def RunCommand(self):
"""Run the BLAST search."""
self.fh_in, self.infile = tempfile.mkstemp()
self.fh_out, self.outfile = tempfile.mkstemp()
with open(self.infile, "w+") as f:
f.write(">Name\n")
f.write(self.command_data[0])
blast_program = self.command_data[1]
database = self.command_data[2]
# Check if user supplied additional options and extract them
if self.command_data[3]:
option = self.command_data[3]
options = {}
for x in range(0, len(option.split()) - 1, 2):
options[option.split()[x]] = option.split()[x + 1]
else:
options = {}
args, kwargs = (
blast_program,
{
"query": self.infile,
"db": database,
"out": self.outfile
},
)
if blast_program.endswith("blastn"):
blast_cmd = NcbiblastnCommandline(args, **kwargs)
elif blast_program.endswith("blastp"):
blast_cmd = NcbiblastpCommandline(args, **kwargs)
elif blast_program.endswith("blastx"):
blast_cmd = NcbiblastxCommandline(args, **kwargs)
elif blast_program.endswith("tblastn"):
blast_cmd = NcbitblastnCommandline(args, **kwargs)
elif blast_program.endswith("tblastx"):
blast_cmd = NcbitblastxCommandline(args, **kwargs)
else:
return
if options:
try:
for key in options:
blast_cmd.set_parameter(key, options[key])
except ValueError as e:
messagebox.showerror("xbb tools",
"Commandline error:\n\n" + str(e))
self.tid.destroy()
return
self.worker = BlastWorker(blast_cmd)
self.worker.start()
self.UpdateResults()
def RunCommand(self):
self.fh_in, self.infile = tempfile.mkstemp()
self.fh_out, self.outfile = tempfile.mkstemp()
with open(self.infile, 'w+') as f:
f.write('>Name\n')
f.write(self.command_data[0])
blast_program = self.command_data[1]
database = self.command_data[2]
# Check if user supplied additional options and extract them
if self.command_data[3]:
option = self.command_data[3]
options = {}
for x in range(0, len(option.split()) - 1, 2):
options[option.split()[x]] = option.split()[x + 1]
else:
options = {}
args, kwargs = blast_program, {
'query': self.infile,
'db': database,
'out': self.outfile
}
if blast_program.endswith('blastn'):
blast_cmd = NcbiblastnCommandline(args, **kwargs)
elif blast_program.endswith('blastp'):
blast_cmd = NcbiblastpCommandline(args, **kwargs)
elif blast_program.endswith('blastx'):
blast_cmd = NcbiblastxCommandline(args, **kwargs)
elif blast_program.endswith('tblastn'):
blast_cmd = NcbitblastnCommandline(args, **kwargs)
elif blast_program.endswith('tblastx'):
blast_cmd = NcbitblastxCommandline(args, **kwargs)
else:
return
if options:
try:
for key in options:
blast_cmd.set_parameter(key, options[key])
except ValueError as e:
messagebox.showerror('xbb tools',
'Commandline error:\n\n' + str(e))
self.tid.destroy()
return
self.worker = BlastWorker(blast_cmd)
self.worker.start()
self.UpdateResults()
def RunCommand(self):
"""Run the BLAST search."""
self.fh_in, self.infile = tempfile.mkstemp()
self.fh_out, self.outfile = tempfile.mkstemp()
with open(self.infile, 'w+') as f:
f.write('>Name\n')
f.write(self.command_data[0])
blast_program = self.command_data[1]
database = self.command_data[2]
# Check if user supplied additional options and extract them
if self.command_data[3]:
option = self.command_data[3]
options = {}
for x in range(0, len(option.split()) - 1, 2):
options[option.split()[x]] = option.split()[x + 1]
else:
options = {}
args, kwargs = blast_program, {'query': self.infile, 'db': database,
'out': self.outfile}
if blast_program.endswith('blastn'):
blast_cmd = NcbiblastnCommandline(args, **kwargs)
elif blast_program.endswith('blastp'):
blast_cmd = NcbiblastpCommandline(args, **kwargs)
elif blast_program.endswith('blastx'):
blast_cmd = NcbiblastxCommandline(args, **kwargs)
elif blast_program.endswith('tblastn'):
blast_cmd = NcbitblastnCommandline(args, **kwargs)
elif blast_program.endswith('tblastx'):
blast_cmd = NcbitblastxCommandline(args, **kwargs)
else:
return
if options:
try:
for key in options:
blast_cmd.set_parameter(key, options[key])
except ValueError as e:
messagebox.showerror('xbb tools',
'Commandline error:\n\n' + str(e))
self.tid.destroy()
return
self.worker = BlastWorker(blast_cmd)
self.worker.start()
self.UpdateResults()
def RunCommand(self):
self.fh_in, self.infile = tempfile.mkstemp()
self.fh_out, self.outfile = tempfile.mkstemp()
with open(self.infile, "w+") as f:
f.write(">Name\n")
f.write(self.command_data[0])
blast_program = self.command_data[1]
database = self.command_data[2]
# Check if user supplied additional options and extract them
if self.command_data[3]:
option = self.command_data[3]
options = {}
for x in range(0, len(option.split()) - 1, 2):
options[option.split()[x]] = option.split()[x + 1]
else:
options = {}
args, kwargs = blast_program, {"query": self.infile, "db": database, "out": self.outfile}
if blast_program.endswith("blastn"):
blast_cmd = NcbiblastnCommandline(args, **kwargs)
elif blast_program.endswith("blastp"):
blast_cmd = NcbiblastpCommandline(args, **kwargs)
elif blast_program.endswith("blastx"):
blast_cmd = NcbiblastxCommandline(args, **kwargs)
elif blast_program.endswith("tblastn"):
blast_cmd = NcbitblastnCommandline(args, **kwargs)
elif blast_program.endswith("tblastx"):
blast_cmd = NcbitblastxCommandline(args, **kwargs)
else:
return
if options:
try:
for key in options:
blast_cmd.set_parameter(key, options[key])
except ValueError as e:
messagebox.showerror("xbb tools", "Commandline error:\n\n" + str(e))
self.tid.destroy()
return
self.worker = BlastWorker(blast_cmd)
self.worker.start()
self.UpdateResults()
def run(self):
print('Begin Resequencing')
print('input_file='+str(self.input_file))
assembly_conf = self.conf['identification']['assembly']
if self.input_file_paired == None:
print('begin assembly')
os.mkdir(os.path.abspath('.')+'/'+self.result_dir+'/identification/assembly')
assembly_obj = assembly.Assembly(self.result_dir+'/identification/assembly', assembly_conf, input_file=self.input_file)
print(assembly_conf['megahit']['enable'], assembly_conf['spades']['enable'], assembly_conf['velvet']['enable'])
if assembly_conf['megahit']['enable'] != False:
assembly_obj.megahit_single()
assembly_result = self.result_dir+'/identification/assembly/megahit_out/final.contigs.fa'
elif assembly_conf['spades']['enable'] != False:
assembly_obj.spades_single()
assembly_result = self.result_dir+'/identification/assembly/spades_out/contigs.fasta'
elif assembly_conf['velvet']['enable'] != False:
assembly_obj.velvet_single()
assembly_result = self.result_dir+'/identification/assembly/velvet_output/contigs.fa'
else:
assembly_result = self.input_file
# assembly_obj.megahit_single()
# assembly_result = self.result_dir+'/identification/assembly/megahit_out/final.contigs.fa'
print('end assembly')
print("Begin QUAST")
try:
completed_process = subprocess.run('quast '+assembly_result+' --min-contig 50 -o '+self.result_dir+'/identification/quast_out', shell=True, check=True)
if completed_process.returncode == 0:
print('Assembly runs successfully! CompleteProcess.returncode = %s.' % completed_process.returncode)
else:
print('An error occurred in Assembly. Please install QUAST.')
print('stdout = %s, stderr = %s.' % (completed_process.stdout, completed_process.stderr))
subprocess.run(os.path.dirname(os.path.realpath(__file__))+'/external_tools/quast-5.0.2/quast.py '+assembly_result+' --min-contig 50 -o '+self.result_dir+'/identification/quast_out', shell=True, check=True)
except Exception as e:
print(e)
print("Please install QUAST")
print("End QUAST")
else:
print('begin assembly')
os.mkdir(os.path.abspath('.')+'/'+self.result_dir+'/identification/assembly')
assembly_obj = assembly.Assembly(self.result_dir+'/identification/assembly', assembly_conf, input_file_1=self.input_file, input_file_2=self.input_file_paired)
if assembly_conf['megahit']['enable'] != False:
assembly_obj.megahit_paired()
assembly_result = self.result_dir+'/identification/assembly/megahit_out/final.contigs.fa'
elif assembly_conf['spades']['enable'] != False:
assembly_obj.spades_paired()
assembly_result = self.result_dir+'/identification/assembly/spades_out/contigs.fasta'
elif assembly_conf['velvet']['enable'] != False:
assembly_obj.velvet_paired()
assembly_result = self.result_dir+'/identification/assembly/velvet_output/contigs.fa'
else:
assembly_result = self.input_file
# assembly_obj.megahit_paired()
# assembly_result = self.result_dir+'/identification/assembly/megahit_out/final.contigs.fa'
print('end assembly')
print("Begin QUAST")
try:
completed_process = subprocess.run('quast '+assembly_result+' --min-contig 50 -o '+self.result_dir+'/identification/quast_out', shell=True, check=True)
if completed_process.returncode == 0:
print('Assembly runs successfully! CompleteProcess.returncode = %s.' % completed_process.returncode)
else:
print('An error occurred in Assembly. Please install QUAST.')
print('stdout = %s, stderr = %s.' % (completed_process.stdout, completed_process.stderr))
subprocess.run(os.path.dirname(os.path.realpath(__file__))+'/external_tools/quast-5.0.2/quast.py '+assembly_result+' --min-contig 50 -o '+self.result_dir+'/identification/quast_out', shell=True, check=True)
except Exception as e:
print(e)
print("Please install QUAST")
print("End QUAST")
temp_file = open(os.path.abspath('.') + '/' + self.result_dir+'/Summary_of_results.html', 'a+')
temp_file.write('<ul>\n')
temp_file.write('<li>assembly result is in %s</li>\n' % './identification/assembly')
temp_file.write('<li><a href="%s">click to assembly result</a></li>\n' % ('./identification/assembly'))
temp_file.write('<li>assembly qc result is in %s</li>\n' % './identification/quast_out')
temp_file.write('<li><a href="%s">click to assembly qc result</a></li>\n' % ('./identification/quast_out/report.html'))
temp_file.write('</ul>\n')
temp_file.close()
if assembly_conf['enable'] != False:
blast_input = assembly_result
else:
scripts.fastq2fasta.fastq2fasta(self.input_file, self.result_dir+"/identification")
blast_input = self.result_dir+"/identification/input.fasta"
# time.sleep(1000)
blastn_conf = self.conf['identification']['blastn']
blastn_cline = NcbiblastnCommandline(cmd=os.path.dirname(os.path.realpath(__file__))+'/external_tools/blastn', query=blast_input, db=self.conf["identification"]['blastn']["blast_db_path"], outfmt=7, out=self.result_dir+"/identification/ncbi_fungi_blast_out.xml")
blastn_cline.set_parameter('num_threads', int(blastn_conf['num_threads']))
blastn_cline.set_parameter('num_alignments', int(blastn_conf['num_alignments']))
blastn_cline.set_parameter('evalue', float(blastn_conf['evalue']))
# if blastn_conf['task'] != None:
# blastn_cline.set_parameter('task', blastn_conf['task'])
if blastn_conf['penalty'] != None:
blastn_cline.set_parameter('penalty', int(blastn_conf['penalty']))
if blastn_conf['reward'] != None:
blastn_cline.set_parameter('reward', int(blastn_conf['reward']))
# if blastn_conf['dust'] != None:
# blastn_cline.set_parameter('dust', blastn_conf['dust'])
# if blastn_conf['filtering_db'] != None:
# blastn_cline.set_parameter('filtering_db', blastn_conf['filtering_db'])
# if blastn_conf['window_masker_taxid'] != None:
# blastn_cline.set_parameter('window_masker_taxid', blastn_conf['window_masker_taxid'])
# if blastn_conf['no_greedy'] != None:
# blastn_cline.set_parameter('no_greedy', blastn_conf['no_greedy'])
# if blastn_conf['min_raw_gapped_score'] != None:
# blastn_cline.set_parameter('min_raw_gapped_score', blastn_conf['min_raw_gapped_score'])
# if blastn_conf['ungapped'] != None:
# blastn_cline.set_parameter('ungapped', blastn_conf['ungapped'])
# if blastn_conf['off_diagonal_range'] != None:
# blastn_cline.set_parameter('off_diagonal_range', blastn_conf['off_diagonal_range'])
print(blastn_cline)
stdout, stderr = blastn_cline()
print(stdout)
print(stderr)
accession_version_list = scripts.handle_blast_xml_result.handle_blast_xml_result_outfmt7(self.result_dir+"/identification/ncbi_fungi_blast_out.xml")
accession_version_list = [accession_version_list[i][0] for i in range(int(self.conf["identification"]['number_of_candidate_similar_genome']))]
# print("accession_version_list="+str(accession_version_list))
temp_file = open(os.path.abspath('.') + '/' + self.result_dir+'/Summary_of_results.html', 'a+')
temp_file.write('<ul>\n')
temp_file.write('<li>candiate closest genome list %s \n' % (accession_version_list))
temp_file.write('</ul>\n')
temp_file.close()
for accession_version in accession_version_list:
scripts.download_nucleotide.download_by_accession_version(self.result_dir, accession_version)
genome_similarity_calculator = calculating_genome_similarity.GenomeSimilarityCalculator(self.result_dir, assembly_result, accession_version_list)
closest_accession_version, max_jaccard = genome_similarity_calculator.search_similar_genome_from_bacteria_dataset()
print("closest_accession_version = %s, max_jaccard = %s" % (closest_accession_version, max_jaccard))
temp_file = open(os.path.abspath('.') + '/' + self.result_dir+'/Summary_of_results.html', 'a+')
temp_file.write('<ul>\n')
temp_file.write('<li>closest accession version is %s in %s Jaccard similarity coefficient</li>\n' % (closest_accession_version, max_jaccard))
temp_file.write('</ul>\n')
temp_file.close()
if self.conf['annotation']['cds_annotation']["enable"] != False:
self.cds_annotation_ngs(closest_accession_version, assembly_result)
if self.conf['annotation']['mlst'] != False:
self.mlst(blast_input)
if self.conf['annotation']['prokka']['enable'] != False:
scripts.prokka_annotation.annotation(blast_input, self.result_dir, self.conf, closest_accession_version)
def run_3gs(self):
print('Begin Resequencing 3gs')
assembly_conf = self.conf['identification']['assembly']
os.mkdir(os.path.abspath('.')+'/'+self.result_dir+'/identification/assembly')
assembly_obj = assembly.Assembly(self.result_dir+'/identification/assembly', assembly_conf, input_file=self.input_file)
if assembly_conf['canu']['enable'] != False:
assembly_obj.canu()
assembly_result = self.result_dir+'/identification/assembly/canu_output/canu_assembly_result.contigs.fasta'
print("Begin QUAST")
try:
completed_process = subprocess.run('quast '+assembly_result+' --min-contig 50 -o '+self.result_dir+'/identification/quast_out', shell=True, check=True)
if completed_process.returncode == 0:
print('Assembly runs successfully! CompleteProcess.returncode = %s.' % completed_process.returncode)
else:
print('An error occurred in Assembly. Please install QUAST.')
print('stdout = %s, stderr = %s.' % (completed_process.stdout, completed_process.stderr))
subprocess.run(os.path.dirname(os.path.realpath(__file__))+'/external_tools/quast-5.0.2/quast.py '+assembly_result+' --min-contig 50 -o '+self.result_dir+'/identification/quast_out', shell=True, check=True)
except Exception as e:
print(e)
print("Please install QUAST")
print("End QUAST")
elif assembly_conf['spades']['enable'] != False:
assembly_obj.spades_3gs()
assembly_result = self.result_dir+'/identification/assembly/spades_out/contigs.fasta'
print("Begin QUAST")
try:
completed_process = subprocess.run('quast '+assembly_result+' --min-contig 50 -o '+self.result_dir+'/identification/quast_out', shell=True, check=True)
if completed_process.returncode == 0:
print('Assembly runs successfully! CompleteProcess.returncode = %s.' % completed_process.returncode)
else:
print('An error occurred in Assembly. Please install QUAST.')
print('stdout = %s, stderr = %s.' % (completed_process.stdout, completed_process.stderr))
subprocess.run(os.path.dirname(os.path.realpath(__file__))+'/external_tools/quast-5.0.2/quast.py '+assembly_result+' --min-contig 50 -o '+self.result_dir+'/identification/quast_out', shell=True, check=True)
except Exception as e:
print(e)
print("Please install QUAST")
print("End QUAST")
else:
assembly_result = self.input_file
# else:
# assembly_obj.canu()
# assembly_result = self.result_dir+'/identification/assembly/canu_output/canu_assembly_result.contigs.fasta'
temp_file = open(os.path.abspath('.') + '/' + self.result_dir+'/Summary_of_results.html', 'a+')
temp_file.write('<ul>\n')
temp_file.write('<li>assembly result is in %s</li>\n' % './identification/assembly')
temp_file.write('<li><a href="%s">click to assembly result</a></li>\n' % ('./identification/assembly'))
temp_file.write('<li>assembly qc result is in %s</li>\n' % './identification/quast_out')
temp_file.write('<li><a href="%s">click to assembly qc result</a></li>\n' % ('./identification/quast_out/report.html'))
temp_file.write('</ul>\n')
temp_file.close()
if assembly_conf['enable'] != False:
blast_input = assembly_result
else:
scripts.fastq2fasta.fastq2fasta(self.input_file, self.result_dir+"/identification")
blast_input = self.result_dir+"/identification/input.fasta"
# scripts.fastq2fasta.fastq2fasta(self.input_file, self.result_dir+"/identification")
# time.sleep(900)
blastn_conf = self.conf['identification']['blastn']
blastn_cline = NcbiblastnCommandline(cmd=os.path.dirname(os.path.realpath(__file__))+'/external_tools/blastn', query=blast_input, db=self.conf["identification"]['blastn']["blast_db_path"], outfmt=7, out=self.result_dir+"/identification/ncbi_fungi_blast_out.xml", evalue=1e-5)
# blastn_cline.set_parameter('num_threads', int(blastn_conf['num_threads']))
blastn_cline.set_parameter('num_threads', int(blastn_conf['num_threads']))
blastn_cline.set_parameter('num_alignments', int(blastn_conf['num_alignments']))
if blastn_conf['evalue'] != None:
blastn_cline.set_parameter('evalue', blastn_conf['evalue'])
# if blastn_conf['task'] != None:
# blastn_cline.set_parameter('task', blastn_conf['task'])
if blastn_conf['penalty'] != None:
blastn_cline.set_parameter('penalty', int(blastn_conf['penalty']))
if blastn_conf['reward'] != None:
blastn_cline.set_parameter('reward', int(blastn_conf['reward']))
# if blastn_conf['dust'] != None:
# blastn_cline.set_parameter('dust', blastn_conf['dust'])
# if blastn_conf['filtering_db'] != None:
# blastn_cline.set_parameter('filtering_db', blastn_conf['filtering_db'])
# if blastn_conf['window_masker_taxid'] != None:
# blastn_cline.set_parameter('window_masker_taxid', blastn_conf['window_masker_taxid'])
# if blastn_conf['no_greedy'] != None:
# blastn_cline.set_parameter('no_greedy', blastn_conf['no_greedy'])
# if blastn_conf['min_raw_gapped_score'] != None:
# blastn_cline.set_parameter('min_raw_gapped_score', blastn_conf['min_raw_gapped_score'])
# if blastn_conf['ungapped'] != None:
# blastn_cline.set_parameter('ungapped', blastn_conf['ungapped'])
# if blastn_conf['off_diagonal_range'] != None:
# blastn_cline.set_parameter('off_diagonal_range', blastn_conf['off_diagonal_range'])
print(blastn_cline)
stdout, stderr = blastn_cline()
print(stdout)
print(stderr)
accession_version_list = scripts.handle_blast_xml_result.handle_blast_xml_result_outfmt7(self.result_dir+"/identification/ncbi_fungi_blast_out.xml")
accession_version_list = [accession_version_list[i][0] for i in range(int(self.conf["identification"]['number_of_candidate_similar_genome']))]
# print("accession_version_list="+str(accession_version_list))
temp_file = open(os.path.abspath('.') + '/' + self.result_dir+'/Summary_of_results.html', 'a+')
temp_file.write('<ul>\n')
temp_file.write('<li>candiate closest genome list %s \n' % (accession_version_list))
temp_file.write('</ul>\n')
temp_file.close()
for accession_version in accession_version_list:
time.sleep(10)
scripts.download_nucleotide.download_by_accession_version(self.result_dir, accession_version)
genome_similarity_calculator = calculating_genome_similarity.GenomeSimilarityCalculator(self.result_dir, assembly_result, accession_version_list)
closest_accession_version, max_jaccard = genome_similarity_calculator.search_similar_genome_from_bacteria_dataset()
print("closest_accession_version = %s, max_jaccard = %s" % (closest_accession_version, max_jaccard))
temp_file = open(os.path.abspath('.') + '/' + self.result_dir+'/Summary_of_results.html', 'a+')
temp_file.write('<ul>\n')
temp_file.write('<li>closest accession version is %s in %s Jaccard similarity coefficient</li>\n' % (closest_accession_version, max_jaccard))
temp_file.write('</ul>\n')
temp_file.close()
# closest_accession_version = accession_version_list[0]
# max_similarity = 0
# for accession_version in accession_version_list:
# print(command_line % (accession_version, accession_version))
# subprocess.run(command_line % (accession_version, accession_version), shell=True, check=True)
# subprocess.run('samtools sort '+self.result_dir+'/identification/minimap2_'+accession_version+'_result.sam -o '+self.result_dir+'/identification/minimap2_'+accession_version+'_result.sorted.bam -O bam', shell=True, check=True)
# res = subprocess.Popen('bedtools genomecov -ibam '+self.result_dir+'/identification/minimap2_'+accession_version+'_result.sorted.bam', shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=True)
# send_messages = res.stdout.readlines()
# print(send_messages[0].decode('utf-8'))
# for message in send_messages:
# message = message.decode('utf-8')
# if message.startswith('genome\t0'):
# print(message)
# line = message.split()
# if line[-1] == '\n':
# new_similarity = 1 - float(line[-2])
# else:
# new_similarity = 1 - float(line[-1])
# break
# print('new_similarity='+str(new_similarity))
# if new_similarity > max_similarity:
# max_similarity = new_similarity
# closest_accession_version = accession_version
# print("closest_accession_version="+str(closest_accession_version))
if self.conf['annotation']['cds_annotation']['enable'] != False:
self.cds_annotation_3gs(closest_accession_version, assembly_result)
if self.conf['annotation']['mlst'] != False:
self.mlst(assembly_result)
if self.conf['annotation']['prokka']['enable'] != False:
scripts.prokka_annotation.annotation(assembly_result, self.result_dir, self.conf, closest_accession_version)
