def setup(self):
self.m = metaseq.genomic_signal(
metaseq.example_filename('gdc.bam'), kind='bam')
line = '[%s] %s\n' % (datetime.datetime.now(), self.__class__.__name__)
print line
sys.stdout.flush()
pass
def setup(self):
self.m = metaseq.genomic_signal(metaseq.example_filename('gdc.bam'),
kind='bam')
line = '[%s] %s\n' % (datetime.datetime.now(), self.__class__.__name__)
print line
sys.stdout.flush()
pass
def test_errors():
"these things should raise errors"
def check(error, callable_obj, args, kwargs):
assert_raises(error, callable_obj, *args, **kwargs)
class X(metaseq.filetype_adapters.BaseAdapter):
def make_fileobj(self):
return None
items = [
(ValueError, metaseq.filetype_adapters.BaseAdapter, (metaseq.example_filename('gdc.bed'),), {}),
(NotImplementedError, metaseq.filetype_adapters.BigWigAdapter(metaseq.example_filename('gdc.bigwig')).__getitem__, (0,), {}),
(ValueError, X("").__getitem__, (0,), {}),
#(ValueError, gs['bam'].local_coverage, ['chr2L:1-5', 'chr2L:1-5'], dict(processes=PROCESSES)),
]
for error, callable_obj, args, kwargs in items:
yield check, error, callable_obj, args, kwargs
def run_metaseq():
# set up a BamSignal object
m = metaseq.genomic_signal(metaseq.example_filename("wgEncodeUwTfbsK562CtcfStdAlnRep1.bam"), kind="bam")
print "metaseq starting...",
sys.stdout.flush()
t0 = time.time()
# Tweak processes and chunksize as needed to balance CPUs and I/O.
PROCESSES = 6
CHUNKSIZE = 100
# the trick is to use a single bin...
ms_array = m.array(windows, processes=PROCESSES, chunksize=CHUNKSIZE, bins=1)
t1 = time.time()
print "completed in %.2fs" % (t1 - t0)
sys.stdout.flush()
return ms_array.ravel()
def run_metaseq():
# set up a BamSignal object
m = metaseq.genomic_signal(
metaseq.example_filename('wgEncodeUwTfbsK562CtcfStdAlnRep1.bam'),
kind='bam')
print 'metaseq starting...',
sys.stdout.flush()
t0 = time.time()
# Tweak processes and chunksize as needed to balance CPUs and I/O.
PROCESSES = 6
CHUNKSIZE = 100
# the trick is to use a single bin...
ms_array = m.array(windows,
processes=PROCESSES,
chunksize=CHUNKSIZE,
bins=1)
t1 = time.time()
print 'completed in %.2fs' % (t1 - t0)
sys.stdout.flush()
return ms_array.ravel()
import multiprocessing
from matplotlib import pyplot as plt
import matplotlib
import numpy as np
import metaseq
import pybedtools
# Use example data and generate some random features
gs = metaseq.genomic_signal(metaseq.example_filename('x.bam'), 'bam')
features = pybedtools.BedTool()\
.window_maker(
b=pybedtools.BedTool('chr2L 0 500000',
from_string=True).fn,
w=1000)\
.shuffle(seed=1, genome={'chr2L': (0, 5000000)})
genes = []
for i, f in enumerate(features):
genes.append('gene_%s' % i)
genes = np.array(genes)
arr = gs.array(features, processes=multiprocessing.cpu_count(), bins=100)
# At this point, each item in `genes` corresponds to the same row in `arr`
ind, breaks = metaseq.plotutils.clustered_sortind(arr, k=5)
# Boundaries of clusters are provided in `breaks`.
# So the first cluster's original indices into `arr` are:
cluster_1_inds = ind[0:breaks[0]]
# Which means the genes in the first cluster are:
"""
Many of these tests use the minimal test/data/gdc.bed file which has just
enough complexity to be useful in testing corner cases. When reading through
the tests, it's useful to have that file open to understand what's happening.
"""
import os
import metaseq
import multiprocessing
from metaseq.array_helpers import ArgumentError
import numpy as np
from nose.tools import assert_raises
from nose.plugins.skip import SkipTest
gs = {}
for kind in ['bed', 'bam', 'bigbed', 'bigwig']:
gs[kind] = metaseq.genomic_signal(metaseq.example_filename('gdc.%s' % kind), kind)
PROCESSES = int(os.environ.get("METASEQ_PROCESSES", multiprocessing.cpu_count()))
def test_tointerval():
assert metaseq.helpers.tointerval("chr2L:1-10[-]").strand == '-'
assert metaseq.helpers.tointerval("chr2L:1-10[+]").strand == '+'
assert metaseq.helpers.tointerval("chr2L:1-10").strand == '.'
def test_local_count():
def check(kind, coord, expected, stranded):
try:
result = gs[kind].local_count(coord, stranded=stranded)
except NotImplementedError:
raise SkipTest("Incompatible bx-python version for bigBed")
def test_example_data_exists():
assert os.path.exists(metaseq.example_filename('x.bam'))
assert os.path.exists(metaseq.example_filename('gdc.bam'))
def setup(self):
self.m = metaseq.genomic_signal(metaseq.example_filename('gdc.bigbed'),
kind='bigbed')
Convenience function to close all mini-browser figures
"""
for fig in FIGS:
plt.close(fig)
# Choices for RUN_TYPE are:
# * 'intron': all introns of all genes on the selected chromosomes
# * 'TSS' : gene-level TSSs, +/- upstream and downstream bp
# * 'peaks' : peaks from ENCODE; acts as a positive control on the numbers
RUN_TYPE = 'TSS'
try:
chip = chipseq.Chipseq(
ip_bam=metaseq.example_filename(
'wgEncodeHaibTfbsK562Atf3V0416101AlnRep1.bam'
),
control_bam=metaseq.example_filename(
'wgEncodeHaibTfbsK562RxlchV0416101AlnRep1.bam'
),
dbfn=metaseq.example_filename(
'Homo_sapiens.GRCh37.66.cleaned.gtf.db')
)
except ValueError:
raise ValueError("please use the download_data.py script in the "
"data directory")
if RUN_TYPE == "TSS":
# Gets all genes on selected chroms, then applies the TSS modifier and
# saves the results
def test_db():
# should work
d.attach_db(None)
d.attach_db(metaseq.example_filename('dmel-all-r5.33-cleaned.gff.db'))
"""
Many of these tests use the minimal test/data/gdc.bed file which has just
enough complexity to be useful in testing corner cases. When reading through
the tests, it's useful to have that file open to understand what's happening.
"""
import os
import metaseq
import multiprocessing
from metaseq.array_helpers import ArgumentError
import numpy as np
from nose.tools import assert_raises
from nose.plugins.skip import SkipTest
gs = {}
for kind in ['bed', 'bam', 'bigbed', 'bigwig']:
gs[kind] = metaseq.genomic_signal(
metaseq.example_filename('gdc.%s' % kind), kind)
PROCESSES = int(
os.environ.get("METASEQ_PROCESSES", multiprocessing.cpu_count()))
def test_tointerval():
assert metaseq.helpers.tointerval("chr2L:1-10[-]").strand == '-'
assert metaseq.helpers.tointerval("chr2L:1-10[+]").strand == '+'
assert metaseq.helpers.tointerval("chr2L:1-10").strand == '.'
def test_local_count():
def check(kind, coord, expected, stranded):
try:
result = gs[kind].local_count(coord, stranded=stranded)
module for testing the larger files (x.bam, x.bed.gz, etc)
"""
import multiprocessing
import metaseq
import pybedtools
CPUS = multiprocessing.cpu_count()
gs = {}
for kind in ['bam', 'bigwig', 'bed', 'bigbed']:
if kind == 'bed':
ext = 'bed.gz'
else:
ext = kind
gs[kind] = metaseq.genomic_signal(
metaseq.example_filename('x.%s' % ext), kind)
# generate the test features
features = pybedtools.BedTool()\
.window_maker(
b=pybedtools.BedTool('chr2L 0 500000',
from_string=True).fn,
w=1000)\
.shuffle(seed=1,
genome={'chr2L': (0, 5000000)})
args = (features,)
kwargs = dict(processes=CPUS, bins=100)
bam_array = gs['bam'].array(*args, **kwargs)
bed_array = gs['bed'].array(*args, **kwargs)
bw_array = gs['bigwig'].array(*args, method='get_as_array', **kwargs)
def peak_panel(self, ax, feature):
bedtool = pybedtools.BedTool(self.bed)
features = bedtool.intersect([feature], u=True)
track = Track(features)
ax.add_collection(track)
ax.axis('tight')
return feature
if __name__ == "__main__":
import metaseq
import gffutils
import pybedtools
G = gffutils.FeatureDB(
metaseq.example_filename('Homo_sapiens.GRCh37.66.cleaned.gtf.db'))
ip = metaseq.genomic_signal(
metaseq.example_filename('wgEncodeUwTfbsK562CtcfStdAlnRep1.bam'),
'bam')
inp = metaseq.genomic_signal(
metaseq.example_filename('wgEncodeUwTfbsK562InputStdAlnRep1.bam'),
'bam')
peaks = pybedtools.BedTool(metaseq.example_filename(
'wgEncodeUwTfbsK562CtcfStdPkRep1.narrowPeak.gz'))
plotting_kwargs = [
dict(color='r', label='IP'),
dict(color='k', linestyle=':', label='input')]
local_coverage_kwargs = dict(fragment_size=200)
import multiprocessing
from matplotlib import pyplot as plt
import matplotlib
import numpy as np
import metaseq
import pybedtools
# Use example data and generate some random features
gs = metaseq.genomic_signal(metaseq.example_filename('x.bam'), 'bam')
features = pybedtools.BedTool()\
.window_maker(
b=pybedtools.BedTool('chr2L 0 500000',
from_string=True).fn,
w=1000)\
.shuffle(seed=1, genome={'chr2L': (0, 5000000)})
genes = []
for i, f in enumerate(features):
genes.append('gene_%s' % i)
genes = np.array(genes)
arr = gs.array(features, processes=multiprocessing.cpu_count(), bins=100)
# At this point, each item in `genes` corresponds to the same row in `arr`
ind, breaks = metaseq.plotutils.clustered_sortind(arr, k=5)
# Boundaries of clusters are provided in `breaks`.
# So the first cluster's original indices into `arr` are:
cluster_1_inds = ind[0:breaks[0]]
# Which means the genes in the first cluster are:
def peak_panel(self, ax, feature):
bedtool = pybedtools.BedTool(self.bed)
features = bedtool.intersect([feature], u=True)
track = Track(features)
ax.add_collection(track)
ax.axis('tight')
return feature
if __name__ == "__main__":
import metaseq
import gffutils
import pybedtools
G = gffutils.FeatureDB(
metaseq.example_filename('Homo_sapiens.GRCh37.66.cleaned.gtf.db'))
ip = metaseq.genomic_signal(
metaseq.example_filename('wgEncodeUwTfbsK562CtcfStdAlnRep1.bam'),
'bam')
inp = metaseq.genomic_signal(
metaseq.example_filename('wgEncodeUwTfbsK562InputStdAlnRep1.bam'),
'bam')
peaks = pybedtools.BedTool(
metaseq.example_filename(
'wgEncodeUwTfbsK562CtcfStdPkRep1.narrowPeak.gz'))
plotting_kwargs = [
dict(color='r', label='IP'),
dict(color='k', linestyle=':', label='input')
]
def setup(self):
self.m = metaseq.genomic_signal(
metaseq.example_filename('gdc.bigbed'), kind='bigbed')
def setup(self):
deseq_fn = metaseq.example_filename('ex.deseq')
db_fn = metaseq.example_filename('dmel-all-r5.33-cleaned.gff.db')
self.d = metaseq.ResultsTable(deseq_fn, db_fn)
def test_example_data_exists():
assert os.path.exists(metaseq.example_filename('x.bam'))
assert os.path.exists(metaseq.example_filename('gdc.bam'))
Diagnostic plots are generated at the end of the script.
TODO: figure out what's causing the discrepancies (open vs closed intervals?
Binning artifact? CIGAR operations?)
"""
import os
import sys
import time
import numpy as np
import metaseq
import pybedtools
from matplotlib import pyplot as plt
bam_fn = metaseq.example_filename("wgEncodeUwTfbsK562CtcfStdAlnRep1.bam")
if not os.path.exists(bam_fn):
raise ValueError("Please run download_data.py in test/data dir to retrieve ENCODE " "data used for examples")
# Construct 10kb windows, but subset to only use chr19 (to speed up the test)
print "creating windows..."
sys.stdout.flush()
windows = pybedtools.BedTool().window_maker(genome="hg19", w=10000).filter(lambda x: x.chrom == "chr19").saveas()
def run_bedtools():
# set up a BAM-based BedTool
bt = pybedtools.BedTool(bam_fn)
if __name__ == "__main__":
import sys
choices = ['xcorr', 'chipseq']
try:
examples = sys.argv[1:]
except IndexError:
print 'Choices are: ', choices
examples = []
for ex in examples:
if ex not in choices:
raise ValueError('%s not in %s' % (ex, choices))
if 'xcorr' in examples:
ip = metaseq.genomic_signal(
metaseq.example_filename(
'wgEncodeUwTfbsK562CtcfStdAlnRep1.bam'), 'bam')
NWINDOWS = 5000
FRAGMENT_SIZE = 1
WINDOWSIZE = 5000
THRESH = FRAGMENT_SIZE / float(WINDOWSIZE) * 10
lags, shift = estimate_shift(
ip, nwindows=NWINDOWS, maxlag=500, thresh=THRESH,
array_kwargs=dict(
processes=8, chunksize=100,
fragment_size=FRAGMENT_SIZE),
verbose=True)
plt.plot(lags, shift.mean(axis=0))
plt.axvline(
lags[np.argmax(shift.mean(axis=0))],
linestyle='--', color='k')
from metaseq import results_table
import metaseq
import numpy as np
fn = metaseq.example_filename('ex.deseq')
d = results_table.ResultsTable(fn)
def test_dataframe_access():
# different ways of accessing get the same data in memory
assert d.id is d.data.id
assert d['id'] is d.data.id
def test_dataframe_subsetting():
assert all(d[:10].data == d.data[:10])
assert all(d.update(d.data[:10]).data == d.data[:10])
def test_copy():
e = d.copy()
e.id = 'a'
assert e.id[0] == 'a'
assert d.id[0] != 'a'
def smoke_tests():
#smoke test for repr
print repr(d)
def test_db():
# should work
"""
module for testing the larger files (x.bam, x.bed.gz, etc)
"""
import multiprocessing
import metaseq
import pybedtools
CPUS = multiprocessing.cpu_count()
gs = {}
for kind in ['bam', 'bigwig', 'bed', 'bigbed']:
if kind == 'bed':
ext = 'bed.gz'
else:
ext = kind
gs[kind] = metaseq.genomic_signal(metaseq.example_filename('x.%s' % ext),
kind)
# generate the test features
features = pybedtools.BedTool()\
.window_maker(
b=pybedtools.BedTool('chr2L 0 500000',
from_string=True).fn,
w=1000)\
.shuffle(seed=1,
genome={'chr2L': (0, 5000000)})
args = (features, )
kwargs = dict(processes=CPUS, bins=100)
bam_array = gs['bam'].array(*args, **kwargs)
bed_array = gs['bed'].array(*args, **kwargs)
if __name__ == "__main__":
import sys
choices = ['xcorr', 'chipseq']
try:
examples = sys.argv[1:]
except IndexError:
print 'Choices are: ', choices
examples = []
for ex in examples:
if ex not in choices:
raise ValueError('%s not in %s' % (ex, choices))
if 'xcorr' in examples:
ip = metaseq.genomic_signal(
metaseq.example_filename('wgEncodeUwTfbsK562CtcfStdAlnRep1.bam'),
'bam')
NWINDOWS = 5000
FRAGMENT_SIZE = 1
WINDOWSIZE = 5000
THRESH = FRAGMENT_SIZE / float(WINDOWSIZE) * 10
lags, shift = estimate_shift(ip,
nwindows=NWINDOWS,
maxlag=500,
thresh=THRESH,
array_kwargs=dict(
processes=8,
chunksize=100,
fragment_size=FRAGMENT_SIZE),
verbose=True)
from metaseq import results_table
import metaseq
import numpy as np
fn = metaseq.example_filename('ex.deseq')
d = results_table.ResultsTable(fn)
def test_dataframe_access():
# different ways of accessing get the same data in memory
assert d.id is d.data.id
assert d['id'] is d.data.id
def test_dataframe_subsetting():
assert all(d[:10].data == d.data[:10])
assert all(d.update(d.data[:10]).data == d.data[:10])
def test_copy():
e = d.copy()
e.id = 'a'
assert e.id[0] == 'a'
assert d.id[0] != 'a'
def smoke_tests():
#smoke test for repr
print repr(d)
def peak_panel(self, ax, feature):
bedtool = pybedtools.BedTool(self.bed)
features = bedtool.intersect([feature], u=True)
track = Track(features)
ax.add_collection(track)
# ax.axis('tight')
return feature
if __name__ == "__main__":
import metaseq
import gffutils
import pybedtools
G = gffutils.FeatureDB(metaseq.example_filename("Homo_sapiens.GRCh37.66.cleaned.gtf.db"))
ip = metaseq.genomic_signal(metaseq.example_filename("wgEncodeUwTfbsK562CtcfStdAlnRep1.bam"), "bam")
inp = metaseq.genomic_signal(metaseq.example_filename("wgEncodeUwTfbsK562InputStdAlnRep1.bam"), "bam")
peaks = pybedtools.BedTool(metaseq.example_filename("wgEncodeUwTfbsK562CtcfStdPkRep1.narrowPeak.gz"))
plotting_kwargs = [dict(color="r", label="IP"), dict(color="k", linestyle=":", label="input")]
local_coverage_kwargs = dict(fragment_size=200)
b = SignalMiniBrowser([ip, inp], plotting_kwargs=plotting_kwargs, local_coverage_kwargs=local_coverage_kwargs)
g = GeneModelMiniBrowser([ip, inp], G, plotting_kwargs=plotting_kwargs, local_coverage_kwargs=local_coverage_kwargs)
p = PeakMiniBrowser([ip, inp], peaks, plotting_kwargs=plotting_kwargs, local_coverage_kwargs=local_coverage_kwargs)
"""
Settings for the ctcf_peaks example script
"""
import gffutils
import metaseq
UPSTREAM = 1000
DOWNSTREAM = 1000
BINS = 100
FRAGMENT_SIZE = 200
GENOME = 'hg19'
CHROMS = ['chr1', 'chr2']
gtfdb = metaseq.example_filename('Homo_sapiens.GRCh37.66.cleaned.gtf.db')
G = gffutils.FeatureDB(gtfdb)
Diagnostic plots are generated at the end of the script.
TODO: figure out what's causing the discrepancies (open vs closed intervals?
Binning artifact? CIGAR operations?)
"""
import os
import sys
import time
import numpy as np
import metaseq
import pybedtools
from matplotlib import pyplot as plt
bam_fn = metaseq.example_filename('wgEncodeUwTfbsK562CtcfStdAlnRep1.bam')
if not os.path.exists(bam_fn):
raise ValueError(
'Please run download_data.py in test/data dir to retrieve ENCODE '
'data used for examples')
# Construct 10kb windows, but subset to only use chr19 (to speed up the test)
print 'creating windows...'
sys.stdout.flush()
windows = pybedtools.BedTool()\
.window_maker(genome='hg19', w=10000)\
.filter(lambda x: x.chrom == 'chr19')\
.saveas()
def setup(self):
deseq_fn = metaseq.example_filename('ex.deseq')
db_fn = metaseq.example_filename('dmel-all-r5.33-cleaned.gff.db')
self.d = metaseq.ResultsTable(deseq_fn, db_fn)
return s
def keys(self):
return self.fn_dict.keys()
def values(self):
return [self._dict[key] for key in self.keys()]
def items(self):
return list((key, self._dict[key]) for key in self.keys())
if __name__ == "__main__":
import metaseq
from matplotlib import pyplot as plt
db = metaseq.example_filename('dmel-all-r5.33-cleaned.gff.db')
import_kwargs = dict(comment='#')
d = DESeqResults(
metaseq.example_filename('rrp6-s2-polyA.final.summary'),
db=db,
import_kwargs=import_kwargs,
)
e = DESeqResults(
metaseq.example_filename('rrp40-s2-polyA.final.summary'),
db=db,
import_kwargs=import_kwargs,
)
d = d.align_with(e)
if (i == j) and hist_kwargs:
ax.hist(xfunc(p.ix[i][val]), **hist_kwargs)
else:
scatter(p.ix[i][val],
p.ix[j][val],
ax=ax,
xlab_prefix=i + " ",
ylab_prefix=j + " ",
**kwargs)
axind += 1
if __name__ == "__main__":
from metaseq import example_filename
dbfn = example_filename('Homo_sapiens.GRCh37.66.cleaned.gtf.db')
db = gffutils.FeatureDB(dbfn)
p = pandas.Panel({
'uninduced_1':
deseq_dataframe(example_filename('GSM847565_SL2585.table'),
index_col='id',
db=db),
'induced_1':
deseq_dataframe(example_filename('GSM847566_SL2592.table'),
index_col='id',
db=db),
'uninduced_2':
deseq_dataframe(example_filename('GSM847567_SL4337.table'),
index_col='id',
db=db),
if score != 0:
fout.write('\t'.join([
feature.chrom,
str(start),
str(stop),
str(score)]) + '\n')
start = start + binsize
this_batch = []
i = 0
fout.close()
if __name__ == "__main__":
import metaseq
ip_bam = metaseq.genomic_signal(
metaseq.example_filename(
'wgEncodeUwTfbsK562CtcfStdAlnRep1.bam'), 'bam')
control_bam = metaseq.genomic_signal(
metaseq.example_filename(
'wgEncodeUwTfbsK562InputStdAlnRep1.bam'), 'bam')
BINSIZE = 10
WINDOWSIZE = 10000
BINS = WINDOWSIZE / BINSIZE
features = pybedtools.BedTool()\
.window_maker(genome='hg19', w=WINDOWSIZE)\
.filter(lambda x: x.chrom == 'chr19')
result = compare(
signal1=ip_bam,
signal2=control_bam,
features=features,
import numpy as np
import os
import metaseq
ip_filename = metaseq.helpers.example_filename("wgEncodeHaibTfbsK562Atf3V0416101AlnRep1_chr17.bam")
input_filename = metaseq.helpers.example_filename("wgEncodeHaibTfbsK562RxlchV0416101AlnRep1_chr17.bam")
ip_signal = metaseq.genomic_signal(ip_filename, "bam")
input_signal = metaseq.genomic_signal(input_filename, "bam")
# If you already have TSSs, skip this part.
import gffutils
db = gffutils.FeatureDB(metaseq.example_filename("Homo_sapiens.GRCh37.66_chr17.gtf.db"))
import pybedtools
from pybedtools.featurefuncs import TSS
from gffutils.helpers import asinterval
def tss_generator():
for transcript in db.features_of_type("transcript"):
yield TSS(asinterval(transcript), upstream=1000, downstream=1000)
if not os.path.exists("tsses.gtf"):
tsses = pybedtools.BedTool(tss_generator()).saveas("tsses.gtf")
tsses = pybedtools.BedTool("tsses.gtf")
from metaseq import persistence
ncols = len(p.items)
axind = 1
for i in p.items:
for j in p.items:
ax = fig.add_subplot(nrows, ncols, axind)
if (i == j) and hist_kwargs:
ax.hist(xfunc(p.ix[i][val]), **hist_kwargs)
else:
scatter(p.ix[i][val], p.ix[j][val], ax=ax, xlab_prefix=i + " ", ylab_prefix=j + " ", **kwargs)
axind += 1
if __name__ == "__main__":
from metaseq import example_filename
dbfn = example_filename('Homo_sapiens.GRCh37.66.cleaned.gtf.db')
db = gffutils.FeatureDB(dbfn)
p = pandas.Panel(
{
'uninduced_1': deseq_dataframe(
example_filename('GSM847565_SL2585.table'),
index_col='id', db=db),
'induced_1': deseq_dataframe(
example_filename('GSM847566_SL2592.table'),
index_col='id', db=db),
'uninduced_2': deseq_dataframe(
example_filename('GSM847567_SL4337.table'),
index_col='id', db=db),
import numpy as np
import os
import metaseq
ip_filename = metaseq.helpers.example_filename(
'wgEncodeHaibTfbsK562Atf3V0416101AlnRep1_chr17.bam')
input_filename = metaseq.helpers.example_filename(
'wgEncodeHaibTfbsK562RxlchV0416101AlnRep1_chr17.bam')
ip_signal = metaseq.genomic_signal(ip_filename, 'bam')
input_signal = metaseq.genomic_signal(input_filename, 'bam')
# If you already have TSSs, skip this part.
import gffutils
db = gffutils.FeatureDB(
metaseq.example_filename('Homo_sapiens.GRCh37.66_chr17.gtf.db'))
import pybedtools
from pybedtools.featurefuncs import TSS
from gffutils.helpers import asinterval
def tss_generator():
for transcript in db.features_of_type('transcript'):
yield TSS(asinterval(transcript), upstream=1000, downstream=1000)
if not os.path.exists('tsses.gtf'):
tsses = pybedtools.BedTool(tss_generator()).saveas('tsses.gtf')
tsses = pybedtools.BedTool('tsses.gtf')
from metaseq import persistence
def test_db():
# should work
d.attach_db(None)
d.attach_db(metaseq.example_filename('dmel-all-r5.33-cleaned.gff.db'))
Convenience function to close all mini-browser figures
"""
for fig in FIGS:
plt.close(fig)
# Choices for RUN_TYPE are:
# * 'intron': all introns of all genes on the selected chromosomes
# * 'TSS' : gene-level TSSs, +/- upstream and downstream bp
# * 'peaks' : peaks from ENCODE; acts as a positive control on the numbers
RUN_TYPE = 'TSS'
try:
chip = chipseq.Chipseq(
ip_bam=metaseq.example_filename(
'wgEncodeHaibTfbsK562Atf3V0416101AlnRep1.bam'),
control_bam=metaseq.example_filename(
'wgEncodeHaibTfbsK562RxlchV0416101AlnRep1.bam'),
dbfn=metaseq.example_filename('Homo_sapiens.GRCh37.66.cleaned.gtf.db'))
except ValueError:
raise ValueError("please use the download_data.py script in the "
"data directory")
if RUN_TYPE == "TSS":
# Gets all genes on selected chroms, then applies the TSS modifier and
# saves the results
tss_fn = 'example_tsses.gtf'
if not os.path.exists(tss_fn):
features = pybedtools.BedTool(helpers.gene_generator())\
.filter(helpers.chromfilter)\
.each(helpers.TSS, upstream=settings.UPSTREAM,
if score != 0:
fout.write('\t'.join(
[feature.chrom,
str(start),
str(stop),
str(score)]) + '\n')
start = start + binsize
this_batch = []
i = 0
fout.close()
if __name__ == "__main__":
import metaseq
ip_bam = metaseq.genomic_signal(
metaseq.example_filename('wgEncodeUwTfbsK562CtcfStdAlnRep1.bam'),
'bam')
control_bam = metaseq.genomic_signal(
metaseq.example_filename('wgEncodeUwTfbsK562InputStdAlnRep1.bam'),
'bam')
BINSIZE = 10
WINDOWSIZE = 10000
BINS = WINDOWSIZE / BINSIZE
features = pybedtools.BedTool()\
.window_maker(genome='hg19', w=WINDOWSIZE)\
.filter(lambda x: x.chrom == 'chr19')
result = compare(signal1=ip_bam,
signal2=control_bam,
features=features,
