feat: refactor vg giraffe (#3644)

<!-- 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
-->

Refactored the wrapper to be able to work with haplotype sampled
pangenome graphs.

### 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**
- Updated output file naming and bundling for genome resources, offering
clearer organization of results.
- Enhanced command construction for processing with new input parameters
for haplotypes and kmer counts.

- **Refactor**
- Streamlined processing by adjusting how optional mapping parameters
are handled and enhancing command construction.

- **Chores**
	- Removed an obsolete genomic sequence entry from the reference data.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

bio/vg/giraffe/test/Snakefile

@@ -1,23 +1,17 @@
-rule vg_autoindex:  # [hide]
-    input:  # [hide]
-        ref="{genome}.fasta",  # [hide]
-    output:  # [hide]
-        multiext("resources/{genome}", ".dist", ".min", ".giraffe.gbz"),  # [hide]
-    log:  # [hide]
-        "logs/vg_autoindex/{genome}.log",  # [hide]
-    params:  # [hide]
-        extra="",  # [hide]
-    threads: 8  # [hide]
-    wrapper:  # [hide]
-        "master/bio/vg/autoindex"  # [hide]
-
-
 rule vg_giraffe_map:
     input:
         reads=["reads/{sample}.1.fastq", "reads/{sample}.2.fastq"],
-        index=multiext("resources/genome", ".dist", ".min", ".giraffe.gbz")
+        graph="resources/{sample}.gbz",
+        #kmers="resources/{sample}.kff", # optional: kmer counts
+        #hapl="resources/{genome}.hapl", # optional: haplotype index
     output:
-        "mapped/{sample}.bam",
+        bam="mapped/{sample}.bam",
+        indexes=multiext(
+            "resources/{sample}",
+            ".dist",
+            ".shortread.withzip.min",
+            ".shortread.zipcodes",
+        ),
     log:
         "logs/vg_giraffe/{sample}.log",
     params:

bio/vg/giraffe/wrapper.py

@@ -20,17 +20,6 @@
 samtools_opts = get_samtools_opts(snakemake, param_name="sort_extra")
 java_opts = get_java_opts(snakemake)
 
-
-expected_files = {".dist": "-d", ".min": "-m", ".giraffe.gbz": "-Z"}
-
-input_cmd = ""
-for ext, param in expected_files.items():
-    matching_files = [file for file in snakemake.input.index if file.endswith(ext)]
-    if not matching_files:
-        raise ValueError(f"Missing required file with extension: {ext}")
-    input_cmd += f" {param} {matching_files[0]}"
-
-
 # Check inputs/arguments.
 if not isinstance(snakemake.input.reads, str) and len(snakemake.input.reads) not in {
     1,
@@ -44,6 +33,12 @@
     else " -f ".join(snakemake.input.reads)
 )
 
+input_cmd = ""
+if snakemake.input.get("hapl", ""):
+    input_cmd += f" --haplotype-name {snakemake.input.hapl}"
+if snakemake.input.get("kmers", ""):
+    input_cmd += f" --kff-name {snakemake.input.kmers}"
+
 if sort_order not in {"coordinate", "queryname"}:
     raise ValueError("Unexpected value for sort_order ({})".format(sort_order))
 
@@ -61,7 +56,7 @@
 elif sort == "fgbio":
     if sort_order == "queryname":
         sort_extra += " -s Queryname"
-    pipe_cmd = "fgbio SortBam -i /dev/stdin -o {snakemake.output[0]} {sort_extra}"
+    pipe_cmd = "fgbio SortBam -i /dev/stdin -o {snakemake.output.bam} {sort_extra}"
 elif sort == "picard":
     # Sort alignments using picard SortSam.
     pipe_cmd = "picard SortSam {java_opts} {sort_extra} --INPUT /dev/stdin --TMP_DIR {tmpdir} --SORT_ORDER {sort_order} --OUTPUT {snakemake.output[0]}"
@@ -71,8 +66,9 @@
 
 with tempfile.TemporaryDirectory() as tmpdir:
     shell(
-        "(vg giraffe"
+        "(vg giraffe -p "
         " -t {snakemake.threads}"
+        " -Z {snakemake.input.graph}"
         " {input_cmd}"
         " -f {reads}"
         " --output-format BAM"