Snakemake workflow: dna-seq-gatk-variant-calling

public public 1yr ago Version: 2 0 bookmarks

This Snakemake pipeline implements the GATK best-practices workflow for calling small germline variants.

Authors

  • Johannes Köster (https://koesterlab.github.io)

Usage

In any case, if you use this workflow in a paper, don't forget to give credits to the authors by citing the URL of this (original) repository and, if available, its DOI (see above).

Step 1: Obtain a copy of this workflow

  1. Create a new github repository using this workflow as a template .

  2. Clone the newly created repository to your local system, into the place where you want to perform the data analysis.

Step 2: Configure workflow

Configure the workflow according to your needs via editing the files config.yaml , samples.tsv and units.tsv .

Step 3: Execute workflow

This workflow will automatically download reference genomes and annotation. In order to save time and space, consider to use between workflow caching by adding the flag --cache to any of the commands below. The workflow already defines which rules are eligible for caching, so no further arguments are required. When caching is enabled, Snakemake will automatically share those steps between different instances of this workflow.

Test your configuration by performing a dry-run via

snakemake --use-conda -n

Execute the workflow locally via

snakemake --use-conda --cores $N

using $N cores or run it in a cluster environment via

snakemake --use-conda --cluster qsub --jobs 100

or

snakemake --use-conda --drmaa --jobs 100

If you not only want to fix the software stack but also the underlying OS, use

snakemake --use-conda --use-singularity

in combination with any of the modes above.

See the Snakemake documentation for further details (e.g. cloud execution).

Step 4: Investigate results

After successful execution, you can create a self-contained interactive HTML report with all results via:

snakemake --report report.html

This report can, e.g., be forwarded to your collaborators. An example (using some trivial test data) can be seen here .

Step 5: Commit changes

Whenever you change something, don't forget to commit the changes back to your github copy of the repository:

git commit -a
git push

Step 6: Obtain updates from upstream

Whenever you want to synchronize your workflow copy with new developments from upstream, do the following.

  1. Once, register the upstream repository in your local copy: git remote add -f upstream [email protected]:snakemake-workflows/dna-seq-gatk-variant-calling.git or git remote add -f upstream https://github.com/snakemake-workflows/dna-seq-gatk-variant-calling.git if you do not have setup ssh keys.

  2. Update the upstream version: git fetch upstream .

  3. Create a diff with the current version: git diff HEAD upstream/master rules scripts envs schemas report > upstream-changes.diff .

  4. Investigate the changes: vim upstream-changes.diff .

  5. Apply the modified diff via: git apply upstream-changes.diff .

  6. Carefully check whether you need to update the config files: git diff HEAD upstream/master config.yaml samples.tsv units.tsv . If so, do it manually, and only where necessary, since you would otherwise likely overwrite your settings and samples.

Step 7: Contribute back

In case you have also changed or added steps, please consider contributing them back to the original repository:

  1. Fork the original repo to a personal or lab account.

  2. Clone the fork to your local system, to a different place than where you ran your analysis.

  3. Copy the modified files from your analysis to the clone of your fork, e.g., cp -r workflow path/to/fork . Make sure to not accidentally copy config file contents or sample sheets. Instead, manually update the example config files if necessary.

  4. Commit and push your changes to your fork.

  5. Create a pull request against the original repository.

Testing

Test cases are in the subfolder .test . They are automtically executed via continuous integration with Github actions.

Code Snippets

17
18
wrapper:
    "0.59.2/bio/vep/annotate"
 9
10
shell:
    "bedextract {wildcards.contig} {input} > {output}"
27
28
wrapper:
    "0.59.0/bio/gatk/haplotypecaller"
39
40
wrapper:
    "0.59.2/bio/gatk/combinegvcfs"
53
54
wrapper:
    "0.59.2/bio/gatk/genotypegvcfs"
64
65
wrapper:
    "0.59.2/bio/picard/mergevcfs"
16
17
wrapper:
    "0.59.0/bio/gatk/selectvariants"
36
37
wrapper:
    "0.59.2/bio/gatk/variantfiltration"
49
50
wrapper:
    "0.59.2/bio/gatk/variantrecalibrator"
64
65
wrapper:
    "0.59.2/bio/picard/mergevcfs"
11
12
wrapper:
    "0.59.2/bio/trimmomatic/se"
29
30
wrapper:
    "0.59.2/bio/trimmomatic/pe"
47
48
wrapper:
    "0.59.2/bio/bwa/mem"
61
62
wrapper:
    "0.59.2/bio/picard/markduplicates"
79
80
wrapper:
    "0.59.2/bio/gatk/baserecalibrator"
88
89
wrapper:
    "0.59.2/bio/samtools/index"
7
8
wrapper:
    "0.59.2/bio/fastqc"
18
19
wrapper:
    "0.59.2/bio/samtools/stats"
SnakeMake From line 18 of rules/qc.smk
32
33
wrapper:
    "0.59.2/bio/multiqc"
12
13
wrapper:
    "0.59.2/bio/reference/ensembl-sequence"
SnakeMake From line 12 of rules/ref.smk
24
25
wrapper:
    "0.59.2/bio/samtools/faidx"
SnakeMake From line 24 of rules/ref.smk
38
39
shell:
    "samtools dict {input} > {output} 2> {log} "
56
57
wrapper:
    "0.59.2/bio/reference/ensembl-variation"
SnakeMake From line 56 of rules/ref.smk
70
71
shell:
    "rbt vcf-fix-iupac-alleles < {input} | bcftools view -Oz > {output}"
84
85
wrapper:
    "0.59.2/bio/tabix"
98
99
wrapper:
    "0.59.2/bio/bwa/index"
SnakeMake From line 98 of rules/ref.smk
111
112
wrapper:
    "0.59.2/bio/vep/cache"
SnakeMake From line 111 of rules/ref.smk
120
121
wrapper:
    "0.59.2/bio/vep/plugins"
SnakeMake From line 120 of rules/ref.smk
 8
 9
10
11
shell:
    "bcftools view --apply-filters PASS --output-type u {input} | "
    "rbt vcf-to-txt -g --fmt DP AD --info ANN | "
    "gzip > {output}"
22
23
script:
    "../scripts/plot-depths.py"
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
import common
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import seaborn as sns

calls = pd.read_table(snakemake.input[0], header=[0, 1])
samples = [name for name in calls.columns.levels[0] if name != "VARIANT"]
sample_info = calls.loc[:, samples].stack([0, 1]).unstack().reset_index(1, drop=False)
sample_info = sample_info.rename({"level_1": "sample"}, axis=1)

sample_info = sample_info[sample_info["DP"] > 0]
sample_info["freq"] = sample_info["AD"] / sample_info["DP"]
sample_info.index = np.arange(sample_info.shape[0])

plt.figure()

sns.stripplot(x="sample", y="freq", data=sample_info, jitter=True)
plt.ylabel("allele frequency")
plt.xticks(rotation="vertical")

plt.savefig(snakemake.output.freqs)

plt.figure()

sns.stripplot(x="sample", y="DP", data=sample_info, jitter=True)
plt.ylabel("read depth")
plt.xticks(rotation="vertical")

plt.savefig(snakemake.output.depths)
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
__author__ = "Johannes Köster"
__copyright__ = "Copyright 2018, Johannes Köster"
__email__ = "[email protected]"
__license__ = "MIT"


import os

from snakemake.shell import shell

known = snakemake.input.get("known", "")
if known:
    known = "--dbsnp " + known

extra = snakemake.params.get("extra", "")
java_opts = snakemake.params.get("java_opts", "")
bams = snakemake.input.bam
if isinstance(bams, str):
    bams = [bams]
bams = list(map("-I {}".format, bams))

log = snakemake.log_fmt_shell(stdout=True, stderr=True)
shell(
    "gatk --java-options '{java_opts}' HaplotypeCaller {extra} "
    "-R {snakemake.input.ref} {bams} "
    "-ERC GVCF "
    "-O {snakemake.output.gvcf} {known} {log}"
)
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
__author__ = "Johannes Köster"
__copyright__ = "Copyright 2018, Johannes Köster"
__email__ = "[email protected]"
__license__ = "MIT"


from snakemake.shell import shell

extra = snakemake.params.get("extra", "")
java_opts = snakemake.params.get("java_opts", "")

log = snakemake.log_fmt_shell(stdout=True, stderr=True)
shell(
    "gatk --java-options '{java_opts}' SelectVariants -R {snakemake.input.ref} -V {snakemake.input.vcf} "
    "{extra} -O {snakemake.output.vcf} {log}"
)
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
__author__ = "Patrik Smeds"
__copyright__ = "Copyright 2016, Patrik Smeds"
__email__ = "[email protected]"
__license__ = "MIT"

from os import path

from snakemake.shell import shell

log = snakemake.log_fmt_shell(stdout=False, stderr=True)

# Check inputs/arguments.
if len(snakemake.input) == 0:
    raise ValueError("A reference genome has to be provided!")
elif len(snakemake.input) > 1:
    raise ValueError("Only one reference genome can be inputed!")

# Prefix that should be used for the database
prefix = snakemake.params.get("prefix", "")

if len(prefix) > 0:
    prefix = "-p " + prefix

# Contrunction algorithm that will be used to build the database, default is bwtsw
construction_algorithm = snakemake.params.get("algorithm", "")

if len(construction_algorithm) != 0:
    construction_algorithm = "-a " + construction_algorithm

shell(
    "bwa index" " {prefix}" " {construction_algorithm}" " {snakemake.input[0]}" " {log}"
)
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
__author__ = "Johannes Köster, Julian de Ruiter"
__copyright__ = "Copyright 2016, Johannes Köster and Julian de Ruiter"
__email__ = "[email protected], [email protected]"
__license__ = "MIT"


from os import path

from snakemake.shell import shell


# Extract arguments.
extra = snakemake.params.get("extra", "")

sort = snakemake.params.get("sort", "none")
sort_order = snakemake.params.get("sort_order", "coordinate")
sort_extra = snakemake.params.get("sort_extra", "")

log = snakemake.log_fmt_shell(stdout=False, stderr=True)

# 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")

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 -Sbh -o {snakemake.output[0]} -"

elif sort == "samtools":

    # Sort alignments using samtools sort.
    pipe_cmd = "samtools sort {sort_extra} -o {snakemake.output[0]} -"

    # Add name flag if needed.
    if sort_order == "queryname":
        sort_extra += " -n"

    prefix = path.splitext(snakemake.output[0])[0]
    sort_extra += " -T " + prefix + ".tmp"

elif sort == "picard":

    # Sort alignments using picard SortSam.
    pipe_cmd = (
        "picard SortSam {sort_extra} INPUT=/dev/stdin"
        " OUTPUT={snakemake.output[0]} SORT_ORDER={sort_order}"
    )

else:
    raise ValueError("Unexpected value for params.sort ({})".format(sort))

shell(
    "(bwa mem"
    " -t {snakemake.threads}"
    " {extra}"
    " {snakemake.params.index}"
    " {snakemake.input.reads}"
    " | " + pipe_cmd + ") {log}"
)
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
__author__ = "Julian de Ruiter"
__copyright__ = "Copyright 2017, Julian de Ruiter"
__email__ = "[email protected]"
__license__ = "MIT"


from os import path
from tempfile import TemporaryDirectory

from snakemake.shell import shell

log = snakemake.log_fmt_shell(stdout=False, stderr=True)


def basename_without_ext(file_path):
    """Returns basename of file path, without the file extension."""

    base = path.basename(file_path)

    split_ind = 2 if base.endswith(".fastq.gz") else 1
    base = ".".join(base.split(".")[:-split_ind])

    return base


# Run fastqc, since there can be race conditions if multiple jobs
# use the same fastqc dir, we create a temp dir.
with TemporaryDirectory() as tempdir:
    shell(
        "fastqc {snakemake.params} --quiet "
        "--outdir {tempdir} {snakemake.input[0]}"
        " {log}"
    )

    # Move outputs into proper position.
    output_base = basename_without_ext(snakemake.input[0])
    html_path = path.join(tempdir, output_base + "_fastqc.html")
    zip_path = path.join(tempdir, output_base + "_fastqc.zip")

    if snakemake.output.html != html_path:
        shell("mv {html_path} {snakemake.output.html}")

    if snakemake.output.zip != zip_path:
        shell("mv {zip_path} {snakemake.output.zip}")
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
__author__ = "Johannes Köster"
__copyright__ = "Copyright 2018, Johannes Köster"
__email__ = "[email protected]"
__license__ = "MIT"


from tempfile import TemporaryDirectory
import os

from snakemake.shell import shell

extra = snakemake.params.get("extra", "")
java_opts = snakemake.params.get("java_opts", "")

with TemporaryDirectory() as tmpdir:
    recal_table = os.path.join(tmpdir, "recal_table.grp")
    log = snakemake.log_fmt_shell(stdout=True, stderr=True)
    known = snakemake.input.get("known", "")
    if known:
        known = "--known-sites {}".format(known)

    shell(
        "gatk --java-options '{java_opts}' BaseRecalibrator {extra} "
        "-R {snakemake.input.ref} -I {snakemake.input.bam} "
        "-O {recal_table} {known} {log}"
    )

    log = snakemake.log_fmt_shell(stdout=True, stderr=True, append=True)
    shell(
        "gatk --java-options '{java_opts}' ApplyBQSR -R {snakemake.input.ref} -I {snakemake.input.bam} "
        "--bqsr-recal-file {recal_table} "
        "-O {snakemake.output.bam} {log}"
    )
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
__author__ = "Johannes Köster"
__copyright__ = "Copyright 2018, Johannes Köster"
__email__ = "[email protected]"
__license__ = "MIT"


import os

from snakemake.shell import shell


extra = snakemake.params.get("extra", "")
java_opts = snakemake.params.get("java_opts", "")
gvcfs = list(map("-V {}".format, snakemake.input.gvcfs))

log = snakemake.log_fmt_shell(stdout=True, stderr=True)
shell(
    "gatk --java-options '{java_opts}' CombineGVCFs {extra} "
    "{gvcfs} "
    "-R {snakemake.input.ref} "
    "-O {snakemake.output.gvcf} {log}"
)
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
__author__ = "Johannes Köster"
__copyright__ = "Copyright 2018, Johannes Köster"
__email__ = "[email protected]"
__license__ = "MIT"


import os

from snakemake.shell import shell


extra = snakemake.params.get("extra", "")
java_opts = snakemake.params.get("java_opts", "")

log = snakemake.log_fmt_shell(stdout=True, stderr=True)
shell(
    "gatk --java-options '{java_opts}' GenotypeGVCFs {extra} "
    "-V {snakemake.input.gvcf} "
    "-R {snakemake.input.ref} "
    "-O {snakemake.output.vcf} {log}"
)
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
__author__ = "Johannes Köster"
__copyright__ = "Copyright 2018, Johannes Köster"
__email__ = "[email protected]"
__license__ = "MIT"


from snakemake.shell import shell

extra = snakemake.params.get("extra", "")
java_opts = snakemake.params.get("java_opts", "")
filters = [
    "--filter-name {} --filter-expression '{}'".format(name, expr.replace("'", "\\'"))
    for name, expr in snakemake.params.filters.items()
]

log = snakemake.log_fmt_shell(stdout=True, stderr=True)
shell(
    "gatk --java-options '{java_opts}' VariantFiltration -R {snakemake.input.ref} -V {snakemake.input.vcf} "
    "{extra} {filters} -O {snakemake.output.vcf} {log}"
)
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
__author__ = "Johannes Köster"
__copyright__ = "Copyright 2018, Johannes Köster"
__email__ = "[email protected]"
__license__ = "MIT"


import os

from snakemake.shell import shell


extra = snakemake.params.get("extra", "")
java_opts = snakemake.params.get("java_opts", "")


def fmt_res(resname, resparams):
    fmt_bool = lambda b: str(b).lower()
    try:
        f = snakemake.input.get(resname)
    except KeyError:
        raise RuntimeError(
            "There must be a named input file for every resource (missing: {})".format(
                resname
            )
        )
    return "{},known={},training={},truth={},prior={}:{}".format(
        resname,
        fmt_bool(resparams["known"]),
        fmt_bool(resparams["training"]),
        fmt_bool(resparams["truth"]),
        resparams["prior"],
        f,
    )


resources = [
    "--resource {}".format(fmt_res(resname, resparams))
    for resname, resparams in snakemake.params["resources"].items()
]
annotation = list(map("-an {}".format, snakemake.params.annotation))
tranches = ""
if snakemake.output.tranches:
    tranches = "--tranches-file " + snakemake.output.tranches

log = snakemake.log_fmt_shell(stdout=True, stderr=True)
shell(
    "gatk --java-options '{java_opts}' VariantRecalibrator {extra} {resources} "
    "-R {snakemake.input.ref} -V {snakemake.input.vcf} "
    "-mode {snakemake.params.mode} "
    "--output {snakemake.output.vcf} "
    "{tranches} {annotation} {log}"
)
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
__author__ = "Julian de Ruiter"
__copyright__ = "Copyright 2017, Julian de Ruiter"
__email__ = "[email protected]"
__license__ = "MIT"


from os import path

from snakemake.shell import shell


input_dirs = set(path.dirname(fp) for fp in snakemake.input)
output_dir = path.dirname(snakemake.output[0])
output_name = path.basename(snakemake.output[0])
log = snakemake.log_fmt_shell(stdout=True, stderr=True)

shell(
    "multiqc"
    " {snakemake.params}"
    " --force"
    " -o {output_dir}"
    " -n {output_name}"
    " {input_dirs}"
    " {log}"
)
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
__author__ = "Johannes Köster"
__copyright__ = "Copyright 2016, Johannes Köster"
__email__ = "[email protected]"
__license__ = "MIT"


from snakemake.shell import shell

log = snakemake.log_fmt_shell(stdout=True, stderr=True)

shell(
    "picard MarkDuplicates {snakemake.params} INPUT={snakemake.input} "
    "OUTPUT={snakemake.output.bam} METRICS_FILE={snakemake.output.metrics} "
    "{log}"
)
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
__author__ = "Johannes Köster"
__copyright__ = "Copyright 2018, Johannes Köster"
__email__ = "[email protected]"
__license__ = "MIT"


from snakemake.shell import shell


inputs = " ".join("INPUT={}".format(f) for f in snakemake.input.vcfs)
log = snakemake.log_fmt_shell(stdout=False, stderr=True)
extra = snakemake.params.get("extra", "")

shell(
    "picard"
    " MergeVcfs"
    " {extra}"
    " {inputs}"
    " OUTPUT={snakemake.output[0]}"
    " {log}"
)
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
__author__ = "Johannes Köster"
__copyright__ = "Copyright 2019, Johannes Köster"
__email__ = "[email protected]"
__license__ = "MIT"

import subprocess as sp
import sys
from itertools import product
from snakemake.shell import shell

species = snakemake.params.species.lower()
release = int(snakemake.params.release)
build = snakemake.params.build

branch = ""
if release >= 81 and build == "GRCh37":
    # use the special grch37 branch for new releases
    branch = "grch37/"

log = snakemake.log_fmt_shell(stdout=False, stderr=True)

spec = ("{build}" if int(release) > 75 else "{build}.{release}").format(
    build=build, release=release
)

suffixes = ""
datatype = snakemake.params.get("datatype", "")
if datatype == "dna":
    suffixes = ["dna.primary_assembly.fa.gz", "dna.toplevel.fa.gz"]
elif datatype == "cdna":
    suffixes = ["cdna.all.fa.gz"]
elif datatype == "cds":
    suffixes = ["cds.all.fa.gz"]
elif datatype == "ncrna":
    suffixes = ["ncrna.fa.gz"]
elif datatype == "pep":
    suffixes = ["pep.all.fa.gz"]
else:
    raise ValueError("invalid datatype, must be one of dna, cdna, cds, ncrna, pep")

success = False
for suffix in suffixes:
    url = "ftp://ftp.ensembl.org/pub/{branch}release-{release}/fasta/{species}/{datatype}/{species_cap}.{spec}.{suffix}".format(
        release=release,
        species=species,
        datatype=datatype,
        spec=spec.format(build=build, release=release),
        suffix=suffix,
        species_cap=species.capitalize(),
        branch=branch,
    )

    try:
        shell("curl -sSf {url} > /dev/null 2> /dev/null")
    except sp.CalledProcessError:
        continue

    shell("(curl -L {url} | gzip -d > {snakemake.output[0]}) {log}")
    success = True
    break

if not success:
    print(
        "Unable to download requested sequence data from Ensembl. "
        "Did you check that this combination of species, build, and release is actually provided?",
        file=sys.stderr,
    )
    exit(1)
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
__author__ = "Johannes Köster"
__copyright__ = "Copyright 2019, Johannes Köster"
__email__ = "[email protected]"
__license__ = "MIT"

import tempfile
import subprocess
import sys
import os
from snakemake.shell import shell
from snakemake.exceptions import WorkflowError

species = snakemake.params.species.lower()
release = int(snakemake.params.release)
build = snakemake.params.build
type = snakemake.params.type

if release < 98:
    print("Ensembl releases <98 are unsupported.", file=open(snakemake.log[0], "w"))
    exit(1)

branch = ""
if release >= 81 and build == "GRCh37":
    # use the special grch37 branch for new releases
    branch = "grch37/"

log = snakemake.log_fmt_shell(stdout=False, stderr=True)

if type == "all":
    if species == "homo_sapiens" and release >= 93:
        suffixes = [
            "-chr{}".format(chrom) for chrom in list(range(1, 23)) + ["X", "Y", "MT"]
        ]
    else:
        suffixes = [""]
elif type == "somatic":
    suffixes = ["_somatic"]
elif type == "structural_variations":
    suffixes = ["_structural_variations"]
else:
    raise ValueError(
        "Unsupported type {} (only all, somatic, structural_variations are allowed)".format(
            type
        )
    )

species_filename = species if release >= 91 else species.capitalize()

urls = [
    "ftp://ftp.ensembl.org/pub/{branch}release-{release}/variation/vcf/{species}/{species_filename}{suffix}.{ext}".format(
        release=release,
        species=species,
        suffix=suffix,
        species_filename=species_filename,
        branch=branch,
        ext=ext,
    )
    for suffix in suffixes
    for ext in ["vcf.gz", "vcf.gz.csi"]
]
names = [os.path.basename(url) for url in urls if url.endswith(".gz")]

try:
    gather = "curl {urls}".format(urls=" ".join(map("-O {}".format, urls)))
    workdir = os.getcwd()
    with tempfile.TemporaryDirectory() as tmpdir:
        if snakemake.input.get("fai"):
            shell(
                "(cd {tmpdir}; {gather} && "
                "bcftools concat -Oz --naive {names} > concat.vcf.gz && "
                "bcftools reheader --fai {workdir}/{snakemake.input.fai} concat.vcf.gz "
                "> {workdir}/{snakemake.output}) {log}"
            )
        else:
            shell(
                "(cd {tmpdir}; {gather} && "
                "bcftools concat -Oz --naive {names} "
                "> {workdir}/{snakemake.output}) {log}"
            )
except subprocess.CalledProcessError as e:
    if snakemake.log:
        sys.stderr = open(snakemake.log[0], "a")
    print(
        "Unable to download variation data from Ensembl. "
        "Did you check that this combination of species, build, and release is actually provided? ",
        file=sys.stderr,
    )
    exit(1)
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
__author__ = "Michael Chambers"
__copyright__ = "Copyright 2019, Michael Chambers"
__email__ = "[email protected]"
__license__ = "MIT"


from snakemake.shell import shell


shell("samtools faidx {snakemake.params} {snakemake.input[0]} > {snakemake.output[0]}")
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
__author__ = "Johannes Köster"
__copyright__ = "Copyright 2016, Johannes Köster"
__email__ = "[email protected]"
__license__ = "MIT"


from snakemake.shell import shell


shell("samtools index {snakemake.params} {snakemake.input[0]} {snakemake.output[0]}")
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
__author__ = "Julian de Ruiter"
__copyright__ = "Copyright 2017, Julian de Ruiter"
__email__ = "[email protected]"
__license__ = "MIT"


from snakemake.shell import shell


extra = snakemake.params.get("extra", "")
region = snakemake.params.get("region", "")
log = snakemake.log_fmt_shell(stdout=False, stderr=True)


shell("samtools stats {extra} {snakemake.input} {region} > {snakemake.output} {log}")
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
__author__ = "Johannes Köster"
__copyright__ = "Copyright 2016, Johannes Köster"
__email__ = "[email protected]"
__license__ = "MIT"


from snakemake.shell import shell

log = snakemake.log_fmt_shell(stdout=False, stderr=True)

shell("tabix {snakemake.params} {snakemake.input[0]} {log}")
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
__author__ = "Johannes Köster, Jorge Langa"
__copyright__ = "Copyright 2016, Johannes Köster"
__email__ = "[email protected]"
__license__ = "MIT"


from snakemake.shell import shell


# Distribute available threads between trimmomatic itself and any potential pigz instances
def distribute_threads(input_files, output_files, available_threads):
    gzipped_input_files = sum(1 for file in input_files if file.endswith(".gz"))
    gzipped_output_files = sum(1 for file in output_files if file.endswith(".gz"))
    potential_threads_per_process = available_threads // (
        1 + gzipped_input_files + gzipped_output_files
    )
    if potential_threads_per_process > 0:
        # decompressing pigz creates at most 4 threads
        pigz_input_threads = (
            min(4, potential_threads_per_process) if gzipped_input_files != 0 else 0
        )
        pigz_output_threads = (
            (available_threads - pigz_input_threads * gzipped_input_files)
            // (1 + gzipped_output_files)
            if gzipped_output_files != 0
            else 0
        )
        trimmomatic_threads = (
            available_threads
            - pigz_input_threads * gzipped_input_files
            - pigz_output_threads * gzipped_output_files
        )
    else:
        # not enough threads for pigz
        pigz_input_threads = 0
        pigz_output_threads = 0
        trimmomatic_threads = available_threads
    return trimmomatic_threads, pigz_input_threads, pigz_output_threads


def compose_input_gz(filename, threads):
    if filename.endswith(".gz") and threads > 0:
        return "<(pigz -p {threads} --decompress --stdout {filename})".format(
            threads=threads, filename=filename
        )
    return filename


def compose_output_gz(filename, threads, compression_level):
    if filename.endswith(".gz") and threads > 0:
        return ">(pigz -p {threads} {compression_level} > {filename})".format(
            threads=threads, compression_level=compression_level, filename=filename
        )
    return filename


extra = snakemake.params.get("extra", "")
log = snakemake.log_fmt_shell(stdout=True, stderr=True)
compression_level = snakemake.params.get("compression_level", "-5")
trimmer = " ".join(snakemake.params.trimmer)

# Distribute threads
input_files = [snakemake.input.r1, snakemake.input.r2]
output_files = [
    snakemake.output.r1,
    snakemake.output.r1_unpaired,
    snakemake.output.r2,
    snakemake.output.r2_unpaired,
]

trimmomatic_threads, input_threads, output_threads = distribute_threads(
    input_files, output_files, snakemake.threads
)

input_r1, input_r2 = [
    compose_input_gz(filename, input_threads) for filename in input_files
]

output_r1, output_r1_unp, output_r2, output_r2_unp = [
    compose_output_gz(filename, output_threads, compression_level)
    for filename in output_files
]

shell(
    "trimmomatic PE -threads {trimmomatic_threads} {extra} "
    "{input_r1} {input_r2} "
    "{output_r1} {output_r1_unp} "
    "{output_r2} {output_r2_unp} "
    "{trimmer} "
    "{log}"
)
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
__author__ = "Johannes Köster, Jorge Langa"
__copyright__ = "Copyright 2016, Johannes Köster"
__email__ = "[email protected]"
__license__ = "MIT"


from snakemake.shell import shell


# Distribute available threads between trimmomatic itself and any potential pigz instances
def distribute_threads(input_file, output_file, available_threads):
    gzipped_input_files = 1 if input_file.endswith(".gz") else 0
    gzipped_output_files = 1 if output_file.endswith(".gz") else 0
    potential_threads_per_process = available_threads // (
        1 + gzipped_input_files + gzipped_output_files
    )
    if potential_threads_per_process > 0:
        # decompressing pigz creates at most 4 threads
        pigz_input_threads = (
            min(4, potential_threads_per_process) if gzipped_input_files != 0 else 0
        )
        pigz_output_threads = (
            (available_threads - pigz_input_threads * gzipped_input_files)
            // (1 + gzipped_output_files)
            if gzipped_output_files != 0
            else 0
        )
        trimmomatic_threads = (
            available_threads
            - pigz_input_threads * gzipped_input_files
            - pigz_output_threads * gzipped_output_files
        )
    else:
        # not enough threads for pigz
        pigz_input_threads = 0
        pigz_output_threads = 0
        trimmomatic_threads = available_threads
    return trimmomatic_threads, pigz_input_threads, pigz_output_threads


def compose_input_gz(filename, threads):
    if filename.endswith(".gz") and threads > 0:
        return "<(pigz -p {threads} --decompress --stdout {filename})".format(
            threads=threads, filename=filename
        )
    return filename


def compose_output_gz(filename, threads, compression_level):
    if filename.endswith(".gz") and threads > 0:
        return ">(pigz -p {threads} {compression_level} > {filename})".format(
            threads=threads, compression_level=compression_level, filename=filename
        )
    return filename


extra = snakemake.params.get("extra", "")
log = snakemake.log_fmt_shell(stdout=True, stderr=True)
compression_level = snakemake.params.get("compression_level", "-5")
trimmer = " ".join(snakemake.params.trimmer)

# Distribute threads
trimmomatic_threads, input_threads, output_threads = distribute_threads(
    snakemake.input[0], snakemake.output[0], snakemake.threads
)

# Collect files
input = compose_input_gz(snakemake.input[0], input_threads)
output = compose_output_gz(snakemake.output[0], output_threads, compression_level)

shell(
    "trimmomatic SE -threads {trimmomatic_threads} {extra} {input} {output} {trimmer} {log}"
)
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
__author__ = "Johannes Köster"
__copyright__ = "Copyright 2020, Johannes Köster"
__email__ = "[email protected]"
__license__ = "MIT"

from pathlib import Path
from snakemake.shell import shell


def get_only_child_dir(path):
    children = [child for child in path.iterdir() if child.is_dir()]
    assert (
        len(children) == 1
    ), "Invalid VEP cache directory, only a single entry is allowed, make sure that cache was created with the snakemake VEP cache wrapper"
    return children[0]


extra = snakemake.params.get("extra", "")
log = snakemake.log_fmt_shell(stdout=False, stderr=True)

fork = "--fork {}".format(snakemake.threads) if snakemake.threads > 1 else ""
stats = snakemake.output.stats
cache = snakemake.input.cache
plugins = snakemake.input.plugins

entrypath = get_only_child_dir(get_only_child_dir(Path(cache)))
species = entrypath.parent.name
release, build = entrypath.name.split("_")

load_plugins = " ".join(map("--plugin {}".format, snakemake.params.plugins))

if snakemake.output.calls.endswith(".vcf.gz"):
    fmt = "z"
elif snakemake.output.calls.endswith(".bcf"):
    fmt = "b"
else:
    fmt = "v"

shell(
    "(bcftools view {snakemake.input.calls} | "
    "vep {extra} {fork} "
    "--format vcf "
    "--vcf "
    "--cache "
    "--cache_version {release} "
    "--species {species} "
    "--assembly {build} "
    "--dir_cache {cache} "
    "--dir_plugins {plugins} "
    "--offline "
    "{load_plugins} "
    "--output_file STDOUT "
    "--stats_file {stats} | "
    "bcftools view -O{fmt} > {snakemake.output.calls}) {log}"
)
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
__author__ = "Johannes Köster"
__copyright__ = "Copyright 2020, Johannes Köster"
__email__ = "[email protected]"
__license__ = "MIT"

from pathlib import Path
from snakemake.shell import shell

extra = snakemake.params.get("extra", "")
log = snakemake.log_fmt_shell(stdout=True, stderr=True)

shell(
    "vep_install --AUTO cf "
    "--SPECIES {snakemake.params.species} "
    "--ASSEMBLY {snakemake.params.build} "
    "--CACHE_VERSION {snakemake.params.release} "
    "--CACHEDIR {snakemake.output} "
    "--CONVERT "
    "--NO_UPDATE {log}"
)
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
__author__ = "Johannes Köster"
__copyright__ = "Copyright 2020, Johannes Köster"
__email__ = "[email protected]"
__license__ = "MIT"

import sys
from pathlib import Path
from urllib.request import urlretrieve
from zipfile import ZipFile
from tempfile import NamedTemporaryFile

if snakemake.log:
    sys.stderr = open(snakemake.log[0], "w")

outdir = Path(snakemake.output[0])
outdir.mkdir()

with NamedTemporaryFile() as tmp:
    urlretrieve(
        "https://github.com/Ensembl/VEP_plugins/archive/release/{release}.zip".format(
            release=snakemake.params.release
        ),
        tmp.name,
    )

    with ZipFile(tmp.name) as f:
        for member in f.infolist():
            memberpath = Path(member.filename)
            if len(memberpath.parts) == 1:
                # skip root dir
                continue
            targetpath = outdir / memberpath.relative_to(memberpath.parts[0])
            if member.is_dir():
                targetpath.mkdir()
            else:
                with open(targetpath, "wb") as out:
                    out.write(f.read(member.filename))
ShowHide 44 more snippets with no or duplicated tags.

Login to post a comment if you would like to share your experience with this workflow.

Do you know this workflow well? If so, you can request seller status , and start supporting this workflow.

Free

Created: 1yr ago
Updated: 1yr ago
Maitainers: public
URL: https://github.com/ocisse/dna-seq-gatk-variant-calling
Name: dna-seq-gatk-variant-calling
Version: 2
Badge:
workflow icon

Insert copied code into your website to add a link to this workflow.

Downloaded: 0
Copyright: Public Domain
License: MIT License
  • Future updates

Related Workflows

cellranger-snakemake-gke
snakemake workflow to run cellranger on a given bucket using gke.
A Snakemake workflow for running cellranger on a given bucket using Google Kubernetes Engine. The usage of this workflow ...