def main():
usage = "usage: %prog [Options]"
parser = OptionParser(usage=usage)
parser.add_option("-o", metavar="EXTENSION", help="val EXTENSION", action="store", type="string", dest="old")
parser.add_option("-n", metavar="EXTENSION", help="err EXTENSION", action="store", type="string", dest="new")
parser.add_option("--extract", help="Extract ERRORs only", action="store_true", dest="extract")
(options, args) = parser.parse_args()
# Print help if no argument given
if util.printHelp(options):
parser.print_help()
sys.exit()
for file in os.listdir('.'):
if options.old in file:
oldfile = file
newfile = "%s.%s" % (oldfile.split(".")[0], options.new)
print "Convert file %s into %s" % (oldfile, newfile)
if options.extract:
cmd = "grep ERROR %s > %s" % (oldfile, newfile)
try:
util.runProcess(cmd)
except Exception, e:
print "Error to extract %s" % oldfile
print e
def main():
usage = "usage: %prog [Options]"
parser = OptionParser(usage=usage)
parser.add_option("-l", metavar="FILE", help="FILE containing the list of all organism common names and its associated sequence file", action="store", type="string", dest="list")
(options, args) = parser.parse_args()
# Print help if no argument given
if util.printHelp(options):
parser.print_help()
sys.exit()
# Read organism common name and related fasta sequence file
list_file = options.list
util.checkFile(list_file)
for line in open(list_file, "r"):
if line[0] == '!':
continue
if line.count('||') < 1:
continue
# ! common_name||sequence_file
line = line.strip()
values = line.split('||')
common_name = values[0]
input_file = values[1]
#util.checkFile(input_file)
doSubmit(common_name, input_file)
def main():
usage = "usage: %prog [Options]"
parser = OptionParser(usage=usage)
parser.add_option("-o", metavar="EXTENSION", help="Old EXTENSION", action="store", type="string", dest="old")
parser.add_option("-n", metavar="EXTENSION", help="New EXTENSION", action="store", type="string", dest="new")
parser.add_option("--convert", help="Do convert genbank file into embl", action="store_true", dest="convert")
(options, args) = parser.parse_args()
# Print help if no argument given
if util.printHelp(options):
parser.print_help()
sys.exit()
for file in os.listdir('.'):
if options.old in file:
oldfile = file
newfile = "%s.%s" % (oldfile.split(".")[0], options.new)
print "Convert file %s into %s" % (oldfile, newfile)
if options.convert:
cmd = "seqret -sequence gb::%s -feature Yes -outseq embl::%s" % (oldfile, newfile)
try:
util.runProcess(cmd)
except Exception, e:
print "Error to convert %s" % oldfile
print e
def main():
usage = "usage: %prog [Options]"
parser = OptionParser(usage=usage)
parser.add_option("-l", metavar="FILE", help="FILE containing the list of all organism common names and its associated sequence file", action="store", type="string", dest="list")
(options, args) = parser.parse_args()
# Print help if no argument given
if util.printHelp(options):
parser.print_help()
sys.exit()
# Get and check input arguments
if options.list:
# Read organism common name and related fasta sequence file
list_file = options.list
util.checkFile(list_file)
for line in open(list_file, "r"):
if line[0] == '!':
continue
if line.count('||') < 1:
continue
# ! common_name||organim_name||strain||locus_tag||fasta_file
line = line.strip()
values = line.split('||')
print "Processing %s" % values[0]
union(file=values[4], common_name=values[0], locus_tag=values[3], organism_name=values[1], strain=values[2])
def main():
usage = "usage: %prog [Options]"
parser = OptionParser(usage=usage)
parser.add_option("-l", "--list", metavar="FILE", help="FILE containing the list of all organism common names and its associated file to load", action="store", type="string", dest="list")
parser.add_option("-D", action="store", dest="dbhost")
(options, args) = parser.parse_args()
# Print help if no argument given
if util.printHelp(options):
parser.print_help()
sys.exit()
# Print command line
cmdline = "$ python "
for argv in sys.argv:
cmdline += argv + " "
logger.info(cmdline)
# Print logger file info
logger.info(logsetup.logpath)
# Setup database connection
host = ropy.util.getDArg("dbhost", raiseOnEmpty = True)
database = ropy.util.getDArg("dbname", raiseOnEmpty = True)
port = ropy.util.getDArg("dbport", raiseOnEmpty = True)
user = ropy.util.getDArg("dbuser", raiseOnEmpty = True)
#password = ropy.util.getDArg("dbpassword", raiseOnEmpty = True)
# Check if chado_load is installed
util.isSoftInstalled("chado_load")
# Read organism common name and load related embl file into the database
data_path = options.list
for line in open(data_path, "r"):
if line[0] == '!':
continue
if line.count('||') < 1:
continue
# ! common_name||taxon_id||filename
line = line.strip()
list = line.split('||')
common_name = list[0]
filename = list[2]
util.checkFile(filename)
# Loader command
cmd = "chado_load embl -o %s -t contig -D %s:%s/%s -U %s %s" % (common_name, host, port, database, user, filename)
# Run command
util.runProcess(cmd)
def main():
usage = "usage: %prog [Options]"
parser = OptionParser(usage=usage)
parser.add_option("-l", metavar="FILE", help="FILE containing the list of all organism common names, its associated information", action="store", type="string", dest="list")
parser.add_option("--submit", help="To submit data, not only checking locus_tag", action="store_true", dest="submit")
(options, args) = parser.parse_args()
# Print help if no argument given
if util.printHelp(options):
parser.print_help()
sys.exit()
# Get and check input arguments
# Read organism common name and related fasta sequence file
list_file = options.list
util.checkFile(list_file)
for line in open(list_file, "r"):
if line[0] == '!':
continue
if line.count('||') < 1:
continue
# ! organism_name||strain||locus_tag||seq_size||seq_depth||dna_source||description
line = line.strip()
values = line.split('||')
organism_name = values[0]
strain = values[1]
locus_tag = values[2]
seq_size = values[3]
seq_depth = values[4]
if values[5] == 'GHP':
dna_source = 'Gut Health Programme, Rowett Institute of Nutrition and Health, University of Aberdeen. http://www.rowett.ac.uk/divisions/ghp/'
elif values[5] == 'INRA':
dna_source = 'INRA Clermont-Ferrand-Theix. http://www.clermont.inra.fr/'
elif values[5] == 'DSMZ':
dna_source = 'Deutsche Sammlung von Mikroorganismen und Zellkulturen. GmbH http://www.dsmz.de/'
elif values[5] == 'NCTC':
dna_source = "Health Protection Agency's National Collection of Type Cultures. http://www.hpacultures.org.uk/"
else:
print "DNA source %s not found! Please provide details..." % values[5]
continue
#print dna_source
description = values[6]
doSubmit(organism_name=organism_name, strain=strain, locus_tag=locus_tag,
seq_size=seq_size, seq_depth=seq_depth, dna_source=dna_source,
description=description, submit=options.submit)
def main():
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")
parser.add_option("-j", metavar="ID", help="input job ID to fetch results", action="store", type="string", dest="jobid")
parser.add_option("-l", metavar="FILE", help="FILE containing the list of all organism common names and its associated sequence file", action="store", type="string", dest="list")
parser.add_option("--fetch", help="To fetch results, job id must be provided", action="store_true", dest="fetch")
(options, args) = parser.parse_args()
# Print help if no argument given
if util.printHelp(options):
parser.print_help()
sys.exit()
# Get and check input arguments
if options.list:
# Read organism common name and related fasta sequence file
list_file = options.list
util.checkFile(list_file)
for line in open(list_file, "r"):
if line[0] == '!':
continue
if line.count('||') < 1:
continue
# ! common_name||sequence_file
line = line.strip()
values = line.split('||')
common_name = values[0]
if options.fetch:
job_id = values[2]
doFetch(common_name, job_id)
else:
input_file = checkValidInput(values[1], common_name)
doSubmit(common_name, input_file)
else:
common_name = options.name
if options.fetch:
job_id = options.jobid
doFetch(common_name, job_id)
else:
input_file = checkValidInput(options.input, common_name)
doSubmit(common_name, input_file)
def main():
usage = "usage: %prog [Options]"
parser = OptionParser(usage=usage)
parser.add_option("-l", metavar="FILE", help="FILE containing the list of all organism common names and its associated information (common_name||organim_name||strain||locus_tag||genome_project_id||coverage)", action="store", type="string", dest="list")
parser.add_option("--convert", help="Do convert embl file into tbl", action="store_true", dest="convert")
(options, args) = parser.parse_args()
# Print help if no argument given
if util.printHelp(options):
parser.print_help()
sys.exit()
# Get and check input arguments
if options.list:
# Read organism common name and related locus tag
list_file = options.list
util.checkFile(list_file)
for line in open(list_file, "r"):
if line[0] == '!':
continue
if not line.count('||') == 6:
continue
# ! common_name||organim_name||strain||locus_tag||genome_project_id||coverage||source
line = line.strip()
values = line.split('||')
common_name=values[0]
locus_tag=values[3]
embl_file = "../IMG/%s.4dep.embl" % common_name
util.checkFile(embl_file)
tbl_file = "%s.tbl" % common_name
log.info("Convert file %s into %s" % (embl_file, tbl_file))
if options.convert:
try:
doConvert(embl_file, tbl_file, locus_tag)
except Exception, e:
log.error("Converting %s" % embl_file)
log.error(traceback.extract_stack())
log.error(e)
def main():
usage = "usage: %prog [Options]"
parser = OptionParser(usage=usage)
parser.add_option("-l", metavar="FILE", help="FILE containing the list of all organism common names and its associated locus tag", action="store", type="string", dest="list")
parser.add_option("--convert", help="Do convert genbank file into embl", action="store_true", dest="convert")
(options, args) = parser.parse_args()
# Print help if no argument given
if util.printHelp(options):
parser.print_help()
sys.exit()
# Get and check input arguments
if options.list:
# Read organism common name and related locus tag
list_file = options.list
util.checkFile(list_file)
for line in open(list_file, "r"):
if line[0] == '!':
continue
if line.count('||') < 1:
continue
# ! common_name||organim_name||strain||locus_tag||fasta_file
line = line.strip()
values = line.split('||')
common_name=values[0]
locus_tag=values[3]
gbk_file = "%s.img.embl" % common_name
util.checkFile(gbk_file)
tbl_file = "%s.tbl" % common_name
print "Convert file %s into %s" % (gbk_file, tbl_file)
if options.convert:
try:
doConvert(gbk_file, tbl_file, locus_tag)
except Exception, e:
print "ERROR to convert %s" % gbk_file
print e
def main():
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")
parser.add_option("-p", metavar="ID", help="IMG project ID (GOLD Stamp ID)", action="store", type="string", dest="id")
parser.add_option("-l", metavar="FILE", help="FILE containing the list of all organism common names, its associated sequence file and IMG project ID", action="store", type="string", dest="list")
(options, args) = parser.parse_args()
# Print help if no argument given
if util.printHelp(options):
parser.print_help()
sys.exit()
# Get and check input arguments
if options.list:
# Read organism common name and related fasta sequence file
list_file = options.list
util.checkFile(list_file)
for line in open(list_file, "r"):
if line[0] == '!':
continue
if line.count('||') < 1:
continue
# ! common_name||sequence_file
line = line.strip()
values = line.split('||')
common_name = values[0]
input_file = values[1]
id = values[2]
util.checkFile(input_file)
doSubmit(common_name, input_file, id)
else:
common_name = options.name
input_file = options.input
id = options.id
util.checkFile(input_file)
doSubmit(common_name, input_file, id)
def main():
usage = "usage: %prog [Options]"
parser = OptionParser(usage=usage)
parser.add_option("-o", metavar="EXTENSION", help="Old EXTENSION", action="store", type="string", dest="old")
parser.add_option("-n", metavar="EXTENSION", help="New EXTENSION", action="store", type="string", dest="new")
parser.add_option("--rename", help="Do rename", action="store_true", dest="rename")
(options, args) = parser.parse_args()
# Print help if no argument given
if util.printHelp(options):
parser.print_help()
sys.exit()
for file in os.listdir('.'):
if options.old in file:
oldfile = file
newfile = "%s.%s" % (oldfile.split(".")[0], options.new)
print "Rename old file %s into %s" % (oldfile, newfile)
if options.rename:
cmd = "mv %s %s" % (oldfile, newfile)
util.runProcess(cmd)
if not options.rename:
print "To perform the action, please use --rename"
def main():
usage = "usage: %prog [Options]"
parser = OptionParser(usage=usage)
parser.add_option("-l", "--list", metavar="FILE", help="FILE containing the list of all organisms", action="store", type="string", dest="list")
parser.add_option("-D", action="store", dest="dbhost")
(options, args) = parser.parse_args()
# Print help if no argument given
if util.printHelp(options):
parser.print_help()
sys.exit()
# Print command line
cmdline = "$ python "
for argv in sys.argv:
cmdline += argv + " "
logger.info(cmdline)
# Print logger file info
logger.info(logsetup.logpath)
# Setup database connection
host = ropy.util.getDArg("dbhost", raiseOnEmpty = True)
database = ropy.util.getDArg("dbname", raiseOnEmpty = True)
port = ropy.util.getDArg("dbport", raiseOnEmpty = True)
user = ropy.util.getDArg("dbuser", raiseOnEmpty = True)
password = ropy.util.getDArg("dbpassword")
connectionFactory = ropy.query.ConnectionFactory(host, database, user, password, port)
# Read organism list file and load it into the database
data_path = options.list
for line in open(data_path, "r"):
if line[0] == '!':
continue
if line.count('||') < 1:
continue
# ! Genus||species||strain||taxonId
line = line.strip()
list = line.split('||')
genus = list[0]
species = list[1].replace('sp.', 'unknown')
strain = list[2]
taxonid = list[3]
# Load organism
chado_species = "%s (%s)" % (species, strain)
common_name = getCommonName(genus, species, strain)
abbreviation = common_name
comment = None
logger.info(common_name)
logger.info(db.makeOrganism(connectionFactory, genus, chado_species, abbreviation, common_name, comment))
# Load translation table
logger.info(db.makeOrganismProp(connectionFactory, genus, chado_species, "genedb_misc", "translationTable", 11))
# Load taxonomy id
logger.info(db.makeOrganismProp(connectionFactory, genus, chado_species, "genedb_misc", "taxonId", taxonid))
# Load HTML name fields for GeneDB web
htmlFullName = getHtmlFullName(genus, species, strain)
logger.info(db.makeOrganismProp(connectionFactory, genus, chado_species, "genedb_misc", "htmlFullName", htmlFullName))
htmlShortName = getHtmlShortName(genus, species, strain)
logger.info(db.makeOrganismProp(connectionFactory, genus, chado_species, "genedb_misc", "htmlShortName", htmlShortName))