def read(handle, format):
alphabet = IUPAC.unambiguous_dna
counts = {}
if format=="pfm":
# reads the motif from Jaspar .pfm file
letters = "ACGT"
for letter, line in zip(letters, handle):
words = line.split()
#if there is a letter in the beginning, ignore it
if words[0]==letter:
words = words[1:]
counts[letter] = map(float, words)
motif = Motif(alphabet, counts=counts)
elif format=="sites":
# reads the motif from Jaspar .sites file
instances = []
for line in handle:
if not line.startswith(">"):
break
# line contains the header ">...."
# now read the actual sequence
line = handle.next()
instance = ""
for c in line.strip():
if c==c.upper():
instance += c
instance = Seq(instance, alphabet)
instances.append(instance)
motif = Motif(alphabet, instances=instances)
else:
raise ValueError("Unknown format %s" % format)
motif.mask = "*"*motif.length
return motif
def read(handle):
"""read(handle)"""
record = Record()
line = handle.next()
record.version = line.strip()
line = handle.next()
record.command = line.strip()
for line in handle:
line = line.strip()
if line=="":
pass
elif line[:4]=="Para":
record.parameters={}
elif line[0]=="#":
seq_name = line.split("\t")[1]
record.sequences.append(seq_name)
elif "=" in line:
par_name, par_value = line.split("=")
par_name = par_name.strip()
par_value = par_value.strip()
record.parameters[par_name]=par_value
elif line[:5]=="Input":
record.sequences=[]
elif line[:5]=="Motif":
words = line.split()
assert words[0]=="Motif"
number = int(words[1])
instances = []
elif line[:3]=="MAP":
motif = Motif(IUPAC.unambiguous_dna, instances)
motif.score = float(line.split()[-1])
motif.number = number
motif.mask = mask
record.append(motif)
elif len(line.split("\t"))==4:
seq = Seq(line.split("\t")[0],IUPAC.unambiguous_dna)
instances.append(seq)
elif "*" in line:
mask = line.strip("\r\n")
else:
raise ValueError(line)
return record