def verifIdent(fic):
"""
"""
ficOut = "outest.txt"
f = open(ficOut,"w")
lines = open(fic,"r").read().split("\n")
for line in lines:
if line != "":
idg = "-"
idp = "-"
lis = line.split("\t")
loc1 = lis[0]
loc2 = lis[1]
if loc1 != "" and loc2 != "":
ficg1 = "FastaGene/%s.tfa" % loc1
ficg2 = "FastaGene/%s.tfa" % loc2
ficp1 = "FastaProt/%s.tfa" % loc1
ficp2 = "FastaProt/%s.tfa" % loc2
if os.path.isfile(ficg1) and os.path.isfile(ficg2):
alignement.ali_needle(ficg1,ficg2)
idg = alignement.extrait_id_needle("FastaGene/%s-%s.needle" % (files.get_name(ficg1).lower(),files.get_name(ficg2).lower()))
if os.path.isfile(ficp1) and os.path.isfile(ficp2):
alignement.ali_needle(ficp1,ficp2)
idp = alignement.extrait_id_needle("FastaProt/%s-%s.needle" % (files.get_name(ficp1).lower(),files.get_name(ficp2).lower()))
f.write("%s\t%s\t%s\t%s\n" % (loc1,loc2,idg,idp))
f.close
def lanceBlastxFromScaff():
print "toto"
allfile = glob.glob("/Users/afutil/Documents/Genolevures/PiFa/AssemblageGenome/AssemblagesFinaux/assemblageRef1.0/*.tfa")
database = "/Users/afutil/Documents/Genolevures/PiFa/AssemblageGenome/AssemblagesFinaux/SynteniePistPiso/DBblast/pistPisoProtFmt6"
repout = "/Users/afutil/Documents/Genolevures/PiFa/AssemblageGenome/AssemblagesFinaux/SynteniePistPiso/BlastxFmt6"
for file in allfile:
seq = fasta.seqEnVar(file)
fname = files.get_name(file)
print "%s\t%s" % (fname,len(seq))
if len(seq) < 2000:
outfile = "%s/%s.blastx" % (repout,fname)
alignement.run_blastxFmt(file,outfile,database)
else :
fic1 = "%s/%s-deb.tfa" % (repout,fname)
fic2 = "%s/%s-fin.tfa" % (repout,fname)
of1 = open(fic1,"w")
of2 = open(fic2,"w")
#print ">%s\n%s\n" % (files.get_name(fic1),seq[0:1000])
of1.write(">%s\n%s\n" % (files.get_name(fic1),seq[0:1000]))
of2.write(">%s\n%s\n" % (files.get_name(fic2),seq[-1000:]))
of1.close()
of2.close()
for fic in fic1,fic2:
outfile = "%s/%s.blastx" % (repout,files.get_name(fic))
alignement.run_blastxFmt(file,outfile,database)
def calcIdent(fic):
"""
"""
if os.path.isdir(fic):
allfile = glob.glob("%s/*.tfa" % fic)
fout = "ficOut"
f = open(fout,"w")
f.write("el1\tel2\tid\tsim\n")
listFic = allfile
for file in allfile :
f1 = listFic[0]
listFic = listFic[1:]
for f2 in listFic:
#ficg1 = "FastaGene/%s.tfa" % loc1[0:-1]
#ficg2 = "FastaGene/%s.tfa" % loc2[0:-1]
#ficp1 = "FastaProt/%s.tfa" % loc1[0:-1]
#ficp2 = "FastaProt/%s.tfa" % loc2[0:-1]
name = "%s-%s.needle" % (files.get_name(f1).lower(),files.get_name(f2).lower())
outfile = "%s/%s" % (fic, name)
if not os.path.isfile(outfile):
alignement.ali_needle(f1,f2,outfile)
if os.path.isfile(outfile):
id = alignement.extrait_id_needle(outfile)
sim = alignement.extrait_sim_needle(outfile)
f.write("%s\t%s\t%s\t%s\n" % (files.get_name(f1),files.get_name(f2),id,sim))
f.close()
def recreeFicPEfq(ficPE1, ficPE2, outDir):
outR1 = "%s/%s.fq" % (outDir, files.get_name(ficPE1))
outR2 = "%s/%s.fq" % (outDir, files.get_name(ficPE2))
listeReadPE = creeListeDesPE(ficPE1, ficPE2)
longL = len(listeReadPE)
fM1 = open(ficPE1, "r")
or1 = open(outR1, "w")
line1 = fM1.readline()
toW = 0
i = 0
while line1 and i < longL:
#if line1[0]== "@":
#if line1[0:5]== "@HWI-":
if line1[0:4] == "@FCC":
toW = 0
if line1[:-2] == listeReadPE[i]:
#if line1[:-7] == listeReadPE[i]:
toW = 1
i += 1
if toW == 1:
or1.write("%s" % line1)
if i == longL:
j = 0
while j < 3:
line1 = fM1.readline()
or1.write("%s" % line1)
j += 1
line1 = fM1.readline()
fM1.close()
or1.close()
fM2 = open(ficPE2, "r")
or2 = open(outR2, "w")
line2 = fM2.readline()
toW = 0
i = 0
while line2 and i < longL:
#if line2[0]== "@":
#if line2[0:5]== "@HWI-":
if line2[0:4] == "@FCC":
toW = 0
if line2[:-2] == listeReadPE[i]:
#if line2[:-7] == listeReadPE[i]:
toW = 1
i += 1
if toW == 1:
or2.write("%s" % line2)
if i == longL:
j = 0
while j < 3:
line2 = fM2.readline()
or2.write("%s" % line2)
j += 1
line2 = fM2.readline()
fM2.close()
or2.close()
def ali_needleFasta(fic1,fic2,outfile = "", gop = 10, gep = 0.5):
# par defaut, le fichier de sortie est place dans le repertoire du fichier 1
if outfile == "":
rep = files.get_filepath(fic1)
name = "%s-%s.needle" % (files.get_name(fic1).lower(),files.get_name(fic2).lower())
outfile = "%s/%s" % (rep, name)
cmd = "%s -asequence %s -bsequence %s -gapopen %s -gapextend %s -outfile %s -aformat3 fasta" % (System.NEEDLE,fic1,fic2,gop,gep,outfile)
os.system(cmd)
def ali_water(fic1,fic2,outfile = "", gop = 10, gep = 0.5):
# par defaut, le fichier de sortie est place dans le repertoire du fichier 1
if outfile == "":
rep = files.get_filepath(fic1)
name = "%s-%s.water" % (files.get_name(fic1).lower(),files.get_name(fic2).lower())
outfile = "%s/%s" % (rep, name)
cmd = "%s -asequence %s -bsequence %s -gapopen %s -gapextend %s -outfile %s" % (System.WATER,fic1,fic2,gop,gep,outfile)
#print cmd
os.system(cmd)
def lanceAllSoapCoverageSNP():
allfile = glob.glob("/test/friedric/Pifa/Assemblage/SoapSplite/ResuParScaff/resuL1234SE*")
for fileSE in allfile:
scaff = files.get_name(fileSE)[12:]
filePE = fileSE.replace('resuL1234SE','resuL1234PE')
ref = "/test/friedric/Pifa/Assemblage/SoapSplite/ScaffRef/%s.tfa" % scaff
resu = "/test/friedric/Pifa/Assemblage/SoapSplite/SoapCoverage/%s.cov" % files.get_name(fileSE.replace('resuL1234SE','resuL1234'))
cmd = "/test/friedric/Pifa/SOAPcoverage/2.7.7/soap.coverage -phy -refsingle %s -il_single %s -il_soap %s -o %s" % (ref,fileSE,filePE,resu)
print cmd
def ali_stretcherFasta(fic1,fic2,outfile = ""):
# par defaut, le fichier de sortie est place dans le repertoire du fichier 1
if outfile == "":
rep = files.get_filepath(fic1)
name = "%s-%s.stretcher" % (files.get_name(fic1).lower(),files.get_name(fic2).lower())
outfile = "%s/%s" % (rep, name)
if not os.path.isfile(outfile):
cmd = "%s -asequence %s -bsequence %s -outfile %s -aformat3 fasta" % (System.STRETCHER,fic1,fic2,outfile)
#print cmd
os.system(cmd)
else:
print "%s already exists" % outfile
def extraitPEUnmappedReads(ficSamX, reads1, reads2, strain):
readsUnmapped1 = "/Volumes/BioSan/Users/friedrich/Gonorrhoeae/BWA/UnmappedReads/%s/%s.fq" % (
strain, files.get_name(reads1).replace("Cleandata", "unmapped"))
readsUnmapped2 = "/Volumes/BioSan/Users/friedrich/Gonorrhoeae/BWA/UnmappedReads/%s/%s.fq" % (
strain, files.get_name(reads2).replace("Cleandata", "unmapped"))
fM = open(ficSamX, "r")
# cree liste des paires ou l un au moins n est pas mappe
lUnmapped = list()
line = fM.readline()
el = line.split("\t")
lUnmapped.append(el[0])
line = fM.readline()
while line:
el = line.split("\t")
if el[0] != lUnmapped[-1]:
lUnmapped.append(el[0])
line = fM.readline()
fM.close()
print len(lUnmapped)
fr1 = open(reads1, "r")
fr2 = open(reads2, "r")
of1 = open(readsUnmapped1, "w")
of2 = open(readsUnmapped2, "w")
lineR1 = fr1.readline()
lineR2 = fr2.readline()
i = 0
toW = 0
while lineR1:
# attention: condition a adpater en fonction du format des reads
if lineR1[0:5] == "@FCC1":
el = lineR1.split("\t")
if i < len(lUnmapped):
# attention: condition a adpater en fonction du format des reads
if el[0][1:-3] == lUnmapped[i]:
i += 1
toW = 1
else:
toW = 0
else:
toW = 0
if toW == 1:
of1.write(lineR1)
of2.write(lineR2)
lineR1 = fr1.readline()
lineR2 = fr2.readline()
of1.close()
of2.close()
def defSimilarite(fic):
"""
"""
lines = open(fic,"r").read().split("\n")
for line in lines:
if line != "":
nsimg = "-"
nsimp = "-"
simg = "-"
simp = "-"
lis = line.split("\t")
loc1 = lis[0]
loc2 = lis[2]
if loc1 != "" and loc2 != "":
ficg1 = "FastaGene/%s.tfa" % loc1
ficg2 = "FastaGene/%s.tfa" % loc2
ficp1 = "FastaProt/%s.tfa" % loc1
ficp2 = "FastaProt/%s.tfa" % loc2
outf = "%s-%s.needle" % (files.get_name(ficg1).lower(),files.get_name(ficg2).lower())
if os.path.isfile("FastaGene/%s" % outf):
sizeg1 = len(fasta.seqEnVar(ficg1))
sizeg2 = len(fasta.seqEnVar(ficg2))
if sizeg1 > sizeg2:
sizeg = sizeg2
else:
sizeg = sizeg1
simg = string.atof(alignement.extrait_sim_needle("FastaGene/%s" % outf))
nsimg = alignement.extrait_nbsim_needle("FastaGene/%s" % outf)
nsimg = string.atof(nsimg)/sizeg*100
if os.path.isfile("FastaProt/%s" % outf):
sizep1 = len(fasta.seqEnVar(ficp1))
sizep2 = len(fasta.seqEnVar(ficp2))
if sizep1 > sizep2:
sizep = sizep2
else:
sizep = sizep1
simp = string.atof(alignement.extrait_sim_needle("FastaProt/%s" % outf))
nsimp = alignement.extrait_nbsim_needle("FastaProt/%s" % outf)
nsimp = string.atof(nsimp)/sizep*100
if simp != "-" and simg != "-":
print "%.1f\t%.1f\t%s\t%s\t%.1f\t%.1f\t" % (simg,simp,loc1,loc2,nsimg,nsimp)
else:
print "%s\t%s\t%s\t%s\t%s\t%s" % (simg,simp,loc1,loc2,nsimg,nsimp)
else:
print "\t\t%s\t%s" % (loc1,loc2)
def defNouvelIdent(fic):
"""
"""
lines = open(fic,"r").read().split("\n")
for line in lines:
if line != "":
nidg = "-"
nidp = "-"
idg = "-"
idp = "-"
lis = line.split("\t")
loc1 = lis[0]
loc2 = lis[2]
if loc1 != "" and loc2 != "":
ficg1 = "FastaGene/%s.tfa" % loc1
ficg2 = "FastaGene/%s.tfa" % loc2
ficp1 = "FastaProt/%s.tfa" % loc1
ficp2 = "FastaProt/%s.tfa" % loc2
outf = "%s-%s.needle" % (files.get_name(ficg1).lower(),files.get_name(ficg2).lower())
if os.path.isfile("FastaGene/%s" % outf):
sizeg1 = len(fasta.seqEnVar(ficg1))
sizeg2 = len(fasta.seqEnVar(ficg2))
if sizeg1 > sizeg2:
sizeg = sizeg2
else:
sizeg = sizeg1
idg = string.atof(alignement.extrait_id_needle("FastaGene/%s" % outf))
nidg = alignement.extrait_nbid_needle("FastaGene/%s" % outf)
nidg = string.atof(nidg)/sizeg*100
if os.path.isfile("FastaProt/%s" % outf):
sizep1 = len(fasta.seqEnVar(ficp1))
sizep2 = len(fasta.seqEnVar(ficp2))
if sizep1 > sizep2:
sizep = sizep2
else:
sizep = sizep1
idp = string.atof(alignement.extrait_id_needle("FastaProt/%s" % outf))
nidp = alignement.extrait_nbid_needle("FastaProt/%s" % outf)
nidp = string.atof(nidp)/sizep*100
if idp != "-" and idg != "-":
print "%.1f\t%.1f\t%s\t%s\t%.1f\t%.1f\t" % (idg,idp,loc1,loc2,nidg,nidp)
else:
print "%s\t%s\t%s\t%s\t%s\t%s" % (idg,idp,loc1,loc2,nidg,nidp)
else:
print "\t\t%s\t%s" % (loc1,loc2)
def reverseComplement(fastq,outfile=""): if outfile == "": outfile = "%s_RC.fq" % files.get_name(fastq) cmd = "/Volumes/BioSan/opt/fastx_toolkit/fastx_reverse_complement -i %s -o %s" % (fastq,outfile) os.system(cmd)
def lancetBlastnGeneIntron():
repGenome = "/Users/afutil/Documents/Genolevures/PiFa/Annotation/PourPascal/tBlastNPisoIntron"
allfile = glob.glob("%s/ProtIntron/*.tfa" % repGenome)
#outdir1 = "%s/tBlastn" % repGenome
outdir2 = "%s/tBlastnFmt6" % repGenome
#db1 = "%s/DBblast/pifaScaff" % repGenome
db2 = "%s/DBblast/pifaScaffFmt6" % repGenome
#print "outdir1 = %s, db1 = %s" % (outdir1,db1)
for file in allfile:
# print "--%s--" % file
#outfile1 = "%s/%s.tblastn" % (outdir1,files.get_name(file).lower())
#if not os.path.isfile(outfile1):
# print "++%s++" % outfile1
# alignement.run_tblastn(file,outfile1,db1)
#else:
# print "outfile1 exists"
outfile2 = "%s/%s.tblastn" % (outdir2,files.get_name(file).lower())
if not os.path.isfile(outfile2):
print "++%s++" % outfile2
alignement.run_tblastnFmt(file,outfile2,db2)
else:
print "outfile2 exists"
def renommeFic(dir,suffix):
allfile = glob.glob("%s/*.tfa" % dir)
for fic in allfile:
newName = "%s-%s.tfa" % (files.get_name(fic),suffix)
newFile = "%s%s" % (dir,newName)
shutil.copy(fic,newFile)
def creeFic6Strains():
liStrains = ["CBS10367", "CBS5828", "CBS3082a", "NRBC10572", "68917-2", "CBS6546"]
repO = "/Users/anfutil/Documents/Projets/GB-3G/LDHat/6souches"
# liChrom = ['Sakl0A','Sakl0B','Sakl0C','Sakl0D','Sakl0E','Sakl0F','Sakl0G','Sakl0H']
for rep in glob.glob("/Users/anfutil/Documents/Projets/GB-3G/LDHat/Sakl0?"):
nomRep = files.get_name(rep)
repOut = "%s/%s" % (repO, nomRep)
if not os.path.isdir(repOut):
os.mkdir(repOut)
ficSites = "%s/%s.sites" % (rep, nomRep)
ficOut = "%s/%s.sites" % (repOut, nomRep)
of = open(ficOut, "w")
lines = open(ficSites, "r").read().split("\n")
el = lines[0].split("\t")
of.write("6\t%s\t%s\n" % (el[1], el[2]))
toW = 0
for line in lines[1:]:
if line != "":
if line[0] == ">":
if line[1:] in liStrains:
toW = 1
else:
toW = 0
if toW == 1:
of.write("%s\n" % line)
of.close()
def ajoutIncrementalPrefHeader(infile, prefix, outfile=""):
"""
"""
if outfile == "":
outfile = "%s-incrPrefix.tfa" % (files.get_name(infile))
print "outfile est %s" % outfile
f = open(outfile, "w")
lines = open(infile, "r").read().split("\n")
i = 1
for line in lines:
if line != "":
if line[0] == ">":
if i < 10:
digit = "000%s" % i
elif i < 100:
digit = "00%s" % i
elif i < 1000:
digit = "0%s" % i
else:
digit = i
f.write(">%s%s %s\n" % (prefix, digit, line[1:]))
i = i + 1
else:
f.write("%s\n" % line)
f.close()
def lanceRechercheSimInc(file,repOut,db):
#outfile = "%s/%s-11strains.tblastn" % (repOut,files.get_name(file))
#outfileB = "%s/%s-11strains-Fmt6.tblastn" % (repOut,files.get_name(file))
outfile = "%s/%s-4strains.tblastn" % (repOut,files.get_name(file))
outfileB = "%s/%s-4strains-Fmt6.tblastn" % (repOut,files.get_name(file))
if not os.path.isfile(outfile):
alignement.run_tblastn(file,outfile,db)
else:
print "%s exists" % outfile
if not os.path.isfile(outfileB):
alignement.run_tblastnFmt(file,outfileB,db)
else:
print "%s exists" % outfileB
return outfileB
def statsALarracheALaChaine(rep):
print "GeneRef\tlongRefP\tnbSeqPil01\tlongIL01P\tnbDiffP\tnbDiffPIsolees\tlongRefG\tnbSeqGil01\tlongIL01G\tnbDiffG\tnbDiffGIsolees"
outfile = "stat.txt"
for file in glob.glob("%s/*.tfa" % rep):
suff = files.get_name(file)
statsALarrache(suff,outfile)
def lancementPipeAnalyseComplete(rep):
repSim = "%s/tblastn" % rep
repGene = "%s/SeqGene" % rep
repProt = "%s/SeqProt" % rep
repAliG = "%s/AliGene" % rep
repAliP = "%s/AliProt" % rep
repGeneFY = "/Users/afutil/Documents/DataJoseph/SaceStrains/FY/Gene"
#db = ssys.DB11STRAINS
#repSeq = ssys.SQ11STRAINS
db = ssys.DB4STRAINS
repSeq = ssys.SQ4STRAINS
if not os.path.isdir(repSim):
os.mkdir(repSim)
if not os.path.isdir(repGene):
os.mkdir(repGene)
if not os.path.isdir(repProt):
os.mkdir(repProt)
if not os.path.isdir(repAliG):
os.mkdir(repAliG)
if not os.path.isdir(repAliP):
os.mkdir(repAliP)
for file in glob.glob("%s/*.tfa" % rep):
suff = files.get_name(file)
print "sim..."
ficSim = lanceRechercheSimInc(file,repSim,db)
print "creation gene..."
creeGeneSelonSim(ficSim,repGene,repSeq)
print "creation prot..."
creeSeqProtSelonSeqGene(suff,repGene,repProt)
# copie la seq proteique dans le bon rep
newF = "%s/%s.tfa" % (repProt,suff)
shutil.copyfile(file, newF)
#seqToAlign = "%s-11strains.fasta" % suff
seqToAlign = "%s-4strains.fasta" % suff
concatSeqAAligner(suff,repProt,seqToAlign)
# copie la seq nucleique dans le bon rep
ficG = "%s/%s.tfa" % (repGeneFY,suff)
newFicG = "%s/%s.tfa" % (repGene,suff)
shutil.copyfile(ficG, newFicG)
#seqGToAlign = "%s-G-11strains.fasta" % suff
seqGToAlign = "%s-G-4strains.fasta" % suff
concatSeqAAligner(suff,repGene,seqGToAlign)
# construction alignement prot
print "seqtoalign est: %s" % seqToAlign
print "alignement..."
ficAliP = "%s/%s" % (repAliP,seqToAlign)
if not os.path.isfile(ficAliP):
#alignement.run_clustalw("%s/%s" % (repProt,seqToAlign),ficAliP,fasta,1)
alignement.run_mafft("%s/%s" % (repProt,seqToAlign),ficAliP)
# reste a tranalign en ali gene. attention : je dois aussi cree le fic du gene de fy et l incorpore dans un fic de gene global
if os.path.isfile(ficAliP):
ficAliG = "%s/%s" % (repAliG,seqGToAlign)
alignement.run_tranalign("%s/%s" % (repGene,seqGToAlign),ficAliP,ficAliG)
def stats4StrainsALarracheALaChaine(rep):
#print "GeneRef\tlongRefP\tnbSeqPil01\tlongIL01P\tnbDiffP\tnbDiffPIsolees\tlongRefG\tnbSeqGil01\tlongIL01G\tnbDiffG\tnbDiffGIsolees"
outfile = "stat.txt"
of = open(outfile, 'a')
of.write("gene\tposition\tresIL01\tresFY\tresWE372\tresNC02\tresYJM981\tIL=WE?=NC?\tYJM=FY\tProfilOK\n")
of.close()
for file in glob.glob("%s/*.tfa" % rep):
suff = files.get_name(file)
stats4StrainsALarrache(suff,outfile)
def lanceAlignementsWater(repWork):
repout = "%s/Alignements" % repWork
allfile = glob.glob("%s/*.tfa" % repWork)
for file in allfile:
fname = files.get_name(file)
outFile = "%s/%s.water" % (repout,fname)
name = fname.split("_")[0]
ficFY = "/Users/afutil/Documents/DataJoseph/Incompatibilites/FY4-IL01/MappedRegions/ProtFY/RegionChr8/%s.tfa" % name
alignement.ali_water(file,ficFY,outFile)
def lanceDelly(aln, repOut, ref):
out = "%s/%s.delly" % (repOut, files.get_name(aln))
# options DELLY
# -g pour donner le genome de reference (utilise pour le mapping)
# -q min. paired-end mapping quality (-q 1 calls uniquely mapped reads)
# -p inclus breakpoint detection
cmd = "{0:s} -p -g {1:s} -q 1 -o {2:s} {3:s}".format(System.DELLY, ref, out, aln)
os.system(cmd)
return out
def lanceJumpy(aln, repOut, ref):
out = "%s/%s.jumpy" % (repOut, files.get_name(aln))
# options JUMPY
# -g pour donner le genome de reference (utilise pour le mapping)
# -q min. paired-end mapping quality (-q 1 calls uniquely mapped reads)
# -p inclus breakpoint detection
cmd = "%s -p -g %s -q 1 -o %s %s" % (System.JUMPY, ref, out, aln)
os.system(cmd)
return out
def lanceReverseComplementALaChaine():
for fqFile in glob.glob("/Volumes/BioSan/Users/friedrich/Reads/BGI/20130726/CleanData/CBS4104/*.fq"):
repOut = files.get_filepath(fqFile).replace("CleanData/", "CleanData/ReverseComplement/")
#repOut = rep
if not os.path.isdir(repOut):
os.mkdir(repOut)
cmd = "chmod 777 %s" % repOut
os.system(cmd)
outfile = "%s/%s.fq" % (repOut, files.get_name(fqFile))
reverseComplement(fqFile, outfile)
def creeSeqProtSelonSeqGene(suff,repIn,repOut):
allfile = glob.glob("%s/%s*.tfa" % (repIn,suff))
for file in allfile:
print file
ficName = files.get_name(file)
outFile = "%s/%s.tfa" % (repOut,ficName)
if not os.path.isfile(outFile):
sequences.translateSeq(file, outFile,1)
else:
print "ouFile : %s already exists" % outFile
def verifLongEtExtrGene():
allfile = glob.glob("/Users/anfutil/Documents/Genolevures/Pifa/Annotation/PropositionGenesSelontBlastN/Combinaison/*.tfa")
print "GeneName\tSeqLen"
for file in allfile:
seq = fasta.seqEnVar(file)
if seq[0:3] == "ATG":
#if seq[-3:] == "TAA" or seq[-3:] == "TAG" or seq[-3:] == "TGA":
if seq[-3:] in ["TAA","TGA","TAG"]:
if len(seq) < 900:
print "%s\t%s" % (files.get_name(file), len(seq))
def copieFicInteret(file):
lines = open(file,"r").read().split("\n")
for line in lines:
if line != "":
lis = line.split("\t")
fic = lis[0]
ofic1 = "%s.blastp" % files.get_name(fic).lower()
if os.path.isfile(ofic1):
ofic2 = "Subset/%s" % ofic1
shutil.copy(ofic1,ofic2)
def lanceAllSoapSNP():
allfile = glob.glob("/Users/anfutil/Documents/Genolevures/Pifa/AssemblageGenome/TestSoapAligner/SoapSplite/ResuParScaff/*_trie")
for file in allfile:
scaff = files.get_name(file)[12:-5]
ref = "/Users/anfutil/Documents/Genolevures/Pifa/AssemblageGenome/TestSoapAligner/SoapSplite/ScaffRef/%s.tfa" % scaff
resu = "/Users/anfutil/Documents/Genolevures/Pifa/AssemblageGenome/TestSoapAligner/SoapSplite/SoapSNP/%s_consensus" % files.get_name(file)
cmd = "soapsnp -i %s -d %s -o %s -r 0.0001 -t -u -m" % (file,ref,resu)
#print cmd
os.system(cmd)
def analyseBlastPrelim():
# extrait infos pertinentes des resultats de blastp Fmt6
repGenome = "/Users/afutil/Documents/Genolevures/Pifa/Annotation/ModelGenes/ProtJigsaw/BlastP/ContrePiso/Eq1n"
allfile = glob.glob("%s/*-Fmt6.blastp" % repGenome)
repPiso = "/Users/afutil/Documents/Genolevures/Piso/SeqFinales/FastaProt"
#repPiso = "/Users/afutil/Documents/Genolevures/Pist/Fasta/CGOB"
repPab = "/Users/afutil/Documents/Genolevures/Pifa/Annotation/ModelGenes/ProtJigsaw"
print "SeqPifa\tChromoPifa\tnumGene\tlgSeqPifa\tnbXSeqPifa\tSeqPist\tlgSeqPist\tlgAli\t%ageId\tBestEvalue"
for file in allfile:
pab = files.get_name(file).replace("-Fmt6","")
chromo = pab[5:10]
numGen = pab[12:]
ficPab = "%s/PIFA.%s.tfa" % (repPab,pab[5:])
seqPab = fasta.seqEnVar(ficPab)
lgPab = len(seqPab)
nbXPab = seqPab.count('X')
#print pab
lgResu = open(file,"r").read().split("\n")
piso = ""
lgAli = []
id = []
lgSeqPiso = 0
for resu in lgResu:
if resu != "":
elem = resu.split("\t")
#print elem[1][8:]
if piso == "" or piso == elem[1][8:]:
piso = elem[1][8:]
#print piso
if lgSeqPiso == 0:
ficPiso = "%s/%s.tfa" % (repPiso,piso)
#print ficPiso
lgSeqPiso = len(fasta.seqEnVar(ficPiso))
eval = elem[10]
#print eval
lgAli.append(elem[3])
#print lgAli
id.append(elem[2])
#print id
else:
if piso == "":
print "%s\t%s\t%s\t%s\t%s\tNo hits found" % (pab,chromo,numGen,lgPab,nbXPab)
else:
idT = 0
lgAliT = 0
i = 0
while i < len(id) :
idT += string.atof(id[i])*string.atof(lgAli[i])
lgAliT += string.atoi(lgAli[i])
i += 1
ident = idT/lgAliT
print "%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%.2f\t%s" % (pab,chromo,numGen,lgPab,nbXPab,piso,lgSeqPiso,lgAliT,ident,eval)
break
def creeFastaSeqPartielle(infile, deb, fin):
"""
cree un fichier fasta contenant une partie de la sequence
(de la position de debut a la position de fin) issue du fichier fourni
"""
sequence = seqEnVar(infile)
seqPart = extraitSeqPartielle(sequence, deb, fin)
header = "%s_%s-%s" % (files.get_name(infile), deb, fin)
outfile = "%s.fasta" % header
if not os.path.isfile(outfile):
fromSeqToFasta(seqPart, header, outfile)
