def main():
#Get currentDirectory and filename
originalFileName = "board2.txt"
currentDirectory = os.path.dirname(os.path.realpath(__file__))
fileName = os.path.join(currentDirectory,
"../test_boards/" + originalFileName)
#2d Array of board, with None in empty places
startingBoard = parseInputFile(fileName)
board = Board(startingBoard)
#Print the starting board
print("Starting Board:")
printBoard(startingBoard)
#Run AC3 Algorithm
print("Calling AC3 Algorithmn")
resolvedBoard = AC3Functions.getAC3(board)
print("AC3 Finished")
if (resolvedBoard == None):
print("Board Not solvable!")
return None
print()
print()
print("Calling backtracking")
print()
if (engine.lower() == "c"):
FileFunctions.callBackTrackingInC(resolvedBoard.domainDict,
originalFileName)
else:
BackTracking.backTrackHelper(board)
def Boltzmann_Calc(constraintes, StructfileRepos, numberofsruct, MFESnbrstruct,
rna, Redondantestructure):
Energy = defaultdict(aa)
Boltzman = defaultdict(aa)
ConditionalBoltzman = defaultdict(aa)
ZBolzman = defaultdict(aa)
for Condition in constraintes:
FileStructure = StructfileRepos + '/' + Condition
#print FileStructure,"ffftft"
Energy[Condition] = ENERGY_VALUES_STRUCTURES(
FileStructure, rna
) # list of energy values for the structures present in the Condition
#print Energy,"llllllllllllllllllllll","done"
for Condition in constraintes:
#print MFESnbrstruct
if Condition == "MFES":
Boltzman[Condition] = [
BoltzmannEnergy(Energy[Condition][i]) for i in range(2)
]
#print "heehrh",Boltzman[Condition]
#for i in range(MFESnbrstruct):
# print i, Boltzman[Condition][i]
#print Boltzman[Condition],"mfe"
else:
listawithoutRedonddnace = []
for i in range(numberofsruct):
Boltzman[Condition][i] = BoltzmannEnergy(Energy[Condition][i])
if Redondantestructure[Condition][
i] == 0: # if the structure is not redundant
listawithoutRedonddnace.append(
BoltzmannEnergy(Energy[Condition][i]))
#print Boltzman, "eeeeeeeeeeeeeeeeeeeeeeeeee"
ZBolzman[Condition] = sum(
listawithoutRedonddnace) # Partition function
#FF.PickleVariable(Boltzman, os.path.join(conf.PickledData, "Boltzman.pkl"))
listall = []
for Condition in constraintes[:-1]: # to not count MFES
lista = []
for i in range(numberofsruct):
if Redondantestructure[Condition][i] == 0:
lista.append(
BoltzmannEnergy(Energy[Condition][i]) /
ZBolzman[Condition])
else:
lista.append(
0
) # to solve the problem of the number of structure variation
listall += lista
ConditionalBoltzman[Condition] = lista
FF.PickleVariable(
ConditionalBoltzman,
os.path.join(conf.PickledData, "ConditionalBoltzman.pkl"))
FF.PickleVariable(ZBolzman, os.path.join(conf.PickledData, "ZBolzman.pkl"))
return Boltzman
def DistanceStruct(StructFile, SVMlFile, numberofsruct, MFESnbrstruct,
constrainte):
Redondantestructure = defaultdict(aa)
MatDist = defaultdict(aa)
Redondantestructure1 = []
DicStruct = {}
Dicnumberofsruct = {}
for i in range(len(constrainte) - 1):
Dicnumberofsruct[constrainte[i]] = numberofsruct
Dicnumberofsruct[constrainte[len(constrainte) - 1]] = MFESnbrstruct
nb, DicStruct = GetBasePairsFromStructFile(StructFile)
for i in range(0, nb):
for j in range(i + 1, nb):
MatDist[i][j] = DistanceTwoBPlist(DicStruct[i], DicStruct[j])
if MatDist[i][j] == 0:
if j not in Redondantestructure1:
if j > numberofsruct * (len(constrainte) - 1):
Dicnumberofsruct[constrainte[len(constrainte) -
1]] -= 1
else:
Dicnumberofsruct[constrainte[int(j /
numberofsruct)]] -= 1
Redondantestructure1.append(j)
MatDist[j][i] = MatDist[i][j]
for elem in Redondantestructure1:
if elem < numberofsruct * (len(constrainte) - 1):
ConditionNumber = int((elem) / numberofsruct)
else:
ConditionNumber = len(constrainte) - 1
StructureNumber = elem - ConditionNumber * numberofsruct
Redondantestructure[constrainte[ConditionNumber]][StructureNumber] = 1
# strore the distance matrix in the file SVMLFile
o = open(os.path.join("output", SVMlFile), "w")
for i in range(len(MatDist)):
o.write("%i\t" % (i + 1))
for j in range(len(MatDist)):
if (i != j):
o.write("%i:%.4f\t" % (j + 1, MatDist[i][j]))
o.write("\n")
o.close()
if Redondantestructure != 0:
print "Warning! redundant structures"
FF.PickleVariable(MatDist, os.path.join(conf.PickledData,
"dissmatrix.pkl"))
FF.PickleVariable(
Redondantestructure1,
os.path.join(conf.PickledData, "Redondantestructures.pkl"))
FF.PickleVariable(
Redondantestructure,
os.path.join(conf.PickledData, "Redondantestructures_Id.pkl"))
FF.PickleVariable(Dicnumberofsruct,
os.path.join(conf.PickledData, "Dicnumberofsruct.pkl"))
return 0
def DistanceStruct(StructFile, SVMlFile, numberofsruct, constrainte):
conf = loadConfig()
Redondantestructure = defaultdict(aa)
MatDist = defaultdict(aa)
Redondantestructure1 = {}
Dicnumberofsruct = {}
for i in range(len(constrainte)):
Dicnumberofsruct[constrainte[i]] = numberofsruct
nb, DicStruct = GetBasePairsFromStructFile(StructFile)
progress.StartTask("Dissimilarity Loop")
for i in range(0, nb):
for j in range(i + 1, nb):
MatDist[i][j] = DistanceTwoStructs(DicStruct[i], DicStruct[j])
MatDist[j][i] = MatDist[i][j]
####### Check for redundancy
if MatDist[i][j] == 0:
jconstraint = int(j / numberofsruct)
if j not in Redondantestructure1 and int(
i / numberofsruct
) == jconstraint: # To be sure that the redundant structure belongs to the same probing condition
Dicnumberofsruct[constrainte[jconstraint]] -= 1
Redondantestructure1[j] = jconstraint
progress.EndTask()
progress.StartTask("Export dissimilarity matrix")
for elem in Redondantestructure1:
jconstraint = Redondantestructure1[elem]
StructureNumber = elem - jconstraint * numberofsruct
Redondantestructure[constrainte[jconstraint]][
StructureNumber] = 1 # we mark redundant structures by value 1
# store the distance matrix in the SVMLFile
SVMLFullPath = os.path.join(conf.OutputFolder, "tmp", SVMlFile)
if os.path.isfile(SVMLFullPath):
os.remove(SVMLFullPath) # To clean the previous version
o = open(SVMLFullPath, "w")
for i in range(len(MatDist)):
o.write("%i\t" % (i + 1))
for j in range(len(MatDist)):
if (i != j):
o.write("%i:%.4f\t" % (j + 1, MatDist[i][j]))
o.write("\n")
o.close()
progress.EndTask()
progress.StartTask("Pickle all data")
FF.PickleVariable(MatDist, "dissmatrix.pkl")
FF.PickleVariable(list(Redondantestructure1.keys()),
"Redondantestructures.pkl")
FF.PickleVariable(Redondantestructure, "Redondantestructures_Id.pkl")
FF.PickleVariable(Dicnumberofsruct, "Dicnumberofsruct.pkl")
progress.EndTask()
return 0
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 run_functions(c_loc, m_loc, f_loc):
# reads the file and creates the desired matrices based on the parameters given
matrix = FileFunctions.read_covariance_matrix(c_loc)
model = FileFunctions.read_model(m_loc)
fiducial = FileFunctions.read_fiducial(f_loc)
matrices = []
for m in model:
temp = Matrix(m[0], m[1], matrix, fiducial)
temp.print_covariance_matrix()
temp.print_fisher_matrix()
matrices.append(temp)
return matrices
def test_getSoftwareListWithFilesAndFolders(self):
vCorrectSWList = ["800-A0443_SBB_ANTENNA_ON_AIR_FTP", "800-A0575_LGA-5005_Main_Assy_NF_Functional_Test_Script", "800-A0582_SCM_HASS_Test_Script"]
# vSourceDirectory = "D:\\Projects\\Xerox Copier\\TestFolders\\MixedFileFolders"
vSourceDirectory = "c:\\Projects\\Software\\Non-Framework\\Applications\\ProductionChangeover\\TestFolders\\MixedFileFolders"
vSWList = FileFunctions.GetSoftwareList(vSourceDirectory)
for i in range(len(vSWList) ):
self.assertEqual(vSWList[i].PartNumber, vCorrectSWList[i], "The list should have 3 elements")
def test_GetFormattedSoftwareListFileNotFound(self):
# Create list of SoftwareItem objects
vSWItemList = []
vSWItem = FileFunctions.SoftwareItem("MissingFile")
vSWItemList.append(vSWItem)
vExpectedResult = []
vPcName = "CPT1-EUD-D00191"
# Mock method for IsOnline
FileFunctions.IsOnline = MagicMock(return_value=0)
# Mock method for CheckFile
FileFunctions.CheckFile = MagicMock(return_value=False)
vActualResult = FileFunctions.GetFormattedSoftwareList(vPcName, vSWItemList)
self.assertCountEqual(vActualResult, vExpectedResult, "The Lists are not the same.")
def test_GetFormattedSoftwareListWithNoPcName(self):
# Create list of SoftwareItem objects
vSWItemList = []
vSWItem = FileFunctions.SoftwareItem("800-A0443_SBB_ANTENNA_ON_AIR_FTP")
vSWItemList.append(vSWItem)
# vSWItem = FileFunctions.SoftwareItem("800-A0582_SCM_HASS_Test_Script")
# vSWItemList.append(vSWItem)
vExpectedResult = []
vPcName = ""
# Mock method for IsOnline
FileFunctions.IsOnline = MagicMock(return_value=3)
vActualResult = FileFunctions.GetFormattedSoftwareList(vPcName, vSWItemList)
self.assertCountEqual(vActualResult, vExpectedResult, "The Lists are not the same.")
def make(self, argument=None):
"""Performs a make on the application. The unix exit code is
returned. Any arguments given are passed onto as in
dv.make('clean').
"""
import FileFunctions
return FileFunctions.make(self, argument)
def drawStructure(Sequence, Shapefile, outfile):
lines = ""
f = FF.Parsefile(Shapefile)
lines = ";".join(
["%.3f" % float(line.strip().split('\t')[1]) for line in f])
cmd = 'java -cp VARNAv3-93.jar fr.orsay.lri.varna.applications.VARNAcmd -i ' + Sequence + ' -colorMap ' + '"' + lines + '"' + ' -colorMapStyle ' + '"-5.00:#4747B6,0.00:#4747FF,0.40:#1CFF47,0.70:#FF4747,2.41:#FFFF00"' + ' -algorithm line -o ' + outfile + " > /dev/null"
os.system(cmd)
def Adjust_structure(File, directory, IndexRna):
rnaaligned = FF.Parsefile(File)[0]
listdeletion = [i for i, j in enumerate(rnaaligned) if j == '_']
lines = FF.Parsefile(File)
#SeqLen=len(lines[1])-1
#print SeqLen,"seq length"
fileout = os.path.join(directory, IndexRna + 'MSA')
o = open(fileout, "w")
o.write('>' + IndexRna + 'MSA\n')
for struct in lines[2:-2]:
struc = list(struct)
for k in listdeletion:
#print struct
struc[k] = ""
o.write('%s' % ("".join(struc)))
o.close()
def make(self, argument=None):
"""Performs a make on the application. The unix exit code is
returned. Any arguments given are passed onto as in
dv.make('clean').
"""
import FileFunctions
return FileFunctions.make(self, argument)
def test_GetFilePathListWithEmptyPath(self):
vExpectResult = []
vFile = "Data"
vPcName = ""
vPath = ""
vActualResult = []
FileFunctions.GetFilePathList(vFile, vPcName + vPath, vActualResult)
self.assertCountEqual(vActualResult, vExpectResult, "The expected list should be empty.")
def test_GetFormattedSoftwareListWithEmptySoftwareList(self):
# Create list of SoftwareItem objects
vSWItemList = []
vExpectedResult = []
vPcName = ""
vActualResult = FileFunctions.GetFormattedSoftwareList(vPcName, vSWItemList)
self.assertCountEqual(vActualResult, vExpectedResult)
def test_GetFilePathListWithMissingNestedFile(self):
vExpectResult = []
vFile = "800-A0580_SCM_Functional_Test_Script.ini"
vPcName = "c:\\Projects\\Software\\Non-Framework\\Applications\\ProductionChangeover"
vPath = "\\Production\\800-A0582_SCM_HASS_Test_Script"
vActualResult = []
FileFunctions.GetFilePathList(vFile, vPcName + vPath, vActualResult)
self.assertCountEqual(vActualResult, vExpectResult, "The expected list should be empty.")
def test_GetFilePathListWithIncorrectPath(self):
vExpectResult = []
vFile = "Data"
vPcName = ""
vPath = "\\Production\\800-A0582_SCM_HASS_Test_Script\\"
vActualResult = []
FileFunctions.GetFilePathList(vFile, vPcName + vPath, vActualResult)
self.assertCountEqual(vActualResult, vExpectResult, "The expected list should be empty.")
def test_GetFilePathListWithMissingFile(self):
vExpectResult = []
vFile = "800-A0580_SCM_Functional_Test_Script.ini"
vPath = "\\Production\\800-A0443_SBB_ANTENNA_ON_AIR_FTP\\"
vPcName = "c:\\Projects\\Software\\Non-Framework\\Applications\\ProductionChangeover"
vActualResult = []
FileFunctions.GetFilePathList(vFile, vPcName + vPath, vActualResult)
self.assertEqual(vActualResult, vExpectResult, "The expected result was False. The file should not be found.")
def test_GetFilePathListWithMissingDir(self):
vExpectResult = []
vFile = "Tools"
vPcName = "c:\\Projects\\Software\\Non-Framework\\Applications\\ProductionChangeover"
vPath = "\\Production\\800-A0443_SBB_ANTENNA_ON_AIR_FTP"
vActualResult = []
FileFunctions.GetFilePathList(vFile, vPcName + vPath, vActualResult)
self.assertEqual(vActualResult, vExpectResult, "The expected result was False. The Directory should not be found.")
def FromStructFiletoRNAEvalInput(StructFile, InputRNAeval, rna):
lines = FF.Parsefile(StructFile)
o = open(
InputRNAeval, "w"
) # geneate intermediate file with sequence+strcuture , seq+strcture .... as the input format to use RNAeval
# print "sdfqspkojr",len(lines)
for i in range(1, len(lines)):
o.write("%s%s\t" % (rna, lines[i]))
o.close()
def Boltzmann_Calc(constraintes, StructfileRepository, NumStructures, rna,
Redondantestructure):
Energy = defaultdict(aa)
Boltzman = defaultdict(aa)
ConditionalBoltzman = defaultdict(aa)
ZBolzman = defaultdict(aa)
# Calculate structure energies in each condition sample
for Condition in constraintes:
FileStructure = os.path.join(StructfileRepository, Condition)
Energy[Condition] = EvalStructuresEnergies(
FileStructure, rna
) # list of energy values for the structures present in the Condition
for Condition in constraintes:
ListwithoutRedundnacy = []
for i in range(NumStructures):
Boltzman[Condition][i] = BoltzmannFactor(Energy[Condition][i])
if Redondantestructure[Condition][
i] == 0: # if the structure is not redundant
ListwithoutRedundnacy.append(Boltzman[Condition][i])
# Calculate the normalization term as the sum over all Boltzmann probabilities for one copy of each structure
ZBolzman[Condition] = sum(ListwithoutRedundnacy) # Partition function
# FF.PickleVariable(Boltzman, "Boltzman.pkl")
listall = []
for Condition in constraintes: # to not count MFES
lista = []
for i in range(NumStructures):
if Redondantestructure[Condition][
i] == 0: # a non redundnat structure
lista.append(Boltzman[Condition][i] / ZBolzman[Condition])
else:
lista.append(
0.
) # Redundant structures have a conditional Boltzmann value NULL
listall += lista
ConditionalBoltzman[Condition] = lista
# print "Condition \t ConditionalBoltzman", Condition, ConditionalBoltzman[Condition]
FF.PickleVariable(Boltzman, "Boltzman.pkl")
FF.PickleVariable(ConditionalBoltzman, "ConditionalBoltzman.pkl")
FF.PickleVariable(ZBolzman, "ZBolzman.pkl")
return ConditionalBoltzman
def test_GetFilePathListWithValidPcNameAndDir(self):
vExpectResult = [
"c:\\Projects\\Software\\Non-Framework\\Applications\\ProductionChangeover\\Production\\800-A0443_SBB_ANTENNA_ON_AIR_FTP\\Data"
]
vFile = "Data"
vPcName = "c:\\Projects\\Software\\Non-Framework\\Applications\\ProductionChangeover"
vPath = "\\Production\\800-A0443_SBB_ANTENNA_ON_AIR_FTP"
vActualResult = []
FileFunctions.GetFilePathList(vFile, vPcName + vPath, vActualResult)
self.assertEqual(vActualResult, vExpectResult, "The expected result was True.")
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 EnergyValuesFromStructure(StructFile, rna):
Energy = []
# generate the rnaeval input file
FromStructFiletoRNAEvalInput(StructFile, "InputRNAeval", rna)
# launch the RNaeval command
os.system('RNAeval <' + "InputRNAeval" + '>' + "energyvalues")
# Parse the RNAevaloutput to extract energy values
lines = FF.Parsefile("energyvalues")
for i in xrange(1, len(lines), 2):
Energy.append(lines[i].split(" ")[1][1:-2])
return Energy
def GetBasePairsFromStructFile(
faPath): #return dic={structure:[liste de pairs de base ],....}
#print faPath
DicStruct = {}
lines = FF.Parsefile(faPath)
#print lines
SeqLen = len(lines[1]) - 1
#print SeqLen,"seq length"
for j in range(len(lines)):
DicStruct[j] = ListBasePairsFromStruct(lines[j].strip().split(' ')[0])
return len(lines), DicStruct
def drawStructure(Sequence, Structure, Shapefile, OutFile):
conf = CF.loadConfig()
cmopt = ""
#print "shape",Shapefile
if os.path.isfile(Shapefile):
vals = FF.parseReactivityfile(Shapefile)
cmopt = ' -colorMap "' + ";".join(["%.3f" % float(v) for v in vals]) + '"' + COLOR_MAP
dummyout = os.path.join(conf.OutputFolder, "tmp", "varnamsg.txt")
cmd = 'java -cp VARNAv3-93.jar fr.orsay.lri.varna.applications.VARNAcmd -bpStyle simple -sequenceDBN "%s" -structureDBN "%s" '%(Sequence, Structure) + cmopt + ' -algorithm line -o ' + OutFile
#print cmd
subprocess.call(cmd, stdin=None, stdout=open(dummyout, 'wb'),
stderr=open(dummyout, 'w'), shell=True)
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 BasePairsbyCluster(clusters, Structurefile, Boltzmann, numberofsruct,
constrainte, cutoff):
ListBPbyCluster = defaultdict()
ListBPbyStruct = defaultdict(lambda: defaultdict())
Zcluster = defaultdict(lambda: defaultdict())
BoltzmannOverPairsbyCluster = defaultdict(
lambda: defaultdict(lambda: defaultdict(lambda: 0)))
Fiftypercent = defaultdict()
for ClusterNumber in clusters:
liste = []
for structure in clusters[ClusterNumber]:
#print structure, 'clusters[ClusterNumber]',clusters[ClusterNumber]
ConditionNumber = int((structure - 1) / numberofsruct)
StructureNumber = (structure - 1) - ConditionNumber * numberofsruct
#print 'ConditionNumber', ConditionNumber,'StructureNumber',StructureNumber, Boltzmann[constrainte[ConditionNumber]][StructureNumber]
if (Boltzmann[constrainte[ConditionNumber]][StructureNumber] != 0):
liste.append(
Boltzmann[constrainte[ConditionNumber]][StructureNumber])
print "LILSALISALISA", ClusterNumber, liste
Zcluster[ClusterNumber] = sum(liste)
list1 = []
for structure in clusters[ClusterNumber]:
ConditionNumber = int((structure - 1) / numberofsruct)
StructureNumber = (structure - 1) - ConditionNumber * numberofsruct
for (i, j) in SF.ListBasePairsFromStruct(
FF.GetlinefromFile(Structurefile, structure - 1)):
BoltzmannOverPairsbyCluster[ClusterNumber][i][j] += Boltzmann[
constrainte[ConditionNumber]][StructureNumber] / Zcluster[
ClusterNumber]
ListBPbyStruct[ClusterNumber][
structure] = SF.ListBasePairsFromStruct(
FF.GetlinefromFile(Structurefile, structure - 1))
ListBPbyCluster[ClusterNumber] = list1
Fiftypercent[ClusterNumber] = len(clusters) / 2
return ListBPbyStruct, ListBPbyCluster, Fiftypercent, BoltzmannOverPairsbyCluster
def test_GetFilePathListWithValidNestedFile(self):
vExpectResult = [
"c:\\Projects\\Software\\Non-Framework\\Applications\\ProductionChangeover\\Production\\800-A0582_SCM_HASS_Test_Script\\SCM_1\\800-A0582_SCM_HASS_Test_Script.ini",
"c:\\Projects\\Software\\Non-Framework\\Applications\\ProductionChangeover\\Production\\800-A0582_SCM_HASS_Test_Script\\SCM_2\\800-A0582_SCM_HASS_Test_Script.ini",
"c:\\Projects\\Software\\Non-Framework\\Applications\\ProductionChangeover\\Production\\800-A0582_SCM_HASS_Test_Script\\SCM_3\\800-A0582_SCM_HASS_Test_Script.ini",
"c:\\Projects\\Software\\Non-Framework\\Applications\\ProductionChangeover\\Production\\800-A0582_SCM_HASS_Test_Script\\SCM_4\\800-A0582_SCM_HASS_Test_Script.ini"
]
vFile = "800-A0582_SCM_HASS_Test_Script.ini"
vPcName = "c:\\Projects\\Software\\Non-Framework\\Applications\\ProductionChangeover"
vPath = "\\Production\\800-A0582_SCM_HASS_Test_Script"
vActualResult = []
FileFunctions.GetFilePathList(vFile, vPcName + vPath, vActualResult)
self.assertCountEqual(vActualResult, vExpectResult, "The expected list should have 4 items.")
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')
def CentroidBycluster(clusters, StructFile, Boltzmann, numberofsruct, constrainte, rna):
progress.StartTask("Computing centroids")
dim_clustering = len(clusters)
E = defaultdict()
mycentroid = defaultdict()
Intradistance = []
centroids = defaultdict(lambda: defaultdict())
Myproba = defaultdict(lambda: defaultdict(lambda: defaultdict(lambda: 0)))
ListStructures = [SF.BasePairsFromStruct(Struct) for Struct in FF.Parsefile(StructFile)]
progress.StartTask("Gathering base pairs")
ListBPbystructure, ListBP, Myproba, Boltzmancluster = BasePairsbyCluster(clusters, ListStructures, Boltzmann,
numberofsruct,
constrainte)
# Eliminate cluster reporting one structure
ListDiameters, Listeliminated_clusers = ClustersDiameter(clusters, ListBPbystructure)
for elem in Listeliminated_clusers:
del clusters[elem]
progress.EndTask()
progress.StartTask("Computing cluster distance distribution")
E = ClustersDistances(clusters, Boltzmann, ListBPbystructure, numberofsruct, constrainte)
progress.EndTask()
progress.StartTask("Computing MEA centroids")
for ClusterNumber in clusters:
mycentroid[ClusterNumber], centroids[ClusterNumber] = MEA(Myproba[ClusterNumber], rna)
progress.EndTask()
MatriceDistanceCentroids = scipy.zeros([dim_clustering, dim_clustering])
MatriceDistanceClustersEucld = scipy.zeros([dim_clustering, dim_clustering])
for ClusterNumber in clusters.keys():
for ClusterNumber2 in clusters.keys():
if ClusterNumber2 > ClusterNumber:
l = SF.DistanceTwoStructs(centroids[ClusterNumber], centroids[ClusterNumber2])
#print "BP_centoid_distances", "\t", ClusterNumber, "\t", ClusterNumber2, "\t", l
Intradistance.append(l)
# print "distance between clusters comparing the centroide's distances",l
MatriceDistanceCentroids[ClusterNumber][ClusterNumber2] = l
MatriceDistanceCentroids[ClusterNumber2][ClusterNumber] = l
# print "distance between clusters comparing the means distances", ClusterNumber, ClusterNumber2, np.abs(E[ClusterNumber]-E[ClusterNumber2]),np.sqrt(abs(pow(E[ClusterNumber],2)-pow(E[ClusterNumber2],2)))
# print E
l = np.sqrt(abs(pow(E[ClusterNumber], 2) - pow(E[ClusterNumber2], 2)))
MatriceDistanceClustersEucld[ClusterNumber][ClusterNumber2] = l
MatriceDistanceClustersEucld[ClusterNumber2][ClusterNumber] = l
# print "distance between clusters compring the centroide's distances", ClusterNumber, ClusterNumber2, DistanceTwoBPlist(ListBPbystrcut[ClusterNumber][listCentroidStructure[ClusterNumber][0]],ListBPbystrcut[ClusterNumber2][listCentroidStructure[ClusterNumber2][0]])
# VT.plotDistanceClusters(MatriceDistanceCentroids, clusters, "blue", " Base pair distance between centroids")
# VT.plotDistanceClusters(MatriceDistanceClustersEucld, clusters, "red", "Eucledian distance between structures")
#print "BZ_distance_btw_clusters", "\t", E
progress.EndTask()
return mycentroid, Boltzmancluster, E, MatriceDistanceCentroids, ListDiameters, Intradistance
def getpack(self, options=''):
"""Performs a getpack on the package given within the environment
of the application. The unix exit code is returned
"""
import FileFunctions
return FileFunctions.getpack(self, options)
