feat: Unified seqtk wrapper (#1777)

<!-- 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/seqtk/seq/environment.yaml → bio/seqtk/environment.yaml

@@ -4,3 +4,4 @@ channels:
   - nodefaults
 dependencies:
   - seqtk =1.4
+  - pigz

bio/seqtk/meta.yaml

@@ -0,0 +1,15 @@
+name: seqtk 
+description: Toolkit for processing sequences in FASTA/Q formats
+url: https://github.com/lh3/seqtk
+authors:
+  - Filipe G. Vieira
+input:
+  - fastx file(s) (can be gzip bcompressed)
+output:
+  - fastn files (can be gzip bcompressed)
+params:
+  - n: number of reads after subsampling (for `sample`)
+  - extra: additional program options (e.g. `-s` for `sample` or `-b/-e` for `trimfq`)
+  - compress_lvl: compression level (see `gzip` manual for details)
+notes: |
+  * Multiple threads can be used during compression of the output file.

bio/seqtk/test/Snakefile

@@ -0,0 +1,91 @@
+rule seqtk_seq_fq2fas:
+    input:
+        "reads/{prefix}.fastq",
+    output:
+        "results/fq2fas/{prefix}.fasta",
+    log:
+        "logs/fq2fas/{prefix}.log",
+    params:
+        command="seq",
+        extra="-A",
+    wrapper:
+        "master/bio/seqtk"
+
+
+rule seqtk_seq_convBQ:
+    input:
+        "reads/{prefix}.fastq",
+    output:
+        "results/convBQ/{prefix}.fasta",
+    log:
+        "logs/convBQ/{prefix}.log",
+    params:
+        command="seq",
+        extra="-aQ 64 -q 20 -n N",
+    wrapper:
+        "master/bio/seqtk"
+
+
+rule seqtk_subseq_list:
+    input:
+        "reads/{prefix}.fastq",
+        "reads/id.list",
+    output:
+        "results/subseq_list/{prefix}.fq.gz",
+    log:
+        "logs/subseq_list/{prefix}.log",
+    params:
+        command="subseq",
+        extra="",
+    wrapper:
+        "master/bio/seqtk"
+
+
+rule seqtk_mergepe:
+    input:
+        r1="reads/{sample}.1.fastq.gz",
+        r2="reads/{sample}.2.fastq.gz",
+    output:
+        merged="results/mergepe/{sample}.fastq.gz",
+    log:
+        "logs/mergepe/{sample}.log",
+    params:
+        command="mergepe",
+        compress_lvl=9,
+    threads: 2
+    wrapper:
+        "master/bio/seqtk"
+
+
+rule seqtk_sample_se:
+    input:
+        "reads/{sample}.fastq.gz",
+    output:
+        "results/sample_se/{sample}.fastq.gz",
+    log:
+        "logs/sample_se/{sample}.log",
+    params:
+        command="sample",
+        n=3,
+        extra="-s 12345",
+    threads: 1
+    wrapper:
+        "master/bio/seqtk"
+
+
+rule seqtk_sample_pe:
+    input:
+        f1="reads/{sample}.1.fastq.gz",
+        f2="reads/{sample}.2.fastq.gz",
+    output:
+        f1="results/sample_pe/{sample}.1.fastq.gz",
+        f2="results/sample_pe/{sample}.2.fastq.gz",
+    log:
+        "logs/sample_pe/{sample}.log",
+    params:
+        command="sample",
+        n=3,
+        extra="-s 12345",
+    threads: 1
+    wrapper:
+        "master/bio/seqtk"

bio/seqtk/test/reads/id.list

@@ -0,0 +1 @@
+1

bio/seqtk/wrapper.py

@@ -0,0 +1,31 @@
+"""Snakemake wrapper for SeqTk."""
+
+__author__ = "Filipe G. Vieira"
+__copyright__ = "Copyright 2023, Filipe G. Vieira"
+__license__ = "MIT"
+
+from snakemake.shell import shell
+
+log = snakemake.log_fmt_shell(stdout=False, stderr=True, append=False)
+extra = snakemake.params.get("extra", "")
+compress_lvl = snakemake.params.get("compress_lvl", "6")
+
+pipe_comp = (
+    f"| pigz --processes {snakemake.threads} -{compress_lvl} --stdout"
+    if snakemake.output[0].endswith(".gz")
+    else ""
+)
+
+if snakemake.params.command == "sample":
+    n_reads = snakemake.params.get("n", "")
+    assert len(snakemake.input) == len(
+        snakemake.output
+    ), "Command 'sample' requires same number of input and output files."
+    for in_fx, out_fx in zip(snakemake.input, snakemake.output):
+        shell(
+            "(seqtk {snakemake.params.command} {extra} {in_fx} {n_reads} {pipe_comp} > {out_fx}) {log}"
+        )
+else:
+    shell(
+        "(seqtk {snakemake.params.command} {extra} {snakemake.input} {pipe_comp} > {snakemake.output}) {log}"
+    )