def print_meme_header(alph):
sys.stdout.write("\nMEME version 4\n\n")
if alph == alphabet.getByName("DNA") or alph == alphabet.getByName("Protein"):
sys.stdout.write("ALPHABET= {}\n\n".format("".join(alph.getSymbols())))
else:
sys.stdout.write("ALPHABET {}\n".format(json.dumps(alph.getName())))
sys.stdout.write(alph.asText())
sys.stdout.write("END ALPHABET\n\n")
if alph.isComplementable():
sys.stdout.write("strands: + -\n\n")
sys.stdout.write("Background letter frequencies (from uniform background):\n")
freq = 1.0 / alph.getLen()
for sym in alph.getSymbols():
sys.stdout.write("{:s} {:.4f} ".format(sym, freq))
sys.stdout.write("\n");
def print_meme_header(alph):
sys.stdout.write("\nMEME version 4\n\n")
if alph == alphabet.getByName("DNA") or alph == alphabet.getByName("Protein"):
sys.stdout.write("ALPHABET= {}\n\n".format("".join(alph.getSymbols())))
else:
sys.stdout.write("ALPHABET {}\n".format(json.dumps(alph.getName())))
sys.stdout.write(alph.asText())
sys.stdout.write("END ALPHABET\n\n")
if alph.isComplementable():
sys.stdout.write("strands: + -\n\n")
sys.stdout.write("Background letter frequencies (from uniform background):\n")
freq = 1.0 / alph.getLen()
for sym in alph.getSymbols():
sys.stdout.write("{:s} {:.4f} ".format(sym, freq))
sys.stdout.write("\n");
def __init__(self, sequence, alpha=None, name="", seqinfo=""):
"""Create a sequence with sequence data.
Specifying the alphabet is optional, so is the name and info.
Example:
>>> myseq = sequence.Sequence('MVSAKKVPAIAMSFGVSF')
will create a sequence with name "", and assign one of the predefined alphabets on basis of what symbols were used.
>>> myseq.getAlphabet().getSymbols()
will most likely output the standard protein alphabet:
('A', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'K', 'L', 'M', 'N', 'P', 'Q', 'R', 'S', 'T', 'V', 'W', 'Y')
"""
self.name = name
self.info = seqinfo
if type(sequence) is str:
self.data = tuple(sequence)
elif type(sequence) is tuple:
self.data = sequence
elif type(sequence) is list:
self.data = tuple(sequence)
else:
raise RuntimeError(
"Sequence data is not specified correctly: must be string or tuple"
)
# Resolve choice of alphabet
if alpha == None:
# Alphabet is not set, attempt to set it automatically...
alpha = alphabet.getBySeq(self.data)
if alpha == None:
raise RuntimeError("Could not identify alphabet from sequence")
elif isinstance(alpha, basestring):
alphaname = alpha
alpha = alphabet.getByName(alphaname)
if alpha == None:
raise RuntimeError("No predefined alphabet with name \"" +
alphaname + "\"")
if not (alpha.isValidString(self.data)):
raise RuntimeError("Invalid alphabet specified: " +
"".join(alpha.getSymbols()) +
" is not compatible with sequence '" +
"".join(self.data) + "'")
elif isinstance(alpha, alphabet.Alphabet):
if not (alpha.isValidString(self.data)):
raise RuntimeError("Invalid alphabet specified: " +
"".join(alpha.getSymbols()) +
" is not compatible with sequence '" +
"".join(self.data) + "'")
else:
raise RuntimeError("Unexpected type for alpha")
def __init__(self, sequence, alpha = None, name = "", seqinfo = ""):
"""Create a sequence with sequence data.
Specifying the alphabet is optional, so is the name and info.
Example:
>>> myseq = sequence.Sequence('MVSAKKVPAIAMSFGVSF')
will create a sequence with name "", and assign one of the predefined alphabets on basis of what symbols were used.
>>> myseq.getAlphabet().getSymbols()
will most likely output the standard protein alphabet:
('A', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'K', 'L', 'M', 'N', 'P', 'Q', 'R', 'S', 'T', 'V', 'W', 'Y')
"""
self.name = name
self.info = seqinfo
if type(sequence) is str:
self.data = tuple(sequence)
elif type(sequence) is tuple:
self.data = sequence
elif type(sequence) is list:
self.data = tuple(sequence)
else:
raise RuntimeError("Sequence data is not specified correctly: must be string or tuple")
# Resolve choice of alphabet
if alpha == None:
# Alphabet is not set, attempt to set it automatically...
alpha = alphabet.getBySeq(self.data)
if alpha == None:
raise RuntimeError("Could not identify alphabet from sequence")
elif isinstance(alpha, basestring):
alphaname = alpha
alpha = alphabet.getByName(alphaname)
if alpha == None:
raise RuntimeError("No predefined alphabet with name \"" + alphaname + "\"")
if not(alpha.isValidString(self.data)):
raise RuntimeError("Invalid alphabet specified: "+"".join(alpha.getSymbols())+" is not compatible with sequence '"+"".join(self.data)+"'")
elif isinstance(alpha, alphabet.Alphabet):
if not(alpha.isValidString(self.data)):
raise RuntimeError("Invalid alphabet specified: "+"".join(alpha.getSymbols())+" is not compatible with sequence '"+"".join(self.data)+"'")
else:
raise RuntimeError("Unexpected type for alpha")
def convert_ambigs(strings, alph):
"""Convert aliases to prime symbol and ambiguous to wildcard
in each of a list of strings. Changes are made in place.
"""
ms = alph.translator(False)
for i in range(len(strings)):
strings[i] = strings[i].translate(ms)
return(strings)
#------------------ Main method -------------------
# Executed if you run this file from the operating system prompt, e.g.
# > python sequence.py
if __name__=='__main__':
alpha = alphabet.getByName('DNA')
#seqs = readFASTA('pos.fasta')
seqs = []
aln = readStrings('tmp0')
#regexp = RegExp(alpha, '[AG]G.[DE]TT[AS].')
pwm = PWM(alpha)
pwm.setFromAlignment(aln)
for row in pwm.pretty():
print row
for s in seqs:
print s.getName(), s.getLen(), s.getAlphabet().getSymbols()
for m in regexp.match( s ):
print "pos: %d pat: %s %4.2f" % (m[0], m[1], m[2])
for m in pwm.match( s ):
print "pos: %d pat: %s %4.2f" % (m[0], m[1], m[2])
def convert_ambigs(strings, alph):
"""Convert aliases to prime symbol and ambiguous to wildcard
in each of a list of strings. Changes are made in place.
"""
ms = alph.translator(False)
for i in range(len(strings)):
strings[i] = strings[i].translate(ms)
return (strings)
#------------------ Main method -------------------
# Executed if you run this file from the operating system prompt, e.g.
# > python sequence.py
if __name__ == '__main__':
alpha = alphabet.getByName('DNA')
#seqs = readFASTA('pos.fasta')
seqs = []
aln = readStrings('tmp0')
#regexp = RegExp(alpha, '[AG]G.[DE]TT[AS].')
pwm = PWM(alpha)
pwm.setFromAlignment(aln)
for row in pwm.pretty():
print row
for s in seqs:
print s.getName(), s.getLen(), s.getAlphabet().getSymbols()
for m in regexp.match(s):
print "pos: %d pat: %s %4.2f" % (m[0], m[1], m[2])
for m in pwm.match(s):
print "pos: %d pat: %s %4.2f" % (m[0], m[1], m[2])