def makeposavg_wf0(genelist, GFFfile, utrgfffile, seqwin, densityfile,
outfilestring, riboshift, thresh):
gffgen = GFF.parse(GFFfile)
GFFlist = seqtools.makeGFFlist(gffgen)
doingUTR5 = 0
if type(utrgfffile) == list:
utrgff = GFF.parse(utrgfffile[0])
utrtable = seqtools.makeutrtable(utrgff)
doingUTR5 = 1
elif utrgfffile == "0":
utrtable = 0
else:
utrgff = GFF.parse(utrgfffile)
utrtable = seqtools.makeutrtable(utrgff)
GFFlists = [GFFlist, utrtable, doingUTR5]
counts1p = builddense.readcountsf(densityfile + "_plus_")
counts1m = builddense.readcountsf(densityfile + "_minus_")
readcounts = [counts1p, counts1m]
genesinavg = makeposavg(genelist, GFFlists, seqwin, readcounts,
outfilestring, riboshift, thresh)
print "positions in avg = " + str(genesinavg[0])
print "positions not in avg because zero count = " + str(genesinavg[1])
print "positions with zero ORF count = " + str(genesinavg[2])
def motifavg_2_wf(GFFfile, utr5gfffile, utr3gfffile, counts_filestring,
motifsize, inframe, thresh, outfilestring, mismatches, shift,
windowsize, avgwindow):
codons = {} # Just a placeholder
counts0 = builddense.readcountsf(counts_filestring + "_plus_")
counts1 = builddense.readcountsf(counts_filestring + "_minus_")
counts = [counts0, counts1]
GFFgen = GFF.parse(GFFfile)
GFFlist = seqtools.makeGFFlist(GFFgen)
avglist = []
outlist = []
outlist.append([
"motif", "na", "na", "na", "na", "hitsincluded", "na", "na", "tothits",
"Pausescore"
])
GFFs = GFFlist
motifdata = motifavg_2_simple(GFFs, motifsize, inframe, thresh, mismatches,
codons, shift, counts, windowsize, avgwindow)
for mm in motifdata.keys():
print mm
motifdata[mm][1] = 0 # Variable not used
if motifdata[mm][5] > 0:
for i in range(sum(avgwindow)):
motifdata[mm][0][i] /= float(
motifdata[mm][5]) #Normalization taking place.
motifdata[mm][3] = 0 # Variable not used
# Get pause scores:
numerator = sum(
motifdata[mm][0][avgwindow[0] - windowsize:avgwindow[0] + 1 +
windowsize])
denominator = sum(motifdata[mm][0])
denominator /= len(motifdata[mm][0])
numerator /= (2 * windowsize + 1)
if denominator != 0:
pause = numerator / denominator
else:
pause = 0
motifdata[mm][10] = pause
outlist.append([mm] + motifdata[mm][1:9] + [motifdata[mm][10]])
avglist += (motifdata[mm][0]) #Concatenate average files.
# WRite out list.
gentools.writelisttoexcel(outlist,
outfilestring) #Includes new pause scores.
# Write out avg file.
favg = open(outfilestring + ".bin", "wb")
gentools.writelistbinint(avglist, favg)
favg.close()
def makeposstats_wf(genelist, GFFfile, utrgfffile, seqwin, pausewin,
densityfile, outfilestring, riboshift, motiflen):
gffgen = GFF.parse(GFFfile)
GFFlist = seqtools.makeGFFlist(gffgen)
if utrgfffile == "0":
utrtable = 0
else:
utrgff = GFF.parse(utrgfffile)
utrtable = seqtools.makeutrtable(utrgff)
GFFlists = [GFFlist, utrtable]
counts1p = builddense.readcountsf(densityfile + "_plus_")
counts1m = builddense.readcountsf(densityfile + "_minus_")
readcounts = [counts1p, counts1m]
newdict = makeposstats(genelist, GFFlists, seqwin, pausewin, readcounts,
riboshift, motiflen)
listavg.writedicttoexcel(newdict, outfilestring)
def totalquant_wf(filebase,counts_filestring,bp5,bp3,ignoreutr5,ignoreutr3,shift,filtermodule,thresh,GFFgen_filename,utrgfffilename,utr5gfffilename): GFFgen=GFF.parse(GFFgen_filename) GFFlist=seqtools.makeGFFlist(GFFgen) counts0=builddense.readcountsf(counts_filestring+"_plus_") counts1=builddense.readcountsf(counts_filestring+"_minus_") counts=[counts0,counts1] utrgffgen=GFF.parse(utrgfffilename) utrtable=seqtools.makeutrtable(utrgffgen) utrgffgen=GFF.parse(utr5gfffilename) utrtable2=seqtools.makeutrtable(utrgffgen) mgl=makegenelist(counts,GFFlist,utrtable,utrtable2,bp5,bp3,ignoreutr5,ignoreutr3,shift,filtermodule,thresh) writedicttoexcel(mgl,filebase+"_genelist")
def totalavg_wf(regionlength5,regionlength3,filebase,counts_filestring,bp5,bp3,ignoreutr5,ignoreutr3,shift,filtermodule,thresh,equalweight,GFFgen_filename,utrgfffilename,utr5gfffilename,alignpos,goodzone):
f=open(filebase+"_avg_"+str(alignpos)+"_","wb")
GFFgen=GFF.parse(GFFgen_filename)
GFFlist=seqtools.makeGFFlist(GFFgen)
if filtermodule=='0':
filtermodule=0
counts0=builddense.readcountsf(counts_filestring+"_plus_")
counts1=builddense.readcountsf(counts_filestring+"_minus_")
counts=[counts0,counts1]
utrgffgen=GFF.parse(utrgfffilename)
utrtable=seqtools.makeutrtable(utrgffgen)
utrgffgen=GFF.parse(utr5gfffilename)
utrtable2=seqtools.makeutrtable(utrgffgen)
gene=makeavggene(regionlength5,regionlength3,counts,GFFlist,utrtable,utrtable2,ignoreutr5,ignoreutr3,bp5,bp3,shift,filtermodule,thresh,alignpos,equalweight,goodzone)
for i in range(0,len(gene)):
f.write(struct.pack("f",float(gene[i])))
f.close()