def GetExec(self, optList, frame):
# Respond to the "embossn" type command.
self.frame = frame
plugin_exe = r"C:/mEMBOSS/needle.exe"
self.outfile = r"C:\Users\francis\Documents\Monguis\BioGui\plugins\needle.txt"
self.outtype = "fasta"
cline = NeedleCommandline(plugin_exe, asequence=str(self.frame.paramBoxes[1].GetValue()), bsequence=str(self.frame.paramBoxes[3].GetValue()))
cline.outfile = self.outfile
cline.gapopen = self.param[7].GetValue()
cline.gapextend = self.param[9].GetValue()
if self.param[10].GetValue():
cline.similarity = True
else:
cline.similarity = False
if self.frame.abet=="AA":
cline.snucleotide = False
cline.sprotein = True
elif self.frame.abet=="DNA" or self.frame.abet=="RNA":
cline.snucleotide = True
cline.sprotein = False
if self.frame.options:
t = self.boxList[3].GetValue()
if t != '':
cline.datafile = str(t)
return str(cline)
def out():
filename1 = e1.get()
filename2 = e2.get()
outfile = e3.get()
needle_cline = NeedleCommandline()
needle_cline.asequence = filename1
needle_cline.bsequence = filename2
needle_cline.gapopen = int(gapopen)
needle_cline.gapextend = int(gapextend)
needle_cline.outfile = "needle.txt"
print(needle_cline)
print(needle_cline.outfile)
stdout, stderr = needle_cline()
print(stdout + stderr)
align = AlignIO.read("needle.txt", "emboss")
file = open("needle.txt", "r")
# print(file.read())
view = ("\n\n%s" % file.read())
with open(outfile, "w") as f:
f.write(view)
root = Tk()
S = Scrollbar(root)
T = Text(root, height=50, width=500)
S.pack(side=RIGHT, fill=Y)
T.pack(side=LEFT, fill=Y)
S.config(command=T.yview)
S.config(command=T.xview)
T.config(yscrollcommand=S.set)
T.config(xscrollcommand=S.set)
quote = view
T.insert(END, quote, 'color')
mainloop()
win.destroy()
def GetExec(self, optList, frame):
# Respond to the "embossn" type command.
self.frame = frame
plugin_exe = r"C:/mEMBOSS/needle.exe"
self.outfile = r"C:\Users\francis\Documents\Monguis\BioGui\plugins\needle.txt"
self.outtype = "fasta"
cline = NeedleCommandline(
plugin_exe,
asequence=str(self.frame.paramBoxes[1].GetValue()),
bsequence=str(self.frame.paramBoxes[3].GetValue()))
cline.outfile = self.outfile
cline.gapopen = self.param[7].GetValue()
cline.gapextend = self.param[9].GetValue()
if self.param[10].GetValue():
cline.similarity = True
else:
cline.similarity = False
if self.frame.abet == "AA":
cline.snucleotide = False
cline.sprotein = True
elif self.frame.abet == "DNA" or self.frame.abet == "RNA":
cline.snucleotide = True
cline.sprotein = False
if self.frame.options:
t = self.boxList[3].GetValue()
if t != '':
cline.datafile = str(t)
return str(cline)
def each_seq_align(each_id=0, record_list=list(), pair_aln_dir=''):
# prepare pairwise sequence alignment files
tmp_a_seq = os.path.join(pair_aln_dir, '{0}_a.fasta'.format(str(each_id)))
SeqIO.write(record_list[0], tmp_a_seq, 'fasta')
tmp_b_seq = os.path.join(pair_aln_dir, '{0}_b.fasta'.format(str(each_id)))
SeqIO.write(record_list[1], tmp_b_seq, 'fasta')
result_file = os.path.join(pair_aln_dir, "{0}.txt".format(str(each_id)))
needle_cline = NeedleCommandline()
needle_cline.asequence = tmp_a_seq
needle_cline.bsequence = tmp_b_seq
needle_cline.gapopen = 10
needle_cline.gapextend = 0.5
needle_cline.outfile = result_file
devnull = open(os.devnull, 'w')
try:
subprocess.call(str(needle_cline),
shell=True,
stdout=devnull,
stderr=devnull)
except OSError:
sys.exit(1)
os.remove(tmp_a_seq)
os.remove(tmp_b_seq)
in_pattern = re.compile(r'Identity.*\((\d+\.\d+)%\)')
gene_alignment_result = ''
with open(result_file, 'r') as f1:
for a_line in f1.readlines():
if 'Identity' in a_line:
m = re.search(in_pattern, a_line.strip())
similarity = m.group(1)
gene_alignment_result = '{0}\t{1}\n'.format(
str(each_id), str(similarity))
os.remove(result_file)
with open(result_file, 'w') as f2:
f2.write(gene_alignment_result)
def needleAlign(seq1, seq2, gapopen, gapextend):
needle = NeedleCommandline()
needle.asequence = seq1
needle.bsequence = seq2
needle.gapopen = gapopen
needle.gapextend = gapextend
needle.outfile = "needle.txt"
stdout, stderr = needle()
print(stdout)
def build_target_matrix(self):
if self.mysubject_file.read().count(
'>') > self.mytarget_file.read().count('>'):
# Ensures the subject file is the smaller one
(self.mysubject_file, self.mytarget_file) = (self.mytarget_file,
self.mysubject_file)
(self.subjectname, self.targetname) = (self.targetname,
self.subjectname)
self.mysubject_file.seek(0)
matrixfile = self.outdir + '/matrix'
if os.path.exists(matrixfile):
self.assignments = pickle.load(open(matrixfile))
return
count = self.mysubject_file.read().count('>')
results = re.compile(
r'# 2: (\w+).+?# Gaps:\s+\d+/\d+ \((\d+\.\d+)%\).+?# Score: (\d+\.\d+)',
re.DOTALL)
needle = NeedleCommandline()
needle.gapopen = self.gapopen
needle.gapextend = self.gapextend
needle.outfile = 'stdout'
needle.bsequence = self.mytarget_file.name
mytargets = SeqIO.parse(self.mytarget_file.name, 'fasta')
mytargets = SeqIO.to_dict(mytargets)
mysubjects = SeqIO.parse(self.mysubject_file.name, 'fasta')
print "Creating alignment matrix. Please wait..."
pbar = ProgressBar(widgets=[Percentage(), Bar()], maxval=count).start()
for i, subject in enumerate(mysubjects):
needle.asequence = 'asis:%s' % str(subject.seq)
(stdout, stderr) = needle()
gaps = results.findall(stdout)
gaps.sort(key=lambda x: float(x[2]), reverse=True)
self.assignments.setdefault(subject.id,
[]).extend(gaps[0:self.assign])
pbar.update(i + 1)
#pbar.finish()
'''
outfile = tempfile.NamedTemporaryFile(delete=False)
mycmd = 'ggsearch36 -s BL62 -m 8 -w 80 -f -8 -g -2 -b=3 -3 -k 500 %s %s'%(self.mysubject_file.name,self.mytarget_file.name)
handle = subprocess.Popen(mycmd,shell=True,stdout=subprocess.PIPE)
(stdout,stderr) = handle.communicate()
results = re.compile('#.+?(^[^#].+?)#',re.MULTILINE|re.DOTALL)
res = results.findall(stdout+"#")
rows = [i.split('\n') for i in res]
myrows = []
for row in rows:
row.pop()
row.sort(key=lambda x:float(x.split('\t')[-1]),reverse=True)
myrows.append(row[0:self.assign])
for i in myrows:
[self.assignments.setdefault(sub,[]).append(tar) for sub,tar in [x.split('\t')[0:2] for x in i if bool(re.search('\t',x))]]
'''
pickle.dump(self.assignments, open(matrixfile, 'w'))
return
if __name__ == "__main__":
with open(os.path.join('data', 'rosalind_need.txt')) as dataset:
ids = dataset.read().split()
handle = Entrez.efetch(db='nucleotide', id=ids, rettype="fasta")
records = list(SeqIO.parse(handle, 'fasta'))
for i, r in enumerate(records):
with open(ids[i], 'w') as f:
SeqIO.write(r, f, 'fasta')
needle_cline = NeedleCommandline()
needle_cline.asequence = ids[0]
needle_cline.bsequence = ids[1]
needle_cline.outfile = "need.txt"
needle_cline.gapopen = 11
needle_cline.gapextend = 1
needle_cline.endopen = 11
needle_cline.endextend = 1
needle_cline.endweight = True
needle_cline()
with open('need.txt') as f:
output = f.readlines()
for line in output:
if 'Score:' in line:
print(int(float(line[:-1].split(':')[-1].strip())))
def each_needle_run(pair_gene_dir, tmp_gene_converted_dir,
pair_gene_alignment_dir, og_id, strain_dict):
"""
This function is used to call Needle program to do pairwise sequence alignment
:param pair_gene_dir: each homologous gene directory
:param tmp_gene_converted_dir: used to put some temporary files and will be deleted in the end
:param pair_gene_alignment_dir: each orthologous gene pair-wised alignment directory
:param og_id: each orthologous gene id
:param strain_dict: inherit from load_strains_label function with strain information
:return: the alignment result of each gene
"""
if not os.path.exists(pair_gene_dir):
logger.error("There is no directory contains gene file, please check.")
logger.error(last_exception())
sys.exit(1)
tmp_gene_fasta = os.path.join(pair_gene_dir, og_id + '.fasta')
converted_records = []
re_pattern = re.compile(r'fig\|(\d+\.\d+)\.peg\.(\d+)\s(.*)')
in_pattern = re.compile(r'Identity.*\((\d+\.\d+)%\)')
annotation = ''
og_list = []
for record in SeqIO.parse(tmp_gene_fasta, 'fasta'):
m = re.search(re_pattern, record.description)
strain_id = m.group(1)
gene_id = '{0}.peg.{1}'.format(strain_id, m.group(2))
og_list.append(gene_id)
annotation = m.group(3)
record.id = strain_dict[strain_id][0]
final_record = SeqRecord(record.seq, record.id, description='')
converted_records.append(final_record)
the_strain_fasta = os.path.join(tmp_gene_converted_dir, 'a.fasta')
other_strain_fasta = os.path.join(tmp_gene_converted_dir, 'b.fasta')
SeqIO.write(converted_records[0], the_strain_fasta, 'fasta')
SeqIO.write(converted_records[1], other_strain_fasta, 'fasta')
result_file = os.path.join(pair_gene_alignment_dir,
"{0}.txt".format(og_id))
needle_cline = NeedleCommandline()
needle_cline.asequence = the_strain_fasta
needle_cline.bsequence = other_strain_fasta
needle_cline.gapopen = 10
needle_cline.gapextend = 0.5
needle_cline.outfile = result_file
devnull = open(os.devnull, 'w')
try:
subprocess.call(str(needle_cline),
shell=True,
stdout=devnull,
stderr=devnull)
except OSError:
logger.info(
'Try to call Needle program failed, please check if Needle has been installed successfully.'
)
logger.error(last_exception())
sys.exit(1)
os.remove(the_strain_fasta)
os.remove(other_strain_fasta)
gene_alignment_result = ''
with open(result_file, 'r') as f:
for a_line in f.readlines():
if 'Identity' in a_line:
m = re.search(in_pattern, a_line.strip())
identity = m.group(1)
gene_alignment_result = '{0}\t[{1}|{2}]\t{3}\t{4}\n'.format(
og_id, og_list[0], og_list[1], identity, annotation)
return gene_alignment_result
Entrez.email = "*****@*****.**"
if __name__ == "__main__":
with open('rosalind_need.txt') as dataset:
ids = dataset.read().split()
handle = Entrez.efetch(db='nucleotide', id=ids, rettype="fasta")
records = list(SeqIO.parse(handle, 'fasta'))
for i, r in enumerate(records):
with open(ids[i], 'w') as f:
SeqIO.write(r, f, 'fasta')
needle_cline = NeedleCommandline()
needle_cline.asequence = ids[0]
needle_cline.bsequence = ids[1]
needle_cline.outfile = "rosalind_need_output.txt"
needle_cline.gapopen = 10
needle_cline.gapextend = 1
needle_cline.endopen = 10
needle_cline.endextend = 1
needle_cline.endweight = True
needle_cline()
with open('rosalind_need_output.txt') as f:
output = f.readlines()
for line in output:
if 'Score:' in line:
print(int(float(line[:-1].split(':')[-1].strip())))
handle = Entrez.efetch(db='nucleotide', id=ids, rettype='fasta')
records = list(SeqIO.parse(handle, 'fasta'))
for i, record in enumerate(records):
with open(ids[i], 'w') as f:
SeqIO.write(record, f, 'fasta')
# Following step can be done in command line
# using 'needle'
needle_cl = NeedleCommandline()
needle_cl.asequence = ids[0]
needle_cl.bsequence = ids[1]
needle_cl.outfile = 'need_output.txt'
needle_cl.gapopen = 10
needle_cl.gapextend = 1
needle_cl.endopen = 10
needle_cl.endextend = 1
needle_cl.endweight = True
needle_cl()
# Score
with open('need_output.txt', 'r') as f:
content = f.readlines()
for line in content:
if 'Score' in line:
score = float(line.split()[-1])
print(score)
break
