def infoseq(file):
"""
Run EMBOSS infoseq to
Display basic information about sequences
"""
util.checkFile(file)
util.checkSoft("infoseq")
cmd = "infoseq -only -length -noheading %s -outfile %s.infoseq" % (file, file)
util.runProcess(cmd)
def union(file, common_name, locus_tag, organism_name, strain):
"""
Merge scaffolds into one sequence file
Run EMBOSS union if more than on '>' is found
"""
util.checkFile(file)
cmd = "grep '>' %s | wc -l" % file
result = util.runProcess(cmd)
if int(result) > 1:
new_file = "%s.fsa" % common_name
util.checkSoft("union")
util.checkSoft("descseq")
name = "%s [organism=%s] [strain=%s] [gcode=11]" % (locus_tag, organism_name, strain)
cmd_union = "union -sequence %s -stdout Yes -auto Yes | descseq -filter Yes -name '%s' -auto Yes > %s" % (file, name, new_file)
util.runProcess(cmd_union)
return new_file
else:
return file
def checkValidInput(input_file, common_name):
"""
Check if the input fasta sequence file is of correct format.
RAST re-arrange the scaffolds if a splitted sequences is submitted
Run EMBOSS union before if more than on '>' is found
"""
util.checkFile(input_file)
cmd = "grep '>' %s | wc -l" % input_file
result = util.runProcess(cmd)
if int(result) > 1:
new_input_file = "%s.fna" % common_name
util.checkSoft("union")
util.checkSoft("descseq")
cmd_union = "union -sequence %s -stdout Yes -auto Yes | descseq -filter Yes -name '%s' -auto Yes > %s" % (input_file, common_name, new_input_file)
util.runProcess(cmd_union)
return new_input_file
else:
return input_file
def doRun():
usage = "usage: %prog [Options]"
parser = OptionParser(usage=usage)
parser.add_option("-o", metavar="NAME", help="organism common name", action="store", type="string", dest="name")
parser.add_option(
"-i",
metavar="FILE",
help="input organism sequence file in FASTA format",
action="store",
type="string",
dest="input",
)
(options, args) = parser.parse_args()
try:
common_name = options.name
input_file = checkValidInput(options.input, common_name)
output_file = "%s.prodigal" % common_name
# Print info
log.info("Running prodigal on %s\n" % common_name)
log.info("Getting sequence from %s\n" % input_file)
# Run prodigal
softname = "prodigal"
util.checkSoft(softname)
cmd = "%s < %s > %s" % (softname, input_file, output_file)
util.runProcess(cmd)
# Run the conversion only if successful
if os.path.exists(output_file):
# Convert output results into a feature table EMBL file.
tab_file = convertToTab(output_file, common_name)
# Tidy up
util.rmFile(common_name + ".fna")
util.rmFile(output_file)
log.info("%s is the final feature table Prodigal predictions\n" % tab_file)
else:
log.info("%s file does not exists\n" % output_file)
except Exception, e:
log.error(e)
raise e
def checkValidInput(input_file, common_name):
"""
Check if the input fasta sequence file is of correct format.
Segmentation fault while running glimmer on splitted sequences with a fasta file
Run EMBOSS union before if more than on '>' is found
"""
try:
util.checkFile(input_file)
cmd = "grep '>' %s | wc -l" % input_file
result = util.runProcess(cmd)
if int(result) > 1:
new_input_file = "%s.fna" % common_name
util.checkSoft("union")
util.checkSoft("descseq")
cmd_union = "union -sequence %s -stdout Yes -auto Yes | descseq -filter Yes -name '%s' -auto Yes > %s" % (input_file, common_name, new_input_file)
util.runProcess(cmd_union)
return new_input_file
else:
return input_file
except util.UtilException, ue:
raise ue
