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 bxd_correlations():
#
inbredsetid = 1
genofile = "/home/leiyan/gn/web/genotypes/BXD.geno"
outputdir = "/home/leiyan/gn2/wqflask/maintenance/dataset/datadir/20140205_Ash_correlations/output"
#
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))
#
probesetfreezes = datastructure.get_probesetfreezes(inbredsetid)
print "From DB, get %d probesetfreezes" % (len(probesetfreezes))
for probesetfreeze in probesetfreezes:
correlations(outputdir=outputdir, genos=genos, probesetfreeze=probesetfreeze)
def probesetfreeze_list():
#
inbredsetid = 1
outputdir = "/home/leiyan/gn2/wqflask/maintenance/dataset/datadir/20140205_Ash_correlations/output"
#
probesetfreezes = datastructure.get_probesetfreezes(inbredsetid)
print "From DB, get %d probesetfreezes" % (len(probesetfreezes))
file = open(outputdir + '/' + 'probesetfreezes.txt', 'w+')
#
for probesetfreeze in probesetfreezes:
#
print probesetfreeze
probesetfreezeid = probesetfreeze[0]
probesetfreezename = probesetfreeze[1]
probesetfreezefullname = probesetfreeze[2]
#
file.write("%s\t" % probesetfreezeid)
file.write("%s" % probesetfreezefullname)
file.write("\n")
file.flush()
#
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()