def run( self ):
self.start()
if os.path.isfile( self._inData ):
FastaUtils.convertFastaHeadersFromChkToChr( self._inData, self._mapFile, self._outFile )
else:
lInFiles = glob.glob( self._inData )
if len(lInFiles) == 0:
msg = "WARNING: no file corresponds to pattern '%'" % ( self._inData )
sys.stdout.write( "%s\n" % ( msg ) )
self.end()
for inFile in lInFiles:
outFile = "%s.onChr" % ( inFile )
FastaUtils.convertFastaHeadersFromChkToChr( inFile, self._mapFile, outFile )
self.end()
def run( self ):
"""
Run the program.
"""
self.start()
lInitHeaders = FastaUtils.dbHeaders( self.getInputFile(), self.getVerbosityLevel()-1 )
csh = ChangeSequenceHeaders()
csh.setInputFile( self.getInputFile() )
csh.setFormat( "fasta" )
csh.setStep( 1 )
csh.setPrefix( "seq" )
csh.setLinkFile( "%s.shortHlink" % ( self.getInputFile() ) )
csh.setOutputFile( "%s.shortH" % ( self.getInputFile() ) )
csh.setVerbosityLevel( self.getVerbosityLevel() - 1 )
csh.run()
bsDB = BioseqDB( "%s.shortH" % ( self.getInputFile() ) )
bsDB.upCase()
bsDB.save( "%s.shortHtmp" % ( self.getInputFile() ) )
del bsDB
os.rename( "%s.shortHtmp" % ( self.getInputFile() ),
"%s.shortH" % ( self.getInputFile() ) )
self.setProgramCommandLine()
cmd = self.getProgramCommandLine()
if self.getVerbosityLevel() > 0:
print "LAUNCH: %s" % ( cmd )
sys.stdout.flush()
exitStatus = os.system( cmd )
if exitStatus != 0:
string = "ERROR: program '%s' returned exit status '%i'" % ( self.getProgramName(), exitStatus )
print string
sys.exit(1)
csh.setInputFile( "%s.shortH.fa_aln" % ( self.getInputFile() ) )
csh.setFormat( "fasta" )
csh.setStep( 2 )
csh.setLinkFile( "%s.shortHlink" % ( self.getInputFile() ) )
csh.setOutputFile( "%s.shortH.fa_aln.initH" % ( self.getInputFile() ) )
csh.setVerbosityLevel( self.getVerbosityLevel() - 1 )
csh.run()
absDB = AlignedBioseqDB( "%s.shortH.fa_aln.initH" % ( self.getInputFile() ) )
outFileHandler = open( self.getOutputFile(), "w" )
for header in lInitHeaders:
bs = absDB.fetch( header )
bs.upCase()
bs.write( outFileHandler )
outFileHandler.close()
os.remove( "%s.shortH.fa_aln.initH" % ( self.getInputFile() ) )
self.end()
def main():
inFileName = ""
outFileName = ""
verbose = 0
try:
opts, args=getopt.getopt(sys.argv[1:],"hi:o:v:")
except getopt.GetoptError:
help()
sys.exit(1)
for o,a in opts:
if o == "-h":
help()
sys.exit(0)
elif o == "-i":
inFileName = a
elif o == "-o":
outFileName = a
elif o == "-v":
verbose = int(a)
if inFileName == "":
print "*** Error: missing compulsory options"
help()
sys.exit(1)
if verbose > 0:
print "beginning of %s" % (sys.argv[0].split("/")[-1])
sys.stdout.flush()
log = FastaUtils.sortSequencesByIncreasingLength( inFileName, outFileName, verbose )
if log != 0:
print "*** Error: sortSequencesByIncreasingLength() returned %i" % ( log )
sys.exit(1)
if verbose > 0:
print "%s finished successfully" % (sys.argv[0].split("/")[-1])
sys.stdout.flush()
return 0
if sbjFileName != "":
if not os.path.exists( sbjFileName ):
string = "subject file '%s' doesn't exist" % ( sbjFileName )
logging.error( string )
print "ERROR: %s" % ( string )
sys.exit(1)
else:
sbjFileName = qryFileName
logging.info( "remove redundancy among '%s' (queries) compare to '%s' (subjects)" % ( qryFileName, sbjFileName ) )
#--------------------------------------------------------------------------
# check the input files are not empty, otherwise exit
nbSeqQry = FastaUtils.dbSize( qryFileName )
if nbSeqQry == 0:
string = "query file is empty"
logging.info( string )
print "WARNING: %s" % ( string )
logging.info( "finished" )
sys.exit(0)
nbSeqSbj = FastaUtils.dbSize( sbjFileName )
if sbjFileName != qryFileName:
nbSeqSbj = FastaUtils.dbSize( sbjFileName )
if nbSeqSbj == 0:
string = "subject file is empty"
logging.info( string )
print "WARNING: %s" % ( string )
logging.info( "finished" )
elif o == "-v":
verbose = int(a)
if inData == "" or ( not os.path.isfile( inData ) \
and not os.path.isdir( inData ) ):
msg = "ERROR: missing input file or directory (-i or -I)"
sys.stderr.write( "%s\n" % msg )
help()
sys.exit(1)
if outData == "":
print "ERROR: missing name of output file or directory (-o or -O)"
help()
sys.exit(1)
if verbose > 0:
print "START %s" % ( sys.argv[0].split("/")[-1] )
sys.stdout.flush()
FastaUtils.dbShuffle( inData, outData, verbose )
if verbose > 0:
print "END %s" % ( sys.argv[0].split("/")[-1] )
sys.stdout.flush()
return 0
if __name__ == "__main__":
main()
print "prepare MSP file"; sys.stdout.flush()
prg = os.environ["REPET_PATH"] + "/bin/align2recon.py"
cmd = prg
cmd += " -i %s" % ( alignFileName )
cmd += " -o %s_MSP_file" % ( projectName )
cmd += " -v %i" % ( verbose - 1 )
returnStatus = os.system( cmd )
if returnStatus != 0:
msg = "ERROR: '%s' returned '%i'" % ( prg, returnStatus )
sys.stderr.write( "%s\n" % ( msg ) )
sys.exit(1)
if verbose > 0:
print "prepare seq file"; sys.stdout.flush()
lSeqNames = FastaUtils.dbHeaders( faFileName, verbose - 1 )
lSeqNames.sort()
seqListFile = open( projectName + "_seq_list", "w" )
seqListFile.write( str(len(lSeqNames)) + "\n" )
for seqName in lSeqNames:
seqListFile.write( ">%s\n" % ( seqName ) )
seqListFile.close()
if verbose > 0:
print "Recon is running..."; sys.stdout.flush()
prg = "recon.pl"
cmd = prg
cmd += " %s_seq_list" % ( projectName )
cmd += " %s_MSP_file" % ( projectName )
cmd += " 1"
elif o == "-d":
newDir = True
elif o == "-s":
useSeqHeader = True
elif o == "-p":
prefix = a
elif o == "-v":
verbose = int(a)
if inFile == "":
msg = "ERROR: missing input file (-i)"
sys.stderr.write( "%s\n" % ( msg ) )
help()
sys.exit(1)
if verbose > 0:
print "START %s" % ( sys.argv[0].split("/")[-1] )
sys.stdout.flush()
FastaUtils.dbSplit( inFile, nbSeqPerBatch, newDir, useSeqHeader, prefix, verbose )
if verbose > 0:
print "END %s" % ( sys.argv[0].split("/")[-1] )
sys.stdout.flush()
return 0
if __name__ == "__main__":
main()
sys.stderr.write( "%s\n" % ( msg ) )
help()
sys.exit(1)
if clusteringMethod == "":
msg = "ERROR: missing clustering method (-c)"
sys.stderr.write( "%s\n" % ( msg ) )
help()
sys.exit(1)
if not os.path.exists( inFileName ):
msg = "ERROR: can't find file '%s'" % ( inFileName )
sys.stderr.write( "%s\n" % ( msg ) )
help()
sys.exit(1)
if verbose > 0:
print "START %s" % (sys.argv[0].split("/")[-1])
sys.stdout.flush()
FastaUtils.splitSeqPerCluster( inFileName, clusteringMethod, simplifyHeader,
createDir, "seqCluster", verbose )
if verbose > 0:
print "END %s" % (sys.argv[0].split("/")[-1])
sys.stdout.flush()
return 0
if __name__ == "__main__":
main()