def __call__(self, **kw):
def _shift(stream, shift):
istart = stream.fields.index('start')
iend = stream.fields.index('end')
i1 = min(istart, iend)
i2 = max(istart, iend)
def _apply_shift(x):
return x[:i1] + (x[i1] + shift,) + x[i1 + 1:i2] + (x[i2] + shift,) + x[i2 + 1:]
return track.FeatureStream((_apply_shift(x) for x in stream),
fields=stream.fields)
tfwd = track.track(kw.get('forward'), chrmeta=kw.get('assembly') or None)
trev = track.track(kw.get('reverse'), chrmeta=kw.get('assembly') or None)
if not kw.get('assembly'): # btrack does the job, take the max of both chromosome lengths
chrmeta = tfwd.chrmeta
for k, v in trev.chrmeta.iteritems():
chrmeta.setdefault(k, {})['length'] = max(v['length'], chrmeta.get(k, {}).get('length', 0))
elif tfwd.chrmeta:
chrmeta = tfwd.chrmeta # For sql files, btrack doesn't make it,
elif trev.chrmeta:
chrmeta = trev.chrmeta # so one can contain the info while the second does not.
else:
raise ValueError("Must specify an assembly.") # In case nothing works - should not happen
shiftval = int(kw.get('shift', 0))
if shiftval < 0: # Determine shift automatically
shiftval = None
xcor_lim = 300
for chrom, v in chrmeta.iteritems():
chrsize = v['length']
xcor_lim = min(xcor_lim, 0.01 * chrsize)
xcor = correlation([tfwd.read(chrom), trev.read(chrom)], regions=(1, chrsize),
limits=(-xcor_lim, xcor_lim))
max_xcor_idx = xcor.argmax()
if xcor[max_xcor_idx] > 0.2:
shiftval = (max_xcor_idx - xcor_lim - 1) / 2
#print "Autocorrelation shift=%i, correlation is %f at index %d for chromosome %s." \
# % (shiftval,xcor[max_xcor_idx],max_xcor_idx,chrom)
break
if not shiftval:
raise ValueError("Unable to detect shift automatically. Must specify a shift value.")
output = self.temporary_path(fname='density_merged', ext='sql')
fields = ['chr', 'start', 'end', 'score']
tout = track.track(output, format='sql', fields=fields, chrmeta=chrmeta,
info={'datatype': 'quantitative'})
mode = 'write'
for chrom in chrmeta.keys():
tout.write(merge_scores([_shift(tfwd.read(selection=chrom), shiftval[chrom]),
_shift(trev.read(selection=chrom), -shiftval[chrom])]),
chrom=chrom, mode=mode, clip=True)
mode = 'append'
tout.close()
trev.close()
tfwd.close()
self.new_file(output, 'density_merged')
return 1
def __call__(self, **kw):
feature_type = int(kw.get('feature_type') or 0)
assembly_id = kw.get('assembly') or None
chrmeta = "guess"
if assembly_id:
assembly = genrep.Assembly(assembly_id)
chrmeta = assembly.chrmeta
genes = assembly.gene_track
exons = assembly.exon_track
elif not(feature_type == 2):
raise ValueError("Please specify an assembly")
signals = kw.get('signals', [])
if not isinstance(signals, list): signals = [signals]
snames = [os.path.splitext(os.path.basename(sig))[0] for sig in signals]
signals = [track(sig, chrmeta=chrmeta) for sig in signals]
if feature_type == 0: #bodies
features = genes
elif feature_type == 1: #promoters
prom_pars = {'before_start': int(kw.get('upstream') or prom_up_def),
'after_start': int(kw.get('downstream') or prom_down_def),
'on_strand': True}
features = lambda c: neighborhood(genes(c), **prom_pars)
elif feature_type == 2: #exons
features = exons
elif feature_type == 3: #custom track
_t = track(kw.get('features'), chrmeta=chrmeta)
chrmeta = _t.chrmeta
features = _t.read
else:
raise ValueError("Feature type not known: %i" % feature_type)
pdf = self.temporary_path(fname='plot_pairs.pdf')
narr = None
if int(kw['mode']) == 0: #correl
xarr = array(range(-cormax, cormax + 1))
srtdchrom = sorted(chrmeta.keys())
features = [x[:3] for chrom in srtdchrom
for x in sorted_stream(features(chrom))]
_f = ['chr', 'start', 'end', 'score']
narr = correlation([s.read(fields=_f) for s in signals],
features, (-cormax, cormax), True)
elif int(kw['mode']) == 1: #density
xarr = None
for chrom in chrmeta:
feat = features(chrom)
means = score_by_feature([s.read(chrom) for s in signals], feat)
mf = means.fields[len(feat.fields):]
_n, _l = score_array(means, mf)
if _n.size == 0: continue
if narr is None: narr = _n
else: narr = vstack((narr, _n))
else:
raise ValueError("Mode not implemented: %s" % kw['mode'])
if narr is None:
raise ValueError("No data")
pairs(narr, xarr, labels=snames, output=pdf)
self.new_file(pdf, 'plot_pairs')
return self.display_time()
