def probesetfreeze_list(inbredsetid, dir):
strains = datastructure.get_strains(inbredsetid)
print(strains)
probesetfreezes = datastructure.get_probesetfreezes(inbredsetid)
print "From DB, get %d probesetfreezes" % (len(probesetfreezes))
for probesetfreeze in probesetfreezes:
print probesetfreeze
probesetfreeze_item(strains, dir, probesetfreeze)
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 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 traverse(outputfile):
#
file = open(outputfile, 'w')
inbredsetid = 1
strains = datastructure.get_strains(inbredsetid)
print("strains: %s" % len(strains))
sum = [0] * len(strains)
probesetfreezes = datastructure.get_probesetfreezes(inbredsetid)
print("probesetfreezes: %s" % len(probesetfreezes))
#
cursor, con = utilities.get_cursor()
#
file.write("DatasetID\t")
file.write("DatasetName\t")
file.write("RecordNumber\t")
for strain in strains:
file.write("%s\t" % strain[1])
file.write("\n")
file.flush()
# phenotypes
publishxrefs = phenotypes.get_publishxrefs(inbredsetid)
file.write("-\t")
file.write("%s\t" % "Phenotypes")
file.write("%d\t" % len(publishxrefs))
#
for i,strain in enumerate(strains):
sql = """
SELECT COUNT(PublishData.Id)
FROM PublishXRef,PublishData
WHERE PublishXRef.InbredSetId=%s
AND PublishXRef.DataId=PublishData.Id
AND PublishData.StrainId=%s
AND PublishData.value IS NOT NULL
"""
cursor.execute(sql, (inbredsetid, strain[0]))
n = cursor.fetchone()[0]
file.write("%d\t" % n)
file.flush()
sum[i] += n
#
file.write("\n")
file.flush()
#
for probesetfreeze in probesetfreezes:
#
probesetfreezeid = probesetfreeze[0]
probesetfreezename = probesetfreeze[1]
probesetfreezefullname = probesetfreeze[2]
probesetxrefs = probesets.get_probesetxref(probesetfreezeid)
#
file.write("%d\t" % probesetfreezeid)
file.write("%s\t" % probesetfreezefullname)
file.write("%d\t" % len(probesetxrefs))
#
for i,strain in enumerate(strains):
sql = """
SELECT COUNT(ProbeSetData.`Id`)
FROM ProbeSetXRef,ProbeSetData
WHERE ProbeSetXRef.`ProbeSetFreezeId`=%s
AND ProbeSetXRef.`DataId`=ProbeSetData.`Id`
AND ProbeSetData.`StrainId`=%s
AND ProbeSetData.`value` IS NOT NULL
"""
cursor.execute(sql, (probesetfreezeid, strain[0]))
n = cursor.fetchone()[0]
file.write("%d\t" % n)
file.flush()
sum[i] += n
#
file.write("\n")
file.flush()
# sum
file.write("-\t")
file.write("%s\t" % "Sum")
file.write("-\t")
#
for e in sum:
file.write("%d\t" % e)
file.flush()
#
file.write("\n")
file.flush()
#
file.close()
con.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()