feat: Taxonkit wrapper (#2755)

<!-- 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
-->

<!-- 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),
* the `environment.yaml` pinning has been updated by running
`snakedeploy pin-conda-envs environment.yaml` on a linux machine,
* 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/environment.yaml

@@ -1,5 +1,4 @@
 channels:
-  - conda-forge
   - bioconda
   - nodefaults
 dependencies:

bio/seqkit/meta.yaml

@@ -1,5 +1,5 @@
 name: SeqKit generic wrapper
-url: https://bioinf.shenwei.me/seqkit/usage/
+url: https://bioinf.shenwei.me/seqkit/
 description: |
   Run SeqKit.
 authors:

bio/taxonkit/environment.linux-64.pin.txt

@@ -0,0 +1,5 @@
+# This file may be used to create an environment using:
+# $ conda create --name <env> --file <this file>
+# platform: linux-64
+@EXPLICIT
+https://conda.anaconda.org/bioconda/linux-64/taxonkit-0.16.0-h9ee0642_0.tar.bz2#d58328deecfbc00948320e07d5a885c4

bio/taxonkit/environment.yaml

@@ -0,0 +1,5 @@
+channels:
+  - bioconda
+  - nodefaults
+dependencies:
+  - taxonkit =0.16.0

bio/taxonkit/meta.yaml

@@ -0,0 +1,14 @@
+name: TaxonKit generic wrapper
+url: https://bioinf.shenwei.me/taxonkit/
+description: |
+  Run TaxonKit.
+authors:
+  - Filipe G. Vieira
+input:
+  - input: input file(s)
+  - taxdump: taxdump files
+output:
+  - taxdump: output taxdump files
+params:
+  - command: TaxonKit command to use.
+  - extra: Optional parameters.

bio/taxonkit/test/Snakefile

@@ -0,0 +1,225 @@
+rule taxonkit_list_txt:
+    input:
+        taxdump=multiext(
+            "test-taxdump/",
+            "taxid.map",
+            "nodes.dmp",
+            "names.dmp",
+            "merged.dmp",
+            "delnodes.dmp",
+        ),
+    output:
+        "out/list/{sample}.txt",
+    log:
+        "logs/list/{sample}.log",
+    params:
+        command="list",
+        extra="--ids 36846609 --indent '\t' --show-name --show-rank",
+    threads: 2
+    wrapper:
+        "master/bio/taxonkit"
+
+
+rule taxonkit_list_json:
+    input:
+        taxdump=multiext(
+            "test-taxdump/",
+            "taxid.map",
+            "nodes.dmp",
+            "names.dmp",
+            "merged.dmp",
+            "delnodes.dmp",
+        ),
+    output:
+        "out/list/{sample}.json",
+    log:
+        "logs/list/{sample}.log",
+    params:
+        command="list",
+        extra="--ids 36846609 --show-name --show-rank",
+    threads: 2
+    wrapper:
+        "master/bio/taxonkit"
+
+
+rule taxonkit_lineage:
+    input:
+        input="taxon_ids.txt",
+        taxdump=multiext(
+            "test-taxdump/",
+            "taxid.map",
+            "nodes.dmp",
+            "names.dmp",
+            "merged.dmp",
+            "delnodes.dmp",
+        ),
+    output:
+        "out/lineage/{sample}.txt",
+    log:
+        "logs/lineage/{sample}.log",
+    params:
+        command="lineage",
+        extra="--show-status-code",
+    threads: 2
+    wrapper:
+        "master/bio/taxonkit"
+
+
+rule taxonkit_reformat:
+    input:
+        input="taxon_ids.txt",
+        taxdump=multiext(
+            "test-taxdump/",
+            "taxid.map",
+            "nodes.dmp",
+            "names.dmp",
+            "merged.dmp",
+            "delnodes.dmp",
+        ),
+    output:
+        "out/reformat/{sample}.txt",
+    log:
+        "logs/reformat/{sample}.log",
+    params:
+        command="reformat",
+        extra="--taxid-field 1",
+    threads: 2
+    wrapper:
+        "master/bio/taxonkit"
+
+
+rule taxonkit_name2taxid:
+    input:
+        input="taxon_name.txt",
+        taxdump=multiext(
+            "test-taxdump/",
+            "taxid.map",
+            "nodes.dmp",
+            "names.dmp",
+            "merged.dmp",
+            "delnodes.dmp",
+        ),
+    output:
+        "out/name2taxid/{sample}.txt",
+    log:
+        "logs/name2taxid/{sample}.log",
+    params:
+        command="name2taxid",
+        extra="--show-rank",
+    threads: 2
+    wrapper:
+        "master/bio/taxonkit"
+
+
+rule taxonkit_filter:
+    input:
+        input="taxon_ids.txt",
+        taxdump=multiext(
+            "test-taxdump/",
+            "taxid.map",
+            "nodes.dmp",
+            "names.dmp",
+            "merged.dmp",
+            "delnodes.dmp",
+        ),
+    output:
+        "out/filter/{sample}.txt",
+    log:
+        "logs/filter/{sample}.log",
+    params:
+        command="filter",
+        extra="--equal-to species",
+    threads: 2
+    wrapper:
+        "master/bio/taxonkit"
+
+
+rule taxonkit_lca:
+    input:
+        input="taxon_ids.txt",
+        taxdump=multiext(
+            "test-taxdump/",
+            "taxid.map",
+            "nodes.dmp",
+            "names.dmp",
+            "merged.dmp",
+            "delnodes.dmp",
+        ),
+    output:
+        "out/lca/{sample}.txt",
+    log:
+        "logs/lca/{sample}.log",
+    params:
+        command="lca",
+        extra="--separator ','",
+    threads: 2
+    wrapper:
+        "master/bio/taxonkit"
+
+
+rule taxonkit_create_taxdump:
+    input:
+        input=["lineages1.txt", "lineages2.txt"],
+    output:
+        taxdump=multiext(
+            "out/create-taxdump/{sample}/",
+            "taxid.map",
+            "nodes.dmp",
+            "names.dmp",
+            "merged.dmp",
+            "delnodes.dmp",
+        ),
+    log:
+        "logs/create-taxdump/{sample}.log",
+    params:
+        command="create-taxdump",
+        extra="--field-accession 1 --rank-names 'superkingdom,phylum,class,order,family,genus,species'",
+    threads: 2
+    wrapper:
+        "master/bio/taxonkit"
+
+
+rule taxonkit_profile2cami:
+    input:
+        input="abundance.tsv",
+        taxdump=multiext(
+            "test-taxdump/",
+            "taxid.map",
+            "nodes.dmp",
+            "names.dmp",
+            "merged.dmp",
+            "delnodes.dmp",
+        ),
+    output:
+        "out/profile2cami/{sample}.txt",
+    log:
+        "logs/profile2cami/{sample}.log",
+    params:
+        command="profile2cami",
+        extra="--sample-id sample1 --taxonomy-id 2021-10-01",
+    threads: 2
+    wrapper:
+        "master/bio/taxonkit"
+
+
+rule taxonkit_cami_filter:
+    input:
+        input=rules.taxonkit_profile2cami.output[0],
+        taxdump=multiext(
+            "test-taxdump/",
+            "taxid.map",
+            "nodes.dmp",
+            "names.dmp",
+            "merged.dmp",
+            "delnodes.dmp",
+        ),
+    output:
+        "out/cami_filter/{sample}.tsv",
+    log:
+        "logs/cami_filter/{sample}.log",
+    params:
+        command="cami-filter",
+        extra="--taxids 2759",
+    threads: 2
+    wrapper:
+        "master/bio/taxonkit"

bio/taxonkit/test/abundance.tsv

@@ -0,0 +1,4 @@
+2824115	0.2	merged to 483329
+483329	0.2	absord 2824115
+239935	0.5	no change
+1657696	0.1	deleted

bio/taxonkit/test/lineages1.txt

@@ -0,0 +1,2 @@
+2026160944	Archaea	Halobacteriota	Halobacteria	Halobacteriales	Haloferacaceae	Halobellus	Halobellus inordinatus
+2088315078	Archaea	Halobacteriota	Methanosarcinia	Methanotrichales	Methanotrichaceae	Methanothrix_A	Methanothrix_A sp001602645

bio/taxonkit/test/lineages2.txt

@@ -0,0 +1,3 @@
+2090174402	Archaea	Thermoproteota	Nitrososphaeria_A	Caldarchaeales	Wolframiiraptoraceae	Geocrenenecus	Geocrenenecus arthurdayi
+2139920326	Archaea	Huberarchaeota	Huberarchaeia	Huberarchaeales	Huberarchaeaceae	Huberarchaeum	Huberarchaeum crystalense
+2143941790	Archaea	Thermoproteota	Nitrososphaeria	Nitrososphaerales	UBA57	UBA57	UBA57 sp002495905

bio/taxonkit/test/taxon_ids.txt

@@ -0,0 +1,5 @@
+2026160944
+2088315078
+2090174402
+2139920326
+2143941790

bio/taxonkit/test/taxon_name.txt

@@ -0,0 +1,3 @@
+Archaeoglobi
+001639295
+CSSED10-239