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 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 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 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 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 statsAce(inrep):
#pour chaque scaff et contig
# recuperation du nom, de la taille de la sequence et du nombre de N
allfile = glob.glob("%s/*" % inrep)
for file in allfile:
nom = files.get_name(file)
nom = string.replace(nom,"_L13","")
seq = fasta.seqEnVar(file)
nbN = seq.lower().count("n")
print "%s\t%s\t%s\t" % (nom,len(seq),nbN)
def creeSequenceDeGene(scaff,deb,fin):
header = "%s %s %s" % (scaff,deb,fin)
filename = "%s-%s-%s.tfa" % (scaff,deb,fin)
ficScaff = "ScaffTfa/%s.tfa" % scaff
seq = fasta.seqEnVar(ficScaff)
seqGen = extraitSeqGene(seq,string.atoi(deb),string.atoi(fin))
if os.path.isfile(filename):
filename = "%s-2" % filename
fasta.fromSeqToFasta(seqGen,header,filename)
def creeSequenceDeGene(scaff,deb,fin,geneN,repGene,repSeq):
header = "%s-%s-%s" % (scaff,deb,fin)
filename = "%s/%s_%s-%s-%s.tfa" % (repGene,geneN,scaff,deb,fin)
ficScaff = "%s/%s.tfa" % (repSeq,scaff)
seq = fasta.seqEnVar(ficScaff)
seqGen = extraitSeqGene(seq,string.atoi(deb),string.atoi(fin))
if os.path.isfile(filename):
print "il existe deja"
if not os.path.isfile(filename):
fasta.fromSeqToFasta(seqGen,header,filename)
def lanceMicroPipe():
if not os.path.isdir("SeqGene"):
os.mkdir("SeqGene")
if not os.path.isdir("SeqProt"):
os.mkdir("SeqProt")
if not os.path.isdir("AliGene"):
os.mkdir("AliGene")
if not os.path.isdir("AliProt"):
os.mkdir("AliProt")
if not os.path.isdir("PairwiseGene"):
os.mkdir("PairwiseGene")
if not os.path.isdir("PairwiseProt"):
os.mkdir("PairwiseProt")
blastDB = "/BlastDB/Nucleic/Sace/1002Genomes.nt"
for gene in glob.glob("*fasta"):
long = len(fasta.seqEnVar("%s" % gene)) * 3
#print long
geneN = files.get_name(gene)
ficOut = "%s.blastn" % (geneN)
cmdBl1 = "blast -query %s -db %s -out %s -seg no -soft_masking false" % (gene, blastDB, ficOut)
cmdBl2 = "blastn -query %s -db %s -out %s-6 -outfmt 6 -seg no m-soft_masking false" % (gene, blastDB, ficOut)
os.system(cmdBl1)
os.system(cmdBl2)
lanceRecupSeq("%s-6" % ficOut, long, geneN)
#
concatSeqAAligner(geneN, "SeqGene", "AliGene/%s_all.fasta" % geneN)
# alignement de ces sequences
alignement.run_mafft("AliGene/%s_all.fasta" % geneN, "AliGene/%s_all-ali.tfa" % geneN)
os.system("rm AliGene/%s_all.fasta" % geneN)
concatPaireSeqAAligner(geneN, "SeqGene", "PairwiseGene/%s.fasta" % geneN)
alignement.run_mafft("PairwiseGene/%s.fasta" % geneN, "PairwiseGene/%s-ali.fasta" % geneN)
lignes = open("PairwiseGene/%s-ali.fasta" % geneN, "r").read().split("\n")
if len(lignes) == 1:
os.system("rm PairwiseGene/%s-ali.fasta" % geneN)
os.system("rm PairwiseGene/%s.fasta" % geneN)
creeSeqProtSelonSeqGene("%s*" % (geneN), "SeqGene", "SeqProt")
concatPaireSeqAAligner(geneN, "SeqProt", "PairwiseProt/%s.fasta" % geneN)
alignement.run_mafft("PairwiseProt/%s.fasta" % geneN, "PairwiseProt/%s-ali.fasta" % geneN)
lignes = open("PairwiseProt/%s-ali.fasta" % geneN, "r").read().split("\n")
if len(lignes) == 1:
os.system("rm PairwiseProt/%s-ali.fasta" % geneN)
os.system("rm PairwiseProt/%s.fasta" % geneN)
concatSeqAAligner(geneN, "SeqProt", "AliProt/%s_all.fasta" % geneN)
# alignement de ces sequences
alignement.run_mafft("AliProt/%s_all.fasta" % geneN, "AliProt/%s_all-ali.tfa" % geneN)
os.system("rm AliProt/%s_all.fasta" % geneN)
def defSimilaritePseudo(fic):
"""
"""
lines = open(fic,"r").read().split("\n")
for line in lines:
if line != "":
nsimg = "-"
simg = "-"
lis = line.split("\t")
loc1 = lis[0]
loc2 = lis[2]
if loc1 != "" and loc2 != "":
ficg1 = "Genes+Pseudos/%s.tfa" % loc1
ficg2 = "Genes+Pseudos/%s.tfa" % loc2
outf = "%s-%s.needle" % (files.get_name(ficg1).lower(),files.get_name(ficg2).lower())
if not os.path.isfile("Genes+Pseudos/%s" % outf):
alignement.ali_needle(ficg1,ficg2)
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("Genes+Pseudos/%s" % outf))
nsimg = alignement.extrait_nbsim_needle("Genes+Pseudos/%s" % outf)
nsimg = string.atof(nsimg)/sizeg*100
if simg != "-":
print "%.1f\t%s\t%s\t%.1f\t" % (simg,loc1,loc2,nsimg)
else:
print "%s\t%s\t%s\t%s" % (simg,loc1,loc2,nsimg)
else:
print "\t\t%s\t%s" % (loc1,loc2)
def extraitInfoDispersionSevScaffDansBlast():
print "scaff\tseq length\tnb hits\tdiffScaff"
rep = "/Users/anfutil/Documents/Genolevures/Pifa/Annotation"
#lignes = open(fic,"r").read().split("\n")
allfile = glob.glob("%s/tBlastNFmt6-Pist/*.tblastn" % rep)
for file in allfile:
nbHit = 0
fname = files.get_name(file)
sqLen = len(fasta.seqEnVar("%s/Proteome-Pist/%s.tfa" % (rep,fname)))
lines = open(file,"r").read().split("\n")
expect = 0
scaff = ""
difSc = 0
min = 1000000000
max = 0
for line in lines:
if line != "":
lis = line.split("\t")
expect = lis[10]
if expect.find("e") != -1 or expect =="0.0":
# si je couvre plus de 90% de ma seq de depart, je considere que l orf est complete
if (string.atof(lis[7])-string.atoi(lis[6]))/sqLen>0.9:
break
# si j ai plus de 30% d identite sur au moins 10% de la seq soumise
# je considere que mon hit est potentiellement interessant
if string.atof(lis[2]) > 30 and (string.atof(lis[7])-string.atoi(lis[6]))/sqLen>0.1:
if lis[1] == scaff:
if string.atof(lis[7]) > string.atoi(lis[6]):
min = minimum(min,string.atoi(lis[6]))
max = maximum(max,string.atoi(lis[7]))
else:
min = minimum(min,string.atoi(lis[6]))
max = maximum(max,string.atoi(lis[7]))
continue
else :
maxN = maximum(string.atoi(lis[6]),string.atoi(lis[7]))
minN = minimum(string.atoi(lis[6]),string.atoi(lis[7]))
if maxN < max and minN > min:
break
else:
difSc += 1
print line
max = maximum(max,maxN)
min = minimum(min,minN)
scaff = lis[1]
if nbHit > 1:
print "%s\t%s\t%s hits\t%s\t%s" % (fname,sqLen,nbHit,mmSc,difSc)
def identifieRecouvrement100():
# va parser tous les blast
allfile = glob.glob("/Users/anfutil/Documents/Genolevures/Pifa/Annotation/tBlastNFmt6-Pist/*.tblastn")
for file in allfile:
# recupere la taille de la sequence traitee
name = files.get_name(file)
ficSeq = "/Users/anfutil/Documents/Genolevures/Pifa/Annotation/Proteome-Pist/%s.tfa" % name
#ficSeq = "/Users/anfutil/Documents/Genolevures/Piso/SeqFinales/FastaProt/%s.tfa" % name
sqLen = len(fasta.seqEnVar(ficSeq))
# compare a la taille de la sequence alignees
lines = open(file,"r").read().split("\n")
if lines[0] != "":
el = lines[0].split("\t")
long = string.atoi(el[7]) - string.atoi(el[6]) + 1
if sqLen == long:
print "%s\t%s-%s-%s.tfa\t%s" % (name,el[1],el[8],el[9],el[2])
def recapGeneProt():
# nb de genes / taille / pourcentage de N / nb de genes avec des N
allfile = glob.glob("./FastaProt/*.tfa")
idxNbG = 0
idxNbGN = 0
nbNTot = 0
lgSeqTot = 0
for file in allfile:
nbN = 0
name = files.get_name(file)
idxNbG += 1
seq = fasta.seqEnVar(file)
lgSeq = len(seq)
lgSeqTot = lgSeqTot + lgSeq
if "N" in seq:
idxNbGN +=1
nbN = seq.count('N')
nbNTot = nbNTot + nbN
print "%s\t%s\t%s\t" % (name,lgSeq,nbN)
print "Au final\n%s prot dont %s contiennent au moins 1 \"N\", taille cumulee : %s pb dont %s N" % (idxNbG, idxNbGN,lgSeqTot,nbNTot)
def creeSequenceDeGene(scaff, deb, fin, geneN, repGene, repSeq, long):
header = "%s" % (scaff)
filename = "%s/%s_%s-%s-%s.tfa" % (repGene, geneN, scaff, deb, fin)
ficScaff = "%s/%s.tfa" % (repSeq, scaff)
seq = fasta.seqEnVar(ficScaff)
seqGen = extraitSeqGene(seq, string.atoi(deb), string.atoi(fin)).upper()
# creation de la sequence uniquement si taille > a 98% de la sequence reference et si la taille est un multiple de 3
#if (len(seqGen) > long * 0.85 or len(seqGen) > 500) and len(seqGen) % 3 == 0:
if 1 == 1:
if os.path.isfile(filename):
print "il existe deja"
else:
seqGen = seqGen.replace("X", "N")
seqGen = seqGen.replace("S", "N")
seqGen = seqGen.replace("W", "N")
seqGen = seqGen.replace("R", "N")
seqGen = seqGen.replace("Y", "N")
seqGen = seqGen.replace("K", "N")
seqGen = seqGen.replace("M", "N")
fasta.fromSeqToFasta(seqGen, header, filename)
def recapIdentiteFYIL():
workdir = "/Users/afutil/Documents/DataJoseph/Incompatibilites/FY4-IL01/MappedRegions/"
allfile = glob.glob("%sGeneFY/RegionChr8/*.tfa" % workdir)
repAliG = "%sGeneIL01/RegionChr8/Alignements/" % workdir
repAliP = "%sProtIL01/RegionChr8/Alignements/" % workdir
print "eltType\tgeneN\tgeneLength\tnbSnp\tAliLen\t%ageIdMoyen\tcouverture\tdetail/ali"
for file in allfile:
#print file
lid = []
lnbSnp = []
lLen = []
#print file
#seqG = fasta.seqEnVar(file)
#print seqG
seqLen = len(fasta.seqEnVar(file))
allAli = glob.glob("%s%s*" % (repAliG,files.get_name(file)))
if allAli != []:
#print allAli
for ali in allAli:
longAli = alignement.extrait_lg_water(ali)
lid.append(alignement.extrait_id_water(ali))
nbId = alignement.extrait_nbid_water(ali)
lnbSnp.append(string.atoi(longAli) - string.atoi(nbId))
lLen.append(longAli)
toWr = "Gene\t%s\t%stoto" % (files.get_name(file),seqLen)
tId = 0
tSnp = 0
tLen = 0
i = 0
for snp in lnbSnp:
long = lLen[i]
id = lid[i]
tId += string.atof(id) * string.atof(long)
tLen += string.atof(long)
tSnp += snp
toWr += "\t%s\t%s" % (snp,long)
i += 1
meanId = tId / tLen
meanCov = tLen / seqLen * 100
toWr = string.replace(toWr,"toto","\t%s\t%.0f\t%.2f\t%.0f" % (tSnp,tLen,meanId,meanCov))
#toWr += "\t%s\t%.0f\t%.2f\t%.0f" % (tSnp,tLen,meanId,meanCov)
print toWr
allAliP = glob.glob("%s%s*" % (repAliP,files.get_name(file)))
lid = []
lnbSnp = []
lLen = []
if allAliP != []:
#print allAli
for ali in allAliP:
longAli = alignement.extrait_lg_water(ali)
lid.append(alignement.extrait_id_water(ali))
nbId = alignement.extrait_nbid_water(ali)
lnbSnp.append(string.atoi(longAli) - string.atoi(nbId))
lLen.append(longAli)
toWr = "Prot\t%s\t%stoto" % (files.get_name(file),seqLen/3)
tId = 0
tSnp = 0
tLen = 0
i = 0
for snp in lnbSnp:
long = lLen[i]
id = lid[i]
tId += string.atof(id) * string.atof(long)
tLen += string.atof(long)
tSnp += snp
toWr += "\t%s\t%s" % (snp,long)
i += 1
meanId = tId / tLen
meanCov = tLen / (seqLen/3) * 100
toWr = string.replace(toWr,"toto","\t%s\t%.0f\t%.2f\t%.0f" % (tSnp,tLen,meanId,meanCov))
#toWr += "\t%s\t%.0f\t%.2f\t%.0f" % (tSnp,tLen,meanId,meanCov)
print toWr
def trouveTelom(fic):
sequence = fasta.seqEnVar(fic)
print sequence
def extraitInfoBlastBIS(fic):
"""
extrait id + %age identite + long ali + long seq1 et seq2
d un fichier blast formate avec l option -outfmt 6
prend en entree le repertoire qui contient l ensemble des fichiers a traiter
"""
rep = "/Users/afutil/Documents/Genolevures/PiSo/AnalyseGenome/CladeCTG/RechercheSimFmt6"
lignes = open(fic,"r").read().split("\n")
#allfile = glob.glob("%s/*.blastp" % inrep)
outfile = "outputAnaBlast"
outfile2 = "outTest.tab"
f = open(outfile,"w")
f2 = open(outfile2,"w")
for ligne in lignes:
el = ligne.split("\t")
fname = el[1].lower()
#categorie = el[1]
if fname == "" or fname[-1].lower() == "r":
print ""
f.write("\n\n")
f2.write("%s\n" % fname)
continue
file = "%s/%s.blastp" % (rep,fname.lower())
print fname
if os.path.isfile("/Users/afutil/Documents/Genolevures/PiSo/SeqFinales/FastaProt/%s.tfa" % fname.upper()) and os.path.isfile(file):
sqLen = len(fasta.seqEnVar("/Users/afutil/Documents/Genolevures/PiSo/SeqFinales/FastaProt/%s.tfa" % fname.upper()))
else:
f.write("\n\n")
f2.write("%s\n" % fname)
continue
print sqLen
debha = 0; canal = 0; cantr = 0; picgu = 0; picst = 0; canlu = 0; lodel = 0; canpa = 0; candu = 0
debha2 = 0; canal2 = 0; cantr2 = 0; picgu2 = 0; picst2 = 0; canlu2 = 0; lodel2 = 0; canpa2 = 0; candu2 = 0
deb = ""; caa = ""; cat = ""; pig = ""; pis = ""; cal = ""; lod = ""; cap = ""; cad = ""
lines = open(file,"r").read().split("\n")
expect = 0
for line in lines:
if line != "":
lis = line.split("\t")
expect = lis[10]
print "expect est %s" % expect
if expect.find("e") != -1 or expect =="0.0":
print "a suis rentre"
acc = lis[1]
if acc[9:13] == "CPAG":
if canpa == 0:
cap = "%s,%s,%s,%s" % (lis[1][3:13],sqLen,lis[2],lis[3])
if string.atof(lis[2]) > 30 and (string.atof(lis[7])-string.atoi(lis[6]))/sqLen>0.3:
canpa = 1
canpa2 += 1
else:
suff = acc[17:]
if suff == "DEBHA":
if debha == 0:
deb = "%s,%s,%s,%s" % (lis[1][10:],sqLen,lis[2],lis[3])
print "%s - %s " % (string.atof(lis[2]),(string.atof(lis[7])-string.atoi(lis[6]))/sqLen)
if string.atof(lis[2]) > 30 and (string.atof(lis[7])-string.atoi(lis[6]))/sqLen>0.3:
print "+"
debha = 1
debha2 += 1
elif suff == "CANAL":
if canal == 0:
caa = "%s,%s,%s,%s" % (lis[1][10:],sqLen,lis[2],lis[3])
if string.atof(lis[2]) > 30 and (string.atof(lis[7])-string.atoi(lis[6]))/sqLen>0.3:
canal = 1
canal2 += 1
elif suff == "CANTT" or suff == "CANTR":
if cantr == 0:
cat = "%s,%s,%s,%s" % (lis[1][10:],sqLen,lis[2],lis[3])
if string.atof(lis[2]) > 30 and (string.atof(lis[7])-string.atoi(lis[6]))/sqLen>0.3:
cantr = 1
cantr2 += 1
elif suff == "PICGU":
if picgu == 0:
pig = "%s,%s,%s,%s" % (lis[1][10:],sqLen,lis[2],lis[3])
if string.atof(lis[2]) > 30 and (string.atof(lis[7])-string.atoi(lis[6]))/sqLen>0.3:
picgu = 1
picgu2 +=1
elif suff == "PICST":
if picst == 0:
pis = "%s,%s,%s,%s" % (lis[1][10:],sqLen,lis[2],lis[3])
if string.atof(lis[2]) > 30 and (string.atof(lis[7])-string.atoi(lis[6]))/sqLen>0.3:
picst = 1
picst2 += 1
elif suff == "CLALS" or suff == "CLAL4":
if canlu == 0:
cal = "%s,%s,%s,%s" % (lis[1][10:],sqLen,lis[2],lis[3])
if string.atof(lis[2]) > 30 and (string.atof(lis[7])-string.atoi(lis[6]))/sqLen>0.3:
canlu = 1
canlu2 += 1
elif suff == "LODEL":
if lodel == 0:
lod = "%s,%s,%s,%s" % (lis[1][10:],sqLen,lis[2],lis[3])
if string.atof(lis[2]) > 30 and (string.atof(lis[7])-string.atoi(lis[6]))/sqLen>0.3:
lodel = 1
lodel2 += 1
elif suff == "CANDU" or suff == "CANDC":
if candu == 0:
cad = "%s,%s,%s,%s" % (lis[1][10:],sqLen,lis[2],lis[3])
if string.atof(lis[2]) > 30 and (string.atof(lis[7])-string.atoi(lis[6]))/sqLen>0.3:
candu = 1
candu2 += 1
else:
print "a suis pas rentre"
break
f.write("%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\n" % (fname,deb,pis,pig,cal,caa,cad,cat,cap,lod))
#print "%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s" % (fname,debha,canal,cantr,picgu,picst,canlu,lodel,canpa)
f.write("%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\n" % (fname,debha,picst,picgu,canlu,canal,candu,cantr,canpa,lodel))
f2.write ("%s\t'%s%s%s%s%s%s%s%s%s'\t'%s;%s;%s;%s;%s;%s;%s;%s;%s'\n" % (fname,debha,picst,picgu,canlu,canal,candu,cantr,canpa,lodel,debha2,picst2,picgu2,canlu2,canal2,candu2,cantr2,canpa2,lodel2))
print "%s\t'%s%s%s%s%s%s%s%s%s'\t'%s;%s;%s;%s;%s;%s;%s;%s;%s'" % (fname,debha,picst,picgu,canlu,canal,candu,cantr,canpa,lodel,debha2,picst2,picgu2,canlu2,canal2,candu2,cantr2,canpa2,lodel2)
f.close()
f2.close()
def tailleGenesPiso():
allfile = glob.glob("/Users/afutil/Documents/Genolevures/PiSo/SeqFinales/FastaGene/*tfa")
for file in allfile:
lgseq = len(fasta.seqEnVar(file))
print "%s\t%s" % (files.get_name(file),lgseq)
