feat: Bwameth index (#3162)

<!-- 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 I have followed the [documentation for contributing
to
`snakemake-wrappers`](https://snakemake-wrappers.readthedocs.io/en/stable/contributing.html).

While the contributions guidelines are more extensive, please
particularly ensure that:
* [x] `test.py` was updated to call any added or updated example rules
in a `Snakefile`
* [x] `input:` and `output:` file paths in the rules can be chosen
arbitrarily
* [x] wherever possible, command line arguments are inferred and set
automatically (e.g. based on file extensions in `input:` or `output:`)
* [x] 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
* [x] the `meta.yaml` contains a link to the documentation of the
respective tool or command under `url:`
* [x] conda environments use a minimal amount of channels and packages,
in recommended ordering


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->

## Summary by CodeRabbit

- **New Features**
- Introduced `environment.linux-64.pin.txt` and `environment.yaml` files
for simplified conda environment setup tailored for bioinformatics
applications.
- Added `meta.yaml` file containing essential metadata for the `bwa-meth
index` functionality, enhancing user guidance.
- Implemented a new Snakefile for testing `bwameth` indexing
functionality, ensuring reliable performance.
- Created a new genomic FASTA file for sample data storage and analysis.
- Developed a wrapper script to automate the BWA-Meth indexing process,
improving user experience.

- **Tests**
- Added a new test function to validate the `bwameth` indexing command,
ensuring reliability in processing.

<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Co-authored-by: tdayris <[email protected]>
Co-authored-by: tdayris <[email protected]>
Co-authored-by: Johannes Köster <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: snakedeploy-bot[bot] <115615832+snakedeploy-bot[bot]@users.noreply.github.com>
Co-authored-by: Felix Mölder <[email protected]>
Co-authored-by: Christopher Schröder <[email protected]>
Co-authored-by: Filipe G. Vieira <[email protected]>

bio/bwameth/index/environment.linux-64.pin.txt

@@ -0,0 +1,46 @@
+# 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/conda-forge/linux-64/_libgcc_mutex-0.1-conda_forge.tar.bz2#d7c89558ba9fa0495403155b64376d81
+https://conda.anaconda.org/conda-forge/linux-64/ca-certificates-2024.7.4-hbcca054_0.conda#23ab7665c5f63cfb9f1f6195256daac6
+https://conda.anaconda.org/conda-forge/linux-64/ld_impl_linux-64-2.40-hf3520f5_7.conda#b80f2f396ca2c28b8c14c437a4ed1e74
+https://conda.anaconda.org/conda-forge/noarch/tzdata-2024a-h8827d51_1.conda#8bfdead4e0fff0383ae4c9c50d0531bd
+https://conda.anaconda.org/conda-forge/linux-64/libgomp-14.1.0-h77fa898_0.conda#ae061a5ed5f05818acdf9adab72c146d
+https://conda.anaconda.org/conda-forge/linux-64/_openmp_mutex-4.5-2_gnu.tar.bz2#73aaf86a425cc6e73fcf236a5a46396d
+https://conda.anaconda.org/conda-forge/linux-64/libgcc-ng-14.1.0-h77fa898_0.conda#ca0fad6a41ddaef54a153b78eccb5037
+https://conda.anaconda.org/conda-forge/linux-64/bzip2-1.0.8-h4bc722e_7.conda#62ee74e96c5ebb0af99386de58cf9553
+https://conda.anaconda.org/conda-forge/linux-64/c-ares-1.33.1-heb4867d_0.conda#0d3c60291342c0c025db231353376dfb
+https://conda.anaconda.org/conda-forge/linux-64/keyutils-1.6.1-h166bdaf_0.tar.bz2#30186d27e2c9fa62b45fb1476b7200e3
+https://conda.anaconda.org/conda-forge/linux-64/libdeflate-1.21-h4bc722e_0.conda#36ce76665bf67f5aac36be7a0d21b7f3
+https://conda.anaconda.org/conda-forge/linux-64/libev-4.33-hd590300_2.conda#172bf1cd1ff8629f2b1179945ed45055
+https://conda.anaconda.org/conda-forge/linux-64/libexpat-2.6.2-h59595ed_0.conda#e7ba12deb7020dd080c6c70e7b6f6a3d
+https://conda.anaconda.org/conda-forge/linux-64/libffi-3.4.2-h7f98852_5.tar.bz2#d645c6d2ac96843a2bfaccd2d62b3ac3
+https://conda.anaconda.org/conda-forge/linux-64/libnsl-2.0.1-hd590300_0.conda#30fd6e37fe21f86f4bd26d6ee73eeec7
+https://conda.anaconda.org/conda-forge/linux-64/libstdcxx-ng-14.1.0-hc0a3c3a_0.conda#1cb187a157136398ddbaae90713e2498
+https://conda.anaconda.org/conda-forge/linux-64/libuuid-2.38.1-h0b41bf4_0.conda#40b61aab5c7ba9ff276c41cfffe6b80b
+https://conda.anaconda.org/conda-forge/linux-64/libxcrypt-4.4.36-hd590300_1.conda#5aa797f8787fe7a17d1b0821485b5adc
+https://conda.anaconda.org/conda-forge/linux-64/libzlib-1.2.13-h4ab18f5_6.conda#27329162c0dc732bcf67a4e0cd488125
+https://conda.anaconda.org/conda-forge/linux-64/ncurses-6.5-he02047a_1.conda#70caf8bb6cf39a0b6b7efc885f51c0fe
+https://conda.anaconda.org/conda-forge/linux-64/openssl-3.3.1-hb9d3cd8_3.conda#6c566a46baae794daf34775d41eb180a
+https://conda.anaconda.org/conda-forge/linux-64/xz-5.2.6-h166bdaf_0.tar.bz2#2161070d867d1b1204ea749c8eec4ef0
+https://conda.anaconda.org/bioconda/linux-64/bwa-mem2-2.2.1-hd03093a_5.tar.bz2#a8de1b9c3db53f3436e06f86997b5316
+https://conda.anaconda.org/conda-forge/linux-64/libedit-3.1.20191231-he28a2e2_2.tar.bz2#4d331e44109e3f0e19b4cb8f9b82f3e1
+https://conda.anaconda.org/conda-forge/linux-64/libnghttp2-1.58.0-h47da74e_1.conda#700ac6ea6d53d5510591c4344d5c989a
+https://conda.anaconda.org/conda-forge/linux-64/libsqlite-3.46.0-hde9e2c9_0.conda#18aa975d2094c34aef978060ae7da7d8
+https://conda.anaconda.org/conda-forge/linux-64/libssh2-1.11.0-h0841786_0.conda#1f5a58e686b13bcfde88b93f547d23fe
+https://conda.anaconda.org/conda-forge/linux-64/perl-5.32.1-7_hd590300_perl5.conda#f2cfec9406850991f4e3d960cc9e3321
+https://conda.anaconda.org/conda-forge/linux-64/readline-8.2-h8228510_1.conda#47d31b792659ce70f470b5c82fdfb7a4
+https://conda.anaconda.org/conda-forge/linux-64/tk-8.6.13-noxft_h4845f30_101.conda#d453b98d9c83e71da0741bb0ff4d76bc
+https://conda.anaconda.org/conda-forge/linux-64/zstd-1.5.6-ha6fb4c9_0.conda#4d056880988120e29d75bfff282e0f45
+https://conda.anaconda.org/bioconda/linux-64/bwa-0.7.18-he4a0461_1.tar.bz2#4ecde7d4a03fabe440a90aea1389d62d
+https://conda.anaconda.org/conda-forge/linux-64/krb5-1.21.3-h659f571_0.conda#3f43953b7d3fb3aaa1d0d0723d91e368
+https://conda.anaconda.org/conda-forge/linux-64/python-3.12.3-hab00c5b_0_cpython.conda#2540b74d304f71d3e89c81209db4db84
+https://conda.anaconda.org/conda-forge/linux-64/libcurl-8.8.0-hca28451_1.conda#b8afb3e3cb3423cc445cf611ab95fdb0
+https://conda.anaconda.org/conda-forge/noarch/setuptools-72.2.0-pyhd8ed1ab_0.conda#1462aa8b243aad09ef5d0841c745eb89
+https://conda.anaconda.org/bioconda/noarch/toolshed-0.4.6-pyh864c0ab_3.tar.bz2#61065996a8b60a54d5350427f51a54f3
+https://conda.anaconda.org/conda-forge/noarch/wheel-0.44.0-pyhd8ed1ab_0.conda#d44e3b085abcaef02983c6305b84b584
+https://conda.anaconda.org/bioconda/linux-64/htslib-1.20-h5efdd21_2.tar.bz2#f0923cdb85b44dc77bdead8018645ea9
+https://conda.anaconda.org/conda-forge/noarch/pip-24.2-pyhd8ed1ab_0.conda#6721aef6bfe5937abe70181545dd2c51
+https://conda.anaconda.org/bioconda/linux-64/samtools-1.20-h50ea8bc_1.tar.bz2#1a4c52f8079fea1b18b3e4bd329bab3a
+https://conda.anaconda.org/bioconda/noarch/bwameth-0.2.7-pyh7cba7a3_0.tar.bz2#ab1318507241aab310382b26aaf429e2

bio/bwameth/index/environment.yaml

@@ -0,0 +1,7 @@
+channels:
+  - conda-forge
+  - bioconda
+  - nodefaults
+dependencies:
+  - bwameth =0.2.7
+  - bwa-mem2 =2.2.1

bio/bwameth/index/meta.yaml

@@ -0,0 +1,15 @@
+name: bwa-meth index
+url: https://github.com/brentp/bwa-meth
+description: >
+  Index a reference sequence for future BS-Seq mapping.
+authors:
+  - Thibault Dayris
+input:
+  - Path to reference fasta file.
+output:
+  - List of paths to index files.
+params:
+  No optional argument used, everything is handled by the wrapper.
+notes: >
+  While bwa-meth explicitely writes the index alongside the reference file, this wrapper lets user freely chose the output directory.
+

bio/bwameth/index/test/Snakefile

@@ -0,0 +1,40 @@
+rule test_bwameth_index_mem:
+    input:
+        "genome.fasta",
+    output:
+        multiext(
+            "genome.fasta.bwameth",
+            ".c2t",
+            ".c2t.amb",
+            ".c2t.ann",
+            ".c2t.bwt",
+            ".c2t.pac",
+            ".c2t.sa",
+        ),
+    cache: True  # save space and time with between workflow caching (see docs)
+    threads: 1
+    log:
+        "bwameth_index.log",
+    wrapper:
+        "master/bio/bwameth/index"
+
+
+rule test_bwameth_index_mem2:
+    input:
+        "genome.fasta",
+    output:
+        multiext(
+            "genome.fasta.bwameth",
+            ".c2t",
+            ".c2t.amb",
+            ".c2t.ann",
+            ".c2t.bwt.2bit.64",
+            ".c2t.pac",
+            ".c2t.0123",
+        ),
+    cache: True  # save space and time with between workflow caching (see docs)
+    threads: 1
+    log:
+        "bwameth_index.log",
+    wrapper:
+        "master/bio/bwameth/index"

bio/bwameth/index/test/genome.fasta

@@ -0,0 +1,2 @@
+>Sheila
+GCTAGCTCAGAAAAAAAAAA

bio/bwameth/index/wrapper.py

@@ -0,0 +1,38 @@
+# coding: utf-8
+
+"""Snakemake wrapper for BWA-Meth index"""
+
+__author__ = "Thibault Dayris"
+__mail__ = "[email protected]"
+__copyright__ = "Copyright 2024, Thibault Dayris"
+__license__ = "MIT"
+
+import os
+import os.path
+
+from tempfile import TemporaryDirectory
+from snakemake import shell
+
+log = snakemake.log_fmt_shell(stdout=True, stderr=True, append=True)
+
+# Automatic detection of aligner based on one output file
+subcommand = "index"
+if any(str(outfile).endswith(".0123") for outfile in snakemake.output):
+    subcommand = "index-mem2"
+
+with TemporaryDirectory() as tempdir:
+    # Create symlink to avoid bwa-meth index to be written next to the input reference file
+    ref_basename = os.path.basename(snakemake.input[0])
+    used_reference = os.path.join(tempdir, ref_basename)
+    os.symlink(os.path.abspath(snakemake.input[0]), os.path.join(tempdir, ref_basename))
+
+    # Find user-defined reference directory
+    prefix = os.path.commonprefix(snakemake.output)
+    out_dir = os.path.dirname(prefix) or "./"
+
+    # Run bwameth index command
+    shell("bwameth.py {subcommand} {used_reference} {log}")
+
+    # Return index file to user where they expect them
+    os.unlink(used_reference)
+    shell("mv -v {used_reference}.bwameth.c2t* {out_dir} {log}")

test.py

@@ -488,6 +488,31 @@ def test_sickle_se():
         ],
     )
 
+@skip_if_not_modified
+def test_bwameth_index():
+    run(
+        "bio/bwameth/index",
+        [
+            "snakemake",
+            "--cores",
+            "1",
+            "--use-conda",
+            "-F",
+            "genome.fasta.bwameth.c2t.sa",
+        ],
+    )
+    run(
+        "bio/bwameth/index",
+        [
+            "snakemake",
+            "--cores",
+            "1",
+            "--use-conda",
+            "-F",
+            "genome.fasta.bwameth.c2t.0123",
+        ],
+    )
+
 
 @skip_if_not_modified
 def test_bwa_memx_index():