def muscle_wrapper(work_msa):
app = Applications.MuscleCommandline(
input=work_msa.input_fasta,
out=work_msa.output_aln,
clw=True,
)
app()
def __align_sequences__(args=None, seqs=None):
if args.input_file is not None:
assert args.file_input_format is not None, "Missed the file input format at __retrieve_data__(args=None)"
if args.verbose:
print("\nStarting sequences alignment process...\n\n")
from Bio.Align import Applications
# import subprocess
# global nproc
if args.tool == "clustalo":
started = datetime.now()
print("Starting at: %s" % started.strftime("%Y-%m-%d %H:%M:%S"))
# from Bio.Align.Applications import ClustalwCommandline
binpath = r"/usr/local/bin/clustalo"
cmd=Applications.ClustalOmegaCommandline(\
binpath,\
infile=args.input_file,\
outfile="%s.aln.clustalo" % args.input_file,\
verbose=args.verbose,\
force=True,\
threads=nproc,\
guidetree_out="%s.dnd.clustalo" % args.input_file)
# cmd="%s -i %s -o %s --threads=%i --force --guidetree-out=%s" % (binpath, args.input_file, ("%s.aln.clustalo" % args.input_file), nproc, ("%s.dnd.clustalo" % args.input_file))
# if args.verbose:
# cmd="%s -i %s -o %s --threads=%i --force --guidetree-out=%s -v" % (binpath, args.input_file, ("%s.aln.clustalo" % args.input_file), nproc, ("%s.dnd.clustalo" % args.input_file))
# stdout,stderr=cmd()
child=subprocess.Popen(\
str(cmd),\
stdout=subprocess.PIPE,\
stderr=subprocess.PIPE,\
universal_newlines=True,\
shell=(sys.platform!="win32"))
child.wait()
finished = datetime.now()
print("Finished at: %s" % finished.strftime("%Y-%m-%d %H:%M:%S"))
print("Total elapsed time: %s" % str(finished - started))
if args.verbose:
stdout = child.stdout.read()
if (len(stdout) > 0):
print("\nStandard out is: %s\n" % stdout)
else:
print("\nStandard out is empty!\n")
stderr = child.stderr.read()
if (len(stderr) > 0):
print("Standard error is: %s" % stderr)
else:
print("Standard error is empty")
from Bio import AlignIO
# align=AlignIO.read("tmp.aln","fasta")
align = AlignIO.read("%s.aln.clustalo" % args.input_file, "fasta")
print(align)
elif args.tool == "muscle":
started = datetime.now()
print("Starting at: %s" % started.strftime("%Y-%m-%d %H:%M:%S"))
# from Bio.Align.Applications import ClustalwCommandline
cmd = None
if not args.file_output_format or args.file_output_format is None:
cmd = Applications.MuscleCommandline(input=args.input_file,
out="%s.aln.muscle" %
args.input_file)
else:
if args.file_output_format == "clustal":
cmd = Applications.MuscleCommandline(
input=args.input_file,
clw=True,
out="%s.aln.muscle.clustalwfmt" % args.input_file)
elif args.file_output_format == "clustal-strict":
cmd = Applications.MuscleCommandline(
input=args.input_file,
clwstrict=True,
out="%s.aln.muscle.clustalwstrictfmt" %
args.input_file)
# cmd()
child=subprocess.Popen(\
str(cmd),\
stdout=subprocess.PIPE,\
stderr=subprocess.PIPE,\
universal_newlines=True,\
shell=(sys.platform!="win32"))
child.wait()
finished = datetime.now()
print("Finished at: %s" % finished.strftime("%Y-%m-%d %H:%M:%S"))
print("Total elapsed time: %s" % str(finished - started))
if args.verbose:
stdout = child.stdout.read()
if (len(stdout) > 0):
print("\nStandard out is: %s\n" % stdout)
else:
print("\nStandard out is empty!\n")
stderr = child.stderr.read()
if (len(stderr) > 0):
print("Standard error is: %s" % stderr)
else:
print("Standard error is empty")
from Bio import AlignIO
align = None
if args.file_output_format is None:
align = AlignIO.read("%s.aln.muscle" % args.input_file,
"fasta")
elif args.file_output_format == "clustal":
align = AlignIO.read(
"%s.aln.muscle.clustalwfmt" % args.input_file, "clustal")
elif args.file_output_format == "clustal-strict":
align = AlignIO.read(
"%s.aln.muscle.clustalwstrictfmt" % args.input_file,
"clustal")
print(align)
elif args.tool == "emboss":
raise NotImplementedError(
"Not implemented yet! Fix the a and b sequence files")
outfile = ''
binpath = ''
if args.emboss_algorithm == "needle":
from Bio.Emboss.Applications import NeedleCommandline as EmbossCommandline
outfile = "%s.needle.txt" % args.input_file
binpath = r"/usr/local/bin/needle"
elif args.emboss_algorithm == "water":
from Bio.Emboss.Applications import WaterCommandline as EmbossCommandline
outfile = "%s.water.txt" % args.input_file
binpath = r"/usr/local/bin/water"
started = datetime.now()
print("Starting at: %s" % started.strftime("%Y-%m-%d %H:%M:%S"))
cmd=EmbossCommandline(\
binpath,\
asequence="/home/edario/mines/bio/alpha.faa",\
bsequence="/home/edario/mines/bio/beta.faa",\
gapopen=10,\
gapextend=0.5,\
outfile=outfile)
# stdout,stderr=cmd()
child=subprocess.Popen(\
str(cmd),\
stdout=subprocess.PIPE,\
stderr=subprocess.PIPE,\
universal_newlines=True,\
shell=(sys.platform!="win32"))
child.wait()
finished = datetime.now()
print("Finished at: %s" % finished.strftime("%Y-%m-%d %H:%M:%S"))
print("Total elapsed time: %s" % str(finished - started))
if args.verbose:
stdout = child.stdout.read()
if (len(stdout) > 0):
print("\nStandard out is: %s\n" % stdout)
else:
print("\nStandard out is empty!\n")
stderr = child.stderr.read()
if (len(stderr) > 0):
print("Standard error is: %s" % stderr)
else:
print("Standard error is empty")
from Bio import AlignIO
# align=AlignIO.read("tmp.aln","fasta")
# align=AlignIO.read("%s.needle.txt" % args.input_file,"emboss")
align = AlignIO.read(outfile, "emboss")
print(align)
elif args.tool == "blast":
assert args.blast_app is not None, "Missed the -bap|--blast-app arg"
assert args.blast_database is not None, "Missed the -bdb|--blast-database arg"
# assert args.blast_query_sequence is not None, "Missed the -bqs|--blast-query-sequence arg"
started = datetime.now()
print("Starting at: %s" % started.strftime("%Y-%m-%d %H:%M:%S"))
from Bio.Blast import NCBIWWW
result_handle = None
# args.blast_query_sequence=''
# for seq in SeqIO.parse(args.input_file,args.file_input_format):
# args.blast_query_sequence+=seq.id+'\n'
# if args.blast_query_sequence is not None:
# if args.verbose:
# print("Searching in BLAST with app %s, in database %s and query %s" % (args.blast_app, args.blast_database, args.blast_query_sequence))
# print("(cmd is %s -db %s)" % (args.blast_app, args.blast_database))
# result_handle=NCBIWWW.qblast(args.blast_app, args.blast_database, args.blast_query_sequence)
if args.file_input_format.lower() != "xml":
try:
record = SeqIO.read(args.input_file,
args.file_input_format)
result_handle = NCBIWWW.qblast(args.blast_app,
args.blast_database,
record.seq)
except ValueError as e:
if "more than one record found in handle" in e.args[
0].lower():
records = SeqIO.parse(args.input_file,
args.file_input_format)
query = ''
for rec in records:
query += rec.id + '\n'
print("************query***********")
print(type(query))
result_handle = NCBIWWW.qblast(args.blast_app,
args.blast_database,
query)
quit()
with open("blast.xml", 'w') as out_handle:
# out_handle.write(result_handle.read())
out_handle.write(result_handle.getvalue())
# result_handle.close()
else:
result_handle = open(args.input_file)
# else:
# query=''
# for seq in seqs:
# query+="%s\n" % eq
# result_handle=NCBIWWW.qblast(args.blast_app, args.blast_database, seq)
from Bio.Blast import NCBIXML
blast_records = NCBIXML.parse(result_handle)
for blast_record in blast_records:
for alignment in blast_record.alignments:
for hsp in alignment.hsps:
print("\nALIGNMENT\n")
print("Sequence: ", alignment.title)
print("Length: ", alignment.length)
print("e value: ", hsp.expect)
print(hsp.query[0:75] + "...")
print(hsp.match[0:75] + "...")
print(hsp.sbjct[0:75] + "...")
# print(blast_record)
result_handle.close()
finished = datetime.now()
print("Finished at: %s" % finished.strftime("%Y-%m-%d %H:%M:%S"))
print("Total elapsed time: %s" % str(finished - started))
else:
alignments = pairwise2.align.globalxx(seq1, seq2)
for alignment in alignments:
print(pairwise2.format_alignment(*alignment))