def main():
usage = "usage: %prog [Options]"
parser = OptionParser(usage=usage)
parser.add_option("-a", metavar="EMBL-a", help="First EMBL file", action="store", type="string", dest="first_embl")
parser.add_option("-b", metavar="EMBL-b", help="Second EMBL file to compare", action="store", dest="second_embl")
parser.add_option("--merge", help="To transfer /product of identical annotations into a merged file", action="store_true", dest="merge")
(options, args) = parser.parse_args()
# Print help if no argument given
if util.printHelp(options):
parser.print_help()
sys.exit()
first_record = SeqIO.read(open(options.first_embl), "embl")
second_record = SeqIO.read(open(options.second_embl), "embl")
print "Analysis of EMBL features A from %s" % options.first_embl
print "Analysis of EMBL features B from %s" % options.second_embl
stat(first_record)
if options.merge:
merged_record = transfer(first_record, second_record)
# Write out genbank file
SeqIO.write([merged_record], open("merged.embl", "w"), "embl")
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 to compare", 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()
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
# ! common_name
common_name = line.strip()
gendb_file = "GenDB/%s.gendb.embl" % common_name
rast_file = "RAST/%s.rast.embl" % common_name
img_file = "IMG/%s.img.embl" % common_name
if not os.path.exists(gendb_file) or not os.path.exists(rast_file) or not os.path.exists(img_file):
print "No three results for %s" % common_name
continue
print "Processing %s" % common_name
doCompare(common_name, gendb_file, rast_file, img_file)
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 parameters depending on submitter type",
action="store",
type="string",
dest="list",
)
parser.add_option(
"-r",
"--run",
metavar="SCRIPT",
help="name of the script to run from %s against each genome of the list" % SUBMIT_SCRIPTS,
action="store",
choices=SUBMIT_SCRIPTS,
dest="run",
)
parser.add_option("--submit", help="To submit data, not only for checking", 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()
# Print command line
cmdline = "$ python "
for argv in sys.argv:
cmdline += argv + " "
log.info(cmdline)
script = options.run
try:
if options.list:
util.checkFile(options.list)
if script == "genome_project":
import submitters.genome_project as genome_project
genome_project.doRun(options.list, options.submit)
elif script == "annotated_genome":
import submitters.annotated_genome as annotated_genome
annotated_genome.doRun(options.list, options.submit)
else:
log.info("Organism list file not provided! Please provide one using -l FILE or --list=FILE")
except Exception, e:
import traceback
log.error(traceback.extract_stack())
log.error(e)
def mainUsage():
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 FASTA sequence file", action="store", type="string", dest="list")
parser.add_option("-r", "--run", metavar="SCRIPT", help="name of the script to run from %s against each genome of the list" % ANNOTATOR_SCRIPTS, action="store", choices=ANNOTATOR_SCRIPTS, dest="run")
(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 + " "
log.info(cmdline)
return options
# Comando de la aplicacion.
APP_CMD = "udpClient.py"
# Tiempo que se espera por la respuesta del servidor.
WAIT_FOR_RESPONSE = 2
# Se obtienen los parametros del Servidor UDP, ip, puerto y
# tamano de buffer en bytes.
# Los parametros son seleccionados por defecto o bien pasados en
# la linea de comandos.
connectionIp, connectionPort, bufferSize, helpFlag = util.parseParameters(
sys.argv, DEBUG)
# En caso de solicitarse informacion de ayuda, se imprime y se termina el programa.
if (helpFlag):
util.printHelp(APP_NAME, APP_CMD)
# Se sale del programa
sys.exit()
# Se indican datos del programa.
if (DEBUG):
util.printAppInfo(APP_NAME, connectionIp, connectionPort, bufferSize)
while (1):
try:
# Se crea el socket
sock = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
except socket.error as err_msg:
# En caso de no poder crear la conexion, se indica y se termina el programa.
def main():
# Fasta file extension:
# .ffn for the untranslated nucleotide sequences for each CDS; .faa for protein coding sequences (CDS)
# .fa for the fasta alignment results
# .fna for whole genomic DNA sequences; .frn for nucleotide sequences of RNA related features
usage = "usage: %prog [Options]"
parser = OptionParser(usage=usage)
parser.add_option("-d", "--dna", metavar="FILE", help="input dna FILE in fasta format", action="store", type="string", dest="dna")
parser.add_option("-t", "--tab", metavar="FILE", help="input tab FILE in embl format", action="store", type="string", dest="tab")
parser.add_option("-e", "--embl", metavar="FILE", help="input embl FILE with CDS features in embl format", action="store", type="string", dest="embl")
parser.add_option("--genedb", help="extract reference genome protein sequences from geneDB", action="store_true", dest="db")
parser.add_option("--fasta", help="run fasta against each extracted in-house genomes", action="store_true", dest="fasta")
parser.add_option("--hamap", help="run pfscan against HAMAP profiles", action="store_true", dest="hamap")
parser.add_option("--clean", help="delete all results without deleting reference genomes", action="store_true", dest="clean")
parser.add_option("--deepclean", help="delete all reference genomes and results", action="store_true", dest="deepclean")
(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.debug(cmdline)
# >>> ---------------------------------------------------------------------
# >>> DATA PREPARATION
# >>> ---------------------------------------------------------------------
# List of needed software
for softname in soft_lists:
util.checkSoft(softname)
# Prepare new genome data
if options.dna and options.tab and not options.embl:
util.checkFile(options.dna)
mygenome_emblfile = fasta2embl(options.dna)
mygenome_emblfile_withcds = concatFeatures(mygenome_emblfile, options.tab)
splitSeq(mygenome_dir, mygenome_emblfile_withcds, "CDS")
translateSeq(mygenome_dir)
elif not options.dna and not options.tab and options.embl:
mygenome_emblfile_withcds = options.embl
splitSeq(mygenome_dir, mygenome_emblfile_withcds, "CDS")
#splitSeqWithBiopython(mygenome_emblfile_withcds, "CDS") # does not work with testdata_01
translateSeq(mygenome_dir)
elif not options.deepclean:
util.checkDir(mygenome_dir)
# Extract in house genomes from chado db
if options.db:
chadoDump(refgenomes_dir)
elif not options.deepclean:
util.checkDir(refgenomes_dir)
# bsub output directory
if IS_LSF and not (options.clean or options.deepclean):
util.createDir(bsub_dir)
# >>> ---------------------------------------------------------------------
# >>> ORTHOLOG SEARCH
# >>> ---------------------------------------------------------------------
# Run fasta & reciprocal fasta
if options.fasta:
runFasta(mygenome_dir, refgenomes_dir, fasta_dir)
fasta_hits = topFastaHits(fasta_dir, refgenomes_extractedseq_dir)
concatSeq(mygenome_fastafile_allcds, mygenome_dir)
runReciprocalFasta(refgenomes_extractedseq_dir, mygenome_fastafile_allcds, reciprocalfasta_dir)
reciprocalfasta_hits = topReciprocalFastaHits(reciprocalfasta_dir)
printMSPCrunch(fasta_hits, reciprocalfasta_hits)
hits = getHits(fasta_hits, reciprocalfasta_hits)
logger.info("ORTHOLOGS")
logger.info(hits['ortholog'])
logger.info("SIMILARITY")
logger.info(hits['similarity'])
transferFeatures(hits['ortholog'])
# Run hamap scan
if options.hamap:
runHamapScan(mygenome_dir, hamap_dir)
# >>> ---------------------------------------------------------------------
# >>> CLEANING OUTPUT DATA
# >>> ---------------------------------------------------------------------
# Clean results before a re-run
if options.clean:
# fasta results
util.rmDir(fasta_dir)
util.rmDir(reciprocalfasta_dir)
util.rmDir(refgenomes_extractedseq_dir)
util.rmFile(mygenome_fastafile_allcds)
# hamap results
util.rmDir(hamap_dir)
# bsub outputs
if IS_LSF:
util.rmDir(bsub_dir)
# Deep clean - remove all
if options.deepclean:
util.rmDir(refgenomes_dir)
util.rmDir(mygenome_dir)
util.rmDir(fasta_dir)
util.rmDir(reciprocalfasta_dir)
util.rmDir(refgenomes_extractedseq_dir)
util.rmFile(mygenome_fastafile_allcds)
util.rmDir(hamap_dir)
