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 prepareTwoSNPData(self, db, max_mismatch_rate=0.25, min_no_of_non_NA_pairs=40, report=0): """ 2009-9-23 add arguments max_mismatch_rate & min_no_of_non_NA_pairs, and pass them to twoSNPData. However it's useless to control what should be inserted into db because TwoSNPData.qc_cross_match_table is not defined and even if it's defined, the table it'll create doesn't concord to the one in 149SNP db. 2008-09-10 if self.input_fname is given, get 149SNP data from it , instead of database 2008-8-28 split out of run() so that MpiQC149CrossMatch could call this easily """ import MySQLdb conn = MySQLdb.connect(db=self.dbname, host=self.hostname, user = self.db_user, passwd = self.db_passwd) curs = conn.cursor() if self.input_fname: header, strain_acc_list, category_list, data_matrix = read_data(self.input_fname) else: 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, ignore_strains_with_qc=False) 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] #tg_ecotypeid category_list = [strain_info_data.strain_id2category[strain_id] for strain_id in strain_info_data.strain_id_list] #strainid 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 if self.QC_method_id==4: snpData2 = snpData1 else: 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 to facilitate row-id matching twoSNPData = TwoSNPData(SNPData1=snpData1, SNPData2=snpData2, \ QC_method_id=self.QC_method_id, user=self.db_user, row_matching_by_which_value=0, debug=self.debug,\ max_mismatch_rate=max_mismatch_rate, min_no_of_non_NA_pairs=min_no_of_non_NA_pairs, report=report) return twoSNPData
def prepareTwoSNPData(self,
db,
max_mismatch_rate=0.25,
min_no_of_non_NA_pairs=40,
report=0):
"""
2009-9-23
add arguments max_mismatch_rate & min_no_of_non_NA_pairs, and pass them to twoSNPData.
However it's useless to control what should be inserted into db because TwoSNPData.qc_cross_match_table is
not defined and even if it's defined, the table it'll create doesn't concord to the one in 149SNP db.
2008-09-10
if self.input_fname is given, get 149SNP data from it , instead of database
2008-8-28
split out of run() so that MpiQC149CrossMatch could call this easily
"""
import MySQLdb
conn = MySQLdb.connect(db=self.dbname,
host=self.hostname,
user=self.db_user,
passwd=self.db_passwd)
curs = conn.cursor()
if self.input_fname:
header, strain_acc_list, category_list, data_matrix = read_data(
self.input_fname)
else:
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, ignore_strains_with_qc=False)
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
] #tg_ecotypeid
category_list = [
strain_info_data.strain_id2category[strain_id]
for strain_id in strain_info_data.strain_id_list
] #strainid
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
if self.QC_method_id == 4:
snpData2 = snpData1
else:
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 to facilitate row-id matching
twoSNPData = TwoSNPData(SNPData1=snpData1, SNPData2=snpData2, \
QC_method_id=self.QC_method_id, user=self.db_user, row_matching_by_which_value=0, debug=self.debug,\
max_mismatch_rate=max_mismatch_rate, min_no_of_non_NA_pairs=min_no_of_non_NA_pairs, report=report)
return twoSNPData
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()
