feat: Add seqkit subseq (#1318)

### Description
Adds the seqkit subseq command with support for optional bed and gtf
inputs as well as the CLI --region flag.


### 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 <1151762+fgvieira@users.noreply.github.com>

bio/seqkit/subseq/environment.yaml

@@ -0,0 +1,6 @@
+channels:
+  - conda-forge
+  - bioconda
+  - nodefaults
+dependencies:
+  - seqkit =2.4.0

bio/seqkit/subseq/meta.yaml

@@ -0,0 +1,13 @@
+name: SeqKit subseq
+url: https://bioinf.shenwei.me/seqkit/usage/#subseq
+description: |
+  Run SeqKit grep to get subsequences by region/gtf/bed, including flanking sequences.
+authors:
+  - Connor McEntee
+input:
+  - fasta: Input FASTA file
+  - gtf: GTF (version 2.2) file
+output:
+  - fasta: Output FASTA file
+params:
+  - extra: Optional parameters

bio/seqkit/subseq/test/Snakefile

@@ -0,0 +1,40 @@
+rule seqkit_subseq_bed:
+    input:
+        fasta="sequences/t.fa",
+        bed="sequences/t.bed",
+    output:
+        fasta="out/subseq_bed/t_bed.fa.gz",
+    log:
+        "logs/subseq_bed/bed.log",
+    threads: 2
+    wrapper:
+        "master/bio/seqkit/subseq"
+
+
+rule seqkit_subseq_gtf:
+    input:
+        fasta="sequences/t.fa",
+        gtf="sequences/t.gtf",
+    output:
+        fasta="out/subseq_gtf/t_gtf.fa.gz",
+    log:
+        "logs/subseq_gtf/gtf.log",
+    params:
+        extra="--feature CDS",
+    threads: 2
+    wrapper:
+        "master/bio/seqkit/subseq"
+
+
+rule seqkit_subseq_region:
+    input:
+        fasta="sequences/t.fa",
+    output:
+        fasta="out/subseq_region/t_region.fa.gz",
+    log:
+        "logs/subseq_region/region.log",
+    params:
+        extra="--region 1:12",
+    threads: 2
+    wrapper:
+        "master/bio/seqkit/subseq"

bio/seqkit/subseq/test/sequences/t.bed

@@ -0,0 +1 @@
+seq	4	8

bio/seqkit/subseq/test/sequences/t.fa

@@ -0,0 +1,3 @@
+>seq
+actgACTGactgn
+

bio/seqkit/subseq/test/sequences/t.gtf

@@ -0,0 +1,2 @@
+seq	test	CDS	5	8	.	.	.	gene_id "A"; transcript_id "";
+seq	test	CDS	5	8	.	-	.	gene_id "B"; transcript_id "";

bio/seqkit/subseq/wrapper.py

@@ -0,0 +1,27 @@
+__author__ = "Connor McEntee"
+__license__ = "MIT"
+
+from snakemake.shell import shell
+
+extra = snakemake.params.get("extra", "")
+log = snakemake.log_fmt_shell(stdout=True, stderr=True)
+
+bed = snakemake.input.get("bed", "")
+if bed:
+    bed = f"--bed {bed}"
+
+gtf = snakemake.input.get("gtf", "")
+if gtf:
+    gtf = f"--gtf {gtf}"
+
+
+shell(
+    "seqkit subseq"
+    " --threads {snakemake.threads}"
+    " {bed}"
+    " {gtf}"
+    " {extra}"
+    " --out-file {snakemake.output.fasta}"
+    " {snakemake.input.fasta}"
+    " {log}"
+)

test.py

@@ -287,6 +287,42 @@ def test_seqkit_grep():
         ],
     )
 
+@skip_if_not_modified
+def test_seqkit_subseq():
+    run(
+        "bio/seqkit/subseq",
+        [
+            "snakemake",
+            "--cores",
+            "2",
+            "--use-conda",
+            "-F",
+            "out/subseq_bed/t_bed.fa.gz",
+        ],
+    )
+    run(
+        "bio/seqkit/subseq",
+        [
+            "snakemake",
+            "--cores",
+            "2",
+            "--use-conda",
+            "-F",
+            "out/subseq_gtf/t_gtf.fa.gz",
+        ],
+    )
+    run(
+        "bio/seqkit/subseq",
+        [
+            "snakemake",
+            "--cores",
+            "2",
+            "--use-conda",
+            "-F",
+            "out/subseq_region/t_region.fa.gz",
+        ],
+    )
+
 @skip_if_not_modified
 def test_sickle_pe():
     run(