def Writeproba(dir, Matrixproba, constraintes, rna):
FF.CreateFold(Matrixproba)
for file in constraintes:
PSPath = dir + "/" + file + "_dp.ps"
bpm = loadDotPlotPS(PSPath, "RNAfold")
dp = DotPlot(rna, bpm)
with open(Matrixproba + file.split('.')[0] + ".proba", "w") as o:
for (i, j) in bpm.keys():
o.write("%i\t%i\t%.6f\n" % (i, j, bpm[(i, j)]))
o.close()
def StructSampling(Pathconstraints, InputAlignment, numberofsruct, Tmpr,
Extension, m, b):
print InputAlignment
dir = 'OutputSamples' + str(numberofsruct)
FF.CreateFold(dir)
for Path in Pathconstraints:
for filename in FF.GetListFile(Path, Extension):
print "filename", filename
Input = Path + "/" + filename
output = dir + '/' + os.path.splitext(filename)[0]
#Command = 'RNAsubopt -p ' + str(numberofsruct) + ' -s -T ' + str(Tmpr)+ ' --maxBPspan '+ str(3*444/2)
Command = 'RNAsubopt -p ' + str(numberofsruct) + ' -s -T ' + str(
Tmpr)
if Path == conf.PathConstrainteFile:
Command += ' -C --enforceConstraint'
if Path == conf.PathConstrainteFileShape:
ShapeFile = conf.PathConstrainteFileShape + "/" + os.path.splitext(
filename)[0] + 'Shape.txt'
#Command += ' --shape ' + ShapeFile + ' shapeMethod=Z '+ 'shapeConversion= M' # by default the shapeMethod=D (Deigan et al 2009), where the method Z is from Zarringhalm et al 2012
#Command += ' --shape ' + ShapeFile + ' --shapeMethod="Dm3.48b-1.35"' # DMS new param
#Command += ' --shape ' + ShapeFile #" defaults
#Command += ' --shape ' + ShapeFile + ' --shapeMethod="Dm3.4794b-1.1598"' # for CMCT
#print Command
Command += ' --shape ' + ShapeFile + ' --shapeMethod="Dm' + str(
m) + 'b' + str(b) + '"'
subprocess.call(Command,
stdin=open(Input, 'r'),
stdout=open(output, 'wb'),
shell=True)
#because the version 2.3 of rnaeval does not consider the rna, second line should be removed
lines = []
with open(output, 'r') as f:
lines = f.readlines()
with open(output, 'w') as f:
f.writelines(lines[:1] + lines[2:])
for filename in FF.GetListFile(InputAlignment, '.aln'):
Input = InputAlignment + "/" + filename
print InputAlignment, Input
Output = 'Sample' + os.path.splitext(filename)[0]
#For the sampling from MSA alifold
Command = 'RNAalifold -r -d2 --noLP --aln --stochBT ' + str(
numberofsruct)
subprocess.call(Command,
stdin=open(Input, 'r'),
stdout=open(Output, 'wb'),
shell=True)
Adjust_structure(Output, dir, os.path.splitext(filename)[0])
return dir
def StructSampling(Pathconstraints, Conditions, numberStructures, T, m, b, defaultFasta):
conf = loadConfig()
dir = os.path.join(conf.OutputFolder, "tmp", 'OutputSamples' + str(numberStructures))
FF.CreateFold(dir)
thermoMsgShown = False
for filename in Conditions:
lines = []
header = []
progress.StartTask("Processing %s"%(filename))
while len(lines) - NUM_HEADER_LINES < numberStructures:
# If alternative sequence file found in constraints folder, use it rather than default
Input = defaultFasta
for p in Pathconstraints:
tmpInput = os.path.join(p, filename + '.' + IPANEMAP.FASTA_EXTENSION)
if os.path.isfile(tmpInput):
Input = tmpInput
output = os.path.join(dir, filename)
Command = 'RNAsubopt -p ' + str(numberStructures) + ' -s -T ' + str(T)
(hasHardConstraints, hasSoftConstraints) = (False, False)
hardConstraintFile = os.path.join(conf.PathConstraintsFile, filename + '.txt')
if os.path.isfile(hardConstraintFile):
Command += ' -C --enforceConstraint '
hasHardConstraints = True
Input = hardConstraintFile
ShapeFile = os.path.join(conf.PathConstraintsFileShape, filename + '.txt')
if os.path.isfile(ShapeFile):
Command += ' --shape ' + ShapeFile + ' --shapeMethod="Dm' + str(m) + 'b' + str(b) + '"'
hasSoftConstraints = True
if not (hasHardConstraints or hasSoftConstraints or thermoMsgShown):
progress.Print("Warning: Did not find suitable constraint file for this condition, using purely thermodynamic sampling")
thermoMsgShown = True
subprocess.call(Command, stdin=open(Input, 'r'), stdout=open(output, 'wb'),
stderr=open(os.devnull, 'w'), shell=True)
with open(output, 'r') as f:
nlines = f.readlines()
header = nlines[:NUM_HEADER_LINES]
lines += nlines[NUM_HEADER_LINES:]
with open(output, 'w') as f:
f.writelines(header+lines[:numberStructures])
progress.EndTask()
return dir
def StructSampling(Pathconstraints, numberofsruct, Tmpr, Extension):
dir = 'OutputSamples' + str(numberofsruct)
FF.CreateFold(dir)
for Path in Pathconstraints:
for filename in FF.GetListFile(Path, Extension):
Input = Path + "/" + filename
output = dir + '/' + os.path.splitext(filename)[0]
Command = 'RNAsubopt --noLP -p ' + str(
numberofsruct) + ' -s -T ' + str(Tmpr)
if Path == conf.PathConstrainteFile:
Command += ' -C'
if Path == conf.PathConstrainteFileShape:
ShapeFile = conf.PathConstrainteFileShape + "/" + os.path.splitext(
filename)[0] + 'Shape.txt'
Command += ' --shape ' + ShapeFile
subprocess.call(Command,
stdin=open(Input, 'r'),
stdout=open(output, 'wb'),
shell=True)
return dir
def DotplotRnaFold(dir, PathConstrainteFile, PathConstrainteFileShape):
FF.CreateFold(dir)
for filename in FF.GetListFile(PathConstrainteFile, '.fa'):
name = os.path.splitext(filename)[0]
Input = PathConstrainteFile + "/" + filename
output = dir + '/' + name
#print "command is", 'RNAfold -p -d2 -C --enforceConstraint <'+Input+ '>'+ output
os.system('RNAfold --noLP -p -d2 -C --enforceConstraint <' + Input +
'>' + output)
#Sp.call("RNAfold -p -d2 -C ", stdin=Input, stdout=output, shell=True)
# redirect files to the specific folder dir
shutil.move(name + '_dp.ps', dir + "/" + name + '_dp.ps')
shutil.move(name + '_ss.ps', dir + "/" + name + '_ss.ps')
for filename in FF.GetListFile(PathConstrainteFileShape, '.fa'):
name = os.path.splitext(filename)[0]
Input = PathConstrainteFileShape + "/" + filename
ShapeFile = PathConstrainteFileShape + "/" + name + 'Shape.txt'
output = dir + '/' + name
os.system('RNAfold -p -d2 -C ' + '<' + Input + ' --shape ' +
ShapeFile + '>' + output)
shutil.move(name + '_dp.ps', dir + "/" + name + '_dp.ps')
shutil.move(name + '_ss.ps', dir + "/" + name + '_ss.ps')
import FileFunctions as FF
import Sampling as SP
import StructureFunctions as SF
import StructureFunctions as SF
import VisualizationTools as VT
import ClustersTrait as CT
import Optimize_clustering as OC
from Progress import progress
FASTA_EXTENSION = "fa"
if __name__ == "__main__":
conf = loadConfig()
# Create folders
FF.CreateFold(conf.OutputFolder)
FF.CreateFold(os.path.join(conf.OutputFolder, "tmp"))
FF.CreateFold(os.path.join(conf.OutputFolder, "tmp", conf.PickledData))
# Redirects all the print to the output Log file
sys.stdout = Logger(os.path.join(conf.OutputFolder, conf.OutputLogfile))
# ******************************** Generate sample
try:
rna = os.path.split(conf.RNA)[-1]
RNAName = rna[:-(len(FASTA_EXTENSION) + 1)]
progress.StartTask("Processing RNA %s" % (RNAName))
if not os.path.isfile(conf.RNA):
raise FF.IPANEMAPError("Input file '%s' not found" % (conf.RNA))
