def summary(bwfile1, bwfile2, bwfile_add, bedfile, topnumber, out):
total_result = []
p = BwIO(bwfile1)
q = BwIO(bwfile2)
chrom_len1 = {}
chrom_len2 = {}
for i in p.chromosomeTree['nodes']:
chrom_len1[i['key']] = i['chromSize']
for i in q.chromosomeTree['nodes']:
chrom_len2[i['key']] = i['chromSize']
bwHandle1 = BigWigFile(open(bwfile1, 'rb'))
bwHandle2 = BigWigFile(open(bwfile2, 'rb'))
inf = open(bedfile)
t = time.time()
for line in inf:
ll = line.split()
ll[3] = "-"
if chrom_len1.has_key(ll[0]) and chrom_len2.has_key(ll[0]):
summary = bwHandle1.summarize(ll[0], int(ll[1]), int(ll[2]), 1)
if summary.valid_count == 0:
mean_value1 = 0
else:
mean_value1 = (summary.sum_data / summary.valid_count)[0]
summary = bwHandle2.summarize(ll[0], int(ll[1]), int(ll[2]), 1)
if summary.valid_count == 0:
mean_value2 = 0
else:
mean_value2 = (summary.sum_data / summary.valid_count)[0]
total_result.append(ll + [mean_value1 + mean_value2])
inf.close()
total_result.sort(reverse=True, key=lambda x: x[-1])
bwHs = []
for i in bwfile_add:
bwHs.append(BigWigFile(open(i, 'rb')))
outf = open(out, 'w')
print "scaning 1st ", time.time() - t
t = time.time()
for i in range(min(len(total_result), topnumber)):
ll = total_result[i]
summary = bwHandle1.summarize(ll[0], int(ll[1]), int(ll[2]),
(int(ll[2]) - int(ll[1])))
additional_value1 = ",".join(map(str, list(summary.sum_data)))
summary = bwHandle2.summarize(ll[0], int(ll[1]), int(ll[2]),
(int(ll[2]) - int(ll[1])))
additional_value2 = ",".join(map(str, list(summary.sum_data)))
result = map(str, (ll + [additional_value1, additional_value2]))
for bwH in bwHs:
summary = bwH.summarize(ll[0], int(ll[1]), int(ll[2]),
(int(ll[2]) - int(ll[1])))
additional_value_add = ",".join(map(str, list(summary.sum_data)))
result.append(additional_value_add)
outf.write("\t".join(result) + "\n")
outf.close()
print "scaning 2nd ", time.time() - t
def summary(bwfile,bedfile,topnumber,out):
total_result = []
p=BwIO(bwfile)
chrom_len = {}
for i in p.chromosomeTree['nodes']:
chrom_len[i['key']] = i['chromSize']
bwHandle=BigWigFile(open(bwfile, 'rb'))
inf = open(bedfile)
t = time.time()
for line in inf:
ll = line.split()
ll[3]="-"
if chrom_len.has_key(ll[0]):
summary = bwHandle.summarize(ll[0],int(ll[1]),int(ll[2]),1)
if summary.valid_count == 0:
mean_value = 0
else:
mean_value = (summary.sum_data/summary.valid_count)[0]
total_result.append(ll+[mean_value])
inf.close()
total_result.sort(reverse=True,key=lambda x:x[-1])
outf = open(out,'w')
print "scaning 1st ",time.time()-t
t=time.time()
for i in range(topnumber):
ll = total_result[i]
summary = bwHandle.summarize(ll[0],int(ll[1]),int(ll[2]),(int(ll[2])-int(ll[1])))
additional_value = ",".join(map(str,list(summary.sum_data)))
result = map(str,(ll+[additional_value]))
outf.write("\t".join(result)+"\n")
outf.close()
print "scaning 2nd ",time.time()-t
def get_signal(inputfile,output,signalbw,extend):
signalbw = signalbw.strip().strip(',').split(',')
p=BwIO(signalbw[0])
chrom_len = {}
for i in p.chromosomeTree['nodes']:
chrom_len[i['key']] = i['chromSize']
bwHandle = []
for k in signalbw:
bwHandle.append(BigWigFile(open(k, 'rb')))
inf = open(inputfile)
outf = open(output,'w')
for line in inf:
ll = line.split()
inputlen = len(ll)
if not chrom_len.has_key(ll[0]):
continue
for bwH in bwHandle:
S = (int(ll[1]) + int(ll[2]))/2
E = (int(ll[1]) + int(ll[2]))/2 + 1
try:
signal=bwH.summarize(ll[0],max(0,S-extend),E+extend,1)
except:
break
if float(signal.valid_count) == 0:
ll.append('0')
else:
ll.append(str(float(signal.sum_data/signal.valid_count)))
if len(ll) == ( inputlen + len(bwHandle) ):
outf.write("\t".join(ll)+"\n")
inf.close()
outf.close()
def scan_fp(plusdnase, minusdnase, bed, out, upstream, downstream):
p = BwIO(plusdnase)
chrom_len = {}
for i in p.chromosomeTree['nodes']:
chrom_len[i['key']] = i['chromSize']
bwHandle1 = BigWigFile(open(plusdnase, 'rb'))
bwHandle2 = BigWigFile(open(minusdnase, 'rb'))
inf = open(bed)
outf = open(out, 'w')
for line in inf:
ll = line.split()
if not chrom_len.has_key(ll[0]):
continue
if int(ll[1]) < upstream:
continue
signal1 = bwHandle1.summarize(
ll[0],
int(ll[1]) - upstream,
int(ll[2]) + downstream,
(int(ll[2]) + downstream - int(ll[1]) + upstream))
signal2 = bwHandle2.summarize(
ll[0],
int(ll[1]) - upstream,
int(ll[2]) + downstream,
(int(ll[2]) + downstream - int(ll[1]) + upstream))
#ll.append(str(float(signal.sum_data)))
newll = ll[:6] + map(str, list(signal1.sum_data)) + map(
str, list(signal2.sum_data))
outf.write("\t".join(newll) + "\n")
inf.close()
outf.close()
def get_signal(inputfile, output, vp, vm, dp, dm):
p = BwIO(vp)
chrom_len = {}
for i in p.chromosomeTree['nodes']:
chrom_len[i['key']] = i['chromSize']
vpBw = BigWigFile(open(vp, 'rb'))
vmBw = BigWigFile(open(vm, 'rb'))
dpBw = BigWigFile(open(dp, 'rb'))
dmBw = BigWigFile(open(dm, 'rb'))
inf = open(inputfile)
outf = open(output, 'w')
colnames = [
"chrom", "start", "end", "seq", "motifscore", "strand",
"LncapARsignal", "LncapDNaseCutsite", "LncapDNaseFrag",
"K562DNaseFrag", "LncapFP", "K562FP", "overARpeak", "VehPlus",
"VehMinus", "DHTPlus", "DHTMinus"
]
outf.write("\t".join(colnames) + "\n")
for line in inf:
if line.startswith("chrom"):
continue
ll = line.split()
if not chrom_len.has_key(ll[0]):
continue
signal = vpBw.summarize(ll[0], int(ll[1]) - 50, int(ll[2]) + 50, 1)
ll.append(str(float(signal.sum_data)))
signal = vmBw.summarize(ll[0], int(ll[1]) - 50, int(ll[2]) + 50, 1)
ll.append(str(float(signal.sum_data)))
signal = dpBw.summarize(ll[0], int(ll[1]) - 50, int(ll[2]) + 50, 1)
ll.append(str(float(signal.sum_data)))
signal = dmBw.summarize(ll[0], int(ll[1]) - 50, int(ll[2]) + 50, 1)
ll.append(str(float(signal.sum_data)))
outf.write("\t".join(ll) + "\n")
inf.close()
outf.close()
def get_signal(inputfile, output, Pbw, Nbw, score_range):
persudo = 0.2
p = BwIO(Pbw)
chrom_len = {}
for i in p.chromosomeTree['nodes']:
chrom_len[i['key']] = i['chromSize']
PH = BigWigFile(open(Pbw, 'rb'))
NH = BigWigFile(open(Nbw, 'rb'))
inf = open(inputfile)
outf = open(output, 'w')
for line in inf:
ll = line.split()
if not chrom_len.has_key(ll[0]):
continue
motif_len = int(ll[2]) - int(ll[1])
Psignal = list(
PH.summarize(ll[0], max(int(ll[1]) - 100, 0),
int(ll[1]) + 100, 200).sum_data)
Nsignal = list(
NH.summarize(ll[0], max(int(ll[1]) - 100, 0),
int(ll[1]) + 100, 200).sum_data)
DNase = sum(Psignal) + sum(Nsignal)
if ll[5] == '+':
S_up_same = sum(Psignal[(100 - score_range):100])
S_up_diff = sum(Nsignal[(100 - score_range):100])
S_down_same = sum(Psignal[(100 + motif_len):100 + motif_len +
score_range])
S_down_diff = sum(Nsignal[(100 + motif_len):100 + motif_len +
score_range])
elif ll[5] == '-':
S_up_same = sum(Nsignal[(100 + motif_len):100 + motif_len +
score_range])
S_up_diff = sum(Psignal[(100 + motif_len):100 + motif_len +
score_range])
S_down_same = sum(Nsignal[(100 - score_range):100])
S_down_diff = sum(Psignal[(100 - score_range):100])
else:
print line
sys.exit(1)
# if S_up_same == 0 or S_up_diff ==0 or S_down_same == 0 or S_down_diff == 0:
# continue
FPscore1 = math.log((S_up_same + persudo) * (S_down_diff + persudo) /
((S_up_diff + persudo) * (S_down_same + persudo)),
2)
FPscore2 = math.sqrt(S_up_same) + math.sqrt(S_down_diff) - math.sqrt(
S_up_diff) - math.sqrt(S_down_same)
ll.extend([DNase, FPscore1, FPscore2])
outf.write("\t".join(map(str, ll)) + "\n")
inf.close()
outf.close()
def get_signal(inputfile, output, signalbw):
p = BwIO(signalbw)
chrom_len = {}
for i in p.chromosomeTree['nodes']:
chrom_len[i['key']] = i['chromSize']
bwHandle = BigWigFile(open(signalbw, 'rb'))
inf = open(inputfile)
outf = open(output, 'w')
for line in inf:
ll = line.split()
if not chrom_len.has_key(ll[0]):
continue
signal = bwHandle.summarize(ll[0], max(int(ll[1]) - 50, 0),
int(ll[2]) + 50, 1)
ll.append(str(float(signal.sum_data)))
outf.write("\t".join(ll) + "\n")
inf.close()
outf.close()
def summary(bwfile, bedfile, out, central_max, central_min, flanking_max,
flanking_min, cutoff):
total_result = []
p = BwIO(bwfile)
chrom_len = {}
for i in p.chromosomeTree['nodes']:
chrom_len[i['key']] = i['chromSize']
bwHandle = BigWigFile(open(bwfile, 'rb'))
inf = open(bedfile)
outf = open(out, 'w')
t = time.time()
for line in inf:
ll = line.split()
if chrom_len.has_key(ll[0]):
#t = time.time()
summary = bwHandle.summarize(ll[0], int(ll[1]), int(ll[2]),
(int(ll[2]) - int(ll[1])))
# print "bw sum time",time.time()-t
# t=time.time()
digital = list(summary.sum_data)
# print "trans to list time",time.time()-t
# t=time.time()
FT = (caculate_footprint(digital, central_max, central_min,
flanking_max, flanking_min, cutoff))
# print "scan footprint time",time.time()-t
# time.time()
for ft in FT:
bed = "\t".join(
map(str, [
ll[0],
int(ll[1]) + ft[0],
int(ll[1]) + ft[1], ll[3], ft[2]
])) + "\n"
outf.write(bed)
#print "single time",time.time()-t
#print (int(ll[2])-int(ll[1]))#*1.0/(time.time()-t)
inf.close()
outf.close()
print "scaning 1st ", time.time() - t
def sitepro_scan(pattern,peak,out,w_plus,w_minus,trunk):
inf = open(pattern)
pattern_plus = map(float,inf.readline().strip().split(","))
pattern_minus = map(float,inf.readline().strip().split(","))
all = sum(pattern_plus)+sum(pattern_minus)
p_plus = []
p_minus= []
for i in pattern_plus:
p_plus.append(i/all)
for i in pattern_minus:
p_minus.append(i/all)
inf.close()
l = len(pattern_plus)
p0 = [1.0/(2*l)]*l
inf = open(peak)
p=BwIO(w_plus)
q=BwIO(w_minus)
chrom_len1 = {}
chrom_len2 = {}
for i in p.chromosomeTree['nodes']:
chrom_len1[i['key']] = i['chromSize']
for i in q.chromosomeTree['nodes']:
chrom_len2[i['key']] = i['chromSize']
w_plus_H=BigWigFile(open(w_plus, 'rb'))
w_minus_H=BigWigFile(open(w_minus, 'rb'))
footprint = []
count = 0
t=time.time()
for line in inf:
ll = line.split()
if chrom_len1.has_key(ll[0]) and chrom_len2.has_key(ll[0]):
# print ll[0],int(ll[1])-l,int(ll[2])+l,(int(ll[2])-int(ll[1])+2*l)
p_sum = list(w_plus_H.summarize(ll[0],int(ll[1]),int(ll[2]),(int(ll[2])-int(ll[1]))).sum_data)
m_sum = list(w_minus_H.summarize(ll[0],int(ll[1]),int(ll[2]),(int(ll[2])-int(ll[1]))).sum_data)
#print len(p_sum)
last_start = "NA"
last_end = "NA"
last_value = "NA"
for i in range(len(p_sum)-l):
o_plus = map(float,p_sum[i:i+l])
o_minus = map(float,m_sum[i:i+l])
for k in range(len(o_plus)):
if o_plus[k] > trunk:
o_plus[k]=trunk
if o_minus[k] > trunk:
o_minus[k] = trunk
#print pattern_plus,p0
score = match_pattern(p_plus,p_minus,p0,p0,o_plus,o_minus,l)
if score == "NA":
continue
# print score#i,i+l,score,last_start,last_end,last_value
if last_start == "NA" :
last_start = i
last_end = i+l
last_value = score
elif i >= last_end:
footprint.append([ll[0],int(ll[1])+last_start+3,int(ll[1])+last_end-3,last_value])
last_start = i
last_end = i+l
last_value = score
elif score > last_value:
last_start = i
last_end = i+l
last_value = score
footprint.append([ll[0],int(ll[1])+last_start+3,int(ll[1])+last_end-3,last_value])
if count%100 ==0:
print time.time()-t
t = time.time()
count += 1
outf = open(out,'w')
for fp in footprint:
newline = "\t".join(map(str,fp))+"\n"
outf.write(newline)
outf.close()
def sitepro_scan(pattern,peak,out,w_plus,w_minus,trunk,text,w_chip):
inf = open(pattern)
pattern_plus_pmotif = map(float,inf.readline().strip().split(","))
pattern_minus_pmotif = map(float,inf.readline().strip().split(","))
pattern_plus_mmotif = map(float,inf.readline().strip().split(","))
pattern_minus_mmotif = map(float,inf.readline().strip().split(","))
all_sum_p = sum(pattern_plus_pmotif)+sum(pattern_minus_pmotif)
all_sum_m = sum(pattern_plus_mmotif)+sum(pattern_minus_mmotif)
p_plus = []
p_minus= []
m_plus = []
m_minus = []
for i in range(len(pattern_plus_pmotif)):
p_plus.append(pattern_plus_pmotif[i]/all_sum_p)
p_minus.append(pattern_minus_pmotif[i]/all_sum_p)
m_plus.append(pattern_plus_mmotif[i]/all_sum_m)
m_minus.append(pattern_minus_mmotif[i]/all_sum_m)
inf.close()
l = len(pattern_plus_pmotif)
p0 = [1.0/(2*l)]*l
inf = open(peak)
p=BwIO(w_plus)
q=BwIO(w_minus)
chrom_len1 = {}
chrom_len2 = {}
for i in p.chromosomeTree['nodes']:
chrom_len1[i['key']] = i['chromSize']
for i in q.chromosomeTree['nodes']:
chrom_len2[i['key']] = i['chromSize']
w_plus_H=BigWigFile(open(w_plus, 'rb'))
w_minus_H=BigWigFile(open(w_minus, 'rb'))
w_chip_H=BigWigFile(open(w_chip, 'rb'))
footprint = []
ls=[0]*2*len(pattern_plus_pmotif)
for line in inf:### chr start end name motifscore strand FP DNase chip
ll = line.split()##### 3 below is flanking length
if chrom_len1.has_key(ll[0]) and chrom_len2.has_key(ll[0]):
DNase = float(w_plus_H.summarize(ll[0],(int(ll[1])+int(ll[2]))/2-50,(int(ll[1])+int(ll[2]))/2+50,1).sum_data) + float(w_minus_H.summarize(ll[0],(int(ll[1])+int(ll[2]))/2-50,(int(ll[1])+int(ll[2]))/2+50,1).sum_data)
Chip = float(w_chip_H.summarize(ll[0],(int(ll[1])+int(ll[2]))/2-10,(int(ll[1])+int(ll[2]))/2+10,1).sum_data)
p_sum = list(w_plus_H.summarize(ll[0],int(ll[1])-3-len(pattern_plus_pmotif),int(ll[2])+3+len(pattern_plus_pmotif),(int(ll[2])-int(ll[1])+2*(3+len(pattern_plus_pmotif)))).sum_data)
m_sum = list(w_minus_H.summarize(ll[0],int(ll[1])-3-len(pattern_plus_pmotif),int(ll[2])+3+len(pattern_plus_pmotif),(int(ll[2])-int(ll[1])+2*(3+len(pattern_plus_pmotif)))).sum_data)
last_start = "NA"
last_end = "NA"
last_value = "NA"
for i in range(len(p_sum)-l):
o_plus = map(int,p_sum[i:i+l])
o_minus = map(int,m_sum[i:i+l])
# for k in range(len(o_plus)):
# if o_plus[k] > trunk:
# o_plus[k]=trunk
# if o_minus[k] > trunk:
# o_minus[k] = trunk
if ll[5]=="+":
score = match_pattern(p_plus,p_minus,o_plus,o_minus,l,1)
elif ll[5]=="-":
score = match_pattern(m_plus,m_minus,o_plus,o_minus,l,1)
if i == len(pattern_plus_pmotif):
footprint.append(ll+[score,DNase,Chip])
if last_start == "NA" :
last_start = i
last_end = i+l
last_value = score
elif score > last_value:
last_start = i
last_end = i+l
last_value = score
if last_start ==0 and last_value ==0 :
pass
else:
ls[last_start]+=1
outf = open(out,'w')
for fp in footprint:
newline = "\t".join(map(str,fp))+"\n"
outf.write(newline)
outf.close()
outf = open(text,'w')
outf.write("\t".join(map(str,ls))+"\n")
outf.close()
def sitepro_scan(peak, out, w_plus, w_minus):
inf = open(peak)
p = BwIO(w_plus)
q = BwIO(w_minus)
chrom_len1 = {}
chrom_len2 = {}
for i in p.chromosomeTree['nodes']:
chrom_len1[i['key']] = i['chromSize']
for i in q.chromosomeTree['nodes']:
chrom_len2[i['key']] = i['chromSize']
w_plus_H = BigWigFile(open(w_plus, 'rb'))
w_minus_H = BigWigFile(open(w_minus, 'rb'))
footprint = []
for line in inf: ### chr start end name motifscore strand FP DNase chip
ll = line.split() ##### 3 below is flanking length
if chrom_len1.has_key(ll[0]) and chrom_len2.has_key(ll[0]):
DNase100p = sum(
list(
w_plus_H.summarize(ll[0],
(int(ll[1]) + int(ll[2])) / 2 - 50,
(int(ll[1]) + int(ll[2])) / 2 + 50,
2).sum_data))
DNase100m = sum(
list(
w_minus_H.summarize(ll[0],
(int(ll[1]) + int(ll[2])) / 2 - 50,
(int(ll[1]) + int(ll[2])) / 2 + 50,
2).sum_data))
DNase200p = sum(
list(
w_plus_H.summarize(ll[0],
(int(ll[1]) + int(ll[2])) / 2 - 100,
(int(ll[1]) + int(ll[2])) / 2 + 100,
2).sum_data))
DNase200m = sum(
list(
w_minus_H.summarize(ll[0],
(int(ll[1]) + int(ll[2])) / 2 - 100,
(int(ll[1]) + int(ll[2])) / 2 + 100,
2).sum_data))
DNase300p = sum(
list(
w_plus_H.summarize(ll[0],
(int(ll[1]) + int(ll[2])) / 2 - 150,
(int(ll[1]) + int(ll[2])) / 2 + 150,
2).sum_data))
DNase300m = sum(
list(
w_minus_H.summarize(ll[0],
(int(ll[1]) + int(ll[2])) / 2 - 150,
(int(ll[1]) + int(ll[2])) / 2 + 150,
2).sum_data))
DNase400p = sum(
list(
w_plus_H.summarize(ll[0],
(int(ll[1]) + int(ll[2])) / 2 - 200,
(int(ll[1]) + int(ll[2])) / 2 + 200,
2).sum_data))
DNase400m = sum(
list(
w_minus_H.summarize(ll[0],
(int(ll[1]) + int(ll[2])) / 2 - 200,
(int(ll[1]) + int(ll[2])) / 2 + 200,
2).sum_data))
# Chip = float(w_chip_H.summarize(ll[0],int(ll[1]),int(ll[2]),1).sum_data)
p_sum = list(
w_plus_H.summarize(ll[0],
int(ll[1]) - 200,
int(ll[1]) + 200, 400).sum_data)
m_sum = list(
w_minus_H.summarize(ll[0],
int(ll[1]) - 200,
int(ll[1]) + 200, 400).sum_data)
footprint.append(ll + [
DNase100p, DNase100m, DNase200p, DNase200m, DNase300p,
DNase300m, DNase400p, DNase400m
] + p_sum + m_sum)
outf = open(out, 'w')
for fp in footprint:
newline = "\t".join(map(str, fp)) + "\n"
outf.write(newline)
outf.close()
def main():
usage = "usage: %prog <-r rfile> [options] <bigwig files> ..."
description = "Draw correlation plot for many bigwig files. Based on qc_chIP_whole.py"
optparser = OptionParser(version="%prog 0.1",description=description,usage=usage,add_help_option=False)
optparser.add_option("-h","--help",action="help",help="Show this help message and exit.")
#optparser.add_option("-d","--db",type="str",dest="dbname",help="UCSC db name for the assembly. Default: ce4",default="ce4")
optparser.add_option("-r","--rfile",dest="rfile",
help="R output file. If not set, do not save R file.")
optparser.add_option("-s","--step",dest="step",type="int",
help="sampling step in kbps. default: 100, minimal: 1",default=100)
optparser.add_option("-z","--imgsize",dest="imgsize",type="int",
help="image size in inches, note the PNG dpi is 72. default: 10, minimal: 10",default=10)
optparser.add_option("-f","--format",dest="imgformat",type="string",
help="image format. PDF or PNG",default='PDF')
#optparser.add_option("-m","--method",dest="method",type="string",default="median",
# help="method to process the paired two sets of data in the sampling step. Choices are 'median', 'mean', and 'sample' (just take one point out of a data set). Default: median")
optparser.add_option("-l","--wig-label",dest="wiglabel",type="string",action="append",
help="the wiggle file labels in the figure. No space is allowed. This option should be used same times as wiggle files, and please input them in the same order as -w option. default: will use the wiggle file filename as labels.")
optparser.add_option("--min-score",dest="minscore",type="float",default=-10000,
help="minimum score included in calculation. Points w/ score lower than this will be discarded.")
optparser.add_option("--max-score",dest="maxscore",type="float",default=10000,
help="maximum score included in calculation. Points w/ score larger than this will be discarded.")
optparser.add_option("-H","--heatmap",dest="heatmap",action="store_true",default=False,
help="If True, a heatmap image will be generated instead of paired scatterplot image.")
(options,wigfiles) = optparser.parse_args()
imgfmt = options.imgformat.upper()
if imgfmt != 'PDF' and imgfmt != 'PNG':
print "unrecognized format: %s" % imgfmt
sys.exit(1)
medfunc = mean
wigfilenum = len(wigfiles)
if wigfilenum < 2 or not options.rfile:
error("must provide >=2 wiggle files")
optparser.print_help()
sys.exit(1)
# wig labels
if options.wiglabel and len(options.wiglabel) == wigfilenum:
wiglabel = options.wiglabel
else: # or use the filename
wiglabel = map(lambda x:os.path.basename(x),wigfiles)
if options.step < 1:
error("Step can not be lower than 1!")
sys.exit(1)
if options.imgsize < 10:
error("Image size can not be lower than 10!")
sys.exit(1)
# check the files
for f in wigfiles:
if not os.path.isfile(f):
error("%s is not valid!" % f)
sys.exit(1)
info("number of bigwig files: %d" % wigfilenum)
#get chromosome length from optins.wig[0]:
p=BwIO(wigfiles[0])
chrom_len = {}
for i in p.chromosomeTree['nodes']:
chrom_len[i['key']] = i['chromSize']
# get the common chromosome list:
chrset = set([t['key'] for t in p.chromosomeTree['nodes']])
for bw in wigfiles[1:]:
p=BwIO(bw)
chrset = chrset.intersection(set([t['key'] for t in p.chromosomeTree['nodes']]))
chroms = list(chrset)
if not chroms:
error('No common chrom found')
sys.exit()
info("common chromosomes are %s." % ",".join(chroms))
# Start writing R file
if options.rfile:
rfhd = open(options.rfile,"w")
rfhd.write('''require("RColorBrewer") ## from CRAN\n''')
# for each wig file, sample...
for i in range(len(wigfiles)):
bw = BigWigFile(open(wigfiles[i],'rb'))
info("read wiggle track from bigwig file #%d" % (i+1))
profile = []
for chrom in chroms:
# The too-short chromosome will cause error in bw.summarize function below
# So filter them out
if chrom_len[chrom]/options.step/1000==0:
warn("A very-short chromosome (%s) found and skipped"%chrom)
continue
summary = bw.summarize(chrom, 0, chrom_len[chrom], chrom_len[chrom]/options.step/1000)
if not summary:
continue
profile_chr = summary.sum_data / summary.valid_count
profile_chr = [str(t).replace('nan', 'NA') for t in profile_chr]
profile.extend(profile_chr)
info("write values to r file")
rfhd.write("p%d <- c(%s)\n" %(i, ','.join(profile)))
rfhd.write("c <- cbind(p0")
for i in range(wigfilenum-1):
rfhd.write(",p%d" % (i+1))
rfhd.write(")\n")
rfhd.write("c <- c[ c[,1]<=%f & c[,1]>=%f " % (options.maxscore,options.minscore))
for i in range(wigfilenum-1):
rfhd.write("& c[,%d]<=%f & c[,%d]>=%f " % (i+2,options.maxscore,i+2,options.minscore))
rfhd.write(",]\n")
if imgfmt == 'PDF':
rfhd.write("pdf(\"%s.pdf\",width=%d,height=%d)\n" % (options.rfile,options.imgsize,options.imgsize))
elif imgfmt == 'PNG':
rfhd.write("png(\"%s.png\",units=\"in\",res=150,width=%d,height=%d)\n" % (options.rfile,options.imgsize,options.imgsize))
if options.heatmap: # heatmap
rfhd.write('library(gplots)\n')
rfhd.write('''
m <- cor(c, method="pearson", use="pairwise.complete.obs")
''')
labels = ",".join(map(lambda x:"\""+x+"\"",wiglabel))
rfhd.write("rownames(m) <- c(%s)\n" % labels)
rfhd.write("colnames(m) <- c(%s)\n" % labels)
rfhd.write('# draw the heatmap using gplots heatmap.2\n')
rfhd.write('mn <- -1\n')
rfhd.write('mx <- 1\n')
rfhd.write('n <- 98\n')
rfhd.write('bias <- 1\n')
rfhd.write('mc <- matrix(as.character(round(m, 2)), ncol=dim(m)[2])\n')
rfhd.write('breaks <- seq(mn, mx, (mx-mn)/(n))\n')
rfhd.write('cr <- colorRampPalette(colors = c("#2927FF","#FFFFFF","#DF5C5C"), bias=bias)\n')
rfhd.write('heatmap.2(m, col = cr(n), breaks=breaks, trace="none", cellnote=mc, notecol="black", notecex=1.8, keysize=0.5, density.info="histogram", margins=c(27.0,27.0), cexRow=2.20, cexCol=2.20, revC=T, symm=T)\n')
else: # scatterplot
rfhd.write('''
panel.plot <- function( x,y, ... )
{
par(new=TRUE)
m <- cbind(x,y)
plot(m,col=densCols(m),pch=20)
lines(lowess(m[!is.na(m[,1])&!is.na(m[,2]),]),col="red")
}
panel.cor <- function(x, y, digits=2, prefix="", cex.cor, ...)
{
usr <- par("usr"); on.exit(par(usr))
par(usr = c(0, 1, 0, 1))
r <- cor(x, y,use="complete.obs")
txt <- format(round(r,2),width=5,nsmall=2)
#format(c(r, 0.123456789), digits=digits)[1]
txt <- paste(prefix, txt, sep="")
if(missing(cex.cor)) cex.cor <- 0.8/strwidth(txt)
#text(0.5, 0.5, txt, cex = cex.cor * abs(r))
text(0.5, 0.5, txt, cex = cex.cor)
}
''')
labels = ",".join(map(lambda x:"\""+x+"\"",wiglabel))
rfhd.write('''
pairs(c, lower.panel=panel.plot, upper.panel=panel.cor, labels=c(%s))
''' % (labels))
rfhd.write("dev.off()\n")
rfhd.close()
# try to call R
try:
subprocess.call(['Rscript',options.rfile])
except:
info("Please check %s" % options.rfile)
else:
info("Please check %s" % (options.rfile+'.'+imgfmt))
def sitepro_scan(peak, out, w_plus, w_minus):
inf = open(peak)
p = BwIO(w_plus)
q = BwIO(w_minus)
chrom_len1 = {}
chrom_len2 = {}
for i in p.chromosomeTree['nodes']:
chrom_len1[i['key']] = i['chromSize']
for i in q.chromosomeTree['nodes']:
chrom_len2[i['key']] = i['chromSize']
w_plus_H = BigWigFile(open(w_plus, 'rb'))
w_minus_H = BigWigFile(open(w_minus, 'rb'))
footprint = []
outf = open(out, 'w')
for line in inf: ### chr start end name motifscore strand FP DNase chip
ll = line.split() ##### 3 below is flanking length
try:
START = int(ll[1])
except:
print 'start:', ll[1], line
continue
try:
END = int(ll[2])
except:
print 'end:', ll[2], line
continue
if chrom_len1.has_key(ll[0]) and chrom_len2.has_key(ll[0]):
try:
DNase100p = sum(
list(
w_plus_H.summarize(ll[0], (START + END) / 2 - 50,
(START + END) / 2 + 50,
2).sum_data))
except:
#print ll[0],START,END,(START+END)/2-50,(START+END)/2+50,type(START),type(END),line
DNase100p = sum(
list(
w_plus_H.summarize(ll[0], (START + END) / 2 - 50,
(START + END) / 2 + 50,
1).sum_data))
try:
DNase100m = sum(
list(
w_minus_H.summarize(ll[0], (START + END) / 2 - 50,
(START + END) / 2 + 50,
2).sum_data))
except:
DNase100m = sum(
list(
w_minus_H.summarize(ll[0], (START + END) / 2 - 50,
(START + END) / 2 + 50,
1).sum_data))
DNase200p = sum(
list(
w_plus_H.summarize(ll[0], (START + END) / 2 - 100,
(START + END) / 2 + 100, 2).sum_data))
DNase200m = sum(
list(
w_minus_H.summarize(ll[0], (START + END) / 2 - 100,
(START + END) / 2 + 100, 2).sum_data))
DNase300p = sum(
list(
w_plus_H.summarize(ll[0], (START + END) / 2 - 150,
(START + END) / 2 + 150, 2).sum_data))
DNase300m = sum(
list(
w_minus_H.summarize(ll[0], (START + END) / 2 - 150,
(START + END) / 2 + 150, 2).sum_data))
DNase400p = sum(
list(
w_plus_H.summarize(ll[0], (START + END) / 2 - 200,
(START + END) / 2 + 200, 2).sum_data))
DNase400m = sum(
list(
w_minus_H.summarize(ll[0], (START + END) / 2 - 200,
(START + END) / 2 + 200, 2).sum_data))
# Chip = float(w_chip_H.summarize(ll[0],START,END,1).sum_data)
p_sum = list(
w_plus_H.summarize(ll[0], START - 200, START + 200,
400).sum_data)
m_sum = list(
w_minus_H.summarize(ll[0], START - 200, START + 200,
400).sum_data)
fpline = (ll + [
DNase100p, DNase100m, DNase200p, DNase200m, DNase300p,
DNase300m, DNase400p, DNase400m
] + p_sum + m_sum)
newline = "\t".join(map(str, fpline)) + "\n"
outf.write(newline)
outf.close()
def sitepro_scan(pattern, peak, out, w_plus, w_minus, trunk, text):
inf = open(pattern)
pattern_plus = map(float, inf.readline().strip().split(","))
pattern_minus = map(float, inf.readline().strip().split(","))
all_sum = sum(pattern_plus) + sum(pattern_minus)
p_plus = []
p_minus = []
for i in pattern_plus:
p_plus.append(i / all_sum)
for i in pattern_minus:
p_minus.append(i / all_sum)
inf.close()
l = len(pattern_plus)
p0 = [1.0 / (2 * l)] * l
inf = open(peak)
p = BwIO(w_plus)
q = BwIO(w_minus)
chrom_len1 = {}
chrom_len2 = {}
for i in p.chromosomeTree['nodes']:
chrom_len1[i['key']] = i['chromSize']
for i in q.chromosomeTree['nodes']:
chrom_len2[i['key']] = i['chromSize']
w_plus_H = BigWigFile(open(w_plus, 'rb'))
w_minus_H = BigWigFile(open(w_minus, 'rb'))
footprint = []
# count = 0
# t=time.time()
ls = [0] * 44
for line in inf:
# s=[]
ll = line.split()
if chrom_len1.has_key(ll[0]) and chrom_len2.has_key(ll[0]):
p_sum = list(
w_plus_H.summarize(
ll[0],
int(ll[1]) - 3 - 22,
int(ll[2]) + 3 + 22,
(int(ll[2]) - int(ll[1]) + 6 + 44)).sum_data)
m_sum = list(
w_minus_H.summarize(
ll[0],
int(ll[1]) - 3 - 22,
int(ll[2]) + 3 + 22,
(int(ll[2]) - int(ll[1]) + 6 + 44)).sum_data)
last_start = "NA"
last_end = "NA"
last_value = "NA"
for i in range(len(p_sum) - l):
o_plus = map(int, p_sum[i:i + l])
o_minus = map(int, m_sum[i:i + l])
for k in range(len(o_plus)):
if o_plus[k] > trunk:
o_plus[k] = trunk
if o_minus[k] > trunk:
o_minus[k] = trunk
# o_sum = sum(o_plus)+sum(o_minus)
#print pattern_plus,p0
score = match_pattern(p_plus, p_minus, p0, p0, o_plus, o_minus,
l)
# s.append(score)
if i == 22:
footprint.append(ll + [score])
if last_start == "NA":
last_start = i
last_end = i + l
last_value = score
elif score > last_value:
last_start = i
last_end = i + l
last_value = score
if last_start == 0 and last_value == 0:
pass
else:
ls[last_start] += 1
#footprint.append(ll+[])
# if count%100 ==0:
# print time.time()-t
# print ls
# t = time.time()
# count += 1
outf = open(out, 'w')
for fp in footprint:
newline = "\t".join(map(str, fp)) + "\n"
outf.write(newline)
outf.close()
outf = open(text, 'w')
outf.write("\t".join(map(str, ls)) + "\n")
outf.close()
def getsignal(inputfile,outputfile,BGmatrix,pcut,ncut,pspan,fetch_length=100,gen='hg19'):
p=BwIO(pcut)
chrom_len = {}
for i in p.chromosomeTree['nodes']:
chrom_len[i['key']] = i['chromSize']
pcutbw = BigWigFile(open(pcut, 'rb'))
ncutbw = BigWigFile(open(ncut, 'rb'))
inf = open(inputfile)
pp=[]
pm=[]
X = c.interval(genome=gen)
X.chrom,X.start,X.end,X.val = [],[],[],[]
pBG,nBG = readBG(BGmatrix)
for line in inf:
ll = line.split()
if not chrom_len.has_key(ll[0]):
continue
pout = make_cut(pcutbw,ll,pspan,fetch_length)
nout = make_cut(ncutbw,ll,pspan,fetch_length)
if ll[5] == "-":
pout,nout = nout,pout
if pout == 'NA':
continue
#print len(pout),len(nout),ll[:3]
pp.append(pout)
pm.append(nout)
X.chrom.append(ll[0])
X.start.append(int(ll[1])-pspan -3 + 1)
X.end.append(int(ll[2]) + pspan +3 + 1)
X.val.append(ll[5])
#total[ ( flength - span ) : ( flength + int(ll[2]) - int(ll[1]) + span ) ]
meanp = apply_mean(pp)
meanm = apply_mean(pm)
X.getSequence()
pbglist = []
nbglist = []
for i,elem in enumerate(X.seq):
seq = X.seq[i]
strand = X.val[i]
if 'N' in seq.upper():
continue
pseq = seq[:-1]
nseq = seq[1:]
#if 'N' in pseq or 'N' in nseq:
# continue
p=[]
n=[]
for k in range(len(pseq) +1 - 6):
p.append(pBG[pseq[k:k+6].upper()])
n.append(nBG[nseq[k:k+6].upper()])
if strand != '-':
pbglist.append(p)
nbglist.append(n)
else:
pbglist.append(n[::-1])
nbglist.append(p[::-1])
#print nbglist
meanpbglist = apply_mean(pbglist)
meanmbglist = apply_mean(nbglist)
plot_template(meanp,meanm,meanpbglist,meanmbglist,outputfile)