def combine(trackList, fn, win_size=1000, aggregate={}):
"""
Applies a custom function to a list of tracks, such as union, intersection,
etc., and return a single result track. The input streams need to be ordered
w.r.t 'chr', 'start' and 'end'. To be applied chromosome by chromosome.
Only fields of the first track are kept. Values for a common field are
merged by default according to `common.strand_merge`,`common.no_merge` and `common.generic_merge`,
respectively for strand, chromosome and all others.
:param trackList: list of FeatureStream objects.
:param fn: boolean function to apply, such as bbcflib.gfminer.stream.union.
:param win_size: (int) window size, in bp.
:param aggregate: (dict) for each field name given as a key, its value is the function
to apply to the vector containing all trackList's values for this field in order
to merge them. E.g. ``{'score': lambda x: sum(x)/len(x)}`` will return the average of
all *trackList*'s scores in the output.
:rtype: FeatureStream
"""
aggregate.setdefault('strand',common.strand_merge)
aggregate.setdefault('chr',common.no_merge)
_f = ['start','end']
if all('chr' in t.fields for t in trackList):
_f += ['chr']
if isinstance(fn,str): fn = eval(fn) # can type "combine(...,fn='intersection')"
trackList = [common.cobble(common.reorder(t,fields=_f)) for t in trackList]
return common.fusion(FeatureStream(_combine(trackList,fn,win_size,aggregate),
fields=trackList[0].fields))
def overlap(trackList,trackFeatures,strict=False,annotate=False,flatten=common.cobble):
"""
For each stream in *trackList*, keep only items overlapping at least one element
of *trackFeatures*. The input streams need to be ordered w.r.t 'chr', 'start' and 'end'.
To be applied chromosome by chromosome. If several tracks are given in either trackList
or trackFeatures, they will be concatenated into one.
:param trackList: FeatureStream - the elements to be filtered.
If a list of streams is provided, they will be merged (using `concatenate`).
:param trackFeatures: FeatureStream - the filter.
If a list fo streams is provided, they will be merged (using `concatenate`).
:param strict: (bool) if True, only score regions from *trackList* that
entirely contain a feature region of *trackFeatures* will be returned. [False]
:param annotate: (bool) if True, supplementary annotation (and the corresponding fields)
from *trackFeatures* will be added to the result. [False]
:param flatten: (func) one of None, `common.fusion` or `common.cobble`.
Function to be applied to *trackFeatures* before all. [common.cobble]
:rtype: FeatureStream
"""
def _overlap(tl,tf,stranded,strict):
if strict: olap = lambda x,y: x[0] <= y[0] and y[1] <= x[1]
else: olap = lambda x,y: x[0] < y[1]
if stranded:
tl_strand_idx = tl.fields.index('strand')
tf_strand_idx = tf.fields.index('strand')
same_strand = lambda x,y:x[tl_strand_idx]==y[tf_strand_idx]
else: same_strand = lambda x,y:True
x = tl.next()
for y in tf:
try:
if not same_strand(x,y): x = tl.next()
while x[1] <= y[0]: x = tl.next()
while olap(x,y):
yield x
x = tl.next()
except StopIteration: break
if isinstance(trackFeatures,(list,tuple)): trackList = concatenate(trackFeatures)
if isinstance(trackFeatures,(list,tuple)): trackFeatures = concatenate(trackFeatures)
stranded = 'strand' in (set(trackList.fields) & set(trackFeatures.fields))
if flatten is None: _tf = trackFeatures
else: _tf = flatten(trackFeatures,stranded=stranded)
_tl = common.reorder(trackList,['start','end'])
_tf = common.reorder(trackFeatures,['start','end'])
return FeatureStream(_overlap(_tl,_tf,stranded,strict), _tl.fields)
def merge_scores(trackList, method="arithmetic"):
"""
Creates a stream with per-base average of several score tracks::
X1: __________666666666______
X2: _____2222222222__________
R: _____11111444443333______
:param trackList: list of FeatureStream objects.
:param method: (str) type of average: one of 'arithmetic','geometric', or 'sum' (no average).
:rtype: FeatureStream
"""
tracks = [FeatureStream(common.sentinelize(x, [sys.maxint] * len(x.fields)), x.fields) for x in trackList]
tracks = [common.reorder(t, ["start", "end", "score"]) for t in tracks]
fields = [f for f in tracks[0].fields if all([f in t.fields for t in tracks])] # common fields
elements = [list(x.next()) for x in tracks]
track_denom = 1.0 / len(trackList)
if hasattr(method, "__call__"):
mean_fn = lambda scores, denom: method(scores)
else:
mean_fn = _score_functions.get(method, _arithmetic_mean)
for i in xrange(len(tracks) - 1, -1, -1):
if elements[i][0] == sys.maxint:
tracks.pop(i)
elements.pop(i)
def _stream(tracks):
while tracks:
start = min([x[0] for x in elements])
end = min([x[0] for x in elements if x[0] > start] + [x[1] for x in elements])
scores = [x[2] for x in elements if x[1] > start and x[0] < end]
if len(fields) > 3:
rest = []
for i in range(len(fields[3:])):
r = [str(x[3 + i]) for x in elements if not (x[3 + i] is None) and x[1] > start and x[0] < end]
if all([x == r[0] for x in r]):
rest.append(r[0])
else:
rest.append("|".join(r))
yield (start, end, mean_fn(scores, track_denom)) + tuple(rest)
else:
yield (start, end, mean_fn(scores, track_denom))
for i in xrange(len(tracks) - 1, -1, -1):
if elements[i][0] < end:
elements[i][0] = end
if elements[i][1] <= end:
elements[i] = list(tracks[i].next())
if elements[i][0] == sys.maxint:
tracks.pop(i)
elements.pop(i)
return FeatureStream(_stream(tracks), fields)
def score_by_feature(trackScores, trackFeatures, method='mean'):
"""
For every feature from *trackFeatures*, get the list of all scores it contains
and apply an operation *method* on this list (by default, scores are averaged).
Warning: both score and feature streams must be sorted! (use `common.sorted_stream` is necessary).
The output is a stream similar to *trackFeatures* but with an additional `score` field
for each stream in *trackScores*::
method = 'mean':
X: ------##########--------------##########------
Y: ___________666666666__________6666666666______
R: ______[ 3. ]______________[ 6. ]______
method = 'sum':
X : ------##########--------------##########------
Y1: ___________666666666__________6666666666______
Y2: ___222222_____________________333_____________
R : ______[ 30,6 ]______________[ 60,9 ]______
:param trackScores: (list of) one or several -sorted- score track(s) (FeatureStream).
:param trackFeatures: (FeatureStream) one -sorted- feature track.
:param method: (str of function): operation applied to the list of scores from one feature.
Can be one of 'sum','mean','median','min','max', or a custom function.
:rtype: FeatureStream
"""
def _stream(ts, tf):
X = [common.sentinelize(x, [sys.maxint] * len(x.fields)) for x in ts]
S = [[(-sys.maxint, -sys.maxint, 0.0)] for t in ts]
start_idx = tf.fields.index('start')
end_idx = tf.fields.index('end')
if hasattr(method, '__call__'):
mean_fn = lambda scores, denom: method(scores)
else:
mean_fn = _score_functions.get(method, _arithmetic_mean)
for y in tf:
ystart = y[start_idx]
yend = y[end_idx]
scores = ()
for i in range(len(ts)):
xnext = S[i][-1]
# Load into S all score items which intersect feature y
while xnext[0] < yend:
xnext = X[i].next()
if xnext[1] > ystart: S[i].append(xnext)
n = 0
while S[i][n][1] <= ystart:
n += 1
S[i] = S[i][n:]
scores_y = []
for s in S[i]:
if yend <= s[0]: continue
if s[0] < ystart: start = ystart
else: start = s[0]
if yend < s[1]: end = yend
else: end = s[1]
scores_y.extend([s[2]] * (end - start))
scores += (mean_fn(scores_y, 1.0 / (yend - ystart)), )
yield tuple(y) + scores
if not (isinstance(trackScores, (list, tuple))):
trackScores = [trackScores]
if isinstance(trackFeatures, (list, tuple)):
trackFeatures = concatenate(trackFeatures)
if len(trackScores) > 1 or 'score' in trackFeatures.fields:
_fields = ["score" + str(i) for i in range(len(trackScores))]
else:
_fields = ["score"]
_ts = [common.reorder(t, ['start', 'end', 'score']) for t in trackScores]
return FeatureStream(_stream(_ts, trackFeatures),
trackFeatures.fields + _fields)
def filter_scores(trackScores,
trackFeatures,
method='sum',
strict=False,
annotate=False,
flatten=common.cobble):
"""
Extract from *trackScores* only the regions overlapping *trackFeatures*'s regions.
Warning: both score and features streams must be sorted! (use `common.sorted_stream` if necessary).
Example::
X: _____#########__________#############_______
Y: __________666666666___2222776_444___________
R: __________6666__________22776_444___________
Note: *trackFeatures* is :func:`cobbled <bbcflib.gfminer.common.cobble>` by default (to avoid
score duplications). An alternative is :func:`fusion <bbcflib.gfminer.common.fusion>`, or nothing.
If strand information is present in both *trackScores* and *trackFeatures*, only scores inside
a region of the same strand are kept.
:param trackScores: (FeatureStream) one -sorted- score track.
If a list of streams is provided, they will be merged (using `merge_scores`).
:param trackFeatures: (FeatureStream) one -sorted- feature track.
If a list of streams is provided, they will be merged (using `concatenate`).
:param method: (str) `merge_scores` *method* argument, in case *trackScores* is a list. ['sum']
:param strict: (bool) if True, only score regions from *trackScores* that are
strictly contained in a feature region of *trackFeatures* will be returned. [False]
:param annotate: (bool) if True, supplementary annotation (and the corresponding fields)
from *trackFeatures* will be added to the result. [False]
:param flatten: (func) one of None, `common.fusion` or `common.cobble`.
Function to be applied to *trackFeatures* before all. [common.cobble]
:rtype: FeatureStream
"""
def _stream(ts, tf):
tf = common.sentinelize(tf, [sys.maxint] * len(tf.fields))
info_idx = [k for k, f in enumerate(tf.fields) if f not in ts.fields]
if stranded:
ts_strand_idx = ts.fields.index('strand')
tf_strand_idx = tf.fields.index('strand')
same_strand = lambda x, y: x[ts_strand_idx] == y[tf_strand_idx]
else:
same_strand = lambda x, y: True
Y = []
ynext = (-sys.maxint, -sys.maxint, 0.0)
for x in ts:
xstart = x[0]
xend = x[1]
# Load into Y all feature items which intersect score x
while ynext[0] < xend:
if ynext[1] > xstart:
Y.append(ynext)
ynext = tf.next()
# Remove features that are far behind x
if Y:
n = 0
try:
while Y[n][1] <= xstart:
n += 1
Y = Y[n:]
except IndexError:
Y = [ynext]
# Yield intersections
for y in Y:
if not same_strand(x, y): continue
info = tuple([y[k] for k in info_idx]) if annotate else ()
if strict and (y[0] > xstart or y[1] < xend): continue
if y[0] >= xend: continue # keep for next iteration
start = xstart if y[0] < xstart else y[0]
end = xend if y[1] > xend else y[1]
yield (start, end) + tuple(x[2:]) + info
if isinstance(trackFeatures, (list, tuple)):
trackFeatures = concatenate(trackFeatures)
if isinstance(trackScores, (list, tuple)):
trackScores = merge_scores(trackScores, method)
_info_fields = [
f for f in trackFeatures.fields if f not in trackScores.fields
] if annotate else []
stranded = 'strand' in (set(trackScores.fields)
& set(trackFeatures.fields))
if flatten is None:
_tf = trackFeatures
else:
_tf = flatten(trackFeatures, stranded=stranded)
_ts = common.reorder(trackScores, ['start', 'end'])
_tf = common.reorder(_tf, ['start', 'end'])
return FeatureStream(_stream(_ts, _tf), _ts.fields + _info_fields)
def _test(stream):
return reorder(stream, fields=['2', '1'])
def test_reorder(self):
stream = fstream([(10, 12, 0.5), (14, 15, 1.2)],
fields=['start', 'end', 'score'])
expected = [(12, 0.5, 10), (15, 1.2, 14)]
res = list(reorder(stream, ['end', 'score', 'start']))
self.assertListEqual(res, expected)
def concatenate(trackList, fields=None, remove_duplicates=False, group_by=None, aggregate={}):
"""
Returns one stream containing all features from a list of tracks, ordered by *fields*.
:param trackList: list of FeatureStream objects.
:param fields: (list of str) list of fields to keep in the output (at least ['start','end']).
:param remove_duplicates: (bool) whether to remove items that are identical in several
of the tracks in *trackList*. [False]
:param group_by: (list of str) if specified, elements having all values for these fields in
common will be merged into a singe element. Other fields are merged according to *aggregate*
if specified, or `common.generic_merge` by default.
:aggregate: (dict) for each field name given as a key, its value is the function
to apply to the vector containing all different values for this field in order to merge them.
E.g. ``{'score': lambda x: sum(x)}`` will return the sum of all scores in the output.
:rtype: FeatureStream
"""
def _find_min(feat_tuple):
"""Return the index of the 'smallest' element amongst a tuple of features from
different tracks. Priority is given to the first field; if the first field items
are equal amongst several elements, it looks at the second field, a.s.o."""
nmin = 0
xmin = feat_tuple[0]
for n,x in enumerate(feat_tuple[1:]):
if x[0] == sys.maxint: continue
for k in range(len(x)):
if cmp(hash(x[k]),hash(xmin[k]))<0:
xmin = x
nmin = n+1
break
elif cmp(hash(x[k]),hash(xmin[k]))>0:
break
return nmin
def _weave(_t,N):
"""Generator yielding all features represented in a list of tracks *_t*,
sorted w.r.t the *N* first fields."""
current = [x.next()[:N] for x in _t] # init
allfields = [t.fields for t in _t]
n = _find_min(current)
last = current[n]
current[n] = _t[n].next()[:N]
if not group_by: yield last
while 1:
# Remove duplicates
if remove_duplicates:
while not all([current.count(x)==1 for x in current]):
for k in range(len(current)):
if current.count(current[k]) > 1:
current[k] = _t[k].next()[:N]
n = _find_min(current)
if current[n][0] == sys.maxint: break
if group_by:
idx = [allfields[n].index(f) for f in group_by]
if all(current[n][i] == last[i] for i in idx):
last = tuple(current[n][i] if i in idx \
else aggregate.get(allfields[n][i],common.generic_merge)((last[i],current[n][i])) \
for i in range(len(allfields[n]))) # merge last and current
else:
yield last
last = current[n]
else:
yield current[n]
current[n] = _t[n].next()[:N]
if group_by: yield last
if len(trackList) == 1: return trackList[0]
if fields is None:
fields = trackList[0].fields
fields = [f for f in fields if all(f in t.fields for t in trackList)]
_of = ['start','end']
if 'chr' in fields: _of = ['chr']+_of
if 'name' in fields: _of += ['name']
_of += [f for f in fields if not(f in _of)]
tl = [common.reorder(t,_of) for t in trackList]
tl = [FeatureStream(common.sentinelize(x,(sys.maxint,)*len(x.fields)),x.fields) for x in tl]
return FeatureStream(_weave(tl,len(_of)),fields=_of)
def getNearestFeature(features,
annotations,
thresholdPromot=2000,
thresholdInter=20000,
thresholdUTR=10):
"""
For each element of *features*, searches the nearest element of *annotations* and returns
a stream similar to *features*, with additional annotation fields, e.g.::
('chr5',12,14) -> ('chr5',12,14,'geneId|geneName','location_type','distance').
If there are several genes, they are separated by '_': geneId1|geneName1_geneId2|geneName2.
For each gene, `location_type` is one of:
* 'Intergenic' if there are no genes within a distance `thresholdInter`,
* 'Included' if the feature is included in the gene,
* 'Promot' if the feature is upstream and within `thresholdInter` of the gene start,
* 'Upstream' if the feature is upstream and beyond the promoter of the gene,
* '3UTR' if the feature is downstream and within `thresholdUTR`% of the distance to the next downstream gene,
* 'Downstream' otherwise.
These annotations can be concatenated with '_' as well.
The distance to each gene is negative if the feature is included, positive otherwise.
:param features: (FeatureStream) features track.
:param annotations: (FeatureStream) gene annotation track
(e.g. as obtained with assembly.gene_track()).
:param thresholdPromot: (int) associates the promoter of each gene which promoter is within
this distance of the feature. Above the threshold, associates only the closest. [2000]
:param thresholdInter: (int) no gene beyond this distance will be considered. [100000]
:param thresholdUTR: (int) in case the feature is surrounded by two eligible genes on the
same strand: if distance to gene1's 3'UTR upstream is less than *thresholdUTR*% of the distance
between gene1 and gene2, associated to 3'UTR of gene1, else to promoter of gene2. [10]
:rtype: FeatureStream (..., str, str, str).
::
<-- feat -->
______| thresholdPromot ++++++ thresholdPromot |______
-----|______|-------------------------------------------|______|----------
gene 1 gene 2
feat
______ thresholdInter ++++++ thresholdInter ______
-----|______|----------...------------------...----------------|______|---
gene 1 gene 2
feat
--> ++++++ -->
|______ 10% 90% |______
-----|______|------|------------------|______|----- (attributed to gene1)
gene 1 thresholdUTR gene 2
"""
def _get_feature(_t, _a):
F = []
_a = common.sentinelize(_a, [sys.maxint] * len(_a.fields))
for peak in _t:
distMinBefore = distMinAfter = thresholdInter + 1
gene = dist = typeLoc = ""
geneBefore = geneAfter = strandBefore = strandAfter = None
included = 0
# keep only genes which don't start too far
for annot in _a:
F.append(annot)
if annot[0] > peak[1] + thresholdInter: break
# remove genes that end too far
fpop = -1 # always keep one gene before
for annot in F:
if annot[1] > peak[0] - thresholdInter: break
fpop += 1
if fpop > 0: F = F[fpop:]
for annot in F:
# if the peak is totally included in the gene
if (peak[0] >= annot[0]) and (annot[1] >= peak[1]):
includedGene = annot[2]
includedDist = (
annot[3]
== -1) and annot[1] - peak[1] or peak[0] - annot[0]
included = 1
# if the gene is totally included in the peak
elif (annot[0] > peak[0]) and (peak[1] > annot[1]):
includedGene = annot[2]
includedDist = 0
included = 1
else:
# if annot is not too far 3' and no intersection
if 0 < (peak[0] - annot[1]) < distMinBefore:
distMinBefore = peak[0] - annot[1]
geneBefore = annot[2]
strandBefore = annot[3]
# if intersection (annot is before)
elif annot[0] < peak[0] < annot[1]:
distMinBefore = 0
geneBefore = annot[2]
strandBefore = annot[3]
#print "gene %s overlaps begin of peak %s" % (geneBefore,peakName)
# if annot is not too far 5' and no intersection
if 0 < (annot[0] - peak[1]) < distMinAfter:
distMinAfter = annot[0] - peak[1]
geneAfter = annot[2]
strandAfter = annot[3]
# if intersection (annot is after)
elif annot[0] < peak[1] < annot[1]:
distMinAfter = 0
geneAfter = annot[2]
strandAfter = annot[3]
#print "gene %s overlaps end of peak %s" % (geneAfter,peakName)
# detect intergenic peak
if not (
included
) and distMinBefore > thresholdInter and distMinAfter > thresholdInter:
yield peak + ('', 'Intergenic', thresholdInter)
continue
# detect peak before the first or after the last gene on the chromosome
if geneBefore == None:
if distMinAfter <= thresholdInter:
gene = geneAfter
dist = distMinAfter
typeLoc = (strandAfter == 1) and "Upstream" or "Downstream"
elif geneAfter == None:
if distMinBefore <= thresholdInter:
gene = geneBefore
dist = distMinBefore
typeLoc = (strandBefore
== -1) and "Upstream" or "Downstream"
# detect peak between two genes on the same strand
elif strandBefore == strandAfter:
if strandBefore == 1:
if thresholdUTR * distMinAfter > 100 * distMinBefore:
gene = geneBefore
dist = distMinBefore
if distMinAfter < thresholdPromot:
typeLoc = "3UTR"
else:
typeLoc = "Downstream"
else:
gene = geneAfter
dist = distMinAfter
if dist < thresholdPromot:
typeLoc = "Promot"
else:
typeLoc = "Upstream"
else:
if thresholdUTR * distMinBefore > 100 * distMinAfter:
gene = geneAfter
dist = distMinAfter
if distMinBefore < thresholdPromot:
typeLoc = "3UTR"
else:
typeLoc = "Downstream"
else:
gene = geneBefore
dist = distMinBefore
if dist < thresholdPromot:
typeLoc = "Promot"
else:
typeLoc = "Upstream"
# detect peak between two genes on different strands
else:
# detect peak between 2 promoters
if strandBefore == -1:
typeLoc = "Upstream"
if distMinBefore < distMinAfter:
gene = geneBefore
dist = distMinBefore
if dist < thresholdPromot:
typeLoc = "Promot"
if distMinAfter < thresholdPromot:
typeLoc += "_Promot"
gene += "_" + geneAfter
dist = str(dist) + "_" + str(distMinAfter)
else:
gene = geneAfter
dist = distMinAfter
if dist < thresholdPromot:
typeLoc = "Promot"
if distMinBefore < thresholdPromot:
typeLoc += "_Promot"
gene += "_" + geneBefore
dist = str(dist) + "_" + str(distMinBefore)
# detect peak between 2 3UTR
else:
typeLoc = "Downstream"
# detect peak overlapping the 2 3UTR
if distMinBefore == distMinAfter:
if thresholdUTR * thresholdPromot > 100 * distMinBefore:
typeLoc = "3UTR"
typeLoc += "_" + typeLoc
gene = geneBefore + "_" + geneAfter
dist = str(distMinBefore) + "_" + str(distMinAfter)
elif distMinBefore < distMinAfter:
dist = distMinBefore
gene = geneBefore
if thresholdUTR * thresholdPromot > 100 * dist:
typeLoc = "3UTR"
else:
dist = distMinAfter
gene = geneAfter
if thresholdUTR * thresholdPromot > 100 * dist:
typeLoc = "3UTR"
if included == 1:
gene += "_" + includedGene if gene else includedGene
dist = str(dist)
dist = dist + "_" + str(includedDist) if dist else str(
includedDist)
typeLoc += "_Included" if typeLoc else "Included"
yield peak + (gene, typeLoc, dist)
if isinstance(features, (tuple, list)): features = features[0]
if isinstance(annotations, (tuple, list)): annotations = annotations[0]
features = common.reorder(features, ['start', 'end'])
annot = common.reorder(annotations, ['start', 'end', 'name', 'strand'])
_fields = features.fields + ['gene', 'location_type', 'distance']
return FeatureStream(_get_feature(features, annot), fields=_fields)
def score_by_feature(trackScores, trackFeatures, method="mean"):
"""
For every feature from *trackFeatures*, get the list of all scores it contains
and apply an operation *method* on this list (by default, scores are averaged).
Warning: both score and feature streams must be sorted! (use `common.sorted_stream` is necessary).
The output is a stream similar to *trackFeatures* but with an additional `score` field
for each stream in *trackScores*::
method = 'mean':
X: ------##########--------------##########------
Y: ___________666666666__________6666666666______
R: ______[ 3. ]______________[ 6. ]______
method = 'sum':
X : ------##########--------------##########------
Y1: ___________666666666__________6666666666______
Y2: ___222222_____________________333_____________
R : ______[ 30,6 ]______________[ 60,9 ]______
:param trackScores: (list of) one or several -sorted- score track(s) (FeatureStream).
:param trackFeatures: (FeatureStream) one -sorted- feature track.
:param method: (str of function): operation applied to the list of scores from one feature.
Can be one of 'sum','mean','median','min','max', or a custom function.
:rtype: FeatureStream
"""
def _stream(ts, tf):
X = [common.sentinelize(x, [sys.maxint] * len(x.fields)) for x in ts]
S = [[(-sys.maxint, -sys.maxint, 0.0)] for t in ts]
start_idx = tf.fields.index("start")
end_idx = tf.fields.index("end")
if hasattr(method, "__call__"):
mean_fn = lambda scores, denom: method(scores)
else:
mean_fn = _score_functions.get(method, _arithmetic_mean)
for y in tf:
ystart = y[start_idx]
yend = y[end_idx]
scores = ()
for i in range(len(ts)):
xnext = S[i][-1]
# Load into S all score items which intersect feature y
while xnext[0] < yend:
xnext = X[i].next()
if xnext[1] > ystart:
S[i].append(xnext)
n = 0
while S[i][n][1] <= ystart:
n += 1
S[i] = S[i][n:]
scores_y = []
for s in S[i]:
if yend <= s[0]:
continue
if s[0] < ystart:
start = ystart
else:
start = s[0]
if yend < s[1]:
end = yend
else:
end = s[1]
scores_y.extend([s[2]] * (end - start))
scores += (mean_fn(scores_y, 1.0 / (yend - ystart)),)
yield tuple(y) + scores
if not (isinstance(trackScores, (list, tuple))):
trackScores = [trackScores]
if isinstance(trackFeatures, (list, tuple)):
trackFeatures = concatenate(trackFeatures)
if len(trackScores) > 1 or "score" in trackFeatures.fields:
_fields = ["score" + str(i) for i in range(len(trackScores))]
else:
_fields = ["score"]
_ts = [common.reorder(t, ["start", "end", "score"]) for t in trackScores]
return FeatureStream(_stream(_ts, trackFeatures), trackFeatures.fields + _fields)
def window_smoothing(trackList, window_size, step_size=1, stop_val=sys.maxint, featurewise=False):
"""
Given a (list of) signal track(s) *trackList*, a *window_size* L (in base pairs by default,
or in number of features if *featurewise* is True), and a *step_size*,
return as many signal tracks with, at each position p (multiple of *step_size*),
the average score in the window [p-L/2, p+L/2]::
X: __________666666666666____________
R: ______12345666666666654321________ (not exact scores here)
:param trackList: FeatureStream, or list of FeatureStream objects.
:param window_size: (int) window size in bp.
:param step_size: (int) step length (one score returned per *step_size* positions). [1]
:param stop_val: (int) sequence length. [sys.maxint]
:param featurewise: (bool) bp (False), or number of features (True). [False]
:rtype: FeatureStream
Example of windows, window_size=9, step_size=3:
[0,1,2,3,4,5,6,7,8,9), [3,4,5,6,7,8,9,10,11,12), ...
"""
def _stepping_mean(track, score, denom):
score = 0.0
F = []
score = 0.0
nmid = window_size / 2
for x in track:
F.append(x)
score += x[2]
if len(F) < window_size:
continue
yield (F[nmid][0], F[nmid][1], round(score * denom + 1e-7, 6)) + F[nmid][3:]
for shift in xrange(step_size):
score -= F.pop(0)[2]
def _running_mean(track, win_start, denom):
score = 0.0
F = []
for x in track:
F.append(x)
fstart = F[0][0]
fend = F[0][1]
chrom = F[0][3]
win_start = max(win_start, fstart - window_size)
win_end = win_start + window_size
lstart = F[-1][0]
lend = F[-1][1]
while win_end < lend:
delta = 0
steps = [fend - win_start, lend - win_end]
if fstart > win_start:
steps.append(fstart - win_start)
else:
delta -= F[0][2]
if lstart > win_end:
steps.append(lstart - win_end)
else:
delta += F[-1][2]
nsteps = min(steps)
sst = -(win_start % step_size) % step_size
sen = -(win_start + nsteps % step_size) % step_size
win_center = (win_start + win_end) / 2
if abs(delta) > 1e-11:
delta *= denom
score += delta * sst
for step in xrange(sst, nsteps, step_size):
if score > 1e-11 and win_center + step >= 0 and win_center + step + step_size <= stop_val:
yield (win_center + step, win_center + step + step_size, score, chrom)
score += delta * step_size
score -= delta * sen
else:
if score > 1e-11 and win_center + sst >= 0 and win_center + sen + nsteps <= stop_val:
yield (win_center + sst, win_center + sen + nsteps, score, chrom)
win_start += nsteps
win_end += nsteps
if fend <= win_start:
F.pop(0)
if F:
fstart = F[0][0]
fend = F[0][1]
win_start = max(win_start, fstart - window_size)
win_end = win_start + window_size
if win_end > stop_val:
break
while F:
delta = 0
steps = [fend - win_start]
if fstart > win_start:
steps.append(fstart - win_start)
else:
delta -= F[0][2]
nsteps = min(steps)
sst = -(win_start % step_size) % step_size
sen = -(win_start + nsteps % step_size) % step_size
win_center = (win_start + win_end) / 2
if abs(delta) > 1e-11:
delta *= denom
score += delta * sst
for step in xrange(sst, nsteps, step_size):
if score > 1e-11 and win_center + step >= 0 and win_center + step + step_size <= stop_val:
yield (win_center + step, win_center + step + step_size, score, chrom)
score += delta * step_size
score -= delta * sen
else:
if score > 1e-11 and win_center + sst >= 0 and win_center + sen + nsteps <= stop_val:
yield (win_center + sst, win_center + sen + nsteps, score, chrom)
win_start += nsteps
win_end += nsteps
if fend <= win_start:
F.pop(0)
if F:
fstart = F[0][0]
fend = F[0][1]
win_start = max(win_start, fstart - window_size)
win_end = win_start + window_size
if win_end > stop_val:
break
denom = 1.0 / window_size
win_start = -window_size
_f = ["start", "end", "score"]
if featurewise:
call = _stepping_mean
else:
call = _running_mean
if isinstance(trackList, (list, tuple)):
return [
FeatureStream(call(common.reorder(t, _f), win_start, denom), fields=_f) for n, t in enumerate(trackList)
]
else:
return FeatureStream(call(common.reorder(trackList, _f), win_start, denom), fields=_f)
def filter_scores(trackScores, trackFeatures, method="sum", strict=False, annotate=False, flatten=common.cobble):
"""
Extract from *trackScores* only the regions overlapping *trackFeatures*'s regions.
Warning: both score and features streams must be sorted! (use `common.sorted_stream` if necessary).
Example::
X: _____#########__________#############_______
Y: __________666666666___2222776_444___________
R: __________6666__________22776_444___________
Note: *trackFeatures* is :func:`cobbled <bbcflib.gfminer.common.cobble>` by default (to avoid
score duplications). An alternative is :func:`fusion <bbcflib.gfminer.common.fusion>`, or nothing.
If strand information is present in both *trackScores* and *trackFeatures*, only scores inside
a region of the same strand are kept.
:param trackScores: (FeatureStream) one -sorted- score track.
If a list of streams is provided, they will be merged (using `merge_scores`).
:param trackFeatures: (FeatureStream) one -sorted- feature track.
If a list of streams is provided, they will be merged (using `concatenate`).
:param method: (str) `merge_scores` *method* argument, in case *trackScores* is a list. ['sum']
:param strict: (bool) if True, only score regions from *trackScores* that are
strictly contained in a feature region of *trackFeatures* will be returned. [False]
:param annotate: (bool) if True, supplementary annotation (and the corresponding fields)
from *trackFeatures* will be added to the result. [False]
:param flatten: (func) one of None, `common.fusion` or `common.cobble`.
Function to be applied to *trackFeatures* before all. [common.cobble]
:rtype: FeatureStream
"""
def _stream(ts, tf):
tf = common.sentinelize(tf, [sys.maxint] * len(tf.fields))
info_idx = [k for k, f in enumerate(tf.fields) if f not in ts.fields]
if stranded:
ts_strand_idx = ts.fields.index("strand")
tf_strand_idx = tf.fields.index("strand")
same_strand = lambda x, y: x[ts_strand_idx] == y[tf_strand_idx]
else:
same_strand = lambda x, y: True
Y = []
ynext = (-sys.maxint, -sys.maxint, 0.0)
for x in ts:
xstart = x[0]
xend = x[1]
# Load into Y all feature items which intersect score x
while ynext[0] < xend:
if ynext[1] > xstart:
Y.append(ynext)
ynext = tf.next()
# Remove features that are far behind x
if Y:
n = 0
try:
while Y[n][1] <= xstart:
n += 1
Y = Y[n:]
except IndexError:
Y = [ynext]
# Yield intersections
for y in Y:
if not same_strand(x, y):
continue
info = tuple([y[k] for k in info_idx]) if annotate else ()
if strict and (y[0] > xstart or y[1] < xend):
continue
if y[0] >= xend:
continue # keep for next iteration
start = xstart if y[0] < xstart else y[0]
end = xend if y[1] > xend else y[1]
yield (start, end) + tuple(x[2:]) + info
if isinstance(trackFeatures, (list, tuple)):
trackFeatures = concatenate(trackFeatures)
if isinstance(trackScores, (list, tuple)):
trackScores = merge_scores(trackScores, method)
_info_fields = [f for f in trackFeatures.fields if f not in trackScores.fields] if annotate else []
stranded = "strand" in (set(trackScores.fields) & set(trackFeatures.fields))
if flatten is None:
_tf = trackFeatures
else:
_tf = flatten(trackFeatures, stranded=stranded)
_ts = common.reorder(trackScores, ["start", "end"])
_tf = common.reorder(_tf, ["start", "end"])
return FeatureStream(_stream(_ts, _tf), _ts.fields + _info_fields)
def test_reorder(self):
stream = fstream([(10,12,0.5), (14,15,1.2)], fields=['start','end','score'])
expected = [(12,0.5,10), (15,1.2,14)]
res = list(reorder(stream,['end','score','start']))
self.assertListEqual(res,expected)
def _test(stream):
return reorder(stream,fields=['2','1'])
def window_smoothing(trackList,
window_size,
step_size=1,
stop_val=sys.maxint,
featurewise=False):
"""
Given a (list of) signal track(s) *trackList*, a *window_size* L (in base pairs by default,
or in number of features if *featurewise* is True), and a *step_size*,
return as many signal tracks with, at each position p (multiple of *step_size*),
the average score in the window [p-L/2, p+L/2]::
X: __________666666666666____________
R: ______12345666666666654321________ (not exact scores here)
:param trackList: FeatureStream, or list of FeatureStream objects.
:param window_size: (int) window size in bp.
:param step_size: (int) step length (one score returned per *step_size* positions). [1]
:param stop_val: (int) sequence length. [sys.maxint]
:param featurewise: (bool) bp (False), or number of features (True). [False]
:rtype: FeatureStream
Example of windows, window_size=9, step_size=3:
[0,1,2,3,4,5,6,7,8,9), [3,4,5,6,7,8,9,10,11,12), ...
"""
def _stepping_mean(track, score, denom):
score = 0.0
F = []
score = 0.0
nmid = window_size / 2
for x in track:
F.append(x)
score += x[2]
if len(F) < window_size: continue
yield (F[nmid][0], F[nmid][1], round(score * denom + 1e-7,
6)) + F[nmid][3:]
for shift in xrange(step_size):
score -= F.pop(0)[2]
def _running_mean(track, win_start, denom):
score = 0.0
F = []
for x in track:
F.append(x)
fstart = F[0][0]
fend = F[0][1]
chrom = F[0][3]
win_start = max(win_start, fstart - window_size)
win_end = win_start + window_size
lstart = F[-1][0]
lend = F[-1][1]
while win_end < lend:
delta = 0
steps = [fend - win_start, lend - win_end]
if fstart > win_start: steps.append(fstart - win_start)
else: delta -= F[0][2]
if lstart > win_end: steps.append(lstart - win_end)
else: delta += F[-1][2]
nsteps = min(steps)
sst = -(win_start % step_size) % step_size
sen = -(win_start + nsteps % step_size) % step_size
win_center = (win_start + win_end) / 2
if abs(delta) > 1e-11:
delta *= denom
score += delta * sst
for step in xrange(sst, nsteps, step_size):
if score > 1e-11 and win_center + step >= 0 and win_center + step + step_size <= stop_val:
yield (win_center + step,
win_center + step + step_size, score, chrom)
score += delta * step_size
score -= delta * sen
else:
if score > 1e-11 and win_center + sst >= 0 and win_center + sen + nsteps <= stop_val:
yield (win_center + sst, win_center + sen + nsteps,
score, chrom)
win_start += nsteps
win_end += nsteps
if fend <= win_start:
F.pop(0)
if F:
fstart = F[0][0]
fend = F[0][1]
win_start = max(win_start, fstart - window_size)
win_end = win_start + window_size
if win_end > stop_val: break
while F:
delta = 0
steps = [fend - win_start]
if fstart > win_start: steps.append(fstart - win_start)
else: delta -= F[0][2]
nsteps = min(steps)
sst = -(win_start % step_size) % step_size
sen = -(win_start + nsteps % step_size) % step_size
win_center = (win_start + win_end) / 2
if abs(delta) > 1e-11:
delta *= denom
score += delta * sst
for step in xrange(sst, nsteps, step_size):
if score > 1e-11 and win_center + step >= 0 and win_center + step + step_size <= stop_val:
yield (win_center + step,
win_center + step + step_size, score, chrom)
score += delta * step_size
score -= delta * sen
else:
if score > 1e-11 and win_center + sst >= 0 and win_center + sen + nsteps <= stop_val:
yield (win_center + sst, win_center + sen + nsteps, score,
chrom)
win_start += nsteps
win_end += nsteps
if fend <= win_start:
F.pop(0)
if F:
fstart = F[0][0]
fend = F[0][1]
win_start = max(win_start, fstart - window_size)
win_end = win_start + window_size
if win_end > stop_val: break
denom = 1.0 / window_size
win_start = -window_size
_f = ['start', 'end', 'score']
if featurewise:
call = _stepping_mean
else:
call = _running_mean
if isinstance(trackList, (list, tuple)):
return [
FeatureStream(call(common.reorder(t, _f), win_start, denom),
fields=_f) for n, t in enumerate(trackList)
]
else:
return FeatureStream(call(common.reorder(trackList, _f), win_start,
denom),
fields=_f)
def neighborhood(trackList, before_start=None, after_end=None,
after_start=None, before_end=None, on_strand=False):
"""
Given streams of features and four integers *before_start*, *after_end*,
*after_start* and *before_end*, this will return one or two features
for every input feature:
* Only *before_start* and *after_end* are given::
(start, end, ...) -> (start-before_start, end+after_end, ...)
* Only *before_start* and *after_start* are given::
(start, end, ...) -> (start-before_start, start+after_start, ...)
* Only *after_end* and *before_end* are given::
(start, end, ...) -> (end-before_end, end+after_end, ...)
* If all four parameters are given, a pair of features is generated::
(start, end, ...) -> (start-before_start, start+after_start, ...)
(end-before_end, end+after_end, ...)
* If the boolean parameter *on_strand* is set to True,
then `start` and `end` are understood relative to orientation::
(start, end, -1, ...) -> (start-after_end, start+before_end, -1, ...)
(end-after_start, end+before_start, -1, ...)
(start, end, +1, ...) -> (start-before_start, start+after_start, +1, ...)
(end-before_end, end+after_end, +1, ...)
:param trackList: list of FeatureStream objects.
:param before_start: (int) number of bp before the feature start.
:param after_end: (int) number of bp after feature end.
:param after_start: (int) number of bp after the feature start.
:param before_end: (int) number of bp before the feature end.
:param on_strand: (bool) True to respect strand orientation. [False]
:rtype: FeatureStream
"""
def _generate_single(track,a,b,c,d):
_buf = []
for x in track:
if a:
if on_strand and x[2]<0:
_buf.append((x[0]-after_end, x[0]+before_end+1) + x[2:])
_buf.append((x[1]-after_start-1, x[1]+before_start) + x[2:])
else:
_buf.append((x[0]-before_start, x[0]+after_start+1) + x[2:])
_buf.append((x[1]-before_end-1, x[1]+after_end) + x[2:])
elif b:
if on_strand and x[2]<0:
_buf.append((x[1]-after_start-1, x[1]+before_start) + x[2:])
else:
_buf.append((x[0]-before_start, x[0]+after_start+1) + x[2:])
elif c:
if on_strand and x[2]<0:
_buf.append((x[0]-after_end, x[0]+before_end+1) + x[2:])
else:
_buf.append((x[1]-before_end-1, x[1]+after_end) + x[2:])
elif d:
if on_strand and x[2]<0:
_buf.append((x[0]-after_end, x[1]+before_start) + x[2:])
else:
_buf.append((x[0]-before_start, x[1]+after_end) + x[2:])
_buf.sort()
while _buf and _buf[0][1] < x[0]: yield _buf.pop(0)
while _buf: yield _buf.pop(0)
_fields = ['start','end']
if on_strand: _fields += ['strand']
case1 = True
case2 = True
case3 = True
case4 = True
if before_start is None:
case1 = case2 = case4 = False
if after_end is None:
case1 = case3 = case4 = False
if after_start is None:
case1 = case2 = False
if before_end is None:
case1 = case3 = False
if isinstance(trackList,(list,tuple)):
tl = [common.reorder(t,_fields) for t in trackList]
return [FeatureStream(_generate_single(t,case1,case2,case3,case4),
fields=t.fields) for t in tl]
else:
tl = common.reorder(trackList,_fields)
return FeatureStream(_generate_single(tl,case1,case2,case3,case4),
fields=tl.fields)
def merge_scores(trackList, method='arithmetic'):
"""
Creates a stream with per-base average of several score tracks::
X1: __________666666666______
X2: _____2222222222__________
R: _____11111444443333______
:param trackList: list of FeatureStream objects.
:param method: (str) type of average: one of 'arithmetic','geometric', or 'sum' (no average).
:rtype: FeatureStream
"""
tracks = [
FeatureStream(common.sentinelize(x, [sys.maxint] * len(x.fields)),
x.fields) for x in trackList
]
tracks = [common.reorder(t, ['start', 'end', 'score']) for t in tracks]
fields = [
f for f in tracks[0].fields if all([f in t.fields for t in tracks])
] # common fields
elements = [list(x.next()) for x in tracks]
track_denom = 1.0 / len(trackList)
if hasattr(method, '__call__'):
mean_fn = lambda scores, denom: method(scores)
else:
mean_fn = _score_functions.get(method, _arithmetic_mean)
for i in xrange(len(tracks) - 1, -1, -1):
if elements[i][0] == sys.maxint:
tracks.pop(i)
elements.pop(i)
def _stream(tracks):
while tracks:
start = min([x[0] for x in elements])
end = min([x[0] for x in elements if x[0] > start] +
[x[1] for x in elements])
scores = [x[2] for x in elements if x[1] > start and x[0] < end]
if len(fields) > 3:
rest = []
for i in range(len(fields[3:])):
r = [
str(x[3 + i]) for x in elements if
not (x[3 + i] is None) and x[1] > start and x[0] < end
]
if all([x == r[0] for x in r]):
rest.append(r[0])
else:
rest.append("|".join(r))
yield (start, end, mean_fn(scores, track_denom)) + tuple(rest)
else:
yield (start, end, mean_fn(scores, track_denom))
for i in xrange(len(tracks) - 1, -1, -1):
if elements[i][0] < end:
elements[i][0] = end
if elements[i][1] <= end:
elements[i] = list(tracks[i].next())
if elements[i][0] == sys.maxint:
tracks.pop(i)
elements.pop(i)
return FeatureStream(_stream(tracks), fields)
def getNearestFeature(features, annotations, thresholdPromot=2000, thresholdInter=20000, thresholdUTR=10):
"""
For each element of *features*, searches the nearest element of *annotations* and returns
a stream similar to *features*, with additional annotation fields, e.g.::
('chr5',12,14) -> ('chr5',12,14,'geneId|geneName','location_type','distance').
If there are several genes, they are separated by '_': geneId1|geneName1_geneId2|geneName2.
For each gene, `location_type` is one of:
* 'Intergenic' if there are no genes within a distance `thresholdInter`,
* 'Included' if the feature is included in the gene,
* 'Promot' if the feature is upstream and within `thresholdInter` of the gene start,
* 'Upstream' if the feature is upstream and beyond the promoter of the gene,
* '3UTR' if the feature is downstream and within `thresholdUTR`% of the distance to the next downstream gene,
* 'Downstream' otherwise.
These annotations can be concatenated with '_' as well.
The distance to each gene is negative if the feature is included, positive otherwise.
:param features: (FeatureStream) features track.
:param annotations: (FeatureStream) gene annotation track
(e.g. as obtained with assembly.gene_track()).
:param thresholdPromot: (int) associates the promoter of each gene which promoter is within
this distance of the feature. Above the threshold, associates only the closest. [2000]
:param thresholdInter: (int) no gene beyond this distance will be considered. [100000]
:param thresholdUTR: (int) in case the feature is surrounded by two eligible genes on the
same strand: if distance to gene1's 3'UTR upstream is less than *thresholdUTR*% of the distance
between gene1 and gene2, associated to 3'UTR of gene1, else to promoter of gene2. [10]
:rtype: FeatureStream (..., str, str, str).
::
<-- feat -->
______| thresholdPromot ++++++ thresholdPromot |______
-----|______|-------------------------------------------|______|----------
gene 1 gene 2
feat
______ thresholdInter ++++++ thresholdInter ______
-----|______|----------...------------------...----------------|______|---
gene 1 gene 2
feat
--> ++++++ -->
|______ 10% 90% |______
-----|______|------|------------------|______|----- (attributed to gene1)
gene 1 thresholdUTR gene 2
"""
def _get_feature(_t,_a):
F = []
_a = common.sentinelize(_a, [sys.maxint]*len(_a.fields))
for peak in _t:
distMinBefore = distMinAfter = thresholdInter+1
gene = dist = typeLoc = ""
geneBefore = geneAfter = strandBefore = strandAfter = None
included = 0
# keep only genes which don't start too far
for annot in _a:
F.append(annot)
if annot[0] > peak[1]+thresholdInter: break
# remove genes that end too far
fpop = -1 # always keep one gene before
for annot in F:
if annot[1] > peak[0]-thresholdInter: break
fpop += 1
if fpop>0: F = F[fpop:]
for annot in F:
# if the peak is totally included in the gene
if (peak[0]>=annot[0]) and (annot[1]>=peak[1]):
includedGene = annot[2]
includedDist = (annot[3] == -1) and annot[1]-peak[1] or peak[0]-annot[0]
included = 1
# if the gene is totally included in the peak
elif (annot[0]>peak[0]) and (peak[1]>annot[1]):
includedGene = annot[2]
includedDist = 0
included = 1
else:
# if annot is not too far 3' and no intersection
if 0 < (peak[0]-annot[1]) < distMinBefore:
distMinBefore = peak[0]-annot[1]
geneBefore = annot[2]
strandBefore = annot[3]
# if intersection (annot is before)
elif annot[0] < peak[0] < annot[1]:
distMinBefore = 0
geneBefore = annot[2]
strandBefore = annot[3]
#print "gene %s overlaps begin of peak %s" % (geneBefore,peakName)
# if annot is not too far 5' and no intersection
if 0 < (annot[0]-peak[1]) < distMinAfter:
distMinAfter = annot[0]-peak[1]
geneAfter = annot[2]
strandAfter = annot[3]
# if intersection (annot is after)
elif annot[0] < peak[1] < annot[1]:
distMinAfter = 0
geneAfter = annot[2]
strandAfter = annot[3]
#print "gene %s overlaps end of peak %s" % (geneAfter,peakName)
# detect intergenic peak
if not(included) and distMinBefore > thresholdInter and distMinAfter > thresholdInter:
yield peak+('','Intergenic',thresholdInter)
continue
# detect peak before the first or after the last gene on the chromosome
if geneBefore == None:
if distMinAfter <= thresholdInter:
gene = geneAfter
dist = distMinAfter
typeLoc = (strandAfter == 1) and "Upstream" or "Downstream"
elif geneAfter == None:
if distMinBefore <= thresholdInter:
gene = geneBefore
dist = distMinBefore
typeLoc = (strandBefore == -1) and "Upstream" or "Downstream"
# detect peak between two genes on the same strand
elif strandBefore == strandAfter:
if strandBefore == 1:
if thresholdUTR*distMinAfter > 100*distMinBefore:
gene = geneBefore
dist = distMinBefore
if distMinAfter < thresholdPromot:
typeLoc = "3UTR"
else:
typeLoc = "Downstream"
else:
gene = geneAfter
dist = distMinAfter
if dist < thresholdPromot:
typeLoc = "Promot"
else:
typeLoc = "Upstream"
else:
if thresholdUTR*distMinBefore > 100*distMinAfter:
gene = geneAfter
dist = distMinAfter
if distMinBefore < thresholdPromot:
typeLoc = "3UTR"
else:
typeLoc = "Downstream"
else:
gene = geneBefore
dist = distMinBefore
if dist < thresholdPromot:
typeLoc = "Promot"
else:
typeLoc = "Upstream"
# detect peak between two genes on different strands
else:
# detect peak between 2 promoters
if strandBefore == -1:
typeLoc = "Upstream"
if distMinBefore < distMinAfter:
gene = geneBefore
dist = distMinBefore
if dist < thresholdPromot:
typeLoc = "Promot"
if distMinAfter < thresholdPromot:
typeLoc += "_Promot"
gene += "_"+geneAfter
dist = str(dist)+"_"+str(distMinAfter)
else:
gene = geneAfter
dist = distMinAfter
if dist < thresholdPromot:
typeLoc = "Promot"
if distMinBefore < thresholdPromot:
typeLoc += "_Promot"
gene += "_"+geneBefore
dist = str(dist)+"_"+str(distMinBefore)
# detect peak between 2 3UTR
else:
typeLoc = "Downstream"
# detect peak overlapping the 2 3UTR
if distMinBefore == distMinAfter:
if thresholdUTR*thresholdPromot > 100*distMinBefore:
typeLoc = "3UTR"
typeLoc += "_"+typeLoc
gene = geneBefore+"_"+geneAfter
dist = str(distMinBefore)+"_"+str(distMinAfter)
elif distMinBefore < distMinAfter:
dist = distMinBefore
gene = geneBefore
if thresholdUTR*thresholdPromot > 100*dist:
typeLoc = "3UTR"
else:
dist = distMinAfter
gene = geneAfter
if thresholdUTR*thresholdPromot > 100*dist:
typeLoc = "3UTR"
if included == 1:
gene += "_"+includedGene if gene else includedGene
dist = str(dist)
dist = dist+"_"+str(includedDist) if dist else str(includedDist)
typeLoc += "_Included" if typeLoc else "Included"
yield peak+(gene,typeLoc,dist)
if isinstance(features,(tuple,list)): features = features[0]
if isinstance(annotations,(tuple,list)): annotations = annotations[0]
features = common.reorder(features,['start','end'])
annot = common.reorder(annotations,['start','end','name','strand'])
_fields = features.fields+['gene','location_type','distance']
return FeatureStream(_get_feature(features,annot),fields=_fields)
