def load_genos(file):
genotypes = []
file_geno = open(file, 'r')
for line in file_geno:
line = line.strip()
if line.startswith('#'):
continue
if line.startswith('@'):
continue
cells = line.split()
if line.startswith("Chr"):
strains = cells[4:]
strains = [strain.lower() for strain in strains]
continue
genotype = {}
genotype['chr'] = cells[0]
genotype['locus'] = cells[1]
genotype['cm'] = cells[2]
genotype['mb'] = cells[3]
values = cells[4:]
values = [to_number(value) for value in values]
genotype['values'] = values
genotype['dicvalues'] = utilities.to_dic(strains, values)
genotypes.append(genotype)
return strains, genotypes
def probesetfreeze_item(strains, dir, probesetfreeze):
probesetfreezeid = probesetfreeze[0]
probesetfreezename = probesetfreeze[1]
probesetfreezefullname = probesetfreeze[2]
file = open("%s/ProbeSetFreezeId_%d_FullName_%s.txt" % (dir, probesetfreezeid, probesetfreezename), "w+")
file.write('"ID",')
file.write(','.join(['"%s"' % strain[1] for strain in strains]))
file.write("\n")
file.flush()
probesetxrefs = probesets.get_probesetxref(probesetfreezeid)
print(len(probesetxrefs))
for probesetxref in probesetxrefs:
probesetid = probesetxref[0]
probesetdataid = probesetxref[1]
probeset = probesets.get_probeset(probesetid)
probesetname = probeset[1]
probesetdata = probesets.get_probesetdata(probesetdataid)
if len(probesetdata) == 0:
continue
probesetdata = zip(*probesetdata)
probesetdata = utilities.to_dic(probesetdata[1], probesetdata[2])
#
file.write('"%s"' % probesetname)
#
for strain in strains:
strainname = strain[1]
if strainname in probesetdata:
value = probesetdata[strainname]
else:
value = ''
file.write(',"%s"' % value)
file.write('\n')
file.flush()
#
file.close()
def output_pheno(inbredsetid, file):
#
file = open(file, 'w')
#
strains = datastructure.get_strains(inbredsetid)
print("get %d strains" % (len(strains)))
print("strains: %s" % str(strains))
#
publishxrefs = phenotypes.get_publishxrefs(inbredsetid)
print("get %d publishxrefs" % (len(publishxrefs)))
#
file.write("%s\t" % "PhenotypeID")
file.write("%s\t" % "PhenotypeName")
for strain in strains:
strainname = strain[1]
file.write("%s\t" % strainname)
file.write("\n")
file.flush()
#
for publishxref in publishxrefs:
#
publishxrefid = publishxref[0]
phenotypeid = publishxref[1]
phenotype = phenotypes.get_phenotype(phenotypeid)
publicationid = publishxref[2]
publication = phenotypes.get_publication(publicationid)
publishdataid = publishxref[3]
publishdata = phenotypes.get_publishdata(publishdataid)
publishdata = zip(*publishdata)
if len(publishdata)==0:
continue
publishdata = utilities.to_dic([strain.lower() for strain in publishdata[1]], publishdata[2])
file.write("%s\t" % publishxrefid)
phenotypename = "%s;%s;%s" % (phenotype[0], phenotype[1], phenotype[2])
phenotypename = re.sub('\s+', ' ', phenotypename)
phenotypename = phenotypename.strip()
file.write("%s\t" % phenotypename)
#
for strain in strains:
strainname = strain[1]
strainname = strainname.lower()
if strainname in publishdata:
value = publishdata[strainname]
else:
value = 'x'
file.write("%s\t" % value)
#
file.write("\n")
file.flush()
#
file.flush()
file.close()
def correlations(outputdir, genos, probesetfreeze):
print probesetfreeze
probesetfreezeid = probesetfreeze[0]
probesetfreezename = probesetfreeze[1]
probesetfreezefullname = probesetfreeze[2]
#
outputfile = open("%s/%d_%s.txt" % (outputdir, probesetfreezeid, probesetfreezename), "w+")
outputfile.write("%s\t" % "ProbeSet Id")
outputfile.write("%s\t" % "ProbeSet Name")
outputfile.write("%s\t" % "Geno Name")
outputfile.write("%s\t" % "Overlap Number")
outputfile.write("%s\t" % "Pearson r")
outputfile.write("%s\t" % "Pearson p")
outputfile.write("%s\t" % "Spearman r")
outputfile.write("%s\t" % "Spearman p")
outputfile.write("\n")
outputfile.flush()
#
probesetxrefs = probesets.get_probesetxref(probesetfreezeid)
print "Get %d probesetxrefs" % (len(probesetxrefs))
#
for probesetxref in probesetxrefs:
#
probesetid = probesetxref[0]
probesetdataid = probesetxref[1]
probeset = probesets.get_probeset(probesetid)
probesetname = probeset[1]
probesetdata = probesets.get_probesetdata(probesetdataid)
probesetdata = zip(*probesetdata)
probesetdata = utilities.to_dic([strain.lower() for strain in probesetdata[1]], probesetdata[2])
#
for geno in genos:
genoname = geno['locus']
outputfile.write("%s\t" % probesetid)
outputfile.write("%s\t" % probesetname)
outputfile.write("%s\t" % genoname)
#
dic1 = geno['dicvalues']
dic2 = probesetdata
keys, values1, values2 = utilities.overlap(dic1, dic2)
rs = calculate.correlation(values1, values2)
#
outputfile.write("%s\t" % len(keys))
outputfile.write("%s\t" % rs[0][0])
outputfile.write("%s\t" % rs[0][1])
outputfile.write("%s\t" % rs[1][0])
outputfile.write("%s\t" % rs[1][1])
outputfile.write("\n")
outputfile.flush()
#
outputfile.close()
def generate_probesets(probesetfreezesfile, outputdir):
file = open(probesetfreezesfile, 'r')
for line in file:
line = line.strip()
cells = line.split()
probesetfreezeid = cells[0]
probesetfreeze = datastructure.get_probesetfreeze(probesetfreezeid)
probesetfreezeid = probesetfreeze[0]
probesetfreezename = probesetfreeze[1]
inbredset = datastructure.get_inbredset(probesetfreezeid)
inbredsetid = inbredset[0]
strains = datastructure.get_strains(inbredsetid)
#
outputfile = open("%s/%d_%s.txt" % (outputdir, probesetfreezeid, probesetfreezename), "w+")
outputfile.write("%s\t" % "ProbeSet Id")
outputfile.write("%s\t" % "ProbeSet Name")
outputfile.write('\t'.join([strain[1].upper() for strain in strains]))
outputfile.write("\n")
outputfile.flush()
#
probesetxrefs = probesets.get_probesetxref(probesetfreezeid)
print probesetfreeze
print len(probesetxrefs)
for probesetxref in probesetxrefs:
probesetid = probesetxref[0]
probesetdataid = probesetxref[1]
probeset = probesets.get_probeset(probesetid)
probesetname = probeset[1]
probesetdata = probesets.get_probesetdata(probesetdataid)
probesetdata = zip(*probesetdata)
probesetdata = utilities.to_dic([strain.lower() for strain in probesetdata[1]], probesetdata[2])
#
outputfile.write("%s\t" % probesetid)
outputfile.write("%s\t" % probesetname)
#
for strain in strains:
strainname = strain[1]
strainname = strainname.lower()
if strainname in probesetdata:
value = probesetdata[strainname]
else:
value = 'x'
outputfile.write("%s\t" % value)
outputfile.write("\n")
outputfile.flush()
#
outputfile.close()
file.close()
def bxd_pheno(file):
#
file = open(file, 'w')
inbredsetid = 1
#
strains = datastructure.get_strains(inbredsetid)
print("get %d strains" % (len(strains)))
#
publishxrefs = phenotypes.get_publishxrefs(inbredsetid)
print("get %d publishxrefs" % (len(publishxrefs)))
#
file.write("%s\t" % "PhenotypeID")
file.write("%s\t" % "PhenotypeName")
for strain in strains:
strainname = strain[1]
file.write("%s-expression\t" % strainname)
file.write("%s-N\t" % strainname)
file.write("%s-SE\t" % strainname)
file.write("\n")
file.flush()
#
for publishxref in publishxrefs:
#
publishxrefid = publishxref[0]
phenotypeid = publishxref[1]
publicationid = publishxref[2]
publishdataid = publishxref[3]
#
phenotype = phenotypes.get_phenotype(phenotypeid)
publication = phenotypes.get_publication(publicationid)
#
publishdata = phenotypes.get_publishdata(publishdataid)
publishdata = zip(*publishdata)
if len(publishdata) == 0:
publishdata = {}
else:
publishdata = utilities.to_dic([strain.lower() for strain in publishdata[1]], publishdata[2])
#
publishdatan = phenotypes.get_publishdatan(publishdataid)
publishdatan = zip(*publishdatan)
if len(publishdatan) == 0:
publishdatan = {}
else:
publishdatan = utilities.to_dic([strain.lower() for strain in publishdatan[1]], publishdatan[2])
#
publishdatase = phenotypes.get_publishdatase(publishdataid)
publishdatase = zip(*publishdatase)
if len(publishdatase) == 0:
publishdatase = {}
else:
publishdatase = utilities.to_dic([strain.lower() for strain in publishdatase[1]], publishdatase[2])
#
file.write("%s\t" % publishxrefid)
phenotypename = "%s;%s;%s" % (phenotype[0], phenotype[1], phenotype[2])
phenotypename = re.sub('\s+', ' ', phenotypename)
file.write("%s\t" % phenotypename)
#
for strain in strains:
strainname = strain[1]
strainname = strainname.lower()
#
if strainname in publishdata:
value = publishdata[strainname]
else:
value = 'x'
file.write("%s\t" % value)
#
if strainname in publishdatan:
value = publishdatan[strainname]
else:
value = 'x'
file.write("%s\t" % value)
#
if strainname in publishdatase:
value = publishdatase[strainname]
else:
value = 'x'
file.write("%s\t" % value)
file.write("\n")
file.flush()
file.close()
def bxd_geno_pheno_correlations(file):
#
file = open(file, 'w')
inbredsetid = 1
genofile = "/home/leiyan/gn/web/genotypes/BXD.geno"
#
t = genotypes.load_genos(genofile)
genostrains = t[0]
genos = t[1]
print("From geno file, get %d strains" % (len(genostrains)))
print("From geno file, get %d genos" % (len(genos)))
#
publishxrefs = phenotypes.get_publishxrefs(inbredsetid)
print("get %d publishxrefs" % (len(publishxrefs)))
#
file.write("%s\t" % "PhenotypeID")
file.write("%s\t" % "PhenotypeName")
file.write("%s\t" % "MarkerName")
file.write("%s\t" % "MarkerChromosome")
file.write("%s\t" % "MarkerCentimorgan")
file.write("%s\t" % "MarkerMb")
file.write("%s\t" % "PearsonCorrelation")
file.write("%s\t" % "PearsonPvalue")
file.write("%s\t" % "SpearmanCorrelation")
file.write("%s\t" % "SpearmanPvalue")
file.write("%s\t" % "Number_of_BXDs_used")
file.write("\n")
file.flush()
#
for publishxref in publishxrefs:
#
publishxrefid = publishxref[0]
phenotypeid = publishxref[1]
phenotype = phenotypes.get_phenotype(phenotypeid)
publicationid = publishxref[2]
publication = phenotypes.get_publication(publicationid)
publishdataid = publishxref[3]
publishdata = phenotypes.get_publishdata(publishdataid)
publishdata = zip(*publishdata)
if len(publishdata) != 3:
print("publishdata - %s: %d" % (publishxrefid, len(publishdata)))
continue
publishdata = utilities.to_dic([strain.lower() for strain in publishdata[1]], publishdata[2])
#
for geno in genos:
#
dic1 = geno['dicvalues']
dic2 = publishdata
keys, values1, values2 = utilities.overlap(dic1, dic2)
rs = calculate.correlation(values1, values2)
#
file.write("%s\t" % publishxrefid)
file.write("%s;%s;%s\t" % (phenotype[0], phenotype[1], phenotype[2]))
file.write("%s\t" % geno['locus'])
file.write("%s\t" % geno['chr'])
file.write("%s\t" % geno['cm'])
file.write("%s\t" % geno['mb'])
file.write("%s\t" % rs[0][0])
file.write("%s\t" % rs[0][1])
file.write("%s\t" % rs[1][0])
file.write("%s\t" % rs[1][1])
file.write("%s\t" % len(keys))
file.write("\n")
file.flush()
#
file.close()