def main():
options = mainUsage()
script = options.run
checkDoRun(script)
try:
# 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
common_name, input_file = util.splitLine(line)
util.checkFile(input_file)
# Run command
cmd = 'python -c "from genepy.annotators.%s import doRun; doRun()" -o %s -i %s' % (script, common_name, input_file)
if util.isLsf():
job_name = "%s.%s" % (common_name, ANNOTATOR_EXTENSION[script])
util.submitJob(job_name, cmd, ANNOTATOR_QUEUE[script])
else:
util.runProcess(cmd)
except Exception, e:
log.error(e)
def fasta2embl(infasta):
"""
Transform sequence file format in fasta to embl using EMBOSS seqret
Returns the name of created embl file
"""
util.checkFile(infasta)
outembl = infasta.split(".")[0] + ".embl"
"""
Usage: seqret
Online documentation: http://emboss.open-bio.org/wiki/Appdoc:Seqret
Standard (Mandatory) qualifiers:
[-sequence] seqall (Gapped) sequence(s) filename and optional
format, or reference (input USA)
[-outseq] seqoutall [<sequence>.<format>] Sequence set(s)
filename and optional format (output USA)
The basic USA syntax is one of:
"file"
"file:entry"
"format::file"
"format::file:entry"
"database:entry"
"database"
"@file"
"""
# Create EMBOSS seqret command line
cmd = "seqret -sequence fasta::%s -outseq embl::%s " % (infasta, outembl)
# Call the subprocess using convenience method
util.runProcess(cmd)
logger.info("File", outembl, "created")
return outembl
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 splitSeq(dir, embl, type):
"""
Split sequence into separate file based on CDS features into dir/ directory
based on EMBOSS extractfeat
Usage: extractfeat
Online documentation: http://emboss.open-bio.org/wiki/Appdoc:Extractfeat
Standard (Mandatory) qualifiers:
[-sequence] seqall Sequence(s) filename and optional format, or
reference (input USA)
[-outseq] seqout [.] Sequence filename and
optional format (output USA)
Additional (Optional) qualifiers:
-type string [*] By default every feature in the feature
table is extracted. You can set this to be
any feature type you wish to extract.
See http://www.ebi.ac.uk/Services/WebFeat/
for a list of the EMBL feature types and see
the Uniprot user manual in
http://www.uniprot.org/manual/sequence_annotation
for a list of the Uniprot feature types.
The type may be wildcarded by using '*'.
If you wish to extract more than one type,
separate their names with the character '|',
eg:
*UTR | intron (Any string is accepted)
-featinname boolean [N] To aid you in identifying the type of
feature that has been output, the type of
feature is added to the start of the
description of the output sequence.
Sometimes the description of a sequence is
lost in subsequent processing of the
sequences file, so it is useful for the type
to be a part of the sequence ID name. If
you set this to be TRUE then the name is
added to the ID name of the output sequence.
Associated qualifiers:
"-outseq" associated qualifiers
-ossingle2 boolean Separate file for each entry
-ofdirectory2 string Output directory
The basic USA syntax is one of:
"file"
"file:entry"
"format::file"
"format::file:entry"
"database:entry"
"database"
"@file"
"""
util.checkFile(embl)
# Create directory
util.createDir(dir)
cmd = "extractfeat -sequence embl::%s -type %s -featinname YES -outseq fasta:: -osextension2 ffn -ossingle2 Yes -osdirectory2 %s" % (embl, type, dir)
util.runProcess(cmd)
logger.info("Sequences extracted into %s" % dir)
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 writeFile(data, address):
writeSocket = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
writeSocket.bind((HOST, randint(1024, 65535)))
writeSocket.settimeout(TIMEOUT)
filename = str(data).split('\\x')[2][2:]
if checkFile(data):
serviceMsg(f'File already exists.')
ERRpackage = generatePackage(type=OPCODE['ERROR'], errorCode=6)
writeSocket.sendto(ERRpackage, address)
serviceMsg(f'Sent error to client: {address}. Raw data: {ERRpackage}')
return
else:
ACKpackage = generatePackage(type=OPCODE['ACK'], blockNumber=0)
writeSocket.sendto(ACKpackage, address)
serviceMsg(f'Sent ACK after WRQ to client: {address}. Raw data: {ACKpackage}. Block number: {0}')
fileData = getterHandler(writeSocket, BLOCK_SIZE)
if (fileData is not None):
writeFileBytes(f'f/{filename}', fileData)
serviceMsg(f'Successfully wrote data to f/{filename}')
writeSocket.close()
return
else:
return
def concatFeatures(embl, features):
"""
Concat CDS features in embl format into embl sequence file
- the first two lines of embl sequence containing ID & XX lines
- the CDS features file containing FT lines
- the rest of embl sequence containing SQ lines
Returns the name of created embl sequence file
"""
util.checkFile(embl)
util.checkFile(features)
outembl = embl.split(".")[0] + "_with_cds.embl"
# Create command line
head_cmd = "head -2 %s > %s; cat %s >> %s;" % (embl, outembl, features, outembl)
util.runProcess(head_cmd)
tail_cmd = "tail +3 %s > tail; cat tail >> %s; rm tail;" % (embl, outembl)
util.runProcess(tail_cmd)
logger.info("File", outembl, "created")
return outembl
def runReciprocalFasta(seq_dir, genome_file, fasta_dir):
"""
Run FASTA between extracted in-house protein sequences against new genome
FASTA searches a protein or DNA sequence data bank
version 35.04 Aug. 25, 2009
W.R. Pearson & D.J. Lipman PNAS (1988) 85:2444-2448
"""
util.createDir(fasta_dir)
# Check new genome
util.checkFile(genome_file)
# Check ref genome extracted sequences
util.checkDir(seq_dir)
res_dir = fasta_dir
if IS_LSF:
# Rename new genome sequences for job array to be refgenome_1.faa refgenome_2.faa ...
seq_num = 0
for seq_file in os.listdir(seq_dir):
if not '.faa' in seq_file:
continue
seq_num += 1
if 'refgenome_' in seq_file and '.faa' in seq_file:
continue
seq_newfilepath = "%s/refgenome_%s.faa" % (seq_dir, seq_num)
seq_filepath = "%s/%s" % (seq_dir, seq_file)
os.rename(seq_filepath, seq_newfilepath)
# Submit bsub job array on refgenome_${LSB_JOBINDEX}.faa against mygenome
bsub_dir = "bsub"
util.checkDir(bsub_dir)
cmd = "fasta35 -z 1 -Q -H -S -m 10 %s/refgenome_${LSB_JOBINDEX}.faa %s > %s/refgenome_${LSB_JOBINDEX}.fa" % (seq_dir, genome_file, res_dir)
util.submitJobArray(jobname="genepy-recipfasta", jobnum=seq_num, jobdir=bsub_dir, cmd=cmd)
util.submitJobDependency('genepy-recipfasta')
logger.info("Reciprocal Fasta on LSF finished")
else:
# List of inhouse extracted genome sequences
for seq_file in os.listdir(seq_dir):
if not '.faa' in seq_file:
continue
res_file = seq_file.split(".")[0] + ".fa"
cmd = "fasta35 -z 1 -Q -H -S -m 10 %s/%s %s > %s/%s" % (seq_dir, seq_file, genome_file, res_dir, res_file)
util.runProcess(cmd)
logger.info(seq_file)
logger.info("Reciprocal Fasta finished")
def splitSeqWithBiopython(embl, type):
"""
Split sequence into separate file based on CDS features into sequences/ directory
using Biopython
"""
util.checkFile(embl)
# Create directory sequences/
dirname = "sequences/"
util.createDir(dirname)
record = SeqIO.read(open(embl, "rU"), "embl")
if len(record.features) == 0:
sys.exit("ERROR: EMBL file %s without features" % embl)
for feature in record.features:
if feature.type == 'CDS':
seq = record.seq
# Build up a list of (start,end) tuples that will be used to slice the sequence
locations = []
# If there are sub_features, then this gene is made up of multiple parts.
if len(feature.sub_features):
for sf in feature.sub_features:
locations.append((sf.location.start.position, sf.location.end.position))
# This gene is made up of one part. Store its start and end position.
else:
locations.append((feature.location.start.position, feature.location.end.position))
# Store the joined sequence and nucleotide indices forming the CDS.
seq_str = ''
for begin, end in locations:
seq_str += seq[begin:end].tostring()
# Reverse complement the sequence if the CDS is on the minus strand
if feature.strand == -1:
seq_obj = Seq(seq_str, IUPAC.ambiguous_dna)
seq_str = seq_obj.reverse_complement().tostring()
logger.debug(feature)
logger.debug(SeqRecord(seq=Seq(seq_str), id=feature.qualifiers['systematic_id'][0], description=feature.type).format('fasta'))
logger.info("Sequences extracted into %s" % dirname)
def readConf(file):
'''
:param file: location of config file
:return: conf file as dict
'''
if not checkFile(file):
logger.error('[{}] : Configuration file not found at {}'.format(
datetime.fromtimestamp(time.time()).strftime('%Y-%m-%d %H:%M:%S'),
file))
sys.exit(1)
file_extension = file.split('.')[-1]
if file_extension == 'ini':
parser = SafeConfigParser()
parser.read(file)
conf = {}
for selection in parser.sections():
inter = {}
for name, value in parser.items(selection):
inter[name] = value
conf[selection] = inter
elif file_extension == 'yaml' or file_extension == 'yml':
with open(file) as cf:
conf = yaml.unsafe_load(cf)
# try:
# with open(file) as cf:
# conf = yaml.unsafe_load(cf)
# except Exception as inst:
# logger.error('[{}] : Failed to parse configuration file with {} and {}'.format(
# datetime.fromtimestamp(time.time()).strftime('%Y-%m-%d %H:%M:%S'), type(inst), inst.args))
# sys.exit(1)
else:
logger.error(
'[{}] : Unsupported configuration file extension {}'.format(
datetime.fromtimestamp(
time.time()).strftime('%Y-%m-%d %H:%M:%S'),
file_extension))
sys.exit(1)
return conf
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)
