Snakemake based pipeline for atacseq dataanalysis

public public 1yr ago Version: 2 0 bookmarks
View Workflow
Report
atacseq
atacseq
View Workflow

Snakemake based pipeline for ATAC seq data analysis

Overview

Implemented workflow

dag

Code Snippets

20
21
wrapper:
	"v1.24.0/bio/bowtie2/align"
SnakeMake From line 20 of rules/align.smk 
31
32
wrapper:
	"v1.23.5-48-gf27313f0/bio/samtools/sort"
SnakeMake From line 31 of rules/align.smk 
15
16
17
18
19
20
21
22
23
shell:
	'bamCoverage --bam {input.remdup_bam} '
	'--outFileName {output} '
	'--outFileFormat bigwig '
	'--numberOfProcessors {threads} '
	'--extendReads '
	'--normalizeUsing {params.normalize_using} '
	'--binSize {params.bin_size} '
	'--smoothLength {params.smooth_length} 2>&1 | tee {log}'
SnakeMake DeepTools From line 15 of rules/bw.smk 
15
16
wrapper:
	"v1.24.0/bio/macs2/callpeak"
SnakeMake From line 15 of rules/peaks.smk 
14
15
wrapper:
	"v1.23.5-48-gf27313f0/bio/picard/markduplicates"
SnakeMake From line 14 of rules/post_align_qc.smk 
27
28
wrapper:
	"v1.24.0/bio/bedtools/intersect"
SnakeMake From line 27 of rules/post_align_qc.smk 
38
39
wrapper:
	"v1.25.0-52-g79342b73/bio/samtools/index"
SnakeMake From line 38 of rules/post_align_qc.smk 
55
56
57
58
59
60
61
62
63
shell:
	'samtools idxstats '
	'{input.bam} | cut -f 1 | grep -v chrM | xargs samtools view '
	'--threads {threads} '
	'--write-index '
	'-F {params.remove_reads} '
	'-f {params.keep_reads} '
	'-q {params.mapqual} '
	'-o {output.bam}##idx##{output.idx} {input.bam}'
SnakeMake SAMtools From line 55 of rules/post_align_qc.smk 
75
76
wrapper:
	"v1.23.5-48-gf27313f0/bio/samtools/sort"
SnakeMake From line 75 of rules/post_align_qc.smk 
86
87
wrapper:
	"v1.24.0/bio/samtools/flagstat"
SnakeMake From line 86 of rules/post_align_qc.smk 
100
101
102
103
104
105
106
shell:
	'run_spp.R '
	'-c={input} '
	'-p={threads} '
	'-savp '
	'-odir=results/qc/phantompeakqual '
	'-out={output.stats} 2>&1 | tee {log}'
SnakeMake From line 100 of rules/post_align_qc.smk 
16
17
18
19
20
21
22
23
24
shell:
	'ataqv '
	'--peak-file {input.peaks} '
	'--threads {threads} '
	'--metrics-file {output} '
	'--name {wildcards.sample} '
	'--tss-file {params.tssfile} '
	'--excluded-region-file {params.excludedregionfile} '
	'{params.organism} {input.bam} 2>&1 | tee {log}'
SnakeMake ataqv From line 16 of rules/post_peakcalling_qc.smk 
34
35
36
37
38
shell:
	'mkarv '
	'--concurrency {threads} '
	'--force '
	'results/qc/ataqv/report {input}'
SnakeMake ataqv From line 34 of rules/post_peakcalling_qc.smk 
51
52
53
54
55
56
shell:
	'multiqc '
	'--force '
	'--outdir results/qc/multiqc '
	'--zip-data-dir '
	'. 2>&1 | tee {log}'
SnakeMake MultiQC From line 51 of rules/post_peakcalling_qc.smk 
10
11
wrapper:
	"v1.24.0/bio/fastqc"
SnakeMake FastQC From line 10 of rules/pre_align_qc.smk 
26
27
28
29
30
31
32
33
shell:
	'trim_galore '
	'--gzip '
	'--output_dir results/qc/trimgalore '
	'--cores {params.threads_actual} '
	'--basename {wildcards.sample} '
	'--paired --no_report_file '
	'{input[0]} {input[1]} 2>&1 | tee {log}'
SnakeMake Trim_Galore From line 26 of rules/pre_align_qc.smk 
 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
__author__ = "Johannes Köster, Christopher Schröder"
__copyright__ = "Copyright 2016, Johannes Köster"
__email__ = "koester@jimmy.harvard.edu"
__license__ = "MIT"


import tempfile
from snakemake.shell import shell
from snakemake_wrapper_utils.java import get_java_opts

log = snakemake.log_fmt_shell()

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

bams = snakemake.input.bams
if isinstance(bams, str):
    bams = [bams]
bams = list(map("--INPUT {}".format, bams))

if snakemake.output.bam.endswith(".cram"):
    output = "/dev/stdout"
    if snakemake.params.embed_ref:
        view_options = "-O cram,embed_ref"
    else:
        view_options = "-O cram"
    convert = f" | samtools view -@ {snakemake.threads} {view_options} --reference {snakemake.input.ref} -o {snakemake.output.bam}"
else:
    output = snakemake.output.bam
    convert = ""

with tempfile.TemporaryDirectory() as tmpdir:
    shell(
        "(picard MarkDuplicates"  # Tool and its subcommand
        " {java_opts}"  # Automatic java option
        " {extra}"  # User defined parmeters
        " {bams}"  # Input bam(s)
        " --TMP_DIR {tmpdir}"
        " --OUTPUT {output}"  # Output bam
        " --METRICS_FILE {snakemake.output.metrics}"  # Output metrics
        " {convert} ) {log}"  # Logging
    )
Python Snakemake SAMtools snakemake-wrapper-utils From line 1 of markduplicates/wrapper.py 
 1
 2
 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 2016, Johannes Köster"
__email__ = "koester@jimmy.harvard.edu"
__license__ = "MIT"


import tempfile
from pathlib import Path
from snakemake.shell import shell
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)


with tempfile.TemporaryDirectory() as tmpdir:
    tmp_prefix = Path(tmpdir) / "samtools_fastq.sort_"

    shell(
        "samtools sort {samtools_opts} {extra} -T {tmp_prefix} {snakemake.input[0]} {log}"
    )
Python Snakemake SAMtools snakemake-wrapper-utils From line 1 of sort/wrapper.py 
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
__author__ = "Jan Forster"
__copyright__ = "Copyright 2019, Jan Forster"
__email__ = "j.forster@dkfz.de"
__license__ = "MIT"

from snakemake.shell import shell

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

shell(
    "(bedtools intersect"
    " {extra}"
    " -a {snakemake.input.left}"
    " -b {snakemake.input.right}"
    " > {snakemake.output})"
    " {log}"
)
Python Snakemake From line 1 of intersect/wrapper.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
31
32
33
34
35
36
37
38
39
40
41
__author__ = "Johannes Köster"
__copyright__ = "Copyright 2016, Johannes Köster"
__email__ = "koester@jimmy.harvard.edu"
__license__ = "MIT"


import os
from snakemake.shell import shell
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)


n = len(snakemake.input.sample)
assert (
    n == 1 or n == 2
), "input->sample must have 1 (single-end) or 2 (paired-end) elements."

if n == 1:
    reads = "-U {}".format(*snakemake.input.sample)
else:
    reads = "-1 {} -2 {}".format(*snakemake.input.sample)


index = os.path.commonprefix(snakemake.input.idx).rstrip(".")


shell(
    "(bowtie2"
    " --threads {snakemake.threads}"
    " {reads} "
    " -x {index}"
    " {extra}"
    "| samtools view"
    " {samtools_opts}"
    " -"
    ") {log}"
)
Python Snakemake SAMtools snakemake-wrapper-utils From line 1 of align/wrapper.py 
 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__ = "Julian de Ruiter"
__copyright__ = "Copyright 2017, Julian de Ruiter"
__email__ = "julianderuiter@gmail.com"
__license__ = "MIT"


from os import path
import re
from tempfile import TemporaryDirectory

from snakemake.shell import shell

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


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

    base = path.basename(file_path)
    # Remove file extension(s) (similar to the internal fastqc approach)
    base = re.sub("\\.gz$", "", base)
    base = re.sub("\\.bz2$", "", base)
    base = re.sub("\\.txt$", "", base)
    base = re.sub("\\.fastq$", "", base)
    base = re.sub("\\.fq$", "", base)
    base = re.sub("\\.sam$", "", base)
    base = re.sub("\\.bam$", "", base)

    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} -t {snakemake.threads} "
        "--outdir {tempdir:q} {snakemake.input[0]:q}"
        " {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:q} {snakemake.output.html:q}")

    if snakemake.output.zip != zip_path:
        shell("mv {zip_path:q} {snakemake.output.zip:q}")
Python Snakemake FastQC From line 3 of fastqc/wrapper.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
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
__author__ = "Antonie Vietor"
__copyright__ = "Copyright 2020, Antonie Vietor"
__email__ = "antonie.v@gmx.de"
__license__ = "MIT"

import os
import sys
from snakemake.shell import shell

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

in_contr = snakemake.input.get("control")
params = "{}".format(snakemake.params)
opt_input = ""
out_dir = ""

ext = "_peaks.xls"
out_file = [o for o in snakemake.output if o.endswith(ext)][0]
out_name = os.path.basename(out_file[: -len(ext)])
out_dir = os.path.dirname(out_file)

if in_contr:
    opt_input = "-c {contr}".format(contr=in_contr)

if out_dir:
    out_dir = "--outdir {dir}".format(dir=out_dir)

if any(out.endswith(("_peaks.narrowPeak", "_summits.bed")) for out in snakemake.output):
    if any(
        out.endswith(("_peaks.broadPeak", "_peaks.gappedPeak"))
        for out in snakemake.output
    ):
        sys.exit(
            "Output files with _peaks.narrowPeak and/or _summits.bed extensions cannot be created together with _peaks.broadPeak and/or _peaks.gappedPeak extended output files.\n"
            "For usable extensions please see https://snakemake-wrappers.readthedocs.io/en/stable/wrappers/macs2/callpeak.html.\n"
        )
    else:
        if " --broad" in params:
            sys.exit(
                "If --broad option in params is given, the _peaks.narrowPeak and _summits.bed files will not be created. \n"
                "Remove --broad option from params if these files are needed.\n"
            )

if any(
    out.endswith(("_peaks.broadPeak", "_peaks.gappedPeak")) for out in snakemake.output
):
    if "--broad " not in params and not params.endswith("--broad"):
        params += " --broad "

if any(
    out.endswith(("_treat_pileup.bdg", "_control_lambda.bdg"))
    for out in snakemake.output
):
    if all(p not in params for p in ["--bdg", "-B"]):
        params += " --bdg "
else:
    if any(p in params for p in ["--bdg", "-B"]):
        sys.exit(
            "If --bdg or -B option in params is given, the _control_lambda.bdg and _treat_pileup.bdg extended files must be specified in output. \n"
        )

shell(
    "(macs2 callpeak "
    "-t {snakemake.input.treatment} "
    "{opt_input} "
    "{out_dir} "
    "-n {out_name} "
    "{params}) {log}"
)
Python Snakemake From line 1 of callpeak/wrapper.py 
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
__author__ = "Christopher Preusch"
__copyright__ = "Copyright 2017, Christopher Preusch"
__email__ = "cpreusch[at]ust.hk"
__license__ = "MIT"


from snakemake.shell import shell
from snakemake_wrapper_utils.samtools import get_samtools_opts

samtools_opts = get_samtools_opts(
    snakemake, parse_write_index=False, parse_output=False, parse_output_format=False
)
extra = snakemake.params.get("extra", "")
log = snakemake.log_fmt_shell(stdout=False, stderr=True)

shell(
    "samtools flagstat {samtools_opts} {extra} {snakemake.input[0]} > {snakemake.output[0]} {log}"
)
Python Snakemake SAMtools snakemake-wrapper-utils From line 1 of flagstat/wrapper.py 
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
__author__ = "Johannes Köster"
__copyright__ = "Copyright 2016, Johannes Köster"
__email__ = "koester@jimmy.harvard.edu"
__license__ = "MIT"


from snakemake.shell import shell

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

# Samtools takes additional threads through its option -@
# One thread for samtools merge
# Other threads are *additional* threads passed to the '-@' argument
threads = "" if snakemake.threads <= 1 else " -@ {} ".format(snakemake.threads - 1)

shell(
    "samtools index {threads} {extra} {snakemake.input[0]} {snakemake.output[0]} {log}"
)
Python Snakemake SAMtools From line 1 of index/wrapper.py
ShowHide 17 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/pd321/atacseq
Name: atacseq
Version: 2
Badge:
workflow icon

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

Other Versions:
Version 2.0 Version 3
Downloaded: 0
Copyright: Public Domain
License: None
  • Future updates

Related Workflows

psychip_snakemake
Show Details View Workflow
ENCODE pipeline for histone marks developed for the psychENCODE project
public

public

psychip pipeline is an improved version of the ENCODE pipeline for histone marks developed for the psychENCODE project. The o...
raw sequence reads Alignment Sequence alignment report macs2 ucsc-bedclip bedGraphToBigWig BEDTools BWA Picard SAMtools Snakemake
Free
74
ncov_2
Show Details View Workflow
Near-real time tracking of SARS-CoV-2 in Connecticut
public

public

Repository containing scripts to perform near-real time tracking of SARS-CoV-2 in Connecticut using genomic data. This pipeli...
JSON nextclade Augur Biopython FOCUS Pandas Snakemake bs4 epiweeks geopy matplotlib numpy pycountry pycountry-convert uszipcode
Free
28
cellranger-snakemake-gke
Show Details View Workflow
snakemake workflow to run cellranger on a given bucket using gke.
public

public

A Snakemake workflow for running cellranger on a given bucket using Google Kubernetes Engine. The usage of this workflow ...
macs2 ucsc-bedclip bedGraphToBigWig BEDTools BWA Picard SAMtools Snakemake
Free
74
atlas
Show Details View Workflow
ATLAS - Three commands to start analyzing your metagenome data
public

public

Metagenome-atlas is a easy-to-use metagenomic pipeline based on snakemake. It handles all steps from QC, Assembly, Binning, t...
raw sequence reads Genome assembly Annotation track checkm2 gunc prodigal snakemake-wrapper-utils MEGAHIT Atlas BBMap Biopython BioRuby Bwa-mem2 cd-hit CheckM DAS Diamond eggNOG-mapper v2 MetaBAT 2 Minimap2 MMseqs MultiQC Pandas Picard pyfastx SAMtools SemiBin Snakemake SPAdes SqueezeMeta TADpole VAMB CONCOCT ete3 gtdbtk h5py networkx numpy plotly psutil utils metagenomics
Free
175
rna-seq-star-deseq2
Show Details View Workflow
RNA-seq workflow using STAR and DESeq2
public

public

This workflow performs a differential gene expression analysis with STAR and Deseq2. The usage of this workflow is described ...
raw sequence reads Gene expression profiling ID list snakemake-wrapper-utils biomaRt PCAtools BiocParallel BWA Cutadapt DESeq2 GFFutils MultiQC Pandas SAMtools Snakemake STAR cli stringr tidyverse RNA-Seq
Free
41
dna-seq-gatk-variant-calling
Show Details View Workflow
This Snakemake pipeline implements the GATK best-practices workflow
public

public

This Snakemake pipeline implements the GATK best-practices workflow for calling small germline variants. The usage of thi...
VCF raw sequence reads Variant calling genetic variants gatk rust-bio-tools snakemake-wrapper-utils tabix BCFtools BWA FastQC MultiQC Pandas Picard SAMtools Snakemake Trimmomatic Variant Effect Predictor (VEP) common matplotlib numpy seaborn DNA
Free
57