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 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 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 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 ENERGY_VALUES_STRUCTURES(StructFile, rna):
Energy = []
#generate the rnaeval input file
FromStructFiletoRNAEvalInput(StructFile, "InputRNAeval", rna)
# launch the RNaeval command
os.system('RNAeval <' + "InputRNAeval" + '>' + "energyvalues")
#Sp.call("RNAeval " , stdin="InputRNAeval", stdout="energyvalues", shell=True)
# Parse the RNAevaloutput to extract energy values
lines = FF.Parsefile("energyvalues")
for i in xrange(1, len(lines), 2):
# i is the stucture number and 'lines[i].split(" ")[1][1:-2]' is the corresponding energy value
#print 'holla',(lines[i].split(" ")[1][1:-2])
Energy.append(lines[i].split(" ")[1][1:-2])
return Energy
def Load_Probabilities(mypath):
Dic = {}
B = defaultdict(lambda: defaultdict(lambda: defaultdict(lambda: 0)))
Beta = [
f for f in listdir(mypath)
if isfile(join(mypath, f)) and f.endswith('.proba')
]
for i, file in enumerate(Beta):
Dic[i] = file.split(".proba")[0]
lines = FF.Parsefile(mypath + "/" + file)
for it in range(len(lines)):
lines[it] = lines[it].split("\t")
B[i][int(lines[it][0])][int(lines[it][1])] = float(lines[it][2])
return Dic, B
def RunEval(InputFile):
Energy = []
# launch the RNaeval command
conf = loadConfig()
energiesFile = os.path.join(conf.OutputFolder, "tmp", "energyvalues")
os.system('RNAeval <' + InputFile + '>' + energiesFile)
# Parse the RNAevaloutput to extract energy values
lines = FF.Parsefile(energiesFile)
for i in xrange(1, len(lines), 2):
# i is the stucture number and 'lines[i].split(" ")[1][1:-2]' is the corresponding energy value
# print 'holla',(lines[i].split(" ")[1][1:-2])
Energy.append(
lines[i].split(" ", 1)[1]
[1:-2]) # TODO ,1 is to get the first occurence of the space !!!
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"
rawStructs = []
for j in range(len(lines)):
sec_str = lines[j].strip().split(' ')[0]
rawStructs.append(sec_str)
DicStruct[j] = BasePairsFromStruct(sec_str)
progress.Print("Loaded %s structures (%s distinct)" %
(len(rawStructs), len(set(rawStructs))))
return len(lines), DicStruct
m = 2.6 / 2
b = -0.8 / 2
path_Fasta = 'fasta_files'
Alignementfolder = 'Alignement'
FileExtensionFasta = 'fa'
print("Sampling Process for % s Structures" % (conf.numberofsruct))
OutputSamples = SP.StructSampling(
[conf.PathConstrainteFile, conf.PathConstrainteFileShape],
Alignementfolder, conf.numberofsruct, conf.Temperature,
conf.Fastaextenstion, m, b)
for filz in GetListFile(path_Fasta, FileExtensionFasta):
print filz, "Treatement "
startimebig = time.time()
rna = FF.Parsefile(
os.path.join(path_Fasta, filz + '.' + FileExtensionFasta))[1]
Indexe = filz
SVMlFile = "DissimilarityMatrix" + conf.numberofsruct
listfiles = [filz + state for state in ["NMIA", "1M7", "MSA"]]
OutputSamples = 'OutputSamples' + conf.numberofsruct
MFESnbrstruct = len(
listfiles) # 1 for the case where no constraint is given
FF.MergeFiles(OutputSamples, os.path.join(OutputSamples, 'Samples.txt'),
listfiles, 1)
#endtime=time.time()
#print("Sampling done with success in %53f\t"%(endtime-startime))
#!!!!!!!!!!!!! Distance Matrix calculation !!!!!!!!!!!
#
startime = time.time()
def FromStructFiletoRNAEvalInput(StructFile, InputRNAeval, rna):
lines = FF.Parsefile(StructFile)
StructsToRNAEvalInput(lines[SP.NUM_HEADER_LINES:], InputRNAeval, rna)
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))
# Get the rna sequence
RNASequence = FF.Parsefile(conf.RNA)[1].strip()
# Get probing conditions for the treated RNA
ProbingConditions = [RNAName + state for state in conf.Conditions]
# Specify whether to generate new sample or use a previously generated one
OutputSamples = os.path.join(conf.OutputFolder, "tmp",
'OutputSamples') + conf.SampleSize
if str.lower(
conf.Sampling) == "true" or not os.path.isdir(OutputSamples):
progress.StartTask("Sampling %s structures for each condition" %
(conf.SampleSize))
OutputSamples = SP.StructSampling(
[conf.PathConstraintsFile, conf.PathConstraintsFileShape],
ProbingConditions, int(conf.SampleSize), conf.Temperature,
conf.m, conf.b, conf.RNA)
#!/usr/bin/env python2.7
#@author SAADI AFAF, 2016
import conf , FileFunctions as FF, Sampling as SP, StructureFunctions as SF, Clustering as CL, VisualizationTools as VT, ClustersTrait as CT
import time,os,sys,pickle
from collections import defaultdict
#Redirect all the print to Logfile.txt
sys.stdout =conf.Logger("Logfile.txt")
SVMlFile="DissimilarityMatrix"+conf.numberofsruct
rna = FF.Parsefile(conf.rnafile)[1]
listfiles=conf.constraintes+["MFES"]
#!!!!!!!!!!!!!!Global study by comparing dotplotMatrix
print '**************Calculation of Eucledian distance between different BP dot plot conditions**********'
SF.DotplotRnaFold(conf.Psdotpath, conf.PathConstrainteFile, conf.PathConstrainteFileShape)
SF.Writeproba(conf.Psdotpath, conf.Matrixproba, conf.constraintes, rna)
VT.plotClusteringDistribution(int(conf.numberofsruct), conf.Matrixproba, len(rna))
print "Eucledian distance calculation done"
#!!!!!!!!!!!!! SAMPLING!!!!!!!!!!!
# This step requires as Input: fasta_constraints folder, fasta_Shape folder.
# it generates using RNAsubopt a sample of strctures that will be written in OutptSamples_numberofstructure "Sample.txt"
print '****************Sampling RNA Secondary Structures***********************'
startime=time.time()
print("Sampling Process for % s Structures"%(conf.numberofsruct))
OutputSamples=SP.StructSampling([conf.PathConstrainteFile,conf.PathConstrainteFileShape],conf.numberofsruct,conf.Temperature, conf.Fastaextenstion)
