def test_salmon_quant_single_index(tmpdir, sample1_se_tiny_fq, salmon_index):
snakefile = '''
rule salmon_quant:
input:
unmatedReads='sample1.fq.gz',
index='idx/hash.bin'
output: 'sample1/salmon/quant.sf'
params: extra='--libType A'
log: 'salmon.quant.log'
wrapper: 'file:wrapper'
'''
input_data_func = symlink_in_tempdir(
{
sample1_se_tiny_fq: 'sample1.fq.gz',
salmon_index: 'idx',
}
)
def check():
assert open('sample1/salmon/quant.sf').readline() == (
'Name\tLength\tEffectiveLength\tTPM\tNumReads\n')
run(
dpath('../wrappers/salmon/quant'),
snakefile, check, input_data_func, tmpdir)
def test_demo_pe(sample1_pe_fq, tmpdir):
# In contrast to the sample1_se_tiny_fq fixture used in the previous function,
# here the paired-end fixture `sample1_pe_fq` is a tuple of path names (see
# conftest.sample1_pe_fq())
# The snakefile reflects what the wrapper expects for PE (see
# wrappers/demo/README.md).
snakefile = '''
rule demo:
input:
R1='a1.fastq.gz',
R2='a2.fastq.gz'
output:
R1='b1.fastq.gz',
R2='b2.fastq.gz'
wrapper: "file:wrapper"
'''
# Map fixture to input files. Again, since this is paired-end we need to
# make sure both files are provided the right filename for testing.
input_data_func = symlink_in_tempdir({
sample1_pe_fq[0]: 'a1.fastq.gz',
sample1_pe_fq[1]: 'a2.fastq.gz',
})
def check():
assert open('a1.fastq.gz', 'rb').read() == open('b1.fastq.gz',
'rb').read()
assert open('a2.fastq.gz', 'rb').read() == open('b2.fastq.gz',
'rb').read()
run(dpath('../wrappers/demo'), snakefile, check, input_data_func, tmpdir)
def test_cutadapt_se_with_list(sample1_se_tiny_fq, tmpdir):
snakefile = '''
rule cutadapt:
input: 'sample1_R1.fastq.gz'
output: 'sample1_R1.trim.fastq.gz'
params: extra='-a AAA'
wrapper: "file:wrapper"
'''
input_data_func=symlink_in_tempdir(
{
sample1_se_tiny_fq: 'sample1_R1.fastq.gz'
}
)
def check():
"""
check for line lengths and that they are at least different sized
"""
a = sum(1 for _ in gzip.open('sample1_R1.fastq.gz'))
b = sum(1 for _ in gzip.open('sample1_R1.trim.fastq.gz'))
assert a == b == 4040
assert os.path.getsize('sample1_R1.fastq.gz') != os.path.getsize('sample1_R1.trim.fastq.gz')
run(dpath('../wrappers/cutadapt'), snakefile, check, input_data_func, tmpdir)
def test_featurecounts_pe(sample1_pe_tiny_bam, annotation, tmpdir):
snakefile = '''
rule featurecounts:
input:
annotation='dm6.gtf',
bam='sample1.bam'
output:
counts='sample1.counts',
log: 'featurecounts.log'
params: extra='-p -P -s 1 -B --splitOnly'
wrapper: "file:wrapper"
'''
input_data_func = symlink_in_tempdir({
sample1_pe_tiny_bam: 'sample1.bam',
annotation: 'dm6.gtf',
})
def check():
assert '//===================' in open('featurecounts.log').read()
assert '# Program:featureCounts' in open('sample1.counts').readline()
assert open('sample1.counts.summary').readline().startswith('Status')
assert sum(1 for _ in open('sample1.counts')) == 169
# TODO: maybe assert that below a certain level are counted when all
# those extra arguments are used?
run(dpath('../wrappers/featurecounts'), snakefile, check, input_data_func,
tmpdir)
def test_bowtie2_align_se_rm_unmapped(bowtie2_indexes, sample1_se_tiny_fq,
tmpdir):
d = _dict_of_bowtie2_indexes(bowtie2_indexes, 'dm6')
indexes = list(d.values())
snakefile = '''
rule bowtie2_align:
input:
fastq='sample1_R1.fastq.gz',
index={indexes}
output:
bam='sample1.bam'
params:
samtools_view_extra='-F 0x04'
log: "bowtie2.log"
wrapper: "file:wrapper"
'''.format(indexes=indexes)
d[sample1_se_tiny_fq] = 'sample1_R1.fastq.gz'
input_data_func = symlink_in_tempdir(d)
def check():
assert "overall alignment rate" in open('bowtie2.log').read()
# should have at least some mapped and unmapped
assert int(
list(shell('samtools view -c -f 0x04 sample1.bam',
iterable=True))[0]) == 0
assert int(
list(shell('samtools view -c -F 0x04 sample1.bam',
iterable=True))[0]) > 0
run(dpath('../wrappers/bowtie2/align'), snakefile, check, input_data_func,
tmpdir)
def test_gB_cov_png(sample1_se_tiny_bam, sample1_se_tiny_bam_bai,
annotation_bed12, tmpdir):
snakefile = '''
rule geneBody_coverage:
input:
bam='sample1_R1.sort.bam',
bai='sample1_R1.sort.bam.bai',
bed='dm6.bed12'
output:
txt='sample1_R1.geneBodyCoverage.txt',
r='sample1_R1.geneBodyCoverage.r',
img='sample1_R1.geneBodyCoverage.png',
params:
extra: = '-f png'
wrapper: "file:wrapper"
'''
input_data_func = symlink_in_tempdir({
sample1_se_tiny_bam: 'sample1_R1.sort.bam',
sample1_se_tiny_bam_bai['bai']: 'sample1_R1.sort.bam.bai',
annotation_bed12: 'dm6.bed12'
})
def check():
""" Check that the PNG is created """
assert os.path.exists('sample1_R1.geneBodyCoverage.png')
def test_picard_collectrnaseqmetrics_se_plot(sample1_se_tiny_bam,
annotation_refflat, tmpdir):
snakefile = '''
rule collectrnaseqmetrics:
input:
bam='sample1.bam',
refflat='dm6.refflat',
output:
metrics='sample1.metrics',
plot='sample1.pdf'
log: 'log'
params: extra="STRAND=NONE CHART=sample1.pdf"
wrapper: 'file:wrapper'
'''
input_data_func = symlink_in_tempdir({
sample1_se_tiny_bam: 'sample1.bam',
annotation_refflat: 'dm6.refflat',
})
def check():
assert '## METRICS CLASS' in open('sample1.metrics').read()
run(dpath('../wrappers/picard/collectrnaseqmetrics'),
snakefile,
check,
input_data_func,
tmpdir,
use_conda=True)
def sample1_se_bam_markdups(sample1_se_bam, tmpdir_factory):
snakefile = '''
rule markduplicates:
input:
bam='sample1.bam'
output:
bam='sample1.dupsmarked.bam',
metrics='sample1.dupmetrics.txt'
log: 'log'
wrapper: 'file:wrapper'
'''
input_data_func = symlink_in_tempdir({
sample1_se_bam: 'sample1.bam',
})
tmpdir = str(tmpdir_factory.mktemp('markduplicates_fixture'))
run(dpath('../wrappers/picard/markduplicates'),
snakefile,
None,
input_data_func,
tmpdir,
use_conda=True)
return {
'bam': os.path.join(tmpdir, 'sample1.dupsmarked.bam'),
'metrics': os.path.join(tmpdir, 'sample1.dupmetrics.txt')
}
def generic_fixture(key, mapping, factory):
"""
Tries to handle as much of the magic as possible.
Parameters
----------
key : str
Key into the module-level config dict
mapping : dict
Maps paths from fixtures to input files expected by the snakefile
tmpdir : str
Path to temporary dir, usually created by utils.tmpdir_for_func
Returns
-------
After a successful Snakemake run, returns the dictionary of the config's
`output` key but with paths fixed to be relative to tmpdir. This returned
dict is ready to be used as a fixture by test functions.
"""
conf = config[key]
tmpdir = utils.tmpdir_for_func(factory)
input_data_func = utils.symlink_in_tempdir(mapping)
utils.run(utils.dpath(conf['wrapper']), conf['snakefile'], None,
input_data_func, tmpdir)
output = conf['output'].copy()
for k, v in output.items():
output[k] = os.path.join(tmpdir, v)
return output
def test_picard_collectrnaseqmetrics_too_small_heap(sample1_se_tiny_bam,
annotation_refflat,
tmpdir):
# set the java vm heap size to 128 bytes which should fail. This tests to
# make sure the java args are making it through to the wrapper.
snakefile = '''
rule collectrnaseqmetrics:
input:
bam='sample1.bam',
refflat='dm6.refflat',
output:
metrics='sample1.metrics'
log: 'log'
params:
extra="STRAND=NONE",
java_args='-Xmx128'
wrapper: 'file:wrapper'
'''
input_data_func = symlink_in_tempdir({
sample1_se_tiny_bam: 'sample1.bam',
annotation_refflat: 'dm6.refflat',
})
def check():
assert '## METRICS CLASS' in open('sample1.metrics').read()
run(dpath('../wrappers/picard/collectrnaseqmetrics'),
snakefile,
check,
input_data_func,
tmpdir,
use_conda=True)
def test_bam_stat(sample1_se_tiny_bam, tmpdir):
snakefile = '''
rule bam_stat:
input:
bam='sample1_R1.bam'
output: txt='sample1_R1.bam_stat.txt'
wrapper: "file:wrapper"
'''
input_data_func = symlink_in_tempdir({
sample1_se_tiny_bam: 'sample1_R1.bam',
})
def check():
"""
check for line lengths and that they are at least different sized
"""
with open('sample1_R1.bam_stat.txt', 'r') as handle:
results = handle.readlines()
assert results[5].split(':')[0] == 'Total records'
assert results[-1] == 'Proper-paired reads map to different chrom:0\n'
run(dpath('../wrappers/rseqc/bam_stat'),
snakefile,
check,
input_data_func,
tmpdir,
use_conda=True)
def test_fastq_screen(sample1_se_tiny_fq, bowtie2_indexes, tmpdir):
snakefile = '''
rule fastq_screen:
input:
fastq='sample1_R1.fastq.gz',
dm6={indexes}
output:
txt='sample1_R1_screen.txt'
params:
subset=100000,
aligner='bowtie2'
wrapper:
"file:wrapper"
'''.format(indexes=bowtie2_indexes)
input_data_func = symlink_in_tempdir(
{sample1_se_tiny_fq: 'sample1_R1.fastq.gz'})
def check():
with open('sample1_R1_screen.txt') as fh:
res = fh.readlines()
r1 = res[0].strip().split()
r3 = res[2].strip().split()
assert r1[-1] == '100000'
assert r3[0] == 'dm6'
run(dpath('../wrappers/fastq_screen'), snakefile, check, input_data_func,
tmpdir)
def test_cutadapt_pe(sample1_pe_tiny_fq, tmpdir):
snakefile = '''
rule cutadapt:
input:
R1='sample1_R1.fastq.gz',
R2='sample1_R2.fastq.gz',
output:
R1='sample1_R1.trim.fastq.gz',
R2='sample2_R1.trim.fastq.gz',
params: extra='-a AAA'
log: 'sample1.cutadapt.log'
wrapper: "file:wrapper"
'''
input_data_func=symlink_in_tempdir(
{
sample1_pe_tiny_fq[0]: 'sample1_R1.fastq.gz',
sample1_pe_tiny_fq[1]: 'sample1_R2.fastq.gz',
}
)
def check():
"""
check for line lengths and that they are at least different sized
"""
a = sum(1 for _ in gzip.open('sample1_R1.fastq.gz'))
b = sum(1 for _ in gzip.open('sample1_R1.trim.fastq.gz'))
assert a == b == 4040
assert 'This is cutadapt' in open('sample1.cutadapt.log').readline()
assert os.path.getsize('sample1_R1.fastq.gz') != os.path.getsize('sample1_R1.trim.fastq.gz')
run(dpath('../wrappers/cutadapt'), snakefile, check, input_data_func, tmpdir)
def test_kallisto_quant(tmpdir, sample1_se_tiny_fq, kallisto_index):
snakefile = '''
rule kallisto_quant:
input:
fastq='sample1.fq.gz',
index='out/transcriptome.idx'
params: extra='--single --fragment-length=200 --sd=20'
output:
h5='quant/abundance.h5',
tsv='quant/abundance.tsv',
json='quant/run_info.json',
wrapper: 'file:wrapper'
'''
input_data_func = symlink_in_tempdir({
sample1_se_tiny_fq:
'sample1.fq.gz',
kallisto_index:
'out/transcriptome.idx',
})
def check():
assert sum(1 for _ in open('quant/abundance.tsv')) == 310
assert open('quant/abundance.tsv').readline() == (
'target_id\tlength\teff_length\test_counts\ttpm\n')
keys = [
'call', 'index_version', 'n_bootstraps', 'n_processed',
'n_targets', 'start_time'
]
d = json.load(open('quant/run_info.json'))
for k in keys:
assert k in d
run(dpath('../wrappers/kallisto/quant'), snakefile, check, input_data_func,
tmpdir)
def fastqc(sample1_se_tiny_fq, tmpdir_factory):
snakefile = '''
rule fastqc:
input:
fastq='sample1_R1.fastq.gz'
output:
html='sample1_R1_fastqc.html',
zip='sample1_R1_fastqc.zip'
wrapper: "file:wrapper"'''
input_data_func = symlink_in_tempdir(
{
sample1_se_tiny_fq: 'sample1_R1.fastq.gz'
}
)
tmpdir = str(tmpdir_factory.mktemp('fastqc_fixture'))
run(dpath('../wrappers/fastqc'), snakefile, None, input_data_func, tmpdir)
return os.path.join(tmpdir, 'sample1_R1_fastqc.zip')
def test_gB_cov(sample1_se_tiny_bam, sample1_se_tiny_bam_bai, annotation_bed12,
tmpdir):
snakefile = '''
rule geneBody_coverage:
input:
bam='sample1_R1.sort.bam',
bai='sample1_R1.sort.bam.bai',
bed='dm6.bed12'
output: txt='sample1_R1.geneBodyCoverage.txt',
r='sample1_R1.geneBodyCoverage.r',
img='sample1_R1.geneBodyCoverage.pdf',
wrapper: "file:wrapper"
'''
input_data_func = symlink_in_tempdir({
sample1_se_tiny_bam: 'sample1_R1.sort.bam',
sample1_se_tiny_bam_bai['bai']: 'sample1_R1.sort.bam.bai',
annotation_bed12: 'dm6.bed12'
})
def check():
"""
check for line lengths and that they are at least different sized
"""
# R code
with open('sample1_R1.geneBodyCoverage.r', 'r') as handle:
result = handle.readline().split(' ')[0]
assert result == 'sample1_R1.sort'
# text
with open('sample1_R1.geneBodyCoverage.txt', 'r') as handle:
result = handle.readlines()[1].split('\t')[0]
assert result == 'sample1_R1.sort'
# PDF
assert os.path.exists('sample1_R1.geneBodyCoverage.pdf')
run(dpath('../wrappers/rseqc/geneBody_coverage'),
snakefile,
check,
input_data_func,
tmpdir,
use_conda=True)
def sample1_se_bam_bai(sample1_se_bam, tmpdir_factory):
"""
Returns both the bam and the bam.bai
"""
snakefile = '''
rule index:
input: bam='sample1.sorted.bam'
output: bai='sample1.sorted.bam.bai'
wrapper: 'file:wrapper'
'''
input_data_func = symlink_in_tempdir(
{sample1_se_bam: 'sample1.sorted.bam'})
tmpdir = str(tmpdir_factory.mktemp('sample1_se_bam_bai'))
run(dpath('../wrappers/samtools/index'), snakefile, None, input_data_func,
tmpdir)
return {
'bam': os.path.join(tmpdir, 'sample1.sorted.bam'),
'bai': os.path.join(tmpdir, 'sample1.sorted.bam.bai'),
}
def test_fastqc(sample1_se_tiny_fq, tmpdir):
snakefile = '''
rule fastqc:
input:
fastq='sample1_R1.fastq.gz'
output:
html='results/sample1_R1.html',
zip='sample1_R1.zip'
wrapper: "file:wrapper"'''
input_data_func=symlink_in_tempdir(
{
sample1_se_tiny_fq: 'sample1_R1.fastq.gz'
}
)
def check():
assert '<html>' in open('results/sample1_R1.html').readline()
contents = [
'sample1_R1_fastqc/',
'sample1_R1_fastqc/Icons/',
'sample1_R1_fastqc/Images/',
'sample1_R1_fastqc/Icons/fastqc_icon.png',
'sample1_R1_fastqc/Icons/warning.png',
'sample1_R1_fastqc/Icons/error.png',
'sample1_R1_fastqc/Icons/tick.png',
'sample1_R1_fastqc/summary.txt',
'sample1_R1_fastqc/Images/per_base_quality.png',
'sample1_R1_fastqc/Images/per_tile_quality.png',
'sample1_R1_fastqc/Images/per_sequence_quality.png',
'sample1_R1_fastqc/Images/per_base_sequence_content.png',
'sample1_R1_fastqc/Images/per_sequence_gc_content.png',
'sample1_R1_fastqc/Images/per_base_n_content.png',
'sample1_R1_fastqc/Images/sequence_length_distribution.png',
'sample1_R1_fastqc/Images/duplication_levels.png',
'sample1_R1_fastqc/Images/adapter_content.png',
'sample1_R1_fastqc/fastqc_report.html',
'sample1_R1_fastqc/fastqc_data.txt',
'sample1_R1_fastqc/fastqc.fo'
]
for i in zipfile.ZipFile('sample1_R1.zip').namelist():
assert i in contents
run(dpath('../wrappers/fastqc'), snakefile, check, input_data_func, tmpdir)
def bowtie2_indexes(dm6_fa, tmpdir_factory):
d = tmpdir_for_func(tmpdir_factory)
snakefile = '''
rule bowtie2:
input: fasta='dm6.fa'
output: index=['dm6.1.bt2', 'dm6.2.bt2']
log: 'bowtie2.log'
wrapper: 'file:wrapper'
'''
input_data_func = symlink_in_tempdir({dm6_fa: 'dm6.fa'})
def check():
assert 'Total time for backward call to driver' in open(
'bowtie2.log').readlines()[-1]
assert list(shell('bowtie2-inspect dm6 -n',
iterable=True)) == ['2L', '2R']
run(dpath('../wrappers/bowtie2/build'), snakefile, check, input_data_func,
d)
return aligners.bowtie2_index_from_prefix(os.path.join(d, 'dm6'))
def test_multiqc(fastqc, tmpdir):
snakefile = '''
rule multiqc:
input: 'results/sample1_R1_fastqc.zip'
output: 'multiqc.html'
log: 'log'
params:
analysis_directory='results'
wrapper: 'file:wrapper'
'''
input_data_func = symlink_in_tempdir({
fastqc:
'results/sample1_R1_fastqc.zip',
})
def check():
assert '<!DOCTYPE html>' in open('multiqc.html').readline()
run(dpath('../wrappers/multiqc'), snakefile, check, input_data_func,
tmpdir)
def kallisto_index(tmpdir_factory, transcriptome):
d = tmpdir_for_func(tmpdir_factory)
snakefile = '''
rule kallisto:
input: fasta='transcriptome.fa'
output: index='transcriptome.idx'
log: 'log'
wrapper: 'file:wrapper'
'''
input_data_func = symlink_in_tempdir({
transcriptome: 'transcriptome.fa',
})
def check():
log = open('log').read()
assert '[build] target deBruijn graph'
run(dpath('../wrappers/kallisto/index'), snakefile, check, input_data_func,
d)
return os.path.join(d, 'transcriptome.idx')
def test_tin(sample1_se_tiny_bam, sample1_se_tiny_bam_bai, annotation_bed12,
tmpdir):
snakefile = '''
rule tin:
input:
bam='sample1_R1.sort.bam',
bai='sample1_R1.sort.bam.bai',
bed='dm6.bed12'
output: table='sample1_R1.tin.tsv',
summary='sample1_R1.tin.summary.txt'
wrapper: "file:wrapper"
'''
input_data_func = symlink_in_tempdir({
sample1_se_tiny_bam: 'sample1_R1.sort.bam',
sample1_se_tiny_bam_bai['bai']: 'sample1_R1.sort.bam.bai',
annotation_bed12: 'dm6.bed12'
})
def check():
"""
check for line lengths and that they are at least different sized
"""
# R code
with open('sample1_R1.tin.tsv', 'r') as handle:
result = handle.readline().strip().split('\t')
assert result == ['geneID', 'chrom', 'tx_start', 'tx_end', 'TIN']
# text
with open('sample1_R1.tin.summary.txt', 'r') as handle:
result = handle.readline().strip().split('\t')
assert result == ['Bam_file', 'TIN(mean)', 'TIN(median)', 'TIN(stdev)']
run(dpath('../wrappers/rseqc/tin'),
snakefile,
check,
input_data_func,
tmpdir,
use_conda=True)
def sample1_se_dupradar(sample1_se_bam_markdups, annotation, tmpdir_factory):
snakefile = '''
rule dupradar:
input:
bam='sample1.bam',
annotation='dm6.gtf'
output:
density_scatter='sample1.density_scatter.png',
expression_histogram='sample1.expression_histogram.png',
expression_barplot='sample1.expression_barplot.png',
expression_boxplot='sample1.expression_boxplot.png',
multimapping_histogram='sample1.multimapping_histogram.png',
dataframe='sample1.dupradar.tsv',
model='sample1.model.txt',
curve='sample1.curve.txt'
wrapper:
'file:wrapper'
'''
input_data_func = symlink_in_tempdir({
sample1_se_bam_markdups['bam']: 'sample1.bam',
annotation: 'dm6.gtf',
})
tmpdir = str(tmpdir_factory.mktemp('dupradar_fixture'))
run(dpath('../wrappers/dupradar'),
snakefile,
None,
input_data_func,
tmpdir,
use_conda=False)
mapping = dict(
density_scatter='sample1.density_scatter.png',
expression_histogram='sample1.expression_histogram.png',
expression_barplot='sample1.expression_barplot.png',
expression_boxplot='sample1.expression_boxplot.png',
multimapping_histogram='sample1.multimapping_histogram.png',
dataframe='sample1.dupradar.tsv',
)
for k, v in mapping.items():
mapping[k] = os.path.join(tmpdir, v)
return mapping
def test_hisat2_align_se_SRA(hisat2_indexes, tmpdir):
d = _dict_of_hisat2_indexes(hisat2_indexes, '2L')
indexes = list(d.values())
snakefile = '''
rule hisat2_align:
input:
index={indexes}
output:
bam='sample1.bam'
params: hisat2_extra='--sra-acc SRR1990338'
log: "hisat2.log"
wrapper: "file:wrapper"
'''.format(indexes=indexes)
input_data_func = symlink_in_tempdir(d)
def check():
assert "overall alignment rate" in open('hisat2.log').read()
# should have at least some mapped and unmapped
assert int(list(shell('samtools view -c -f 0x04 sample1.bam', iterable=True))[0]) > 0
assert int(list(shell('samtools view -c -F 0x04 sample1.bam', iterable=True))[0]) > 0
run(dpath('../wrappers/hisat2/align'), snakefile, check, input_data_func, tmpdir)
def hisat2_indexes(dm6_fa, tmpdir_factory):
d = tmpdir_for_func(tmpdir_factory)
snakefile = '''
rule hisat2:
input: fasta='2L.fa'
output: index=['2L.1.ht2', '2L.2.ht2']
log: 'hisat.log'
wrapper: 'file:wrapper'
'''
input_data_func = symlink_in_tempdir(
{
dm6_fa: '2L.fa'
}
)
def check():
assert 'Total time for call to driver' in open('hisat.log').readlines()[-1]
assert list(shell('hisat2-inspect 2L -n', iterable=True)) == ['2L', '2R']
run(
dpath('../wrappers/hisat2/build'),
snakefile, check, input_data_func, d)
return aligners.hisat2_index_from_prefix(os.path.join(d, '2L'))
def salmon_index(tmpdir_factory, transcriptome):
d = tmpdir_for_func(tmpdir_factory)
snakefile = '''
rule salmon:
input: fasta='transcriptome.fa'
output: hash='salmon_index/hash.bin'
log: 'log'
wrapper: 'file:wrapper'
'''
input_data_func = symlink_in_tempdir(
{
transcriptome: 'transcriptome.fa',
}
)
def check():
log = open('log').read()
assert '[info] done building index' in log
run(
dpath('../wrappers/salmon/index'),
snakefile, check, input_data_func, d)
return os.path.join(d, 'salmon_index')
def test_deeptools_bamCoverage(sample1_se_bam, sample1_se_bam_bai, tmpdir):
snakefile = '''
rule deeptools:
input:
bam='sample1.bam',
bai='sample1.bam.bai'
output: 'sample1.bw',
log: 'deeptools.log'
wrapper: "file:wrapper"
'''
input_data_func = symlink_in_tempdir({
sample1_se_bam:
'sample1.bam',
sample1_se_bam_bai['bai']:
'sample1.bam.bai',
})
def check():
bw = pyBigWig.open('sample1.bw')
assert bw.header()['sumData'] == 195295397
assert bw.stats('2L')[0] == 8.242775364434165
run(dpath('../wrappers/deeptools/bamCoverage'), snakefile, check,
input_data_func, tmpdir)
def test_deeptools_bamCoverage(sample1_se_tiny_bam, sample1_se_tiny_bam_bai,
tmpdir):
snakefile = '''
rule deeptools:
input:
bam='sample1.bam',
bai='sample1.bam.bai'
output: 'sample1.bw',
log: 'deeptools.log'
wrapper: "file:wrapper"
'''
input_data_func = symlink_in_tempdir({
sample1_se_tiny_bam:
'sample1.bam',
sample1_se_tiny_bam_bai['bai']:
'sample1.bam.bai',
})
def check():
bw = pyBigWig.open('sample1.bw')
header_keys = list(bw.header().keys())
for k in [
'maxVal', 'minVal', 'nBasesCovered', 'nLevels', 'sumData',
'sumSquared', 'version'
]:
assert k in header_keys
# bigWig version should be independent of BAM input, so we can check
# the value
assert bw.header()['version'] == 4
first_chrom = list(bw.chroms().keys())[0]
assert isinstance(bw.stats(first_chrom)[0], float)
run(dpath('../wrappers/deeptools/bamCoverage'), snakefile, check,
input_data_func, tmpdir)
def test_featurecounts_se(sample1_se_tiny_bam, annotation, tmpdir):
snakefile = '''
rule featurecounts:
input:
annotation='dm6.gtf',
bam='sample1.bam'
output:
counts='sample1.counts',
log: 'featurecounts.log'
wrapper: "file:wrapper"
'''
input_data_func = symlink_in_tempdir({
sample1_se_tiny_bam: 'sample1.bam',
annotation: 'dm6.gtf',
})
def check():
assert '//===================' in open('featurecounts.log').read()
assert '# Program:featureCounts' in open('sample1.counts').readline()
assert open('sample1.counts.summary').readline().startswith('Status')
assert sum(1 for _ in open('sample1.counts')) == 169
run(dpath('../wrappers/featurecounts'), snakefile, check, input_data_func,
tmpdir)
def test_infer_experiment(sample1_se_tiny_bam, annotation_bed12, tmpdir):
snakefile = '''
rule infer_experiment:
input:
bam='sample1_R1.bam',
bed='dm6.bed12'
output:
txt = 'sample1_R1.infer_experiment.txt'
wrapper: "file:wrapper"
'''
input_data_func = symlink_in_tempdir({
sample1_se_tiny_bam: 'sample1_R1.bam',
annotation_bed12: 'dm6.bed12'
})
def check():
"""
check for line lengths and that they are at least different sized
"""
expected = dedent("""\
This is SingleEnd Data
Fraction of reads failed to determine:
Fraction of reads explained by "++,--":
Fraction of reads explained by "+-,-+":""").splitlines(False)
with open('sample1_R1.infer_experiment.txt', 'r') as handle:
results = handle.read().strip()
for ex in expected:
assert ex in results
run(dpath('../wrappers/rseqc/infer_experiment'),
snakefile,
check,
input_data_func,
tmpdir,
use_conda=True)
