def merge_data_out(FILE,just_params=False):
G=list()
with open(FILE) as FH:
for line in FH:
if "#" == line[0]:
chrom,info = line[1:].strip("\n").split(":")
start_stop, N,aN = info.split(",")
start,stop = start_stop.split("-")
G.append(mdt.segment(chrom,int(start),int(stop),float(N), annotation_N=int(aN)))
elif "~" == line[0]:
G[-1].insert_model_info(line)
elif "N:"==line[:2] or "U:"==line[:2]:
G[-1].insert_component(line)
elif not just_params:
line_array = line.strip("\n").split(",")
data_type,peak, data = line_array[0], line_array[1],",".join(line_array[2:])
if data_type != "dbSNP":
data = [(float(d.split(",")[0]),float(d.split(",")[1])) for d in data.split(":") ]
else:
data = [(float(d.split(",")[0]), d.split(",")) for d in data.split(":") ]
setattr(G[-1], data_type, data)
setattr(G[-1], data_type+"_peak", bool(peak=="True"))
if not hasattr(G[-1], "data_types"):
setattr(G[-1], "data_types", list())
G[-1].data_types.append(data_type)
return G
def run(merged_file, out_file_name, penality,diff_threshold):
FHW = open(out_file_name+"_" + str(penality) + "_" + str(diff_threshold) ,"w" )
I = None
with open(merged_file) as FH:
for line in FH:
if "#" == line[0]:
if I is not None:
output(I, FHW, penality,diff_threshold)
chrom,info = line[1:].strip("\n").split(":")
start_stop, N,aN = info.split(",")
start,stop = start_stop.split("-")
I = mdt.segment(chrom,int(start),int(stop),float(N), annotation_N=int(aN))
elif "~" == line[0]:
I.insert_model_info(line)
elif "N:"==line[:2] or "U:"==line[:2]:
I.insert_component(line)
FHW.close()
def run(FILE, penality, diff_threshold, out_file_name, si_thresh, l_thresh, w_thresh, pi_thresh):
FHW = open(
out_file_name
+ "_"
+ str(penality)
+ "_"
+ str(diff_threshold)
+ "_"
+ str(si_thresh)
+ "_"
+ str(l_thresh)
+ "_"
+ str(w_thresh)
+ "_"
+ str(pi_thresh),
"w",
)
I = None
with open(FILE) as FH:
for line in FH:
if "#" == line[0]:
if I is not None:
ouput(I, FHW)
chrom, info = line[1:].strip("\n").split(":")
start_stop, N, aN = info.split(",")
start, stop = start_stop.split("-")
I = mdt.segment(chrom, int(start), int(stop), float(N), annotation_N=int(aN))
elif "~" == line[0]:
I.insert_model_info(line)
elif "N:" == line[:2] or "U:" == line[:2]:
I.insert_component(line)
else:
line_array = line.strip("\n").split(",")
data_type, peak, data = line_array[0], line_array[1], ",".join(line_array[2:])
if data_type != "dbSNP" and data_type != "ClinVar":
data = [(float(d.split(",")[0]), float(d.split(",")[1])) for d in data.split(":")]
else:
data = [(float(d.split(",")[0]), d.split(",")) for d in data.split(":")]
setattr(I, data_type, data)
setattr(I, data_type + "_peak", bool(peak == "True"))
if not hasattr(I, "data_types"):
setattr(I, "data_types", list())
I.data_types.append(data_type)
def parse_file(FILE, G):
with open(FILE) as FH:
header,I = True,None
for line in FH:
if header:
if "#" == line[0]:
if I is not None:
output(I, G)
chrom,info = line[1:].strip("\n").split(":")
start_stop, N = info.split(",")
start,stop = start_stop.split("-")
I = mdt.segment(chrom,int(start),int(stop),float(N) )
elif "~" == line[0]:
I.insert_model_info(line)
elif "N:"==line[:2] or "U:"==line[:2]:
I.insert_component(line)
else:
header=False
