def findDiffFP(self):
cuts = self.reads
forwardArray, backwardArray = cuts["+"], cuts["-"]
cuts2 = self.reads2
forwardArray2, backwardArray2 = cuts2["+"], cuts2["-"]
# Adjust the FDR threshold to a minimum of withCutoff
threshold = min(self.FDR_value, self.MIN_SCORE)
# Find the footprints at this threshold
offsets = self.footprints(threshold)
# Work out the bootstrap scores for these footprints using the other data set
best_probabilities, best_footprintsizes = pyDNase.footprinting.WellingtonC.diff_calculate(
forwardArray, backwardArray, forwardArray2, backwardArray2,
[i[1] for i in offsets], [i[0] for i in offsets], threshold)
result_intervals = []
for i in offsets:
middle = self.interval.startbp + i[0]
fp_halfsize = (best_footprintsizes[i[0]] // 2)
left = middle - fp_halfsize
right = middle + fp_halfsize
ml_score = best_probabilities[i[0]]
result = pyDNase.GenomicInterval(self.interval.chromosome,
left,
right,
score=ml_score)
result_intervals.append(result)
return result_intervals
def footprints(self, withCutoff=-30, merge=1):
"""
This returns reads GenomicIntervalSet with the intervals retrieved below the specific cutoff applied to the selected data
"""
#This find the positions of all the ranges below the cutoff using reads new method
ranges = []
tempMLE, templogProb = np.array(self.lengths), np.array(self.scores)
#Here we have some different logic for selecting the summits of footprints
#TODO: Document this part
while templogProb.min() < withCutoff:
minimapos = templogProb.argmin()
minimafplen = tempMLE[minimapos]
minimaphalffplen = int(minimafplen) / 2
lbound = max(minimapos - (minimaphalffplen), 0)
rbound = min(minimapos + (minimaphalffplen), len(templogProb))
ranges.append((lbound, rbound, templogProb.min(), minimafplen))
templogProb[max(lbound - minimafplen, 0
):min(rbound + minimafplen, len(templogProb))] = 1
returnSet = pyDNase.GenomicIntervalSet()
#Merges overlapping ranges (TODO: documentation)
if ranges:
# This change here changes the way we merge footprints from the probability trace
#TODO: Documentation
if merge:
merged_ranges = []
while len(ranges):
#Find best score
sorted(ranges, key=lambda x: -x[2])
#Take the last value
best = ranges.pop()
merged_ranges.append(best)
#Check for overlapping regions and remove
new_ranges = []
for c, d, e, f in ranges:
if not c <= best[1] <= d:
new_ranges.append([c, d, e, f])
ranges = new_ranges
else:
merged_ranges = ranges
#Creates reads GenomicIntervalSet and adds the footprints to them
for i in merged_ranges:
rstartbp = self.interval.startbp + i[0]
#We must add one to the end base of the footprint to account for the BED file format
rendbp = self.interval.startbp + i[1] + 1
region = pyDNase.GenomicInterval(self.interval.chromosome,
rstartbp,
rendbp,
strand="+",
score=i[2])
returnSet += region
return returnSet