def get_alignment_commands(fastafile_name, outdir, aligner, threads):
geneName = fastafile_name.split('/')[-1].split('.')[0]
if aligner == "prank":
command = PrankCommandline(d=fastafile_name,
o=geneName,
f=8,
codon=True)
elif (threads > 3):
if aligner == "mafft":
command = MafftCommandline(input=fastafile_name,
auto=True,
nuc=True)
elif aligner == "clustal":
command = ClustalOmegaCommandline(
infile=fastafile_name,
outfile=outdir + "aligned_gene_sequences/" + geneName +
".aln.fas",
seqtype="DNA")
elif (threads <= 3):
if aligner == "mafft":
command = MafftCommandline(input=fastafile_name,
auto=True,
thread=threads,
nuc=True)
elif aligner == "clustal":
command = ClustalOmegaCommandline(
infile=fastafile_name,
outfile=outdir + "aligned_gene_sequences/" + geneName +
".aln.fas",
seqtype="DNA",
threads=threads)
return (command, fastafile_name)
def clustalo(geneSeq_file_path,
treeid,
alignment_out_path="",
dist_matrix_out_path="",
aligned=False,
cmd_path="utils/clustalo-1.2.0"):
from Bio.Align.Applications import ClustalOmegaCommandline
# Clustal Omega (v1.2.0)
# Multiple Sequence Alignment
# Output : [treeid].aln alignment file and [treeid].mat distance matrix
# output : alignment + dist matrix
if alignment_out_path and dist_matrix_out_path:
clustalo = ClustalOmegaCommandline(cmd=cmd_path,
infile=geneSeq_file_path,
outfile=alignment_out_path,
distmat_full=True,
distmat_out=dist_matrix_out_path,
verbose=False,
outfmt="clu",
auto=True)
# output : alignment
elif alignment_out_path and not dist_matrix_out_path:
clustalo = ClustalOmegaCommandline(cmd=cmd_path,
infile=geneSeq_file_path,
outfile=alignment_out_path,
verbose=False,
outfmt="clu",
auto=True)
# output : dist matrix
elif not alignment_out_path and dist_matrix_out_path:
if aligned:
clustalo = ClustalOmegaCommandline(
cmd=cmd_path,
infile=geneSeq_file_path,
max_hmm_iterations=-1,
distmat_full=True,
distmat_out=dist_matrix_out_path,
verbose=False)
else:
clustalo = ClustalOmegaCommandline(
cmd=cmd_path,
infile=geneSeq_file_path,
max_hmm_iterations=-1,
distmat_full=True,
distmat_out=dist_matrix_out_path,
dealign=True,
verbose=False)
clustalo()
def alignSeqs(unalignedFastaPath: str(), alignedFastaName: str()) -> list:
'''
Performs a multiple sequence alignment of the protein sequences found within the input fasta file, outputting an aligned fasta file
This function requires the installation of the standalone ClustalOmega alignment software.
'''
from Bio.Align.Applications import ClustalOmegaCommandline
from Bio.Align import MultipleSeqAlignment
from Bio.SeqRecord import SeqRecord
inputfile = unalignedFastaPath
outputfile = alignedFastaName
cOmegaCommand = ClustalOmegaCommandline(infile=inputfile,
outfile=outputfile,
verbose=True,
auto=True)
cOmegaCommand()
alignedSeq = []
with open(outputfile, 'r') as FastaFile:
for line in FastaFile:
if ">" in line:
continue
else:
alignedSeq.append(line)
return alignedSeq #return sequence alignment
def dist_mat(entries,file,out_list):
#parse fasta file for wanted sequences
input_iterator = SeqIO.parse(open(file,'r'),'fasta')
filter_iterator = (x for x in input_iterator if x.id.split('|')[1] in entries)
with open('temp.fasta','w') as f:
SeqIO.write(filter_iterator,f,'fasta')
#run distance matrix/alignment on select sequences with clustalo
in_file, out_file, matrix = 'temp.fasta','out.fasta','matrix'
clustalomega_cline = ClustalOmegaCommandline(infile=in_file,outfile=out_file,distmat_out=matrix,force=True,distmat_full=True)
clustalomega_cline()
#read in distance matrix
with open('matrix','r') as m:
num = int(m.readline())
l = m.read().split()
dist = [float(x) for x in l if '0.' in x]
rows = [dist[i:i+num] for i in range(0,len(dist),num)]
means = []
#find mean difference for every sequence
for row in rows:
means.append(sum(row)/num)
#return sequence with lowest mean difference
want_ind = means.index(min(means))
out_list.append(entries[want_ind])
def align_db(hxb2, ali_root, db_content):
if not os.path.isdir(ali_root):
os.mkdir(ali_root)
hxb2_seq = next(SeqIO.parse(hxb2, "fasta"))
print("HXB2 sequence loaded (%s, %sbp)" % (hxb2_seq.id, len(hxb2_seq.seq)))
db_content_seqs = {}
records = SeqIO.parse(db_content, "fasta")
for record in records:
db_content_seqs[record.id] = record
print("Sequence database loaded (%s records)" % len(db_content_seqs))
print("Aligning Sequences to HXB2 Reference")
total = len(db_content_seqs)
count = 0
for record in tqdm(db_content_seqs.keys()):
records = [hxb2_seq, db_content_seqs[record]]
ali_outfile = ali_root + db_content_seqs[record].id
with open(ali_infile, 'w') as handle:
SeqIO.write(records, handle, "fasta")
clustalomega_cline = ClustalOmegaCommandline(infile=ali_infile,
outfile=ali_outfile,
verbose=True,
auto=True,
force=True,
threads=16)
clustalomega_cline()
count += 1
print("Done, pairwise alignments written out to %s" % ali_root)
def BuildOutputAlignments(options, region_name, AllRegionSequences,
TemplateProtein):
OutputProteinFilePrefix = os.path.join(options.WorkingDirectory,
"Protein_%s" % region_name)
OutputProteinFilePath = OutputProteinFilePrefix + ".fasta"
OutputAlignmentFilePath = OutputProteinFilePrefix + ".aln"
OutputTreeFilePath = OutputProteinFilePrefix + ".dnd"
with open(OutputProteinFilePath, 'w') as f:
SeqIO.write(AllRegionSequences, f, format="fasta")
cmd = ClustalOmegaCommandline(Definitions.ClustalCommand,
infile=OutputProteinFilePath,
outfile=OutputAlignmentFilePath,
guidetree_out=OutputTreeFilePath,
outfmt="clustal",
force=True)
OutputProteinReferenceFilePath = os.path.join(
options.WorkingDirectory, "Protein_ref_%s.fasta" % region_name)
with open(OutputProteinReferenceFilePath, 'w') as f:
SeqIO.write(TemplateProtein, f, format="fasta")
cmd()
def run_clustal_omega(msa_file):
out_file = 'output/msa_output_carbapemenase.fasta'
clustalomega_cline = ClustalOmegaCommandline(infile=msa_file, outfile=out_file, auto=False)
cmd = str(clustalomega_cline) + ' --force'
print(cmd)
os.system(cmd)
def make_alignment(self, method):
### Mulltiple Sequence Alignment ###
path = os.getcwd()
in_file = "example.fasta"
out_file = "alignment.aln"
if os.path.isfile("alignment.aln"):
os.remove("alignment.aln")
clustalomega_cline = ClustalOmegaCommandline(
infile=in_file,
outfile=out_file,
verbose=True,
iterations=1,
max_guidetree_iterations=1,
max_hmm_iterations=1,
dealign=True,
outfmt="clu")
print(clustalomega_cline)
stdout, stderr = clustalomega_cline()
### Convert to phylip format ###
SeqIO.convert("alignment.aln", "clustal", "alignment.phy", "phylip")
### Phylogentetic analysis ###
# Choose method proml, dnaml
# Maximum likelihood analysis #
# Run Phylip Proml program
instructions = bytes("alignment.phy\ny\n", 'utf-8')
proml = Popen("phylip " + method, stdin=PIPE, shell=True)
(out, err) = proml.communicate(instructions)
# Change output files names
files = Popen("mv outfile " + method + ".out", stdin=PIPE, shell=True)
(out, err) = files.communicate()
files = Popen("mv outtree " + method + ".tree", stdin=PIPE, shell=True)
(out, err) = files.communicate()
def allelealigner(self):
"""
Perform a multiple sequence alignment of the allele sequences
"""
logging.info('Aligning alleles')
# Create the threads for the analysis
for _ in range(self.cpus):
threads = Thread(target=self.alignthreads, args=())
threads.setDaemon(True)
threads.start()
for sample in self.samples:
sample.alignpath = os.path.join(self.path, 'alignedalleles',
sample.organism)
make_path(sample.alignpath)
# Create a list to store objects
sample.alignedalleles = list()
for outputfile in sample.allelefiles:
aligned = os.path.join(sample.alignpath,
os.path.basename(outputfile))
sample.alignedalleles.append(aligned)
# Create the command line call
clustalomega = ClustalOmegaCommandline(infile=outputfile,
outfile=aligned,
threads=4,
auto=True)
sample.clustalomega = str(clustalomega)
self.queue.put((sample, clustalomega, outputfile, aligned))
self.queue.join()
def align_genes(gene1, gene2):
"""Align the two genes with clustal-omega"""
# Make temp files for clustal in and out
clust_in = tempfile.NamedTemporaryFile(prefix='CO_in_',
suffix='.fasta',
mode='w+t')
clust_out = tempfile.NamedTemporaryFile(prefix='CO_out_',
suffix='.fasta',
mode='w+t')
# Write the sequences into the temp file
SeqIO.write([gene1, gene2], clust_in, 'fasta')
# Seek to the beginning else the file will appear empty
clust_in.seek(0)
# Run the command
cline = ClustalOmegaCommandline(infile=clust_in.name,
outfile=clust_out.name,
seqtype='protein',
force=True,
iterations=10,
distmat_full=True,
distmat_full_iter=True)
cline()
clust_in.close()
# Return the handle to the output file
return clust_out
def aln_struct_to_core(alnf, outf, seqf, resmap, cwd, merinfo, query, totmer, clustalopath, updates=False, cores=None):
clustalomega_cline = ClustalOmegaCommandline(
infile=cwd + "/" + seqf,
profile1=cwd + "/" + alnf,
outfile=cwd + "/" + outf,
verbose=False,
auto=True,
force=True,
)
clustalomega_cline()
alndata, _ = parse_fasta_aln_multi(cwd + "/" + outf)
refaln = alndata.filter(regex="refseq_", axis=0)
structaln = alndata.filter(regex=".pdb", axis=0)
if not updates:
core = find_core(refaln)
else:
core = cores
resid, broken = find_resid_onetoone(structaln, cwd + "/" + resmap, core)
completemers = {}
fullids = list(set([key.split("|")[0] for key in resid.index]))
for pdb in fullids:
pdbid, mer = pdb.split(".")[0].split("_")
amer = []
# merinfo[pdbid] #What this line was supposed to be ?
for ch in merinfo[pdbid][1][int(mer) - 1]:
if pdb + "|" + ch + "|" in broken:
continue
else:
amer.append(ch)
completemers[pdb] = amer
return (completemers, resid, broken, refaln, structaln, core)
def clustalW():
clustalomega_cline = ClustalOmegaCommandline(infile="teste.fasta",
outfile="out.txt",
verbose=True,
auto=True,
force=True)
clustalomega_cline()
def runclustalomega(self):
"""Run clustalomega."""
try:
# Run clustal omega using the multifasta file
clustalo_cline = ClustalOmegaCommandline(
infile=self.infile,
cmd="clustalo",
outfile=self.outfile,
# "RNA"/"DNA"
seqtype="PROTEIN",
max_hmm_iterations=2,
infmt="fasta",
# "aln", "phy"
outfmt=self.outfmt,
iterations=3, # Notable
verbose=True,
force=True,
log=self.logpath)
clustalo_cline()
stdout, _ = clustalo_cline()
self.clustalolog.info(stdout)
except ApplicationError as err:
self.clustalolog.error(err)
def jalview(request,contig):
print "\n\nJALVIEW! \n\n"
path = os.path.dirname(os.path.abspath(__file__))
ip = get_client_ip(request)
idcluster = Cluster2.objects.values('idcluster').filter(idcontig=contig)
sequences = Read2.objects.values('idread','readseq').filter(idcluster__in=idcluster)
#print "idcluster -> " + str(idcluster)
#print "sequences -> " + str(sequences)
try:
os.makedirs(path + "/jalview/"+ip)
except:
#The folder already exists
pass
with open(path + "/jalview/"+ip+'/clustalIN.fasta', 'wb+') as destination:
print "REAAAAAAAAAAAAAD"+destination.read()
for sequence in sequences:
destination.write(">" + str(sequence["idread"]) + "\n")
destination.write(sequence["readseq"] + "\n")
in_file = path + "/jalview/"+ip+'/clustalIN.fasta'
out_file = path + "/jalview/"+ip+'/clustalOUT.aln'
clustalomega_cline = ClustalOmegaCommandline(infile=in_file, outfile=out_file, verbose=True, auto=False)
print clustalomega_cline
os.system(str(clustalomega_cline) + ' --force ')
return render(request, 'chromevaloaAPP/jalview.html',{'idcontig':contig})
def clustal_align(infasta, outclustal):
cline = ClustalOmegaCommandline(infile=infasta,
outfile=outclustal,
outfmt='clustal',
verbose=True,
auto=False)
sp.check_call(str(cline), shell=True)
def cdsAlign(CDSfile, outfile):
muscle_cline = ClustalOmegaCommandline(infile=CDSfile,
outfile=outfile,
verbose=True,
auto=True)
print(muscle_cline)
subprocess.run(str(muscle_cline), shell=True)
def build_phylogeny_trees():
path = "out/homologous_gene_sequences/"
output_path = "out/aligned_homologous_gene_sequences/"
for homologous_gene_sequence in os.listdir(path):
input = path + homologous_gene_sequence
output = output_path + homologous_gene_sequence
clustal_omega = ClustalOmegaCommandline(infile=input, outfile=output, verbose=True, auto=True)
os.system(str(clustal_omega))
multi_seq_align = AlignIO.read(output, 'fasta')
# Distance Matrix
calculator = DistanceCalculator('identity')
dist_mat = calculator.get_distance(multi_seq_align)
tree_constructor = DistanceTreeConstructor()
phylo_tree = tree_constructor.upgma(dist_mat)
Phylo.draw(phylo_tree)
print('\nPhylogenetic Tree\n', homologous_gene_sequence)
Phylo.draw_ascii(phylo_tree)
Phylo.write([phylo_tree], 'out/phylogenetic_trees/{}_tree.nex'.format(homologous_gene_sequence), 'nexus')
def alignClustalSequences(inFile, outFile):
# Alignment of sequences with Clustal Omega program
clustalomega_cline = ClustalOmegaCommandline(
infile=inFile,
outfile=outFile,
verbose=True, auto=True)
return clustalomega_cline
def weblogo(request):
# performs clustal alignment in order to use it in the weblogo analysis
seqs = unquote(request.GET.get('seq'))
in_file = "unaligned.fasta"
file = open("unaligned.fasta", "w")
file.write(seqs)
file.close()
out_file = "out_filename.fasta"
clustalomega_cline = ClustalOmegaCommandline(infile=in_file,
outfile=out_file,
verbose=True,
auto=False)
print(clustalomega_cline)
os.system('cmd /c crmapp\clustal-omega-1.2.2-win64\\' +
str(clustalomega_cline) + ' --force')
"""
out_file = "out_filename.clustal_num"
clustalomega_cline = ClustalOmegaCommandline(infile=in_file, outfile=out_file, verbose=True, auto=False)
print(clustalomega_cline)
os.system('cmd /c crmapp\clustal-omega-1.2.2-win64\\' + str(clustalomega_cline) + ' --outfmt clustal --force')
"""
file_out = open("out_filename.fasta", "r")
seqs_aligned = file_out.readlines()
# return_data = {'data': seqs_aligned}
seqs = read_seq_data(file_out)
logodata = LogoData.from_seqs(seqs)
logooptions = LogoOptions()
logooptions.title = "VFP WEBSERVER"
logoformat = LogoFormat(logodata, logooptions)
weblogo_txt = txt_formatter(logodata, logoformat)
weblogo_jpeg = jpeg_formatter(logodata, logoformat)
weblogo_file = "weblogo.txt"
weblogo = open(weblogo_file, "w")
data_weblogo = str(weblogo_txt)[2:len(str(weblogo_txt)) - 1].replace(
'\\n', '\n').replace('\\t', '\t')
weblogo.write(data_weblogo)
weblogo.close()
file_out.close()
os.remove(in_file)
os.remove(out_file)
# print(return_data)
output = seqs_aligned[0]
seq_found = False
for i in range(1, len(seqs_aligned) - 1):
if seqs_aligned[i + 1][0] == '>':
output += seqs_aligned[i]
seq_found = True
elif seq_found:
output += seqs_aligned[i]
seq_found = False
else:
output += seqs_aligned[i][0:len(seqs_aligned[i]) - 1]
output += seqs_aligned[len(seqs_aligned) - 1]
return JsonResponse({'data': output}, safe=False)
def clustalo():
for fasta_files in files[:]:
fasta_file_s = fasta_files.split('.')[0]
print fasta_file_s
cline = ClustalOmegaCommandline('clustalo',infile = fasta_files,outfile = fasta_file_s + '.aln' ,verbose= False, auto=True)
cline()
def cluster_align(self, clusterID, allowedOrganisms=None):
alignSeqs = []
homCluster = self.homDB.get_cluster(clusterID)
for org in homCluster:
if allowedOrganisms == None or org in allowedOrganisms:
for seqid in homCluster[org]:
alignSeqs.append((org, seqid))
seqRecords = []
seqID2Element = {}
for org, seqid in alignSeqs:
genSeq = self.genomDB.get_sequence(org, seqid)
seqRecID = "_".join([org, seqid])
seqID2Element[seqRecID] = self.genomDB.get_element(org, seqid)
seq = SeqRecord(Seq(genSeq, generic_dna),
id=seqRecID,
description="")
seqRecords.append(seq)
with tempfile.NamedTemporaryFile(
'w', delete=True) as tmpFastaFile, tempfile.NamedTemporaryFile(
'w', delete=True) as tmpMSAFile:
try:
#print(tmpFastaFile.name)
#print(tmpMSAFile.name)
SeqIO.write(seqRecords, tmpFastaFile, "fasta")
tmpFastaFile.flush()
clustalomega_cline = ClustalOmegaCommandline(
infile=tmpFastaFile.name,
outfile=tmpMSAFile.name,
force=True,
outfmt='fa',
verbose=True,
auto=True)
clustalomega_cline = str(clustalomega_cline)
clustalomega_cline += " --full"
print(clustalomega_cline)
output = subprocess.getoutput([str(clustalomega_cline)])
print("Clustalomega finished")
with open(tmpMSAFile.name, 'r') as fin:
alignment = AlignIO.read(fin, "fasta")
return alignment
finally:
pass
return None
def algo_msa(msa_type: str, seq_id: List[int], consensus: bool = None):
if len(seq_id) > 10:
return "Cannot process more than 10 sequences for MSA. Operation aborted."
result = Virus.query.with_entities("id",
"fasta").filter(Virus.id.in_(seq_id))
result_dict = {}
for r in result:
result_dict[r[0]] = r[1]
fasta_file = "tmp/%s" % str(uuid.uuid4())
with open(fasta_file, "w") as fasta:
# Ensure ordering of sequences based on input
for i in seq_id:
fasta.write(result_dict[i] + "\n\n")
msa_command = None
if msa_type == "muscle":
msa_command = MuscleCommandline("muscle",
input=fasta_file,
html=True,
quiet=True)
ret = msa_command()
elif msa_type == "clustalo":
msa_command = ClustalOmegaCommandline(infile=fasta_file)
ret = msa_command()
else: # if msa_type == "mview":
clustal_file = "tmp/%s" % str(uuid.uuid4())
msa_command = ClustalOmegaCommandline(infile=fasta_file,
outfile=clustal_file)
msa_command()
con = "on" if consensus else "off"
ret = runCommand([
"mview", "--css", "on", "--pcid", "aligned", "--ruler", "on",
"--width", "80", "-coloring", "mismatch", "-colormap", "pink",
"-consensus", con, "-con_threshold", "100", "-html", "head", "-in",
"fasta", clustal_file
])
os.remove(clustal_file)
os.remove(fasta_file)
return ret
def check_what_algorithm(alg, in_file, out_file):
if alg == "CLUSTAL":
clustalomega_cline = ClustalOmegaCommandline(infile=in_file,
outfile=out_file,
verbose=True,
auto=True)
return clustalomega_cline
elif alg.upper() == "KALIGN":
return 0
def clustal_all(request):
if request.method == "POST":
# seqs = unquote(request.GET.get('seq'))
data = request.data
seqs = data['seqs']
type = data['type']
try:
type_os = data['os']
except:
type_os = "linux"
##########################
# type_os = "windows"
###########################
if type == "fasta":
out_file = "aligned.fasta"
elif type == "phylip":
out_file = "aligned_clustal.phy"
else:
out_file = "aligned_clustal.alm"
type = "clu"
in_file = "unaligned_clustal.fasta"
file = open(in_file, "w")
file.write(seqs)
file.close()
clustalomega_cline = ClustalOmegaCommandline(infile=in_file,
outfile=out_file,
verbose=True,
auto=False,
outfmt=type,
guidetree_out="tree.dnd")
print(clustalomega_cline)
if type_os == "windows":
os.system('cmd /c crmapp\clustal-omega-1.2.2-win64\\' + str(clustalomega_cline) + ' --force')
else:
# cmd = 'crmapp/clustal-omega-1.2.2-win64s/' + str(clustalomega_cline) + ' --force'
cmd = str(clustalomega_cline) + ' --force'
# subprocess.Popen(['/bin/bash', '-c', 'chmod u+x clustalo'])
p = subprocess.Popen(['/bin/bash', '-c', cmd])
p.communicate()
file_out = open(out_file, "r")
data_send = file_out.read()
# data_send['dnd'] = file_tree_out.read()
return HttpResponse(data_send, content_type="text/plain")
def clustal(in_file="unaligned.fasta", out_file="out_filename.fasta"):
# file = open("unaligned.fasta", "w")
# file.write(seqs)
# file.close()
clustalomega_cline = ClustalOmegaCommandline(infile=in_file,
outfile=out_file,
verbose=True,
auto=False)
os.system('cmd /c crmapp\clustal-omega-1.2.2-win64\\' +
str(clustalomega_cline) + ' --outfmt clustal --force')
def COP6(in_file, out_file, outfmt, logfile):
"""3 combined iterations with 2 hmm iterations"""
clustalo_cline = ClustalOmegaCommandline(infile=in_file, outfile=out_file, seqtype="DNA", max_hmm_iterations=2,
infmt="fasta", outfmt=outfmt, iterations=3, verbose=True,
threads=8, force=True, log=logfile)
stdout, stderr = clustalo_cline()
clustalo_cline()
print(stdout, stderr)
print("\n" + "File has been created." + "\n")
return;
def COP7(in_file, out_file, outfmt, logfile):
"""Default with auto set to TRUE"""
clustalo_cline = ClustalOmegaCommandline(infile=in_file, outfile=out_file, seqtype="DNA",
infmt="fasta", outfmt=outfmt, iterations=1, verbose=True,
threads=8, auto=True, log=logfile)
stdout, stderr = clustalo_cline()
clustalo_cline()
print(stdout, stderr)
print("\n" + "File has been created." + "\n")
return;
def test_simple_fasta(self):
"""Test a simple fasta file."""
input_file = "Registry/seqs.fasta"
output_file = "temp_test.aln"
cline = ClustalOmegaCommandline(
clustalo_exe, infile=input_file, outfile=output_file, outfmt="clustal"
)
self.standard_test_procedure(cline)
def test_output_filename_with_spaces(self):
"""Test an output filename containing spaces."""
input_file = "Registry/seqs.fasta"
output_file = "temp with spaces.aln"
cline = ClustalOmegaCommandline(
clustalo_exe, infile=input_file, outfile=output_file, outfmt="clustal"
)
self.standard_test_procedure(cline)
def COP2(in_file, out_file, outfmt, logfile):
"""Default parameters while using a profile with 1 iteration"""
clustalo_cline = ClustalOmegaCommandline(profile1="profile.fasta", infile=in_file, outfile=out_file, seqtype="DNA",
infmt="fasta", outfmt=outfmt, iterations=1, verbose=True,
threads=8, force=True, log=logfile)
stdout, stderr = clustalo_cline()
clustalo_cline()
print(stdout, stderr)
print("\n" + "File has been created." + "\n")
return;