def load_environment(global_conf, app_conf): """Configure the Pylons environment via the ``pylons.config`` object """ # Pylons paths root = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) paths = dict( root=root, controllers=os.path.join(root, "controllers"), static_files=os.path.join(root, "public"), templates=[os.path.join(root, "templates")], ) # Initialize config with the basic options config.init_app(global_conf, app_conf, package="helloworld", template_engine="mako", paths=paths) config["routes.map"] = make_map() config["pylons.g"] = app_globals.Globals() config["pylons.h"] = helloworld.lib.helpers # Customize templating options via this variable # tmpl_options = config['buffet.template_options'] # CONFIGURATION OPTIONS HERE (note: all config options will override # any Pylons config options) # 2008-10-05 Use the strict behaviour of the template context object # config['pylons.strict_c'] = True # 2008-10-05 Create the Mako TemplateLookup, with the default auto-escaping. it doesn't work though. config["pylons.g"].mako_lookup = TemplateLookup( directories=paths["templates"], module_directory=os.path.join(app_conf["cache_dir"], "templates"), input_encoding="utf-8", output_encoding="utf-8", imports=["from webhelpers.html import escape"], default_filters=["escape"], ) # 2008-10-05 setup the database connection drivername = config["app_conf"]["drivername"] hostname = config["app_conf"]["hostname"] dbname = config["app_conf"]["dbname"] schema = config["app_conf"]["schema"] db_user = config["app_conf"]["db_user"] db_passwd = config["app_conf"]["db_passwd"] pool_recycle = int(config["app_conf"]["pool_recycle"]) # model.setup() model.db = model.Stock_250kDB.Stock_250kDB( drivername=drivername, username=db_user, password=db_passwd, hostname=hostname, database=dbname, schema=schema, pool_recycle=pool_recycle, ) model.db.setup(create_tables=False) model.genome_db = model.GenomeDB.GenomeDatabase( drivername=drivername, username=db_user, password=db_passwd, hostname=hostname, database="genome", schema=schema, pool_recycle=pool_recycle, ) # from variation.src import dbsnp # snp_db = dbsnp.DBSNP(drivername=drivername, username=db_user, password=db_passwd, \ # hostname=hostname, database='dbsnp', schema=schema, pool_recycle=pool_recycle) # from variation.src import StockDB model.stock_db = model.StockDB.StockDB( drivername=drivername, username=db_user, password=db_passwd, hostname=hostname, database="stock", schema=schema, pool_recycle=pool_recycle, ) model.at_db = model.AtDB.AtDB( drivername=drivername, username=db_user, password=db_passwd, hostname=hostname, database="at", schema=schema, pool_recycle=pool_recycle, ) """ for entity in entities: if entity.__module__==db.__module__: #entity in the same module entity.metadata = metadata #using_table_options_handler(entity, schema=self.schema) """ model.genome_db.setup(create_tables=False) # snp_db.setup(create_tables=False) model.stock_db.setup(create_tables=False) model.at_db.setup(create_tables=False) from variation.src.DrawSNPRegion import DrawSNPRegion def dealWithGeneAnnotation(): gene_annotation_picklef = "/Network/Data/250k/tmp-yh/at_gene_model_pickelf" DrawSNPRegion_ins = DrawSNPRegion( db_user=db_user, db_passwd=db_passwd, hostname=hostname, database=dbname, input_fname="/tmp/dumb", output_dir="/tmp", debug=0, ) gene_annotation = DrawSNPRegion_ins.dealWithGeneAnnotation( gene_annotation_picklef, cls_with_db_args=DrawSNPRegion_ins ) return gene_annotation model.gene_annotation = dealWithGeneAnnotation() # 2008-11-05 a dictionary to link two tables of types in order for cross-linking between pages of DisplayTopSNPTestRM and ScoreRankHistogram/DisplayResultsGene model.CandidateGeneTopSNPTestRMType_id_min_distance2ScoreRankHistogramType_id = {} ScoreRankHistogramType = model.Stock_250kDB.ScoreRankHistogramType CandidateGeneTopSNPTestRMType = model.Stock_250kDB.CandidateGeneTopSNPTestRMType rows = model.db.metadata.bind.execute( "select s.id as sid, s.min_distance, s.call_method_id, c.id as cid from %s s, %s c where s.null_distribution_type_id=c.null_distribution_type_id and\ s.results_type=c.results_type and s.get_closest=c.get_closest and s.min_MAF=c.min_MAF and \ s.allow_two_sample_overlapping=c.allow_two_sample_overlapping" % (ScoreRankHistogramType.table.name, CandidateGeneTopSNPTestRMType.table.name) ) # 2008-1-8 temporarily set call_method_id=17 cuz CandidateGeneTopSNPTestRMType doesn't include call_method_id for row in rows: key_tuple = (row.cid, row.min_distance, row.call_method_id) model.CandidateGeneTopSNPTestRMType_id_min_distance2ScoreRankHistogramType_id[key_tuple] = row.sid # 2009-4-10 takes too long in individual request, put here. used in Accession.py from variation.src.common import map_perlegen_ecotype_name2accession_id, fillInPhenotypeMethodID2ecotype_id_set model.ecotype_name2accession_id = map_perlegen_ecotype_name2accession_id(model.db.metadata.bind) # 2009-11-17 model.PhenotypeMethodID2ecotype_id_set = fillInPhenotypeMethodID2ecotype_id_set(model.Stock_250kDB.PhenotypeAvg) # 2009-11-17 from variation.src.common import fillInCallMethodID2ecotype_id_set model.CallMethodID2ecotype_id_set = fillInCallMethodID2ecotype_id_set(model.Stock_250kDB.CallInfo)
def run(self): 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() """ #2008-02-08 old way to get 2010 data is from raw alignments. didn't realize all SNPs are put into db. alignment_id2positions_to_be_checked_ls, alignment_id2chr_start_end = self.get_alignment_id2positions_to_be_checked_ls(curs, self.alignment_table) SNPpos_snpacc_ls = self.get_SNPpos_snpacc_ls(curs, self.snp_locus_table) SNPpos2col_index, snp_acc_ls = self.setup_SNP_dstruc(SNPpos_snpacc_ls, alignment_id2chr_start_end) ecotype_id2accession_id, ecotype_id2row_index, ecotype_id2info_ls, ecotype_id_ls, accession_id2row_index, accession_id_ls, nativename_ls = self.setup_accession_ecotype_dstruc(curs, self.accession2ecotype_table, self.ecotype_table) accession_X_snp_matrix, accession_X_snp_matrix_touched, snp_index2alignment_id = self.get_accession_X_snp_matrix(curs, accession_id2row_index, SNPpos2col_index, self.sequence_table, self.alignment_table, alignment_id2positions_to_be_checked_ls) """ if self.processing_bits[3]==0: #2009-2-12 will be a problem if snp_locus_table doesn't have field offset SNPpos2col_index, snp_acc_ls = self.setup_SNP_dstruc2(curs, self.snp_locus_table, offset=self.offset) elif self.processing_bits[3]==1: SNPpos2col_index, snp_acc_ls = self.setup_SNP_dstruc2(curs, self.snp_locus_table, \ cross_linking_table=self.data_type2data_table[self.processing_bits[1]], \ offset=self.offset) elif self.processing_bits[3]==2: SNPpos2col_index, snp_acc_ls = self.setup_SNP_dstruc2(curs, self.data_type2data_table[self.processing_bits[1]], \ offset=self.offset) else: sys.stderr.write("Error: unsupported 3rd bit in processing_bits %s.\n"%self.processing_bits[3]) sys.exit(3) from variation.src.common import get_accession_id2name accession_id2name = get_accession_id2name(curs) if self.processing_bits[1]==0: row_id2dstruc = self.setup_row_dstruc(curs, SNPpos2col_index, accession_id2name, offset=self.offset, version=self.version) elif self.processing_bits[1]==1: from variation.src.common import map_perlegen_ecotype_name2accession_id ecotype_name2accession_id = map_perlegen_ecotype_name2accession_id(curs) row_id2dstruc = self.setup_row_dstruc(curs, SNPpos2col_index, accession_id2name, data_type=self.processing_bits[1], \ ecotype_name2accession_id=ecotype_name2accession_id,\ offset=self.offset, version=self.version) else: sys.stderr("Unsupported data type: %s or no ecotype_name2accession_id specified.\n"%self.processing_bits[1]) sys.exit(2) accession_id_ls, accession_name_ls, data_matrix = self.transform_row_id2dstruc_2_matrix(row_id2dstruc) from variation.src.FilterStrainSNPMatrix import FilterStrainSNPMatrix FilterStrainSNPMatrix_instance = FilterStrainSNPMatrix() #2008-02-08 which type of row id/1st column if self.processing_bits[0]==0: from variation.src.common import map_accession_id2ecotype_id accession_id2ecotype_id = map_accession_id2ecotype_id(curs, accession2ecotype_table=self.accession2ecotype_table) accession_id2ecotype_id[99] = 6909 #accession 99 is the reference genome, which col-0 (ecotype_id=6909) ecotype_id_ls = [] rows_to_be_tossed_out=Set() for i in range(len(accession_id_ls)): ecotype_id = accession_id2ecotype_id.get(accession_id_ls[i]) if not ecotype_id: #mapping failed rows_to_be_tossed_out.add(i) ecotype_id_ls.append(ecotype_id) strain_acc_list = ecotype_id_ls header = ['ecotype_id'] #1st column in the header else: rows_to_be_tossed_out=Set() strain_acc_list = accession_id_ls header = ['accession_id'] #2008-02-08 which type of 2nd column if self.processing_bits[2]==0: category_list = [1]*len(accession_name_ls) header.append('duplicate') #2nd column in the header elif self.processing_bits[2]==1: category_list = accession_name_ls header.append('accession_name') else: category_list = accession_name_ls header.append('accession_name') header += snp_acc_ls FilterStrainSNPMatrix_instance.write_data_matrix(data_matrix, self.output_fname, header, strain_acc_list, category_list, rows_to_be_tossed_out=rows_to_be_tossed_out)