def loadAlignment( self, path ):
""" path is a path to an alignment file in .aln format"""
alignment = Clustalw.parse_file( path )
self.allseq = alignment.get_all_seqs()
self.summary = AlignInfo.SummaryInfo(alignment)
self.l = alignment.get_alignment_length()
self.insertLoadedBioAlignment()
def loadAlignment( self, alignmentFile ):
"Populates this object with the given alignment data from a CLUSTAL .aln file."
# ***NOTE*** the CLUSTAL parser does not handle windows line breaks well...
alignment = Clustalw.parse_file(alignmentFile)
alignments = alignment.get_all_seqs()
self.alignmentLength = alignment.get_alignment_length()
for seq in alignments:
sequence = fasta.Record()
align = fasta.Record()
sequence.title = seq.description
align.title = seq.description
align.sequence = seq.seq.tostring()
sequence.sequence = seq.seq.tostring().replace("-","")
self.alignments.append( align )
self.sequences.append( sequence )
#!/usr/bin/env python
"""Example of generating a substitution matrix from an alignment.
"""
# standard library
import sys
# Biopython
from Bio import SubsMat
from Bio import Clustalw
from Bio.Alphabet import IUPAC
from Bio.Align import AlignInfo
# get an alignment object from a Clustalw alignment output
c_align = Clustalw.parse_file('protein.aln', IUPAC.protein)
summary_align = AlignInfo.SummaryInfo(c_align)
# get a replacement dictionary and accepted replacement matrix
# exclude all amino acids that aren't charged polar
replace_info = summary_align.replacement_dictionary(["G", "A", "V", "L", "I",
"M", "P", "F", "W", "S",
"T", "N", "Q", "Y", "C"])
my_arm = SubsMat.SeqMat(replace_info)
print replace_info
my_lom = SubsMat.make_log_odds_matrix(my_arm)
print 'log_odds_mat:', my_lom
my_lom.print_mat()
assert alignment[::-1][2].id == "mixed"
del alignment
del letters
print "testing reading and writing clustal format..."
test_dir = os.path.join(os.getcwd(), 'Clustalw')
test_names = ['opuntia.aln', 'cw02.aln']
test_files = []
for name in test_names:
test_files.append(os.path.join(test_dir, name))
for test_file in test_files:
# parse the alignment file and get an aligment object
alignment = Clustalw.parse_file(test_file)
# print the alignment back out
print alignment
alignment = Clustalw.parse_file(os.path.join(test_dir, test_names[0]))
# test the base alignment stuff
print 'all_seqs...'
for seq_record in alignment:
print 'description:', seq_record.description
print 'seq:', repr(seq_record.seq)
print 'length:', alignment.get_alignment_length()
print 'Calculating summary information...'
align_info = AlignInfo.SummaryInfo(alignment)
# Check Bio.AlignIO.read(...)
alignment = AlignIO.read(handle=open(t_filename), format="clustal")
assert isinstance(alignment, Alignment)
assert compare(alignment, alignments[0])
print "Using Bio.AlignIO.read(...)"
#print "~" * 75
#handle = StringIO()
#AlignIO.write([alignment], handle, "clustal")
#handle.seek(0)
#print handle.read()
#print "~" * 75
print "Using Bio.Clustalw.parse_file(...)"
c_alignment = Clustalw.parse_file(t_filename)
assert isinstance(c_alignment, Alignment)
assert isinstance(c_alignment, Clustalw.ClustalAlignment)
#print " Using Bio.Clustalw.parse_file(...)"
#print "~" * 75
#print c_alignment
#print "~" * 75
#print
# Compare the two...
assert compare(alignment, c_alignment)
# Check Bio.AlignIO can read the Bio.Clustalw's string output
n_alignment = AlignIO.read(StringIO(str(c_alignment)), "clustal")
assert isinstance(alignment, Alignment)
assert alignment[::-1][2].id == "mixed"
del alignment
del letters
print "testing reading and writing clustal format..."
test_dir = os.path.join(os.getcwd(), 'Clustalw')
test_names = ['opuntia.aln', 'cw02.aln']
test_files = []
for name in test_names:
test_files.append(os.path.join(test_dir, name))
for test_file in test_files:
# parse the alignment file and get an aligment object
alignment = Clustalw.parse_file(test_file)
# print the alignment back out
print alignment
alignment = Clustalw.parse_file(os.path.join(test_dir, test_names[0]))
# test the base alignment stuff
print 'all_seqs...'
all_seqs = alignment.get_all_seqs()
for seq_record in all_seqs:
print 'description:', seq_record.description
print 'seq:', repr(seq_record.seq)
print 'length:', alignment.get_alignment_length()
print 'Calculating summary information...'
#!/usr/bin/env python
"""Example of generating a substitution matrix from an alignment.
"""
# standard library
import sys
# Biopython
from Bio import SubsMat
from Bio import Clustalw
from Bio.Alphabet import IUPAC
from Bio.Align import AlignInfo
# get an alignment object from a Clustalw alignment output
c_align = Clustalw.parse_file("protein.aln", IUPAC.protein)
summary_align = AlignInfo.SummaryInfo(c_align)
# get a replacement dictionary and accepted replacement matrix
# exclude all amino acids that aren't charged polar
replace_info = summary_align.replacement_dictionary(
["G", "A", "V", "L", "I", "M", "P", "F", "W", "S", "T", "N", "Q", "Y", "C"]
)
my_arm = SubsMat.SeqMat(replace_info)
print (replace_info)
my_lom = SubsMat.make_log_odds_matrix(my_arm)
print "log_odds_mat:", my_lom
my_lom.print_mat()
# Check Bio.AlignIO.read(...)
alignment = AlignIO.read(handle=open(t_filename), format="clustal")
assert isinstance(alignment, Alignment)
assert compare(alignment, alignments[0])
print "Using Bio.AlignIO.read(...)"
#print "~" * 75
#handle = StringIO()
#AlignIO.write([alignment], handle, "clustal")
#handle.seek(0)
#print handle.read()
#print "~" * 75
print "Using Bio.Clustalw.parse_file(...)"
c_alignment = Clustalw.parse_file(t_filename)
assert isinstance(c_alignment, Alignment)
assert isinstance(c_alignment, Clustalw.ClustalAlignment)
#print " Using Bio.Clustalw.parse_file(...)"
#print "~" * 75
#print c_alignment
#print "~" * 75
#print
# Compare the two...
assert compare(alignment, c_alignment)
# Check Bio.AlignIO can read the Bio.Clustalw's string output
n_alignment = AlignIO.read(StringIO(str(c_alignment)), "clustal")
assert isinstance(alignment, Alignment)
