

I realise that this is not an issue with the wrapper, per se, but the
pindel repo has been archived, and I think that modifying the wrapper
might be a good way to catch potential mistakes.

Not sure whether my implementation is the best way to handle things, so
thoughts and opinions are welcome.

### QC

* [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: Filipe G. Vieira <fgarrettvieira@gmail.com>

bio/pindel/call/meta.yaml

@@ -1,4 +1,18 @@
 name: pindel
 description: Call variants with pindel.
+url: https://gmt.genome.wustl.edu/packages/pindel
 authors:
-  - Johannes Köster
+  - Johannes Köster, Niklas Mähler
+input:
+  - reference genome fasta file
+  - one or more bam files
+  - bam configuration file, see http://gmt.genome.wustl.edu/packages/pindel/quick-start.html
+  - bed file of regions to include (optional)
+  - bed file of regions to exclude (optional)
+output:
+  - >
+    One file for each variant type.
+    For a more detailed description of the output format, see https://gmt.genome.wustl.edu/packages/pindel/user-manual.html#example-output-record.
+notes: >
+  The include and exclude BED file arguments are incompatible with each other.
+  Either supply one of them or none of them.

bio/pindel/call/test/Snakefile

@@ -7,15 +7,43 @@ rule pindel:
         # samples to call
         samples=["mapped/a.bam"],
         # bam configuration file, see http://gmt.genome.wustl.edu/packages/pindel/quick-start.html
-        config="pindel_config.txt"
+        config="pindel_config.txt",
     output:
-        expand("pindel/all_{type}", type=pindel_types)
+        expand("pindel/all_{type}", type=pindel_types),
     params:
-        # prefix must be consistent with output files
-        prefix="pindel/all",
-        extra=""  # optional parameters (except -i, -f, -o)
+        extra="",  # optional parameters (except -i, -f, -o, -j, -J)
     log:
-        "logs/pindel.log"
+        "logs/pindel.log",
+    threads: 4
+    wrapper:
+        "master/bio/pindel/call"
+
+
+rule pindel_include_regions:
+    input:
+        ref="genome.fasta",
+        samples=["mapped/a.bam"],
+        config="pindel_config.txt",
+        include_bed="regions.bed",
+    output:
+        expand("pindel/all_included_{type}", type=pindel_types),
+    log:
+        "logs/pindel_j.log",
+    threads: 4
+    wrapper:
+        "master/bio/pindel/call"
+
+
+rule pindel_exclude_regions:
+    input:
+        ref="genome.fasta",
+        samples=["mapped/a.bam"],
+        config="pindel_config.txt",
+        exclude_bed="regions.bed",
+    output:
+        expand("pindel/all_excluded_{type}", type=pindel_types),
+    log:
+        "logs/pindel_include.log",
     threads: 4
     wrapper:
         "master/bio/pindel/call"

bio/pindel/call/test/regions.bed

@@ -0,0 +1 @@
+1	1000	10000

bio/pindel/call/wrapper.py

@@ -3,13 +3,34 @@
 __email__ = "koester@jimmy.harvard.edu"
 __license__ = "MIT"
 
-import os
 from snakemake.shell import shell
 
 extra = snakemake.params.get("extra", "")
 log = snakemake.log_fmt_shell(stdout=True, stderr=True)
 
+include_bed = snakemake.input.get("include_bed", None)
+exclude_bed = snakemake.input.get("exclude_bed", None)
+
+if include_bed is not None and exclude_bed is not None:
+    raise Exception("supply either include_bed or exclude_bed, not both")
+
+include_arg = ""
+if include_bed is not None:
+    include_arg = f"-j {include_bed}"
+
+exclude_arg = ""
+if exclude_bed is not None:
+    exclude_arg = f"-J {exclude_bed}"
+
+output_prefix = snakemake.output[0].rsplit("_", 1)[0]
+
 shell(
-    "pindel -T {snakemake.threads} {snakemake.params.extra} -i {snakemake.input.config} "
-    "-f {snakemake.input.ref} -o {snakemake.params.prefix} {log}"
+    "pindel "
+    "-T {snakemake.threads} "
+    "{extra} "
+    "{include_arg} "
+    "{exclude_arg} "
+    "-i {snakemake.input.config} "
+    "-f {snakemake.input.ref} "
+    "-o {output_prefix} {log}"
 )

test.py

@@ -2743,7 +2743,51 @@ def test_picard_createsequencedictionary():
 def test_pindel_call():
     run(
         "bio/pindel/call",
-        ["snakemake", "--cores", "1", "pindel/all_D", "--use-conda", "-F"],
+        [
+            "snakemake",
+            "--cores",
+            "1",
+            "pindel/all_D",
+            "--use-conda",
+            "-F",
+        ],
+    )
+
+
+@skip_if_not_modified
+def test_pindel_call_include():
+    def check_log(log):
+        assert "Looking at chromosome 1 bases 1000 to 10000" in log
+
+    run(
+        "bio/pindel/call",
+        [
+            "snakemake",
+            "--cores",
+            "1",
+            "pindel/all_included_D",
+            "--use-conda",
+            "-F",
+        ],
+        check_log=check_log,
+    )
+
+
+@skip_if_not_modified
+def test_pindel_call_exclude():
+    def check_log(log):
+        assert "Looking at chromosome 1 bases 1 to 1000" in log
+
+    run(
+        "bio/pindel/call",
+        [
+            "snakemake",
+            "--cores",
+            "1",
+            "pindel/all_excluded_D",
+            "--use-conda",
+            "-F",
+        ],
     )
 
 
@@ -4867,4 +4911,4 @@ def test_bazam_separated():
     run(
         "bio/bazam",
         ["snakemake", "--cores", "1", "--use-conda", "-F", "results/reads/a.r1.fastq.gz"],
-    )
+    )