feat: added several Seqkit wrappers (#1128)

<!-- 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-->
Added wrappers for `seqkit` `grep`, `stats`, `rmdup`, and `fx2tab`.

### 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/seqkit/fx2tab/environment.yaml

@@ -0,0 +1,6 @@
+channels:
+  - conda-forge
+  - bioconda
+  - nodefaults
+dependencies:
+  - seqkit =2.3.1

bio/seqkit/fx2tab/meta.yaml

@@ -0,0 +1,14 @@
+name: SeqKit fx2tab
+url: https://bioinf.shenwei.me/seqkit/usage/#fx2tab
+description: |
+  Run SeqKit f2tab convert FASTA/Q to tabular format.
+authors:
+  - Filipe G. Vieira
+input:
+  - fastx: Input FASTA/Q file
+output:
+  - tsv: Output TSV file
+params:
+  - extra: Optional parameters
+notes: |
+  * The `extra` param allows for additional program arguments.

bio/seqkit/fx2tab/test/Snakefile

@@ -0,0 +1,12 @@
+rule seqkit_fx2tab:
+    input:
+        fastx="reads/{sample}.fastq",
+    output:
+        tsv="out/fx2tab/{sample}.tsv",
+    log:
+        "logs/fx2tab/{sample}.log",
+    params:
+        extra="--name",
+    threads: 2
+    wrapper:
+        "master/bio/seqkit/fx2tab"

bio/seqkit/fx2tab/test/reads/a.fastq

@@ -0,0 +1,8 @@
+@1
+ACGGCAT
++
+!!!!!!!
+@2
+ATGGCAT
++
+!!!!!!!

bio/seqkit/fx2tab/wrapper.py

@@ -0,0 +1,18 @@
+__author__ = "Filipe G. Vieira"
+__copyright__ = "Copyright 2023, Filipe G. Vieira"
+__license__ = "MIT"
+
+from snakemake.shell import shell
+
+extra = snakemake.params.get("extra", "")
+log = snakemake.log_fmt_shell(stdout=True, stderr=True)
+
+
+shell(
+    "seqkit fx2tab"
+    " --threads {snakemake.threads}"
+    " {extra}"
+    " --out-file {snakemake.output.tsv}"
+    " {snakemake.input.fastx}"
+    " {log}"
+)

bio/seqkit/grep/environment.yaml

@@ -0,0 +1,6 @@
+channels:
+  - conda-forge
+  - bioconda
+  - nodefaults
+dependencies:
+  - seqkit =2.3.1

bio/seqkit/grep/meta.yaml

@@ -0,0 +1,15 @@
+name: SeqKit grep
+url: https://bioinf.shenwei.me/seqkit/usage/#grep
+description: |
+  Run SeqKit grep to search sequences by ID, name, sequence, or sequence motifs.
+authors:
+  - Filipe G. Vieira
+input:
+  - fastx: Input FASTA/Q file
+  - pattern: pattern file (one record per line)
+output:
+  - fastx: Output FASTA/Q file
+params:
+  - extra: Optional parameters
+notes: |
+  * The `extra` param allows for additional program arguments.

bio/seqkit/grep/test/Snakefile

@@ -0,0 +1,28 @@
+rule seqkit_grep_name:
+    input:
+        fastx="reads/{sample}.fastq",
+        patterns="reads/name.txt",
+    output:
+        fastx="out/grep_name/{sample}.fastq.gz",
+    log:
+        "logs/grep_name/{sample}.log",
+    params:
+        extra="--by-name",
+    threads: 2
+    wrapper:
+        "master/bio/seqkit/grep"
+
+
+rule seqkit_grep_seq:
+    input:
+        fastx="reads/{sample}.fastq",
+        patterns="reads/seq.txt",
+    output:
+        fastx="out/grep_seq/{sample}.fastq.gz",
+    log:
+        "logs/grep_seq/{sample}.log",
+    params:
+        extra="--by-seq",
+    threads: 2
+    wrapper:
+        "master/bio/seqkit/grep"

bio/seqkit/grep/test/reads/a.fastq

@@ -0,0 +1,8 @@
+@1
+ACGGCAT
++
+!!!!!!!
+@2
+ATGGCAT
++
+!!!!!!!

bio/seqkit/grep/test/reads/name.txt

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

bio/seqkit/grep/test/reads/seq.txt

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

bio/seqkit/grep/wrapper.py

@@ -0,0 +1,19 @@
+__author__ = "Filipe G. Vieira"
+__copyright__ = "Copyright 2023, Filipe G. Vieira"
+__license__ = "MIT"
+
+from snakemake.shell import shell
+
+extra = snakemake.params.get("extra", "")
+log = snakemake.log_fmt_shell(stdout=True, stderr=True)
+
+
+shell(
+    "seqkit grep"
+    " --threads {snakemake.threads}"
+    " --pattern-file {snakemake.input.patterns}"
+    " {extra}"
+    " --out-file {snakemake.output.fastx}"
+    " {snakemake.input.fastx}"
+    " {log}"
+)

bio/seqkit/rmdup/environment.yaml

@@ -0,0 +1,6 @@
+channels:
+  - conda-forge
+  - bioconda
+  - nodefaults
+dependencies:
+  - seqkit =2.3.1

bio/seqkit/rmdup/meta.yaml

@@ -0,0 +1,16 @@
+name: SeqKit rmdup
+url: https://bioinf.shenwei.me/seqkit/usage/#rmdup
+description: |
+  Run SeqKit rmdup grep to remove duplicated sequences by ID, name, or sequence.
+authors:
+  - Filipe G. Vieira
+input:
+  - fastx: Input FASTA/Q file
+output:
+  - fastx: Output FASTA/Q file
+  - dup_num: Output file to save number and list of duplicated seqs
+  - dup_seq: Output file to save duplicated seqs
+params:
+  - extra: Optional parameters
+notes: |
+  * The `extra` param allows for additional program arguments.

bio/seqkit/rmdup/test/Snakefile

@@ -0,0 +1,30 @@
+rule seqkit_rmdup_name:
+    input:
+        fastx="reads/{sample}.fastq",
+    output:
+        fastx="out/rmdup_name/{sample}.fastq.gz",
+        dup_num="out/rmdup_name/{sample}.num.txt",
+        dup_seq="out/rmdup_name/{sample}.seq.txt",
+    log:
+        "logs/rmdup_name/{sample}.log",
+    params:
+        extra="--by-name",
+    threads: 2
+    wrapper:
+        "master/bio/seqkit/rmdup"
+
+
+rule seqkit_rmdup_seq:
+    input:
+        fastx="reads/{sample}.fastq",
+    output:
+        fastx="out/rmdup_seq/{sample}.fastq.gz",
+        dup_num="out/rmdup_seq/{sample}.num.txt",
+        dup_seq="out/rmdup_seq/{sample}.seq.txt",
+    log:
+        "logs/rmdup_seq/{sample}.log",
+    params:
+        extra="--by-seq",
+    threads: 2
+    wrapper:
+        "master/bio/seqkit/rmdup"

bio/seqkit/rmdup/test/reads/a.fastq

@@ -0,0 +1,16 @@
+@1
+ACGGCAT
++
+!!!!!!!
+@2
+ATGGCAT
++
+!!!!!!!
+@1
+NCGGCAT
++
+!!!!!!!
+@3
+ATGGCAT
++
+!!!!!!!

bio/seqkit/rmdup/wrapper.py

@@ -0,0 +1,30 @@
+__author__ = "Filipe G. Vieira"
+__copyright__ = "Copyright 2023, Filipe G. Vieira"
+__license__ = "MIT"
+
+from snakemake.shell import shell
+
+extra = snakemake.params.get("extra", "")
+log = snakemake.log_fmt_shell(stdout=True, stderr=True)
+
+
+dup_num = snakemake.output.get("dup_num", "")
+if dup_num:
+    dup_num = f"--dup-num-file {dup_num}"
+
+
+dup_seq = snakemake.output.get("dup_seq", "")
+if dup_seq:
+    dup_seq = f"--dup-seqs-file {dup_seq}"
+
+
+shell(
+    "seqkit rmdup"
+    " --threads {snakemake.threads}"
+    " {extra}"
+    " --out-file {snakemake.output.fastx}"
+    " {dup_num}"
+    " {dup_seq}"
+    " {snakemake.input.fastx}"
+    " {log}"
+)

bio/seqkit/stats/environment.yaml

@@ -0,0 +1,6 @@
+channels:
+  - conda-forge
+  - bioconda
+  - nodefaults
+dependencies:
+  - seqkit =2.3.1

bio/seqkit/stats/meta.yaml

@@ -0,0 +1,14 @@
+name: SeqKit stats
+url: https://bioinf.shenwei.me/seqkit/usage/#stats
+description: |
+  Run SeqKit stats to get simple statistics of FASTA/Q files.
+authors:
+  - Filipe G. Vieira
+input:
+  - fastx: Input FASTA/Q file
+output:
+  - stats: Output stats file
+params:
+  - extra: Optional parameters
+notes: |
+  * The `extra` param allows for additional program arguments.

bio/seqkit/stats/test/Snakefile

@@ -0,0 +1,12 @@
+rule seqkit_stats:
+    input:
+        fastx="reads/{sample}.fastq",
+    output:
+        stats="out/stats/{sample}.tsv",
+    log:
+        "logs/stats/{sample}.log",
+    params:
+        extra="--all --tabular",
+    threads: 2
+    wrapper:
+        "master/bio/seqkit/stats"

bio/seqkit/stats/test/reads/a.fastq

@@ -0,0 +1,8 @@
+@1
+ACGGCAT
++
+!!!!!!!
+@2
+ATGGCAT
++
+!!!!!!!

bio/seqkit/stats/wrapper.py

@@ -0,0 +1,18 @@
+__author__ = "Filipe G. Vieira"
+__copyright__ = "Copyright 2023, Filipe G. Vieira"
+__license__ = "MIT"
+
+from snakemake.shell import shell
+
+extra = snakemake.params.get("extra", "")
+log = snakemake.log_fmt_shell(stdout=True, stderr=True)
+
+
+shell(
+    "seqkit stats"
+    " --threads {snakemake.threads}"
+    " {extra}"
+    " --out-file {snakemake.output.stats}"
+    " {snakemake.input.fastx}"
+    " {log}"
+)

test.py

@@ -140,6 +140,84 @@ def run(wrapper, cmd, check_log=None):
 
 
 
+@skip_if_not_modified
+def test_seqkit_stats():
+    run(
+        "bio/seqkit/stats",
+        [
+            "snakemake",
+            "--cores",
+            "2",
+            "--use-conda",
+            "-F",
+            "out/stats/a.tsv",
+        ],
+    )
+
+@skip_if_not_modified
+def test_seqkit_rmdup():
+    run(
+        "bio/seqkit/rmdup",
+        [
+            "snakemake",
+            "--cores",
+            "2",
+            "--use-conda",
+            "-F",
+            "out/rmdup_name/a.fastq.gz",
+        ],
+    )
+    run(
+        "bio/seqkit/rmdup",
+        [
+            "snakemake",
+            "--cores",
+            "2",
+            "--use-conda",
+            "-F",
+            "out/rmdup_seq/a.fastq.gz",
+        ],
+    )
+
+@skip_if_not_modified
+def test_seqkit_fx2tab():
+    run(
+        "bio/seqkit/fx2tab",
+        [
+            "snakemake",
+            "--cores",
+            "2",
+            "--use-conda",
+            "-F",
+            "out/fx2tab/a.tsv",
+        ],
+    )
+
+@skip_if_not_modified
+def test_seqkit_grep():
+    run(
+        "bio/seqkit/grep",
+        [
+            "snakemake",
+            "--cores",
+            "2",
+            "--use-conda",
+            "-F",
+            "out/grep_name/a.fastq.gz",
+        ],
+    )
+    run(
+        "bio/seqkit/grep",
+        [
+            "snakemake",
+            "--cores",
+            "2",
+            "--use-conda",
+            "-F",
+            "out/grep_seq/a.fastq.gz",
+        ],
+    )
+
 @skip_if_not_modified
 def test_sickle_pe():
     run(