def last_against_itself(last_executable, seq_subset_file, last_table_out):
dirname = os.path.dirname(seq_subset_file.name)
cmd='%s -o %s -f 0 %s %s' %(last_executable, last_table_out, dirname + PATHDELIM + 'subset_db', seq_subset_file.name)
result= getstatusoutput(cmd)
def format_db_last(formatdb_executable, seq_subset_file):
dirname = os.path.dirname(seq_subset_file.name)
cmd='%s -p -c %s %s' %(formatdb_executable, dirname + PATHDELIM + 'subset_db', seq_subset_file.name)
result= getstatusoutput(cmd)
def blast_against_itself(blast_executable, seq_subset_file, blast_table_out):
cmd='%s -outfmt 6 -db %s -query %s -out %s' %(blast_executable, seq_subset_file.name, seq_subset_file.name, blast_table_out)
result= getstatusoutput(cmd)
def format_db_blast(formatdb_executable, seq_subset_file):
cmd = '%s -dbtype prot -in %s' % (formatdb_executable,
seq_subset_file.name)
result = getstatusoutput(cmd)
def format_db_blast(formatdb_executable, seq_subset_file):
cmd='%s -dbtype prot -in %s' %(formatdb_executable, seq_subset_file.name)
result= getstatusoutput(cmd)
def last_against_itself(last_executable, seq_subset_file, last_table_out):
dirname = os.path.dirname(seq_subset_file.name)
cmd = '%s -o %s -f 0 %s %s' % (last_executable, last_table_out,
dirname + PATHDELIM + 'subset_db',
seq_subset_file.name)
result = getstatusoutput(cmd)
def blast_against_itself(blast_executable, seq_subset_file, blast_table_out):
cmd = '%s -outfmt 6 -db %s -query %s -out %s' % (
blast_executable, seq_subset_file.name, seq_subset_file.name,
blast_table_out)
result = getstatusoutput(cmd)
def format_db_last(formatdb_executable, seq_subset_file):
dirname = os.path.dirname(seq_subset_file.name)
cmd = '%s -p -c %s %s' % (formatdb_executable, dirname + PATHDELIM +
'subset_db', seq_subset_file.name)
result = getstatusoutput(cmd)
def start_pathway_tools_api_mode(pathway_tools_exe):
command = pathway_tools_exe + " -api"
result = getstatusoutput(command)
def write_sequin_file(tbl_file_name, contig_dict, sample_name, nucleotide_seq_dict, protein_seq_dict, sequin_input_files):
sequin_src_filename = re.sub(r'tbl$', 'src', tbl_file_name)
sequin_output_fasta = re.sub(r'tbl$', 'fasta', tbl_file_name)
sequin_output_sbt = re.sub(r'tbl$', 'sbt', tbl_file_name)
shutil.copy(sequin_input_files['sequin_fasta'], sequin_output_fasta)
shutil.copy(sequin_input_files['sequin_sbt_file'], sequin_output_sbt)
sequin_required_files = { 'fasta': sequin_output_fasta, 'tbl': tbl_file_name, 'src': sequin_src_filename, 'tbl2asn': sequin_input_files['sequin_tbl2asn'], 'sbt': sequin_output_sbt }
outputfile = open(tbl_file_name, 'w')
#print contig_dict
count =0
outputStr=""
for key in contig_dict:
first = True
if count %10000 == 0:
#print "count " + str(count)
outputfile.write(outputStr)
outputStr=""
count+=1
for attrib in contig_dict[key]:
id = attrib['id']
try:
protein_seq = protein_seq_dict[id]
except:
protein_seq = ""
None
definition = sample_name
accession = '.'
version = '.' +spaces(10) + "GI:."
dblink = sample_name
keywords = '.'
source = sample_name
organism = sample_name
if first:
first = False
try:
dna_seq = nucleotide_seq_dict[key]
dna_seq_formatted = format_sequence_origin(dna_seq)
dna_length = len(dna_seq)
sourceStr = "1.." + str(dna_length)
except:
dna_seq = ""
dna_seq_formatted = ""
dna_length = 0
sourceStr ="0..0"
outputStr+=(">Feature %s\n" % (key))
outputStr+=re.sub('\.\.','\t',sourceStr)+'\t'+"REFERENCE" + '\n'
startPrefix = ''
endPrefix = ''
if 'partial' in attrib:
if attrib['partial']=='10':
startPrefix = '<'
if attrib['partial']=='01':
endPrefix = '>'
if attrib['partial']=='11':
startPrefix = '<'
endPrefix = '>'
if 'start' in attrib and 'end' in attrib:
if 'strand' in attrib:
if attrib['strand']=='-':
geneLoc = str(attrib['end']) + endPrefix +'\t' + startPrefix + str(attrib['start'])
else:
geneLoc = startPrefix + str(attrib['start']) +'\t' + str(attrib['end']) + endPrefix
outputStr+=geneLoc + '\t' + "gene" + '\n'
if 'locus_tag' in attrib:
locus_tag = "gene" + '\t' + attrib['locus_tag']
outputStr+='\t\t\t' + locus_tag +'\n'
outputStr+=geneLoc + '\t' + "CDS" + '\n'
if 'product' in attrib:
product_tag = "product" + '\t' + attrib['product']
outputStr+='\t\t\t' + product_tag +'\n'
outputfile.write(outputStr)
outputfile.close()
outputsrcfile = open(sequin_src_filename, 'w')
ncbi_sequin_params = parse_parameter_file(sequin_input_files['sequin_params'])
headers = ['Collection_date', 'Country', 'isolation_source', 'Lat_Lon', 'Organism', 'environmental_sample']
header_values = {}
headerStr = 'Sequence_ID'
for header_name in headers:
headerStr += '\t' + header_name
header_values[header_name]= get_parameter(ncbi_sequin_params, 'SequinHeader', header_name, default='__'+ header_name + '__')
valueStr =""
for header_name in headers:
valueStr += "\t" + header_values[header_name]
fprintf(outputsrcfile, "%s\n", key + headerStr)
for key in contig_dict:
fprintf(outputsrcfile, "%s\n", key + valueStr)
outputsrcfile.close()
# Now open a pipe process and run the tbl2asn script on the sequin input
for file in sequin_required_files:
if not path.exists(sequin_required_files[file]):
print "Could not find file : " + sequin_required_files[file]
print "Make sure all of the following files are present :"
for file in sequin_required_files:
print file
sys.exit(0)
args = [ sequin_required_files['tbl2asn'], '-t', sequin_required_files['sbt'] , '-i', sequin_required_files['fasta'], '-a', 's', '-V', 'v']
command = ' '.join(args)
result = getstatusoutput(command)
if result[0] == 0 :
print "Successfully created the SEQUIN file"
