def clustal_align_protein(rec_1, rec_2, work_dir):
"""Align the two given proteins with clustalw.
"""
fasta_file = op.join(work_dir, "prot-start.fasta")
align_file = op.join(work_dir, "prot.aln")
SeqIO.write((rec_1, rec_2), file(fasta_file, "w"), "fasta")
clustal_cl = Clustalw.MultipleAlignCL(fasta_file, command=CLUSTALW_BIN)
clustal_cl.set_output(align_file, output_order="INPUT")
clustal_cl.set_type("PROTEIN")
Clustalw.do_alignment(clustal_cl)
aln_file = file(clustal_cl.output_file)
alignment = AlignIO.read(aln_file, "clustal")
print >>sys.stderr, "\tDoing clustalw alignment: %s" % clustal_cl
return alignment.format("fasta")
def Align_Results(OutputFileName):
import os
FileIN_Name = """/users/rwbarrettemac/bioinformatics/pythonfolders/FMDanalysisScript/FMDserotypingARRAY/Consensus_Results/%s.FASTA""" % (OutputFileName)
FileOUT_ALN = """/users/rwbarrettemac/bioinformatics/pythonfolders/FMDanalysisScript/FMDserotypingARRAY/Consensus_Results/%s.ALN""" % (OutputFileName)
print FileIN_Name
print FileOUT_ALN
from Bio.Clustalw import MultipleAlignCL
from Bio import Clustalw
cline = MultipleAlignCL(os.path.join(os.curdir, FileIN_Name))
cline.set_output(FileOUT_ALN)
alignment = Clustalw.do_alignment(cline)
cline.close()
def align(self):
"Aligns the sequences using CLUSTAL, storing the results"
if len(self.sequences) == 0:
return
self.sequencesToFile( self.tmpFileName )
commandLine = MultipleAlignCL(os.path.join(os.curdir, self.tmpFileName), self.clustalPath)
alignment = Clustalw.do_alignment(commandLine)
allRecords = alignment.get_all_seqs()
length = alignment.get_alignment_length()
alignmentStrings = []
for record in allRecords:
f = fasta.Record()
f.title = record.description.strip()
f.sequence = record.seq.tostring()
alignmentStrings.append( f )
self.alignments = alignmentStrings
self.alignmentLength = length
os.remove(self.tmpFileName)
# biopython
from Bio.Alphabet import IUPAC
from Bio import Clustalw
from Bio.Clustalw import MultipleAlignCL
from Bio.Align import AlignInfo
from Bio.SubsMat import FreqTable
# create the command line to run clustalw
# this assumes you've got clustalw somewhere on your path, otherwise
# you need to pass a second argument to MultipleAlignCL with the complete
# path to clustalw
cline = MultipleAlignCL(os.path.join(os.curdir, 'opuntia.fasta'))
cline.set_output('test.aln')
# actually perform the alignment and get back an alignment object
alignment = Clustalw.do_alignment(cline)
# get the records in the alignment
all_records = alignment.get_all_seqs()
print 'description:', all_records[0].description
print 'sequence:', all_records[0].seq
# get the length of the alignment
print 'length', alignment.get_alignment_length()
print alignment
# print out interesting information about the alignment
summary_align = AlignInfo.SummaryInfo(alignment)
if not clustalw_exe:
raise MissingExternalDependencyError(\
"Install clustalw or clustalw2 if you want to use Bio.Clustalw.")
#################################################################
print "Checking error conditions"
print "========================="
print "Empty file"
input_file = "does_not_exist.fasta"
assert not os.path.isfile(input_file)
cline = MultipleAlignCL(input_file, command=clustalw_exe)
try:
align = Clustalw.do_alignment(cline)
assert False, "Should have failed, returned %s" % repr(align)
except IOError, err:
print "Failed (good)"
#Python 2.3 on Windows gave (0, 'Error')
#Python 2.5 on Windows gives [Errno 0] Error
assert "Cannot open sequence file" in str(err) \
or "not produced" in str(err) \
or str(err) == "[Errno 0] Error" \
or str(err) == "(0, 'Error')", str(err)
print
print "Single sequence"
input_file = "Fasta/f001"
assert os.path.isfile(input_file)
assert len(list(SeqIO.parse(input_file, "fasta"))) == 1
