tweaking chipseq workflow for ATACseq

public public 1yr ago Version: 3 0 bookmarks
View Workflow
Report
atacseq
atacseq
View Workflow

This is the template for a new Snakemake workflow. Replace this text with a comprehensive description covering the purpose and domain. Insert your code into the respective folders, i.e. scripts , rules , and envs . Define the entry point of the workflow in the Snakefile and the main configuration in the config.yaml file. Inspiration: https://nf-co.re/atacseq

Authors

  • Antonie Vietor (@AntonieV)

Usage

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 in the config/ folder. Adjust config.yaml to configure the workflow execution, and samples.tsv to specify your sample setup.

Step 3: Install Snakemake

Install Snakemake using conda : 

conda create -c bioconda -c conda-forge -n snakemake snakemake

For installation details, see the instructions in the Snakemake documentation .

Step 4: Execute workflow

Activate the conda environment: 

conda activate snakemake

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.

Step 5: 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 6: 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 7: 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/chipseq.git or git remote add -f upstream https://github.com/snakemake-workflows/chipseq.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 workflow > 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 . If so, do it manually, and only where necessary, since you would otherwise likely overwrite your settings and samples.

Step 8: 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 automatically executed via continuous integration with Github Actions .

Code Snippets

14
15
wrapper:
    "0.64.0/bio/cutadapt/pe"
SnakeMake From line 14 of rules/cutadapt.smk 
31
32
wrapper:
    "0.64.0/bio/cutadapt/se"
SnakeMake From line 31 of rules/cutadapt.smk 
15
16
wrapper:
    "0.64.0/bio/samtools/view"
SnakeMake From line 15 of rules/filtering.smk 
28
29
wrapper:
    "0.64.0/bio/bamtools/filter_json"
SnakeMake From line 28 of rules/filtering.smk 
44
45
shell:
    " ../workflow/scripts/rm_orphan_pe_bam.py {input} {output.bam} {params} 2> {log}"
SnakeMake From line 44 of rules/filtering.smk 
58
59
wrapper:
    "0.64.0/bio/samtools/sort"
SnakeMake From line 58 of rules/filtering.smk 
15
16
wrapper:
    "0.64.0/bio/bwa/mem"
SnakeMake From line 15 of rules/mapping.smk 
30
31
wrapper:
    "0.64.0/bio/picard/mergesamfiles"
SnakeMake From line 30 of rules/mapping.smk 
43
44
wrapper:
    "0.64.0/bio/picard/markduplicates"
SnakeMake From line 43 of rules/mapping.smk 
10
11
wrapper:
    "0.64.0/bio/preseq/lc_extrap"
SnakeMake From line 10 of rules/post-analysis.smk 
42
43
wrapper:
    "0.64.0/bio/picard/collectmultiplemetrics"
SnakeMake From line 42 of rules/post-analysis.smk 
55
56
wrapper:
    "0.64.0/bio/bedtools/genomecov"
SnakeMake From line 55 of rules/post-analysis.smk 
65
66
shell:
    "sort -k1,1 -k2,2n {input} > {output} 2> {log}"
SnakeMake From line 65 of rules/post-analysis.smk 
78
79
wrapper:
    "0.64.0/bio/ucsc/bedGraphToBigWig"
SnakeMake bedGraphToBigWig From line 78 of rules/post-analysis.smk 
89
90
shell:
    "find {input} -type f -name '*.bigWig' -exec echo -e 'results/big_wig/\"{{}}\"\t0,0,178' \;  > {output} 2> {log}"
SnakeMake From line 89 of rules/post-analysis.smk 
112
113
wrapper:
    "0.64.0/bio/deeptools/computematrix"
SnakeMake From line 112 of rules/post-analysis.smk 
127
128
wrapper:
    "0.64.0/bio/deeptools/plotprofile"
SnakeMake From line 127 of rules/post-analysis.smk 
142
143
wrapper:
    "0.64.0/bio/deeptools/plotheatmap"
SnakeMake From line 142 of rules/post-analysis.smk 
158
159
160
161
shell:
    "( Rscript -e \"library(caTools); source('../workflow/scripts/run_spp.R')\" "
    "  -c={input} -savp={output.plot} -savd={output.r_data} "
    "  -out={output.res_phantom} -p={threads} 2>&1 ) >{log}"
SnakeMake From line 158 of rules/post-analysis.smk 
173
174
script:
    "../scripts/phantompeak_correlation.R"
SnakeMake From line 173 of rules/post-analysis.smk 
189
190
191
shell:
    "( gawk -v OFS='\t' '{{print $1, $9}}' {input.data} | cat {input.nsc_header} - > {output.nsc} && "
    "  gawk -v OFS='\t' '{{print $1, $10}}' {input.data} | cat {input.rsc_header} - > {output.rsc} 2>&1 ) >{log}"
SnakeMake From line 189 of rules/post-analysis.smk 
 9
10
wrapper:
    "0.64.0/bio/fastqc"
SnakeMake FastQC From line 9 of rules/qc.smk 
20
21
wrapper:
    "0.64.0/bio/multiqc"
SnakeMake MultiQC From line 20 of rules/qc.smk 
31
32
shell:
    "curl -L ftp://ftp.ensembl.org/pub/release-{params.release}/fasta/{params.species}/{params.datatype}/{params.spec_up}.{params.build}.{params.datatype}.{params.suffix}.fa.gz |gzip -d > {output} 2> {log}"
SnakeMake From line 31 of rules/ref.smk 
46
47
wrapper:
    "0.64.0/bio/reference/ensembl-annotation"
SnakeMake From line 46 of rules/ref.smk 
58
59
shell:
    "../workflow/scripts/gtf2bed {input} > {output} 2> {log}"
SnakeMake GFFutils From line 58 of rules/ref.smk 
69
70
wrapper:
    "0.64.0/bio/samtools/faidx"
SnakeMake From line 69 of rules/ref.smk 
82
83
wrapper:
    "0.64.0/bio/bwa/index"
SnakeMake From line 82 of rules/ref.smk 
92
93
shell:
    "cut -f 1,2 {input} > {output} 2> {log}"
SnakeMake From line 92 of rules/ref.smk 
8
9
wrapper:
    "0.64.0/bio/samtools/flagstat"
SnakeMake From line 8 of rules/stats.smk 
19
20
wrapper:
    "0.64.0/bio/samtools/idxstats"
SnakeMake From line 19 of rules/stats.smk 
31
32
wrapper:
    "0.64.0/bio/samtools/stats"
SnakeMake From line 31 of rules/stats.smk 
10
11
wrapper:
    "0.64.0/bio/samtools/index"
SnakeMake From line 10 of rules/utils.smk 
3
4
5
6
7
8
9
log <- file(snakemake@log[[1]], open="wt")
sink(log)
sink(log, type="message")
system(paste0("cp ", snakemake@input[["header"]], " ", snakemake@output[[1]]))
load(snakemake@input[["data"]])
write.table(crosscorr['cross.correlation'], file=snakemake@output[[1]], sep=',', quote=FALSE,
row.names=FALSE, col.names=FALSE, append=TRUE)
R From line 3 of scripts/phantompeak_correlation.R 
 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
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
import os
import pysam
import argparse

############################################
############################################
## PARSE ARGUMENTS
############################################
############################################

Description = 'Remove singleton reads from paired-end BAM file i.e if read1 is present in BAM file without read 2 and vice versa.'
Epilog = """Example usage: bampe_rm_orphan.py <BAM_INPUT_FILE> <BAM_OUTPUT_FILE>"""

argParser = argparse.ArgumentParser(description=Description, epilog=Epilog)

## REQUIRED PARAMETERS
argParser.add_argument('BAM_INPUT_FILE', help="Input BAM file sorted by name.")
argParser.add_argument('BAM_OUTPUT_FILE', help="Output BAM file sorted by name.")

## OPTIONAL PARAMETERS
argParser.add_argument('-fr', '--only_fr_pairs', dest="ONLY_FR_PAIRS", help="Only keeps pairs that are in FR orientation on same chromosome.",action='store_true')
args = argParser.parse_args()

############################################
############################################
## HELPER FUNCTIONS
############################################
############################################

def makedir(path):

    if not len(path) == 0:
        try:
            #!# AVI: changed because of race conditions if directory exists, original code:  os.makedirs(path)
            os.makedirs(path, exist_ok=True)
        except OSError as exception:
            if exception.errno != errno.EEXIST:
                raise

############################################
############################################
## MAIN FUNCTION
############################################
############################################

def bampe_rm_orphan(BAMIn,BAMOut,onlyFRPairs=False):

    ## SETUP DIRECTORY/FILE STRUCTURE
    OutDir = os.path.dirname(BAMOut)
    makedir(OutDir)

    ## COUNT VARIABLES
    totalReads = 0; totalOutputPairs = 0; totalSingletons = 0; totalImproperPairs = 0

    ## ITERATE THROUGH BAM FILE
    EOF = 0
    SAMFin = pysam.AlignmentFile(BAMIn,"rb")  #!# AVI: changed to new API from pysam.Samfile
    SAMFout = pysam.AlignmentFile(BAMOut, "wb",header=SAMFin.header)   #!# AVI: changed to new API from pysam.Samfile
    currRead = next(SAMFin)     #!# AVI: adapted for the use of the iterator, original code: currRead = SAMFin.next()

    for read in SAMFin.fetch(until_eof=True): #!# AVI: added .fetch() to explicitly use new API
        totalReads += 1
        if currRead.qname == read.qname:
            pair1 = currRead; pair2 = read

            ## FILTER FOR READS ON SAME CHROMOSOME IN FR ORIENTATION
            if onlyFRPairs:
                if pair1.tid == pair2.tid:

                    ## READ1 FORWARD AND READ2 REVERSE STRAND
                    if not pair1.is_reverse and pair2.is_reverse:
                        if pair1.reference_start <= pair2.reference_start:
                            totalOutputPairs += 1
                            SAMFout.write(pair1)
                            SAMFout.write(pair2)
                        else:
                            totalImproperPairs += 1

                    ## READ1 REVERSE AND READ2 FORWARD STRAND
                    elif pair1.is_reverse and not pair2.is_reverse:
                        if pair2.reference_start <= pair1.reference_start:
                            totalOutputPairs += 1
                            SAMFout.write(pair1)
                            SAMFout.write(pair2)
                        else:
                            totalImproperPairs += 1

                    else:
                        totalImproperPairs += 1
                else:
                    totalImproperPairs += 1
            else:
                totalOutputPairs += 1
                SAMFout.write(pair1)
                SAMFout.write(pair2)

            ## RESET COUNTER
            try:
                totalReads += 1
                currRead = next(SAMFin)   #!# AVI: adapted for the use of the iterator, original code: currRead = SAMFin.next()
            except:
                StopIteration
                EOF = 1

        ## READS WHERE ONLY ONE OF A PAIR IS IN FILE
        else:
            totalSingletons += 1
            pair1 = currRead
            currRead = read

    if not EOF:
        totalReads += 1
        totalSingletons += 1
        pair1 = currRead

    ## CLOSE ALL FILE HANDLES
    SAMFin.close()
    SAMFout.close()

    LogFile = os.path.join(OutDir,'%s_bampe_rm_orphan.log' % (os.path.basename(BAMOut[:-4])))
    SamLogFile = open(LogFile,'w')
    SamLogFile.write('\n##############################\n')
    SamLogFile.write('FILES/DIRECTORIES')
    SamLogFile.write('\n##############################\n\n')
    SamLogFile.write('Input File: ' + BAMIn + '\n')
    SamLogFile.write('Output File: ' + BAMOut + '\n')
    SamLogFile.write('\n##############################\n')
    SamLogFile.write('OVERALL COUNTS')
    SamLogFile.write('\n##############################\n\n')
    SamLogFile.write('Total Input Reads = ' + str(totalReads) + '\n')
    SamLogFile.write('Total Output Pairs = ' + str(totalOutputPairs) + '\n')
    SamLogFile.write('Total Singletons Excluded = ' + str(totalSingletons) + '\n')
    SamLogFile.write('Total Improper Pairs Excluded = ' + str(totalImproperPairs) + '\n')
    SamLogFile.write('\n##############################\n')
    SamLogFile.close()

############################################
############################################
## RUN FUNCTION
############################################
############################################

bampe_rm_orphan(BAMIn=args.BAM_INPUT_FILE,BAMOut=args.BAM_OUTPUT_FILE,onlyFRPairs=args.ONLY_FR_PAIRS)
Python pysam From line 38 of scripts/rm_orphan_pe_bam.py 
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
__author__ = "Antonie Vietor"
__copyright__ = "Copyright 2020, Antonie Vietor"
__email__ = "[email protected]"
__license__ = "MIT"

from snakemake.shell import shell

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

region = snakemake.params.get("region")
region_param = ""

if region and region is not None:
    region_param = ' -region "' + region + '"'

shell(
    "(bamtools filter"
    " -in {snakemake.input[0]}"
    " -out {snakemake.output[0]}"
    + region_param
    + " -script {snakemake.params.json}) {log}"
)
Python Snakemake From line 1 of filter_json/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
__author__ = "Antonie Vietor"
__copyright__ = "Copyright 2020, Antonie Vietor"
__email__ = "[email protected]"
__license__ = "MIT"

import os
from snakemake.shell import shell

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

genome = ""
input_file = ""

if (os.path.splitext(snakemake.input[0])[-1]) == ".bam":
    input_file = "-ibam " + snakemake.input[0]

if len(snakemake.input) > 1:
    if (os.path.splitext(snakemake.input[0])[-1]) == ".bed":
        input_file = "-i " + snakemake.input.get("bed")
        genome = "-g " + snakemake.input.get("ref")

shell(
    "(genomeCoverageBed"
    " {snakemake.params}"
    " {input_file}"
    " {genome}"
    " > {snakemake.output[0]}) {log}"
)
Python Snakemake From line 1 of genomecov/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
__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}"
)
Python Snakemake BWA From line 1 of index/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
__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}"
)
Python Snakemake SAMtools Picard From line 1 of mem/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
__author__ = "Julian de Ruiter"
__copyright__ = "Copyright 2017, Julian de Ruiter"
__email__ = "[email protected]"
__license__ = "MIT"


from snakemake.shell import shell


n = len(snakemake.input)
assert n == 2, "Input must contain 2 (paired-end) elements."

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

shell(
    "cutadapt"
    " {snakemake.params.adapters}"
    " {snakemake.params.others}"
    " -o {snakemake.output.fastq1}"
    " -p {snakemake.output.fastq2}"
    " -j {snakemake.threads}"
    " {snakemake.input}"
    " > {snakemake.output.qc} {log}"
)
Python Snakemake Cutadapt From line 3 of pe/wrapper.py 
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
__author__ = "Julian de Ruiter"
__copyright__ = "Copyright 2017, Julian de Ruiter"
__email__ = "[email protected]"
__license__ = "MIT"


from snakemake.shell import shell


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

shell(
    "cutadapt"
    " {snakemake.params}"
    " -j {snakemake.threads}"
    " -o {snakemake.output.fastq}"
    " {snakemake.input[0]}"
    " > {snakemake.output.qc} {log}"
)
Python Snakemake Cutadapt From line 3 of se/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
__author__ = "Antonie Vietor"
__copyright__ = "Copyright 2020, Antonie Vietor"
__email__ = "[email protected]"
__license__ = "MIT"

from snakemake.shell import shell

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

out_tab = snakemake.output.get("matrix_tab")
out_bed = snakemake.output.get("matrix_bed")

optional_output = ""

if out_tab:
    optional_output += " --outFileNameMatrix {out_tab} ".format(out_tab=out_tab)

if out_bed:
    optional_output += " --outFileSortedRegions {out_bed} ".format(out_bed=out_bed)

shell(
    "(computeMatrix "
    "{snakemake.params.command} "
    "{snakemake.params.extra} "
    "-R {snakemake.input.bed} "
    "-S {snakemake.input.bigwig} "
    "-o {snakemake.output.matrix_gz} "
    "{optional_output}) {log}"
)
Python Snakemake From line 1 of computematrix/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
__author__ = "Antonie Vietor"
__copyright__ = "Copyright 2020, Antonie Vietor"
__email__ = "[email protected]"
__license__ = "MIT"

from snakemake.shell import shell

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

out_region = snakemake.output.get("regions")
out_matrix = snakemake.output.get("heatmap_matrix")

optional_output = ""

if out_region:
    optional_output += " --outFileSortedRegions {out_region} ".format(
        out_region=out_region
    )

if out_matrix:
    optional_output += " --outFileNameMatrix {out_matrix} ".format(
        out_matrix=out_matrix
    )

shell(
    "(plotHeatmap "
    "-m {snakemake.input[0]} "
    "-o {snakemake.output.heatmap_img} "
    "{optional_output} "
    "{snakemake.params}) {log}"
)
Python Snakemake From line 1 of plotheatmap/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
__author__ = "Antonie Vietor"
__copyright__ = "Copyright 2020, Antonie Vietor"
__email__ = "[email protected]"
__license__ = "MIT"

from snakemake.shell import shell

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

out_region = snakemake.output.get("regions")
out_data = snakemake.output.get("data")

optional_output = ""

if out_region:
    optional_output += " --outFileSortedRegions {out_region} ".format(
        out_region=out_region
    )

if out_data:
    optional_output += " --outFileNameData {out_data} ".format(out_data=out_data)

shell(
    "(plotProfile "
    "-m {snakemake.input[0]} "
    "-o {snakemake.output.plot_img} "
    "{optional_output} "
    "{snakemake.params}) {log}"
)
Python Snakemake From line 1 of plotprofile/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
__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 -t {snakemake.threads} "
        "--outdir {tempdir:q} {snakemake.input[0]:q}"
        " {log:q}"
    )

    # 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 
 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}"
)
Python Snakemake MultiQC From line 3 of multiqc/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
__author__ = "David Laehnemann, Antonie Vietor"
__copyright__ = "Copyright 2020, David Laehnemann, Antonie Vietor"
__email__ = "[email protected]"
__license__ = "MIT"

import sys
from snakemake.shell import shell

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

res = snakemake.resources.get("mem_gb", "3")
if not res or res is None:
    res = 3

exts_to_prog = {
    ".alignment_summary_metrics": "CollectAlignmentSummaryMetrics",
    ".insert_size_metrics": "CollectInsertSizeMetrics",
    ".insert_size_histogram.pdf": "CollectInsertSizeMetrics",
    ".quality_distribution_metrics": "QualityScoreDistribution",
    ".quality_distribution.pdf": "QualityScoreDistribution",
    ".quality_by_cycle_metrics": "MeanQualityByCycle",
    ".quality_by_cycle.pdf": "MeanQualityByCycle",
    ".base_distribution_by_cycle_metrics": "CollectBaseDistributionByCycle",
    ".base_distribution_by_cycle.pdf": "CollectBaseDistributionByCycle",
    ".gc_bias.detail_metrics": "CollectGcBiasMetrics",
    ".gc_bias.summary_metrics": "CollectGcBiasMetrics",
    ".gc_bias.pdf": "CollectGcBiasMetrics",
    ".rna_metrics": "RnaSeqMetrics",
    ".bait_bias_detail_metrics": "CollectSequencingArtifactMetrics",
    ".bait_bias_summary_metrics": "CollectSequencingArtifactMetrics",
    ".error_summary_metrics": "CollectSequencingArtifactMetrics",
    ".pre_adapter_detail_metrics": "CollectSequencingArtifactMetrics",
    ".pre_adapter_summary_metrics": "CollectSequencingArtifactMetrics",
    ".quality_yield_metrics": "CollectQualityYieldMetrics",
}
progs = set()

for file in snakemake.output:
    matched = False
    for ext in exts_to_prog:
        if file.endswith(ext):
            progs.add(exts_to_prog[ext])
            matched = True
    if not matched:
        sys.exit(
            "Unknown type of metrics file requested, for possible metrics files, see https://snakemake-wrappers.readthedocs.io/en/stable/wrappers/picard/collectmultiplemetrics.html"
        )

programs = " PROGRAM=" + " PROGRAM=".join(progs)

out = str(snakemake.wildcards.sample)  # as default
output_file = str(snakemake.output[0])
for ext in exts_to_prog:
    if output_file.endswith(ext):
        out = output_file[: -len(ext)]
        break

shell(
    "(picard -Xmx{res}g CollectMultipleMetrics "
    "I={snakemake.input.bam} "
    "O={out} "
    "R={snakemake.input.ref} "
    "{snakemake.params}{programs}) {log}"
)
Python Snakemake From line 1 of collectmultiplemetrics/wrapper.py 
 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}"
)
Python Snakemake Picard From line 1 of markduplicates/wrapper.py 
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
__author__ = "Julian de Ruiter"
__copyright__ = "Copyright 2017, Julian de Ruiter"
__email__ = "[email protected]"
__license__ = "MIT"


from snakemake.shell import shell


inputs = " ".join("INPUT={}".format(in_) for in_ in snakemake.input)
log = snakemake.log_fmt_shell(stdout=False, stderr=True)

shell(
    "picard"
    " MergeSamFiles"
    " {snakemake.params}"
    " {inputs}"
    " OUTPUT={snakemake.output[0]}"
    " {log}"
)
Python Snakemake Picard From line 3 of mergesamfiles/wrapper.py 
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
__author__ = "Antonie Vietor"
__copyright__ = "Copyright 2020, Antonie Vietor"
__email__ = "[email protected]"
__license__ = "MIT"

import os
from snakemake.shell import shell

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

params = ""
if (os.path.splitext(snakemake.input[0])[-1]) == ".bam":
    if "-bam" not in (snakemake.input[0]):
        params = "-bam "

shell(
    "(preseq lc_extrap {params} {snakemake.params} {snakemake.input[0]} -output {snakemake.output[0]}) {log}"
)
Python Snakemake From line 1 of lc_extrap/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
__author__ = "Johannes Köster"
__copyright__ = "Copyright 2019, Johannes Köster"
__email__ = "[email protected]"
__license__ = "MIT"

import subprocess
import sys
from snakemake.shell import shell

species = snakemake.params.species.lower()
release = int(snakemake.params.release)
fmt = snakemake.params.fmt
build = snakemake.params.build
flavor = snakemake.params.get("flavor", "")

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

if flavor:
    flavor += "."

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

suffix = ""
if fmt == "gtf":
    suffix = "gtf.gz"
elif fmt == "gff3":
    suffix = "gff3.gz"

url = "ftp://ftp.ensembl.org/pub/{branch}release-{release}/{fmt}/{species}/{species_cap}.{build}.{release}.{flavor}{suffix}".format(
    release=release,
    build=build,
    species=species,
    fmt=fmt,
    species_cap=species.capitalize(),
    suffix=suffix,
    flavor=flavor,
    branch=branch,
)

try:
    shell("(curl -L {url} | gzip -d > {snakemake.output[0]}) {log}")
except subprocess.CalledProcessError as e:
    if snakemake.log:
        sys.stderr = open(snakemake.log[0], "a")
    print(
        "Unable to download annotation data from Ensembl. "
        "Did you check that this combination of species, build, and release is actually provided?",
        file=sys.stderr,
    )
    exit(1)
Python Snakemake From line 1 of ensembl-annotation/wrapper.py 
 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]}")
Python Snakemake SAMtools From line 1 of faidx/wrapper.py 
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
__author__ = "Christopher Preusch"
__copyright__ = "Copyright 2017, Christopher Preusch"
__email__ = "cpreusch[at]ust.hk"
__license__ = "MIT"


from snakemake.shell import shell


shell("samtools flagstat {snakemake.input[0]} > {snakemake.output[0]}")
Python Snakemake SAMtools From line 1 of flagstat/wrapper.py 
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
__author__ = "Antonie Vietor"
__copyright__ = "Copyright 2020, Antonie Vietor"
__email__ = "[email protected]"
__license__ = "MIT"


from snakemake.shell import shell

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

shell("samtools idxstats {snakemake.input.bam} > {snakemake.output[0]} {log}")
Python Snakemake SAMtools From line 1 of idxstats/wrapper.py 
 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]}")
Python Snakemake SAMtools From line 1 of index/wrapper.py 
 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 2016, Johannes Köster"
__email__ = "[email protected]"
__license__ = "MIT"


import os
from snakemake.shell import shell


prefix = os.path.splitext(snakemake.output[0])[0]

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

shell(
    "samtools sort {snakemake.params} {threads} -o {snakemake.output[0]} "
    "-T {prefix} {snakemake.input[0]}"
)
Python Snakemake SAMtools From line 1 of sort/wrapper.py 
 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}")
Python Snakemake SAMtools From line 3 of stats/wrapper.py 
 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 view {snakemake.params} {snakemake.input[0]} > {snakemake.output[0]}")
Python Snakemake SAMtools From line 1 of view/wrapper.py 
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
__author__ = "Roman Chernyatchik"
__copyright__ = "Copyright (c) 2019 JetBrains"
__email__ = "[email protected]"
__license__ = "MIT"

from snakemake.shell import shell

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

shell(
    "bedGraphToBigWig {extra}"
    " {snakemake.input.bedGraph} {snakemake.input.chromsizes}"
    " {snakemake.output} {log}"
)
Python Snakemake bedGraphToBigWig From line 4 of bedGraphToBigWig/wrapper.py
ShowHide 50 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/AnnaLorenc/ATACseq
Name: atacseq
Version: 3
Badge:
workflow icon

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

Other Versions:
Version 2.0 Version 2
Downloaded: 0
Copyright: Public Domain
License: MIT License
  • 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