Merge branch 'master' into sexdeterrmine

bio/vg/giraffe/environment.linux-64.pin.txt

@@ -0,0 +1,86 @@
+# 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/vg-1.60.0-h9ee0642_0.tar.bz2#f66289630d4f712e660657d48b227f06
+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-2024.8.30-hbcca054_0.conda#c27d1c142233b5bc9ca570c6e2e0c244
+https://conda.anaconda.org/conda-forge/noarch/font-ttf-dejavu-sans-mono-2.37-hab24e00_0.tar.bz2#0c96522c6bdaed4b1566d11387caaf45
+https://conda.anaconda.org/conda-forge/noarch/font-ttf-inconsolata-3.000-h77eed37_0.tar.bz2#34893075a5c9e55cdafac56607368fc6
+https://conda.anaconda.org/conda-forge/noarch/font-ttf-source-code-pro-2.038-h77eed37_0.tar.bz2#4d59c254e01d9cde7957100457e2d5fb
+https://conda.anaconda.org/conda-forge/noarch/font-ttf-ubuntu-0.83-h77eed37_3.conda#49023d73832ef61042f6a237cb2687e7
+https://conda.anaconda.org/conda-forge/linux-64/ld_impl_linux-64-2.43-h712a8e2_2.conda#048b02e3962f066da18efe3a21b77672
+https://conda.anaconda.org/conda-forge/linux-64/python_abi-3.13-5_cp313.conda#381bbd2a92c863f640a55b6ff3c35161
+https://conda.anaconda.org/conda-forge/noarch/tzdata-2024b-hc8b5060_0.conda#8ac3367aafb1cc0a068483c580af8015
+https://conda.anaconda.org/conda-forge/noarch/fonts-conda-forge-1-0.tar.bz2#f766549260d6815b0c52253f1fb1bb29
+https://conda.anaconda.org/conda-forge/linux-64/libgomp-14.2.0-h77fa898_1.conda#cc3573974587f12dda90d96e3e55a702
+https://conda.anaconda.org/conda-forge/linux-64/_openmp_mutex-4.5-2_gnu.tar.bz2#73aaf86a425cc6e73fcf236a5a46396d
+https://conda.anaconda.org/conda-forge/noarch/fonts-conda-ecosystem-1-0.tar.bz2#fee5683a3f04bd15cbd8318b096a27ab
+https://conda.anaconda.org/conda-forge/linux-64/libgcc-14.2.0-h77fa898_1.conda#3cb76c3f10d3bc7f1105b2fc9db984df
+https://conda.anaconda.org/conda-forge/linux-64/c-ares-1.34.2-heb4867d_0.conda#2b780c0338fc0ffa678ac82c54af51fd
+https://conda.anaconda.org/conda-forge/linux-64/libexpat-2.6.3-h5888daf_0.conda#59f4c43bb1b5ef1c71946ff2cbf59524
+https://conda.anaconda.org/conda-forge/linux-64/libgcc-ng-14.2.0-h69a702a_1.conda#e39480b9ca41323497b05492a63bc35b
+https://conda.anaconda.org/conda-forge/linux-64/libstdcxx-14.2.0-hc0a3c3a_1.conda#234a5554c53625688d51062645337328
+https://conda.anaconda.org/conda-forge/linux-64/libzlib-1.3.1-hb9d3cd8_2.conda#edb0dca6bc32e4f4789199455a1dbeb8
+https://conda.anaconda.org/conda-forge/linux-64/openssl-3.3.2-hb9d3cd8_0.conda#4d638782050ab6faa27275bed57e9b4e
+https://conda.anaconda.org/conda-forge/linux-64/pthread-stubs-0.4-hb9d3cd8_1002.conda#b3c17d95b5a10c6e64a21fa17573e70e
+https://conda.anaconda.org/conda-forge/linux-64/xorg-libice-1.1.1-hb9d3cd8_1.conda#19608a9656912805b2b9a2f6bd257b04
+https://conda.anaconda.org/conda-forge/linux-64/xorg-libxau-1.0.11-hb9d3cd8_1.conda#77cbc488235ebbaab2b6e912d3934bae
+https://conda.anaconda.org/conda-forge/linux-64/xorg-libxdmcp-1.1.5-hb9d3cd8_0.conda#8035c64cb77ed555e3f150b7b3972480
+https://conda.anaconda.org/conda-forge/linux-64/xorg-xorgproto-2024.1-hb9d3cd8_1.conda#7c21106b851ec72c037b162c216d8f05
+https://conda.anaconda.org/conda-forge/linux-64/alsa-lib-1.2.12-h4ab18f5_0.conda#7ed427f0871fd41cb1d9c17727c17589
+https://conda.anaconda.org/conda-forge/linux-64/bzip2-1.0.8-h4bc722e_7.conda#62ee74e96c5ebb0af99386de58cf9553
+https://conda.anaconda.org/conda-forge/linux-64/giflib-5.2.2-hd590300_0.conda#3bf7b9fd5a7136126e0234db4b87c8b6
+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/libffi-3.4.2-h7f98852_5.tar.bz2#d645c6d2ac96843a2bfaccd2d62b3ac3
+https://conda.anaconda.org/conda-forge/linux-64/libiconv-1.17-hd590300_2.conda#d66573916ffcf376178462f1b61c941e
+https://conda.anaconda.org/conda-forge/linux-64/libjpeg-turbo-3.0.0-hd590300_1.conda#ea25936bb4080d843790b586850f82b8
+https://conda.anaconda.org/conda-forge/linux-64/libmpdec-4.0.0-h4bc722e_0.conda#aeb98fdeb2e8f25d43ef71fbacbeec80
+https://conda.anaconda.org/conda-forge/linux-64/libpng-1.6.44-hadc24fc_0.conda#f4cc49d7aa68316213e4b12be35308d1
+https://conda.anaconda.org/conda-forge/linux-64/libsqlite-3.47.0-hadc24fc_1.conda#b6f02b52a174e612e89548f4663ce56a
+https://conda.anaconda.org/conda-forge/linux-64/libssh2-1.11.0-h0841786_0.conda#1f5a58e686b13bcfde88b93f547d23fe
+https://conda.anaconda.org/conda-forge/linux-64/libstdcxx-ng-14.2.0-h4852527_1.conda#8371ac6457591af2cf6159439c1fd051
+https://conda.anaconda.org/conda-forge/linux-64/libuuid-2.38.1-h0b41bf4_0.conda#40b61aab5c7ba9ff276c41cfffe6b80b
+https://conda.anaconda.org/conda-forge/linux-64/libwebp-base-1.4.0-hd590300_0.conda#b26e8aa824079e1be0294e7152ca4559
+https://conda.anaconda.org/conda-forge/linux-64/libxcb-1.17.0-h8a09558_0.conda#92ed62436b625154323d40d5f2f11dd7
+https://conda.anaconda.org/conda-forge/linux-64/ncurses-6.5-he02047a_1.conda#70caf8bb6cf39a0b6b7efc885f51c0fe
+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/xz-5.2.6-h166bdaf_0.tar.bz2#2161070d867d1b1204ea749c8eec4ef0
+https://conda.anaconda.org/conda-forge/linux-64/zlib-1.3.1-hb9d3cd8_2.conda#c9f075ab2f33b3bbee9e62d4ad0a6cd8
+https://conda.anaconda.org/conda-forge/linux-64/freetype-2.12.1-h267a509_2.conda#9ae35c3d96db2c94ce0cef86efdfa2cb
+https://conda.anaconda.org/conda-forge/linux-64/graphite2-1.3.13-h59595ed_1003.conda#f87c7b7c2cb45f323ffbce941c78ab7c
+https://conda.anaconda.org/conda-forge/linux-64/icu-75.1-he02047a_0.conda#8b189310083baabfb622af68fd9d3ae3
+https://conda.anaconda.org/conda-forge/linux-64/lerc-4.0.0-h27087fc_0.tar.bz2#76bbff344f0134279f225174e9064c8f
+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/libnghttp2-1.64.0-h161d5f1_0.conda#19e57602824042dfd0446292ef90488b
+https://conda.anaconda.org/conda-forge/linux-64/pcre2-10.44-hba22ea6_2.conda#df359c09c41cd186fffb93a2d87aa6f5
+https://conda.anaconda.org/conda-forge/linux-64/pixman-0.43.2-h59595ed_0.conda#71004cbf7924e19c02746ccde9fd7123
+https://conda.anaconda.org/conda-forge/linux-64/readline-8.2-h8228510_1.conda#47d31b792659ce70f470b5c82fdfb7a4
+https://conda.anaconda.org/conda-forge/linux-64/xorg-libsm-1.2.4-he73a12e_1.conda#05a8ea5f446de33006171a7afe6ae857
+https://conda.anaconda.org/conda-forge/linux-64/xorg-libx11-1.8.10-h4f16b4b_0.conda#0b666058a179b744a622d0a4a0c56353
+https://conda.anaconda.org/conda-forge/linux-64/zstd-1.5.6-ha6fb4c9_0.conda#4d056880988120e29d75bfff282e0f45
+https://conda.anaconda.org/conda-forge/linux-64/fontconfig-2.15.0-h7e30c49_1.conda#8f5b0b297b59e1ac160ad4beec99dbee
+https://conda.anaconda.org/conda-forge/linux-64/krb5-1.21.3-h659f571_0.conda#3f43953b7d3fb3aaa1d0d0723d91e368
+https://conda.anaconda.org/conda-forge/linux-64/libglib-2.82.2-h2ff4ddf_0.conda#13e8e54035ddd2b91875ba399f0f7c04
+https://conda.anaconda.org/conda-forge/linux-64/libtiff-4.7.0-h6565414_0.conda#80eaf80d84668fa5620ac9ec1b4bf56f
+https://conda.anaconda.org/conda-forge/linux-64/python-3.13.0-h9ebbce0_100_cp313.conda#08e9aef080f33daeb192b2ddc7e4721f
+https://conda.anaconda.org/conda-forge/linux-64/xorg-libxext-1.3.6-hb9d3cd8_0.conda#febbab7d15033c913d53c7a2c102309d
+https://conda.anaconda.org/conda-forge/linux-64/xorg-libxfixes-6.0.1-hb9d3cd8_0.conda#4bdb303603e9821baf5fe5fdff1dc8f8
+https://conda.anaconda.org/conda-forge/linux-64/xorg-libxrender-0.9.11-hb9d3cd8_1.conda#a7a49a8b85122b49214798321e2e96b4
+https://conda.anaconda.org/conda-forge/linux-64/xorg-libxt-1.3.0-hb9d3cd8_2.conda#d8602724ac0d276c380b97e9eb0f814b
+https://conda.anaconda.org/conda-forge/linux-64/cairo-1.18.0-hebfffa5_3.conda#fceaedf1cdbcb02df9699a0d9b005292
+https://conda.anaconda.org/conda-forge/linux-64/lcms2-2.16-hb7c19ff_0.conda#51bb7010fc86f70eee639b4bb7a894f5
+https://conda.anaconda.org/conda-forge/linux-64/libcups-2.3.3-h4637d8d_4.conda#d4529f4dff3057982a7617c7ac58fde3
+https://conda.anaconda.org/conda-forge/linux-64/libcurl-8.10.1-hbbe4b11_0.conda#6e801c50a40301f6978c53976917b277
+https://conda.anaconda.org/conda-forge/noarch/pip-24.3.1-pyh145f28c_0.conda#ca3afe2d7b893a8c8cdf489d30a2b1a3
+https://conda.anaconda.org/bioconda/noarch/snakemake-wrapper-utils-0.6.2-pyhdfd78af_0.tar.bz2#fd8759bbd04116eace828c4fab906096
+https://conda.anaconda.org/conda-forge/linux-64/xorg-libxi-1.8.2-hb9d3cd8_0.conda#17dcc85db3c7886650b8908b183d6876
+https://conda.anaconda.org/conda-forge/linux-64/harfbuzz-9.0.0-hda332d3_1.conda#76b32dcf243444aea9c6b804bcfa40b8
+https://conda.anaconda.org/bioconda/linux-64/htslib-1.21-h5efdd21_0.tar.bz2#06b995dc2244c024b45bbb3e53ae2f27
+https://conda.anaconda.org/conda-forge/linux-64/xorg-libxtst-1.2.5-hb9d3cd8_3.conda#7bbe9a0cc0df0ac5f5a8ad6d6a11af2f
+https://conda.anaconda.org/conda-forge/linux-64/openjdk-22.0.1-h8651b0f_1.conda#672153e7c3d4f70bc65993f3ee513768
+https://conda.anaconda.org/bioconda/linux-64/samtools-1.21-h50ea8bc_0.tar.bz2#4a7fe11223f61cb2d950ed54e20c12ce
+https://conda.anaconda.org/bioconda/noarch/fgbio-minimal-2.3.0-hdfd78af_0.tar.bz2#48e39a611203a971c32302c8d0151432
+https://conda.anaconda.org/bioconda/noarch/picard-slim-3.2.0-hdfd78af_0.tar.bz2#b96f183b2167c69b4784ef921bef19ab

bio/vg/giraffe/environment.yaml

@@ -0,0 +1,10 @@
+channels:
+  - conda-forge
+  - bioconda
+  - nodefaults
+dependencies:
+  - vg =1.60
+  - fgbio-minimal =2.3.0
+  - samtools =1.21
+  - picard-slim =3.2.0
+  - snakemake-wrapper-utils =0.6.2

bio/vg/giraffe/meta.yaml

@@ -0,0 +1,16 @@
+name: "vg giraffe"
+description: Map reads using vg giraffe, with optional sorting using
+  samtools or picard.
+url: https://github.com/vgteam/vg
+authors:
+  - Felix Mölder
+input:
+  - FASTQ file(s)
+  - reference graph
+output:
+  - BAM/SAM or CRAM file
+notes: |
+  * The `extra` param allows for additional arguments for vg giraffe.
+  * The `sort_order` params allows sorting by `queryname` or `coordinate`
+  * The `sorting` param allows to enable sorting, and can be either 'none', 'samtools', 'fgbio' or 'picard'.
+  * The `sort_extra` allows for extra arguments for samtools/picard

bio/vg/giraffe/test/Snakefile

@@ -0,0 +1,30 @@
+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")
+    output:
+        "mapped/{sample}.bam",
+    log:
+        "logs/vg_giraffe/{sample}.log",
+    params:
+        extra="",
+        sorting="none",  # Can be 'none', 'samtools' or 'picard'.
+        sort_order="queryname",  # Can be 'queryname' or 'coordinate'.
+        sort_extra="",  # Extra args for samtools/picard.
+    threads: 8
+    wrapper:
+        "master/bio/vg/giraffe"

bio/vg/giraffe/test/genome.fasta

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

bio/vg/giraffe/test/reads/a.1.fastq

@@ -0,0 +1,4 @@
+@1
+ACGGCAT
++
+!!!!!!!

bio/vg/giraffe/test/reads/a.2.fastq

@@ -0,0 +1,4 @@
+@1
+ACGGCAT
++
+!!!!!!!

bio/vg/giraffe/wrapper.py

@@ -0,0 +1,81 @@
+__author__ = "Felix Mölder"
+__copyright__ = "Copyright 2024, Felix Mölder"
+__email__ = "felix.moelder@uk-essen.de"
+__license__ = "MIT"
+
+
+import tempfile
+from os import path
+from snakemake.shell import shell
+from snakemake_wrapper_utils.java import get_java_opts
+from snakemake_wrapper_utils.samtools import get_samtools_opts
+
+
+# Extract arguments.
+extra = snakemake.params.get("extra", "")
+log = snakemake.log_fmt_shell(stdout=False, stderr=True)
+sort = snakemake.params.get("sorting", "none")
+sort_order = snakemake.params.get("sort_order", "coordinate")
+sort_extra = snakemake.params.get("sort_extra", "")
+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,
+    2,
+}:
+    raise ValueError("input must have 1 (single-end) or 2 (paired-end) elements")
+
+reads = (
+    snakemake.input.reads
+    if isinstance(snakemake.input.reads, str)
+    else " -f ".join(snakemake.input.reads)
+)
+
+if sort_order not in {"coordinate", "queryname"}:
+    raise ValueError("Unexpected value for sort_order ({})".format(sort_order))
+
+
+# Determine which pipe command to use for converting to bam or sorting.
+if sort == "none":
+    # Simply convert to bam using samtools view.
+    pipe_cmd = "samtools view {samtools_opts}"
+elif sort == "samtools":
+    # Add name flag if needed.
+    if sort_order == "queryname":
+        sort_extra += " -n"
+    # Sort alignments using samtools sort.
+    pipe_cmd = "samtools sort {samtools_opts} {sort_extra} -T {tmpdir}"
+elif sort == "fgbio":
+    if sort_order == "queryname":
+        sort_extra += " -s Queryname"
+    pipe_cmd = "fgbio SortBam -i /dev/stdin -o {snakemake.output[0]} {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]}"
+else:
+    raise ValueError(f"Unexpected value for params.sort ({sort})")
+
+
+with tempfile.TemporaryDirectory() as tmpdir:
+    shell(
+        "(vg giraffe"
+        " -t {snakemake.threads}"
+        " {input_cmd}"
+        " -f {reads}"
+        " --output-format BAM"
+        " {extra}"
+        " | " + pipe_cmd + ") {log}"
+    )

test_wrappers.py

@@ -5971,6 +5971,11 @@ def test_vg_construct(run):
         ["snakemake", "--cores", "1", "graph/c.vg", "--use-conda", "-F"],
     )
 
+def test_vg_giraffe(run):
+    run(
+        "bio/vg/giraffe",
+        ["snakemake", "--cores", "1", "mapped/a.bam", "--use-conda", "-F"],
+    )
 
 def test_vg_merge(run):
     run(