def read_genotype_file(self):
'''Read genotype from .geno file instead of database'''
#genotype_1 is Dataset Object without parents and f1
#genotype_2 is Dataset Object with parents and f1 (not for intercross)
genotype_1 = reaper.Dataset()
# reaper barfs on unicode filenames, so here we ensure it's a string
if self.genofile:
full_filename = str(locate(self.genofile, 'genotype'))
else:
full_filename = str(locate(self.name + '.geno', 'genotype'))
genotype_1.read(full_filename)
if genotype_1.type == "group" and self.parlist:
genotype_2 = genotype_1.add(Mat=self.parlist[0], Pat=self.parlist[1]) #, F1=_f1)
else:
genotype_2 = genotype_1
#determine default genotype object
if self.incparentsf1 and genotype_1.type != "intercross":
genotype = genotype_2
else:
self.incparentsf1 = 0
genotype = genotype_1
self.samplelist = list(genotype.prgy)
return genotype
def readGenotype(self):
'''read genotype from .geno file'''
if self.group == 'BXD300':
self.group = 'BXD'
assert self.group, "self.group needs to be set"
#genotype_1 is Dataset Object without parents and f1
#genotype_2 is Dataset Object with parents and f1 (not for intercross)
self.genotype_1 = reaper.Dataset()
full_filename = os.path.join(webqtlConfig.GENODIR,
self.group + '.geno')
# reaper barfs on unicode filenames, so here we ensure it's a string
full_filename = str(full_filename)
self.genotype_1.read(full_filename)
print("Got to after read")
try:
# NL, 07/27/2010. ParInfo has been moved from webqtlForm.py to webqtlUtil.py;
_f1, _f12, _mat, _pat = webqtlUtil.ParInfo[self.group]
except KeyError:
_f1 = _f12 = _mat = _pat = None
self.genotype_2 = self.genotype_1
if self.genotype_1.type == "group" and _mat and _pat:
self.genotype_2 = self.genotype_1.add(Mat=_mat,
Pat=_pat) #, F1=_f1)
#determine default genotype object
if self.incparentsf1 and self.genotype_1.type != "intercross":
self.genotype = self.genotype_2
else:
self.incparentsf1 = 0
self.genotype = self.genotype_1
self.samplelist = list(self.genotype.prgy)
self.f1list = []
self.parlist = []
if _f1 and _f12:
self.f1list = [_f1, _f12]
if _mat and _pat:
self.parlist = [_mat, _pat]
def read_genotype_file(self, use_reaper=False):
'''Read genotype from .geno file instead of database'''
#genotype_1 is Dataset Object without parents and f1
#genotype_2 is Dataset Object with parents and f1 (not for intercross)
#genotype_1 = reaper.Dataset()
# reaper barfs on unicode filenames, so here we ensure it's a string
if self.genofile:
if "RData" in self.genofile: #ZS: This is a temporary fix; I need to change the way the JSON files that point to multiple genotype files are structured to point to other file types like RData
full_filename = str(
locate(self.genofile.split(".")[0] + ".geno", 'genotype'))
else:
full_filename = str(locate(self.genofile, 'genotype'))
else:
full_filename = str(locate(self.name + '.geno', 'genotype'))
if use_reaper:
genotype_1 = reaper.Dataset()
genotype_1.read(full_filename)
else:
genotype_1 = gen_geno_ob.genotype(full_filename)
if genotype_1.type == "group" and self.parlist:
genotype_2 = genotype_1.add(Mat=self.parlist[0],
Pat=self.parlist[1]) #, F1=_f1)
else:
genotype_2 = genotype_1
#determine default genotype object
if self.incparentsf1 and genotype_1.type != "intercross":
genotype = genotype_2
else:
self.incparentsf1 = 0
genotype = genotype_1
self.samplelist = list(genotype.prgy)
return genotype
####### To run this program do: python QTL_Reaper_v2.py 235
#Where 163 is the ProbeSetFreeze Id of the database that we want to calculate #the LRS
#!/usr/bin/python
import sys
import os
import reaper
import MySQLdb
import time
con = MySQLdb.Connect(db='db_webqtl', user='******', passwd='', host="localhost")
cursor = con.cursor()
genotypeDir = '/gnshare/gn/web/genotypes/'
genotype_1 = reaper.Dataset()
#####get all of the genotypes
cursor.execute('select Id, Name from InbredSet')
results = cursor.fetchall()
InbredSets = {}
for item in results:
InbredSets[item[0]] = genotypeDir+str(item[1])+'.geno'
ProbeSetFreezeIds=sys.argv[1:]
if ProbeSetFreezeIds:
#####convert the Ids to integer
ProbeSetFreezeIds=list(map(int, ProbeSetFreezeIds))
else:
#####get all of the dataset that need be updated
cursor.execute('select distinct(ProbeSetFreezeId) from ProbeSetXRef where pValue is NULL order by ProbeSetFreezeId desc')
results = cursor.fetchall()
