def run(self):
if self.debug:
import pdb
pdb.set_trace()
db = StockDB.StockDB(drivername=self.drivername, username=self.db_user,
password=self.db_passwd, hostname=self.hostname, database=self.dbname)
db.setup(create_tables=False)
session = db.session
session.begin()
self.cmp_data_filename = self.findOutCmpDataFilename(self.cmp_data_filename, self.QC_method_id, StockDB.QCMethod)
header, strain_acc_list, category_list, data_matrix = read_data(self.cmp_data_filename)
strain_acc_list = map(int, strain_acc_list) #it's ecotypeid, cast it to integer to be compatible to the later ecotype_id_ls from db
snpData2 = SNPData(header=header, strain_acc_list=strain_acc_list, \
data_matrix=data_matrix) #category_list is not used.
readme = formReadmeObj(sys.argv, self.ad, StockDB.README)
session.save(readme)
import MySQLdb
conn = MySQLdb.connect(db=self.dbname, host=self.hostname, user = self.db_user, passwd = self.db_passwd)
curs = conn.cursor()
from dbSNP2data import dbSNP2data
snp_id2index, snp_id_list, snp_id2info = dbSNP2data.get_snp_id2index_m(curs, StockDB.Calls.table.name, StockDB.SNPs.table.name)
strain_info_data = self.get_strain_id_info(self.QC_method_id)
data_matrix = self.get_data_matrix(db, strain_info_data.strain_id2index, snp_id2index, StockDB.Calls.table.name)
strain_acc_list = [strain_info_data.strain_id2acc[strain_id] for strain_id in strain_info_data.strain_id_list]
category_list = [strain_info_data.strain_id2category[strain_id] for strain_id in strain_info_data.strain_id_list]
header = ['ecotypeid', 'strainid']
for snp_id in snp_id_list:
snp_name, chromosome, position = snp_id2info[snp_id]
header.append(snp_name)
snpData1 = SNPData(header=header, strain_acc_list=strain_acc_list, category_list=category_list, data_matrix=data_matrix, \
snps_table='stock.snps') #snps_table is set to the stock_250k snps_table
twoSNPData = TwoSNPData(SNPData1=snpData1, SNPData2=snpData2, curs=curs, \
QC_method_id=self.QC_method_id, user=self.db_user, row_matching_by_which_value=0, debug=self.debug)
if self.run_type==1:
row_id2NA_mismatch_rate = twoSNPData.cmp_row_wise()
elif self.run_type==2:
#twoSNPData.save_col_wise(session, readme) #2008-08-18 need to implement a new one for 149SNP
row_id2NA_mismatch_rate = {}
else:
sys.stderr.write("run_type=%s is not supported.\n"%self.run_type)
sys.exit(5)
if self.output_fname and self.run_type==1 and row_id2NA_mismatch_rate:
self.output_row_id2NA_mismatch_rate(row_id2NA_mismatch_rate, self.output_fname)
if self.run_type==1 and self.commit and not self.input_dir and row_id2NA_mismatch_rate:
#if self.input_dir is given, no db submission. call_info_id2fname here is fake, it's actually keyed by (array_id, ecotypeid)
#row_id2NA_mismatch_rate might be None if it's method 0.
self.submit_to_call_QC(session, row_id2NA_mismatch_rate, self.QC_method_id, self.db_user, \
twoSNPData.row_id12row_id2, readme)
if self.commit:
session.commit()
else:
session.rollback()
def run(self):
"""
2008-08-11
the database interface changed in variation.src.dbsnp
2008-05-06
"""
import MySQLdb
conn = MySQLdb.connect(db=self.dbname,
host=self.hostname,
user=self.user,
passwd=self.passwd)
curs = conn.cursor()
if self.debug:
import pdb
pdb.set_trace()
db = DBSNP(username=self.user,
password=self.passwd,
hostname=self.hostname,
database=self.dbname)
session = db.session
session.begin()
#transaction = session.create_transaction()
snps_name2possible_mappings, snps_name2snps_id = self.get_snps_name2possible_mappings(
db)
from variation.src.FilterStrainSNPMatrix import FilterStrainSNPMatrix
header, strain_acc_list, category_list, data_matrix = FilterStrainSNPMatrix.read_data(
self.input_fname1)
snpData1 = SNPData(header=header, strain_acc_list=strain_acc_list, category_list=category_list, data_matrix=data_matrix, \
col_id2id=snps_name2snps_id, snps_table='dbsnp.snps')
header, strain_acc_list, category_list, data_matrix = FilterStrainSNPMatrix.read_data(
self.input_fname2)
snpData2 = SNPData(header=header, strain_acc_list=strain_acc_list, category_list=category_list, data_matrix=data_matrix,\
snps_table='stock_250k.snps')
twoSNPData = TwoSNPData384(SNPData1=snpData1,
SNPData2=snpData2,
curs=curs,
user=self.user)
readme = formReadmeObj(sys.argv, self.ad, README)
session.save(readme)
session.flush()
twoSNPData.figureOutABMapping(session, readme,
snps_name2possible_mappings)
if self.commit:
curs.execute("commit")
session.commit()
else:
session.rollback()
def run(self):
self.communicator = MPI.world.duplicate()
node_rank = self.communicator.rank
free_computing_nodes = range(1, self.communicator.size-1) #exclude the 1st and last node
free_computing_node_set = Set(free_computing_nodes)
output_node_rank = self.communicator.size-1
if node_rank not in free_computing_node_set: #computing nodes don't need db connection
db = StockDB.StockDB(drivername=self.drivername, username=self.db_user,
password=self.db_passwd, hostname=self.hostname, database=self.dbname)
db.setup(create_tables=False)
session = db.session
if node_rank == 0:
twoSNPData = self.prepareTwoSNPData(db)
twoSNPData_pickle = cPickle.dumps(twoSNPData, -1)
for node in free_computing_nodes: #send it to the computing_node
sys.stderr.write("passing initial data to nodes from %s to %s ... "%(node_rank, node))
self.communicator.send(twoSNPData_pickle, node, 0)
sys.stderr.write(".\n")
del twoSNPData_pickle
elif node_rank in free_computing_node_set:
data, source, tag = self.communicator.receiveString(0, 0)
twoSNPData = cPickle.loads(data)
del data
sys.stderr.write(".\n")
else:
readme = formReadmeObj(sys.argv, self.ad, StockDB.README)
session.save(readme)
mw = MPIwrapper(self.communicator, debug=self.debug, report=self.report)
mw.synchronize()
if node_rank == 0:
param_obj = PassingData(communicator=self.communicator, twoSNPData=twoSNPData, output_node_rank=output_node_rank, \
QC_method_id=self.QC_method_id, output_fname=getattr(self, 'output_fname', None), report=self.report)
self.input_node(param_obj, free_computing_nodes, self.message_size)
elif node_rank in free_computing_node_set:
computing_parameter_obj = PassingData(twoSNPData=twoSNPData, QC_method_id=self.QC_method_id)
mw.computing_node(computing_parameter_obj, self.computing_node_handler)
else:
if getattr(self, 'output_fname', None):
writer = csv.writer(open(self.output_fname, 'w'), delimiter='\t')
else:
writer = None
param_obj = PassingData(writer=writer, session=session, commit=self.commit, QC_method_id=self.QC_method_id, readme=readme, is_header_written=False)
mw.output_node(free_computing_nodes, param_obj, self.output_node_handler)
del writer
mw.synchronize() #to avoid some node early exits
def run(self):
"""
2008-08-11
the database interface changed in variation.src.dbsnp
2008-05-06
"""
import MySQLdb
conn = MySQLdb.connect(db=self.dbname, host=self.hostname, user = self.user, passwd = self.passwd)
curs = conn.cursor()
if self.debug:
import pdb
pdb.set_trace()
db = DBSNP(username=self.user,
password=self.passwd, hostname=self.hostname, database=self.dbname)
session = db.session
session.begin()
#transaction = session.create_transaction()
snps_name2possible_mappings, snps_name2snps_id = self.get_snps_name2possible_mappings(db)
from variation.src.FilterStrainSNPMatrix import FilterStrainSNPMatrix
header, strain_acc_list, category_list, data_matrix = FilterStrainSNPMatrix.read_data(self.input_fname1)
snpData1 = SNPData(header=header, strain_acc_list=strain_acc_list, category_list=category_list, data_matrix=data_matrix, \
col_id2id=snps_name2snps_id, snps_table='dbsnp.snps')
header, strain_acc_list, category_list, data_matrix = FilterStrainSNPMatrix.read_data(self.input_fname2)
snpData2 = SNPData(header=header, strain_acc_list=strain_acc_list, category_list=category_list, data_matrix=data_matrix,\
snps_table='stock_250k.snps')
twoSNPData = TwoSNPData384(SNPData1=snpData1, SNPData2=snpData2, curs=curs, user=self.user)
readme = formReadmeObj(sys.argv, self.ad, README)
session.save(readme)
session.flush()
twoSNPData.figureOutABMapping(session, readme, snps_name2possible_mappings)
if self.commit:
curs.execute("commit")
session.commit()
else:
session.rollback()
def run(self): if self.debug: import pdb pdb.set_trace() db = StockDB.StockDB(drivername=self.drivername, username=self.db_user, password=self.db_passwd, hostname=self.hostname, database=self.dbname) db.setup(create_tables=False) session = db.session #session.begin() readme = formReadmeObj(sys.argv, self.ad, StockDB.README) session.save(readme) twoSNPData = self.prepareTwoSNPData(db, report=self.report) twoSNPData.cal_row_id2pairwise_dist() self.submitToQCCrossMatch(session, twoSNPData.row_id2pairwise_dist, self.QC_method_id, readme, self.commit,\ max_mismatch_rate=self.max_mismatch_rate, min_no_of_non_NA_pairs=self.min_no_of_non_NA_pairs) """
def run(self):
if self.debug:
import pdb
pdb.set_trace()
db = StockDB.StockDB(drivername=self.drivername,
username=self.db_user,
password=self.db_passwd,
hostname=self.hostname,
database=self.dbname)
db.setup(create_tables=False)
session = db.session
#session.begin()
readme = formReadmeObj(sys.argv, self.ad, StockDB.README)
session.save(readme)
twoSNPData = self.prepareTwoSNPData(db, report=self.report)
twoSNPData.cal_row_id2pairwise_dist()
self.submitToQCCrossMatch(session, twoSNPData.row_id2pairwise_dist, self.QC_method_id, readme, self.commit,\
max_mismatch_rate=self.max_mismatch_rate, min_no_of_non_NA_pairs=self.min_no_of_non_NA_pairs)
"""
def run(self):
"""
2008-04-25
return None if QC_method_id==0
2008-04-20
for plone to call it just to get row_id2NA_mismatch_rate
"""
# database connection and etc
db = Stock_250kDB.Stock_250kDB(
drivername=self.drivername,
username=self.user,
password=self.passwd,
hostname=self.hostname,
database=self.dbname,
)
db.setup()
session = db.session
session.begin()
# transaction = session.create_transaction()
self.cmp_data_filename = self.findOutCmpDataFilename(
self.cmp_data_filename, self.QC_method_id, self.QCMethod_class
)
qm = self.QCMethod_class.query.get(self.QC_method_id) # 2009-5-20
import MySQLdb
conn = MySQLdb.connect(db=self.dbname, host=self.hostname, user=self.user, passwd=self.passwd)
curs = conn.cursor()
self.curs = curs
if self.debug:
import pdb
pdb.set_trace()
readme = formReadmeObj(sys.argv, self.ad, Stock_250kDB.README)
session.save(readme)
QC_method_id2snps_table = self.QC_method_id2snps_table
if self.QC_method_id == 0:
self.cal_independent_NA_rate(db, self.min_probability, readme)
row_id2NA_mismatch_rate = None
else:
# from variation.src.FilterStrainSNPMatrix import FilterStrainSNPMatrix
header, strain_acc_list, category_list, data_matrix = read_data(
self.cmp_data_filename, ignore_het=qm.ignore_het
)
strain_acc_list = map(
int, strain_acc_list
) # it's ecotypeid, cast it to integer to be compatible to the later ecotype_id_ls from db
snpData2 = SNPData(
header=header,
strain_acc_list=strain_acc_list,
data_matrix=data_matrix,
snps_table=QC_method_id2snps_table.get(self.QC_method_id),
ignore_het=qm.ignore_het,
) # category_list is not used. 05/20/09 ignore_het is useless cuz data_matrix is provided.
"""
if self.input_dir and os.path.isdir(self.input_dir):
#04/22/08 Watch: call_info_id2fname here is fake, it's actually keyed by (array_id, ecotypeid)
#no submission to db
call_info_id2fname = self.get_array_id2fname(curs, self.input_dir)
"""
if self.input_dir and os.path.isfile(self.input_dir): # it's file
call_info_id2fname = None
else:
if self.run_type == 2: # no filtering on call_info entries that have been QCed.
filter_calls_QCed = 0
elif self.run_type == 1:
filter_calls_QCed = 1
self.max_call_info_mismatch_rate = 1 # don't use this when doing accession-wise QC
else:
sys.stderr.write("run_type=%s is not supported.\n" % self.run_type)
sys.exit(5)
call_data = self.get_call_info_id2fname(
db,
self.QC_method_id,
self.call_method_id,
filter_calls_QCed,
self.max_call_info_mismatch_rate,
self.debug,
min_no_of_non_NA_pairs=self.min_no_of_non_NA_pairs,
input_dir=self.input_dir,
)
call_info_id2fname = call_data.call_info_id2fname
call_info_ls_to_return = call_data.call_info_ls_to_return
if self.run_type == 2:
snps_name2snps_id = self.get_snps_name2snps_id(db)
else:
snps_name2snps_id = None
if call_info_id2fname:
if self.one_by_one and self.run_type == 1: # one_by_one only for QC by accession
row_id2NA_mismatch_rate = {}
row_id12row_id2 = {}
counter = 0
for call_info_id, value in call_info_id2fname.iteritems():
counter += 1
print "No", counter
tmp_dict = {}
tmp_dict[call_info_id] = value
pdata = self.read_call_matrix(
tmp_dict, self.min_probability
) # 05/20/09 no need for qm.ignore_het because 250k is all h**o
passingdata = self.qcDataMatrixVSsnpData(
pdata, snps_name2snps_id, snpData2, curs, session, readme
)
row_id2NA_mismatch_rate.update(passingdata.row_id2NA_mismatch_rate)
row_id12row_id2.update(passingdata.row_id12row_id2)
del pdata
if self.debug and counter == 10:
break
else:
pdata = self.read_call_matrix(
call_info_id2fname, self.min_probability
) # 05/20/09 no need for qm.ignore_het because 250k is all h**o
passingdata = self.qcDataMatrixVSsnpData(pdata, snps_name2snps_id, snpData2, curs, session, readme)
row_id2NA_mismatch_rate = passingdata.row_id2NA_mismatch_rate
row_id12row_id2 = passingdata.row_id12row_id2
del pdata
else:
# input file is SNP by strain format. double header (1st two lines)
header, snps_name_ls, category_list, data_matrix = read_data(
self.input_dir, double_header=1, ignore_het=qm.ignore_het
)
pdata = PassingData()
pdata.ecotype_id_ls = header[0][2:]
pdata.call_info_id_ls = header[1][2:]
data_matrix = numpy.array(data_matrix)
pdata.data_matrix = data_matrix.transpose()
pdata.header = ["", ""] + snps_name_ls # fake a header for SNPData
passingdata = self.qcDataMatrixVSsnpData(pdata, snps_name2snps_id, snpData2, curs, session, readme)
row_id2NA_mismatch_rate = passingdata.row_id2NA_mismatch_rate
row_id12row_id2 = passingdata.row_id12row_id2
del pdata
if self.output_fname and self.run_type == 1 and row_id2NA_mismatch_rate:
self.output_row_id2NA_mismatch_rate(row_id2NA_mismatch_rate, self.output_fname)
if self.run_type == 1 and self.commit and not self.input_dir and row_id2NA_mismatch_rate:
# if self.input_dir is given, no db submission. call_info_id2fname here is fake, it's actually keyed by (array_id, ecotypeid)
# row_id2NA_mismatch_rate might be None if it's method 0.
self.submit_to_call_QC(
session,
row_id2NA_mismatch_rate,
self.QC_method_id,
self.user,
self.min_probability,
row_id12row_id2,
self.call_method_id,
readme,
)
if self.commit:
curs.execute("commit")
session.commit()
else:
session.rollback()
self.row_id2NA_mismatch_rate = row_id2NA_mismatch_rate # for plone to get the data structure
def run(self):
self.communicator = MPI.world.duplicate()
node_rank = self.communicator.rank
free_computing_nodes = range(1, self.communicator.size -
1) #exclude the 1st and last node
free_computing_node_set = Set(free_computing_nodes)
output_node_rank = self.communicator.size - 1
if node_rank not in free_computing_node_set: #computing nodes don't need db connection
db = StockDB.StockDB(drivername=self.drivername,
username=self.db_user,
password=self.db_passwd,
hostname=self.hostname,
database=self.dbname)
db.setup(create_tables=False)
session = db.session
if node_rank == 0:
twoSNPData = self.prepareTwoSNPData(db)
twoSNPData_pickle = cPickle.dumps(twoSNPData, -1)
for node in free_computing_nodes: #send it to the computing_node
sys.stderr.write(
"passing initial data to nodes from %s to %s ... " %
(node_rank, node))
self.communicator.send(twoSNPData_pickle, node, 0)
sys.stderr.write(".\n")
del twoSNPData_pickle
elif node_rank in free_computing_node_set:
data, source, tag = self.communicator.receiveString(0, 0)
twoSNPData = cPickle.loads(data)
del data
sys.stderr.write(".\n")
else:
readme = formReadmeObj(sys.argv, self.ad, StockDB.README)
session.save(readme)
mw = MPIwrapper(self.communicator,
debug=self.debug,
report=self.report)
mw.synchronize()
if node_rank == 0:
param_obj = PassingData(communicator=self.communicator, twoSNPData=twoSNPData, output_node_rank=output_node_rank, \
QC_method_id=self.QC_method_id, output_fname=getattr(self, 'output_fname', None), report=self.report)
self.input_node(param_obj, free_computing_nodes, self.message_size)
elif node_rank in free_computing_node_set:
computing_parameter_obj = PassingData(
twoSNPData=twoSNPData, QC_method_id=self.QC_method_id)
mw.computing_node(computing_parameter_obj,
self.computing_node_handler)
else:
if getattr(self, 'output_fname', None):
writer = csv.writer(open(self.output_fname, 'w'),
delimiter='\t')
else:
writer = None
param_obj = PassingData(writer=writer,
session=session,
commit=self.commit,
QC_method_id=self.QC_method_id,
readme=readme,
is_header_written=False)
mw.output_node(free_computing_nodes, param_obj,
self.output_node_handler)
del writer
mw.synchronize() #to avoid some node early exits
def run(self):
if self.debug:
import pdb
pdb.set_trace()
db = StockDB.StockDB(drivername=self.drivername,
username=self.db_user,
password=self.db_passwd,
hostname=self.hostname,
database=self.dbname)
db.setup(create_tables=False)
session = db.session
session.begin()
self.cmp_data_filename = self.findOutCmpDataFilename(
self.cmp_data_filename, self.QC_method_id, StockDB.QCMethod)
header, strain_acc_list, category_list, data_matrix = read_data(
self.cmp_data_filename)
strain_acc_list = map(
int, strain_acc_list
) #it's ecotypeid, cast it to integer to be compatible to the later ecotype_id_ls from db
snpData2 = SNPData(header=header, strain_acc_list=strain_acc_list, \
data_matrix=data_matrix) #category_list is not used.
readme = formReadmeObj(sys.argv, self.ad, StockDB.README)
session.save(readme)
import MySQLdb
conn = MySQLdb.connect(db=self.dbname,
host=self.hostname,
user=self.db_user,
passwd=self.db_passwd)
curs = conn.cursor()
from dbSNP2data import dbSNP2data
snp_id2index, snp_id_list, snp_id2info = dbSNP2data.get_snp_id2index_m(
curs, StockDB.Calls.table.name, StockDB.SNPs.table.name)
strain_info_data = self.get_strain_id_info(self.QC_method_id)
data_matrix = self.get_data_matrix(db,
strain_info_data.strain_id2index,
snp_id2index,
StockDB.Calls.table.name)
strain_acc_list = [
strain_info_data.strain_id2acc[strain_id]
for strain_id in strain_info_data.strain_id_list
]
category_list = [
strain_info_data.strain_id2category[strain_id]
for strain_id in strain_info_data.strain_id_list
]
header = ['ecotypeid', 'strainid']
for snp_id in snp_id_list:
snp_name, chromosome, position = snp_id2info[snp_id]
header.append(snp_name)
snpData1 = SNPData(header=header, strain_acc_list=strain_acc_list, category_list=category_list, data_matrix=data_matrix, \
snps_table='stock.snps') #snps_table is set to the stock_250k snps_table
twoSNPData = TwoSNPData(SNPData1=snpData1, SNPData2=snpData2, curs=curs, \
QC_method_id=self.QC_method_id, user=self.db_user, row_matching_by_which_value=0, debug=self.debug)
if self.run_type == 1:
row_id2NA_mismatch_rate = twoSNPData.cmp_row_wise()
elif self.run_type == 2:
#twoSNPData.save_col_wise(session, readme) #2008-08-18 need to implement a new one for 149SNP
row_id2NA_mismatch_rate = {}
else:
sys.stderr.write("run_type=%s is not supported.\n" % self.run_type)
sys.exit(5)
if self.output_fname and self.run_type == 1 and row_id2NA_mismatch_rate:
self.output_row_id2NA_mismatch_rate(row_id2NA_mismatch_rate,
self.output_fname)
if self.run_type == 1 and self.commit and not self.input_dir and row_id2NA_mismatch_rate:
#if self.input_dir is given, no db submission. call_info_id2fname here is fake, it's actually keyed by (array_id, ecotypeid)
#row_id2NA_mismatch_rate might be None if it's method 0.
self.submit_to_call_QC(session, row_id2NA_mismatch_rate, self.QC_method_id, self.db_user, \
twoSNPData.row_id12row_id2, readme)
if self.commit:
session.commit()
else:
session.rollback()
def run(self):
"""
2008-04-25
return None if QC_method_id==0
2008-04-20
for plone to call it just to get row_id2NA_mismatch_rate
"""
#database connection and etc
db = Stock_250kDB.Stock_250kDB(drivername=self.drivername,
username=self.user,
password=self.passwd,
hostname=self.hostname,
database=self.dbname)
db.setup(create_tables=False)
session = db.session
session.begin()
#transaction = session.create_transaction()
self.cmp_data_filename = self.findOutCmpDataFilename(
self.cmp_data_filename, self.QC_method_id, self.QCMethod_class)
qm = self.QCMethod_class.query.get(self.QC_method_id) #2009-5-20
import MySQLdb
conn = MySQLdb.connect(db=self.dbname,
host=self.hostname,
user=self.user,
passwd=self.passwd)
curs = conn.cursor()
self.curs = curs
if self.debug:
import pdb
pdb.set_trace()
readme = formReadmeObj(sys.argv, self.ad, Stock_250kDB.README)
session.add(readme)
QC_method_id2snps_table = self.QC_method_id2snps_table
if self.QC_method_id == 0:
self.cal_independent_NA_rate(db, self.min_probability, readme)
row_id2NA_mismatch_rate = None
else:
#from variation.src.FilterStrainSNPMatrix import FilterStrainSNPMatrix
header, strain_acc_list, category_list, data_matrix = read_data(
self.cmp_data_filename, ignore_het=qm.ignore_het)
strain_acc_list = map(
int, strain_acc_list
) #it's ecotypeid, cast it to integer to be compatible to the later ecotype_id_ls from db
snpData2 = SNPData(header=header, strain_acc_list=strain_acc_list, \
data_matrix=data_matrix, snps_table=QC_method_id2snps_table.get(self.QC_method_id),\
ignore_het=qm.ignore_het) #category_list is not used. 05/20/09 ignore_het is useless cuz data_matrix is provided.
"""
if self.input_dir and os.path.isdir(self.input_dir):
#04/22/08 Watch: call_info_id2fname here is fake, it's actually keyed by (array_id, ecotypeid)
#no submission to db
call_info_id2fname = self.get_array_id2fname(curs, self.input_dir)
"""
if self.input_dir and os.path.isfile(self.input_dir): #it's file
call_info_id2fname = None
else:
if self.run_type == 2: #no filtering on call_info entries that have been QCed.
filter_calls_QCed = 0
elif self.run_type == 1:
filter_calls_QCed = 1
self.max_call_info_mismatch_rate = 1 #don't use this when doing accession-wise QC
else:
sys.stderr.write("run_type=%s is not supported.\n" %
self.run_type)
sys.exit(5)
call_data = self.get_call_info_id2fname(db, self.QC_method_id, self.call_method_id, \
filter_calls_QCed, self.max_call_info_mismatch_rate, self.debug,\
min_no_of_non_NA_pairs=self.min_no_of_non_NA_pairs, input_dir=self.input_dir)
call_info_id2fname = call_data.call_info_id2fname
call_info_ls_to_return = call_data.call_info_ls_to_return
if self.run_type == 2:
snps_name2snps_id = self.get_snps_name2snps_id(db)
else:
snps_name2snps_id = None
if call_info_id2fname:
db_id2chr_pos = db.getSNPID2ChrPos() #2011-22
from DB_250k2data import DB_250k2Data
db_id2index = DB_250k2Data.getSNPID2index(
call_info_id2fname.values()[0][1], db_id2chr_pos)
if self.one_by_one and self.run_type == 1: #one_by_one only for QC by accession
row_id2NA_mismatch_rate = {}
row_id12row_id2 = {}
counter = 0
for call_info_id, value in call_info_id2fname.iteritems():
counter += 1
print "No", counter
tmp_dict = {}
tmp_dict[call_info_id] = value
pdata = self.read_call_matrix(
tmp_dict,
self.min_probability,
db_id2chr_pos=db_id2chr_pos,
db_id2index=db_id2index)
#05/20/09 no need for qm.ignore_het because 250k is all h**o
passingdata = self.qcDataMatrixVSsnpData(
pdata, snps_name2snps_id, snpData2, curs, session,
readme)
row_id2NA_mismatch_rate.update(
passingdata.row_id2NA_mismatch_rate)
row_id12row_id2.update(passingdata.row_id12row_id2)
del pdata
if self.debug and counter == 10:
break
else:
pdata = self.read_call_matrix(call_info_id2fname,
self.min_probability,
db_id2chr_pos=db_id2chr_pos,
db_id2index=db_id2index)
#05/20/09 no need for qm.ignore_het because 250k is all h**o
passingdata = self.qcDataMatrixVSsnpData(
pdata, snps_name2snps_id, snpData2, curs, session,
readme)
row_id2NA_mismatch_rate = passingdata.row_id2NA_mismatch_rate
row_id12row_id2 = passingdata.row_id12row_id2
del pdata
else:
#input file is SNP by strain format. double header (1st two lines)
header, snps_name_ls, category_list, data_matrix = read_data(
self.input_dir, double_header=1, ignore_het=qm.ignore_het)
pdata = PassingData()
pdata.ecotype_id_ls = header[0][2:]
pdata.call_info_id_ls = header[1][2:]
data_matrix = numpy.array(data_matrix)
pdata.data_matrix = data_matrix.transpose()
pdata.header = ['', ''
] + snps_name_ls #fake a header for SNPData
passingdata = self.qcDataMatrixVSsnpData(
pdata, snps_name2snps_id, snpData2, curs, session, readme)
row_id2NA_mismatch_rate = passingdata.row_id2NA_mismatch_rate
row_id12row_id2 = passingdata.row_id12row_id2
del pdata
if self.output_fname and self.run_type == 1 and row_id2NA_mismatch_rate:
self.output_row_id2NA_mismatch_rate(row_id2NA_mismatch_rate,
self.output_fname)
if self.run_type == 1 and self.commit and not self.input_dir and row_id2NA_mismatch_rate:
#if self.input_dir is given, no db submission. call_info_id2fname here is fake, it's actually keyed by (array_id, ecotypeid)
#row_id2NA_mismatch_rate might be None if it's method 0.
self.submit_to_call_QC(session, row_id2NA_mismatch_rate, self.QC_method_id, self.user, self.min_probability, \
row_id12row_id2, self.call_method_id, readme)
if self.commit:
curs.execute("commit")
session.commit()
else:
session.rollback()
self.row_id2NA_mismatch_rate = row_id2NA_mismatch_rate #for plone to get the data structure