feat: add memory inference to samtools sort (#1208)

<!-- 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-->
Add memory inference to Samtools Sort

### 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/samtools/sort/environment.yaml

@@ -4,4 +4,4 @@ channels:
   - nodefaults
 dependencies:
   - samtools =1.16.1
-  - snakemake-wrapper-utils =0.5.2
+  - snakemake-wrapper-utils =0.5.3

bio/samtools/sort/meta.yaml

@@ -1,8 +1,13 @@
 name: samtools sort
 description: Sort bam file with samtools.
+url: http://www.htslib.org/doc/samtools-sort.html
 authors:
   - Johannes Köster
   - Filipe G. Vieira
-notes: |
-  * The `extra` param allows for additional program arguments (not `-@/--threads`, `--write-index`, `-o` or `-O/--output-fmt`).
-  * For more information see, http://www.htslib.org/doc/samtools-sort.html
+input:
+  - SAM/BAM/CRAM file
+output:
+  - SAM/BAM/CRAM file
+  - SAM/BAM/CRAM index file (optional)
+params:
+  - extra: additional program arguments (not `-@/--threads`, `--write-index`, `-m`, `-o` or `-O/--output-fmt`).

bio/samtools/sort/wrapper.py

@@ -7,17 +7,19 @@
 import tempfile
 from pathlib import Path
 from snakemake.shell import shell
+from snakemake_wrapper_utils.snakemake import get_mem
 from snakemake_wrapper_utils.samtools import get_samtools_opts
 
 
 samtools_opts = get_samtools_opts(snakemake)
 extra = snakemake.params.get("extra", "")
 log = snakemake.log_fmt_shell(stdout=True, stderr=True)
 
+mem_per_thread_mb = int(get_mem(snakemake) / snakemake.threads)
 
 with tempfile.TemporaryDirectory() as tmpdir:
-    tmp_prefix = Path(tmpdir) / "samtools_fastq.sort_"
+    tmp_prefix = Path(tmpdir) / "samtools_sort"
 
     shell(
-        "samtools sort {samtools_opts} {extra} -T {tmp_prefix} {snakemake.input[0]} {log}"
+        "samtools sort {samtools_opts} -m {mem_per_thread_mb}M {extra} -T {tmp_prefix} {snakemake.input[0]} {log}"
     )

bio/samtools/stats/meta.yaml

@@ -1,8 +1,12 @@
 name: samtools stats
 description: Generate stats using samtools.
+url: http://www.htslib.org/doc/samtools-stats.html
 authors:
   - Julian de Ruiter
   - Filipe G. Vieira
-notes: |
-  * The `extra` param allows for additional program arguments (not `-@/--threads`).
-  * For more information see, http://www.htslib.org/doc/samtools-stats.html
+input:
+  - SAM/BAM/CRAM file
+output:
+  - statistics file
+params:
+  - extra: additional program arguments (not `-@/--threads`).

bio/samtools/stats/test/Snakefile

@@ -1,7 +1,7 @@
 rule samtools_stats:
     input:
         bam="mapped/{sample}.bam",
-        bed="design.bed",              #Optional input, specify target regions
+        bed="design.bed",  #Optional input, specify target regions
     output:
         "samtools_stats/{sample}.txt",
     params:

bio/samtools/stats/wrapper.py

@@ -12,7 +12,7 @@
 
 bed = snakemake.input.get("bed", "")
 if bed:
-    bed = "-t " + bed
+    bed = f"-t {bed}"
 
 samtools_opts = get_samtools_opts(
     snakemake, parse_write_index=False, parse_output=False, parse_output_format=False
@@ -25,5 +25,5 @@
 
 
 shell(
-    "samtools stats {samtools_opts} {extra} {snakemake.input.bam} {bed} {region} > {snakemake.output} {log}"
+    "samtools stats {samtools_opts} {extra} {snakemake.input[0]} {bed} {region} > {snakemake.output[0]} {log}"
 )