def setUp(self):
self.ACin = open("Motif/alignace.out")
self.MEMEin = open("Motif/meme.out")
self.PFMin = open("Motif/SRF.pfm")
self.SITESin = open("Motif/Arnt.sites")
self.TFout = "Motif/tf.out"
self.FAout = "Motif/fa.out"
self.PFMout = "Motif/fa.out"
from Bio.Seq import Seq
self.m = Motif.Motif()
self.m.add_instance(Seq("ATATA", self.m.alphabet))
def build_motif(seqs):
"""Create motif from sequences"""
m = Motif.Motif(alphabet=IUPAC.unambiguous_dna)
for seq in seqs:
try:
m.add_instance(Seq(seq, m.alphabet))
except:
print "Diff motif size length?"
return None
m.make_counts_from_instances()
return m
def get_pwm_from_clustalw(clustalw_fname):
"""
Get PWM from CLUSTALW alignments file.
Return PWM and motif object.
"""
from Bio import Motif
from Bio.Alphabet import IUPAC
import Bio.Seq as bio_seq
import Bio.AlignIO as align_io
# Load CLUSTALW file
if not os.path.isfile(clustalw_fname):
raise Exception, "CLUSTALW file %s does not exist" % (clustalw_fname)
clustalw_input = align_io.read(clustalw_fname, "clustal")
motif_obj = Motif.Motif(alphabet=IUPAC.unambiguous_dna)
# Add sequences from CLUSTALW alignment to motif object
for clustalw_seq in clustalw_input.get_all_seqs():
curr_seq = bio_seq.Seq(str(clustalw_seq.seq), IUPAC.unambiguous_dna)
motif_obj.add_instance(curr_seq)
# Compute PWM
pwm = motif_obj.pwm()
return pwm, motif_obj
#!/usr/bin/env python # counts a motif (arg1) with overlaps in a fasta file (arg2) import sys from Bio.Seq import Seq from Bio import SeqIO from Bio import Motif from Bio.Alphabet import IUPAC theMotif = sys.argv[1] fastafile = sys.argv[2] momo=Motif.Motif(alphabet=IUPAC.unambiguous_dna) momo.add_instance(Seq(theMotif,momo.alphabet)) momoc=0 handle = open(fastafile) def countMotif(myseqrecord, mymotif): i=0 for pos in mymotif.search_instances(myseqrecord.seq): i+=1 return i for seq_record in SeqIO.parse(handle, "fasta"): momoc=momoc + countMotif(seq_record,momo) handle.close() print "motif",theMotif, "found", momoc, "times in the", fastafile, "file"
def test_sites_parsing(self):
"""Test to be sure that Motif can parse sites files.
"""
motif = Motif.Motif()
motif.from_jaspar_sites(self.SITESin)
assert motif.length == 6
def test_pfm_parsing(self):
"""Test to be sure that Motif can parse pfm files.
"""
motif = Motif.Motif()
motif.from_jaspar_pfm(self.PFMin)
assert motif.length == 12
#!/usr/bin/env python
# counts all dinucleotides in a DNA fasta file
import sys
from Bio.Seq import Seq
from Bio import SeqIO
from Bio import Motif
from Bio.Alphabet import IUPAC
fastafile = sys.argv[1]
AA=Motif.Motif(alphabet=IUPAC.unambiguous_dna)
AA.add_instance(Seq("AA",AA.alphabet))
CA=Motif.Motif(alphabet=IUPAC.unambiguous_dna)
CA.add_instance(Seq("CA",CA.alphabet))
GA=Motif.Motif(alphabet=IUPAC.unambiguous_dna)
GA.add_instance(Seq("GA",GA.alphabet))
TA=Motif.Motif(alphabet=IUPAC.unambiguous_dna)
TA.add_instance(Seq("TA",TA.alphabet))
AC=Motif.Motif(alphabet=IUPAC.unambiguous_dna)
AC.add_instance(Seq("AC",AC.alphabet))
CC=Motif.Motif(alphabet=IUPAC.unambiguous_dna)
CC.add_instance(Seq("CC",CC.alphabet))
GC=Motif.Motif(alphabet=IUPAC.unambiguous_dna)
GC.add_instance(Seq("GC",GC.alphabet))
TC=Motif.Motif(alphabet=IUPAC.unambiguous_dna)
TC.add_instance(Seq("TC",TC.alphabet))
AG=Motif.Motif(alphabet=IUPAC.unambiguous_dna)
AG.add_instance(Seq("AG",AG.alphabet))
CG=Motif.Motif(alphabet=IUPAC.unambiguous_dna)
CG.add_instance(Seq("CG",CG.alphabet))
GG=Motif.Motif(alphabet=IUPAC.unambiguous_dna)
GG.add_instance(Seq("GG",GG.alphabet))
