Exemplo n.º 1
0
    def run(self):
        if self.debug:
            import pdb

            pdb.set_trace()
        import MySQLdb

        mysql_conn = MySQLdb.connect(db=self.dbname, host="banyan.usc.edu", user=self.db_user, passwd=self.db_passwd)
        mysql_curs = mysql_conn.cursor()
        from pymodule import get_gene_symbol2gene_id_set

        gene_symbol2gene_id_set = get_gene_symbol2gene_id_set(
            mysql_curs, 3702, table="genome.gene_symbol2id", upper_case_gene_symbol=1
        )  # 3702 is At's tax id

        from variation.src.DrawSNPRegion import DrawSNPRegion

        DrawSNPRegion_ins = DrawSNPRegion(
            db_user=self.db_user,
            db_passwd=self.db_passwd,
            hostname=self.hostname,
            database=self.dbname,
            input_fname="/tmp/dumb",
            output_dir="/tmp",
            debug=0,
        )  # input_fname and output_dir are just random stuff
        gene_annotation = DrawSNPRegion_ins.dealWithGeneAnnotation(
            self.gene_annotation_picklef, cls_with_db_args=DrawSNPRegion_ins
        )
        self.improveTAIRGeneGFF(self.input_fname, gene_symbol2gene_id_set, gene_annotation, self.output_fname)
Exemplo n.º 2
0
    def run(self):
        """
		2008-08-19
		"""
        if self.debug:
            import pdb
            pdb.set_trace()
        db = Stock_250kDB(drivername=self.drivername,
                          username=self.db_user,
                          password=self.db_passwd,
                          hostname=self.hostname,
                          database=self.dbname,
                          schema=self.schema)
        db.setup(create_tables=False)
        import MySQLdb
        mysql_conn = MySQLdb.connect(db=self.dbname,
                                     host='banyan.usc.edu',
                                     user=self.db_user,
                                     passwd=self.db_passwd)
        mysql_curs = mysql_conn.cursor()
        from pymodule import get_gene_symbol2gene_id_set
        gene_symbol2gene_id_set = get_gene_symbol2gene_id_set(
            mysql_curs,
            3702,
            table='genome.gene_symbol2id',
            upper_case_gene_symbol=1)  #3702 is At's tax id

        session = db.session
        session.begin()
        self.putGeneListIntoDb(self.input_fname, self.list_type_id,
                               self.list_type_name, gene_symbol2gene_id_set,
                               db, self.skip_1st_line)
        if self.commit:
            session.commit()
Exemplo n.º 3
0
	def run(self):
		"""
		2008-08-19
		"""
		db = Stock_250kDB(drivername=self.drivername, username=self.db_user,
				   password=self.db_passwd, hostname=self.hostname, database=self.dbname, schema=self.schema)
		db.setup(create_tables=False)
		session = db.session
		session.begin()
		
		import MySQLdb
		mysql_conn = MySQLdb.connect(db=self.dbname, host='banyan.usc.edu', user = self.db_user, passwd = self.db_passwd)
		mysql_curs = mysql_conn.cursor()
		from pymodule import get_gene_symbol2gene_id_set
		gene_symbol2gene_id_set = get_gene_symbol2gene_id_set(mysql_curs, 3702, table='genome.gene_symbol2id', upper_case_gene_symbol=1)	#3702 is At's tax id
		
		
		reader = csv.reader(open(self.input_fname), delimiter=self.delimiter)
		reader.next()
		counter = 0
		success_counter = 0
		gene_id_pathway_id_set = Set()
		for row in reader:
			gene_symbol = row[0].upper()
			pathway_id = int(row[1])
			gene_id_set = gene_symbol2gene_id_set.get(gene_symbol)
			if gene_id_set==None:
				sys.stderr.write("Linking to gene id failed for %s. No such gene_symbol, %s, in gene_symbol2gene_id_set.\n"%(gene_symbol,gene_symbol))
			elif len(gene_id_set)==1:
				gene_id = list(gene_id_set)[0]
				gene_id_pathway_id_set.add((gene_id, pathway_id))
				success_counter += 1
			elif len(gene_id_set)>1:
				sys.stderr.write("Too many gene_ids: %s, %s.\n"%(gene_symbol, gene_id_set))
			elif len(gene_id_set)==0:
				sys.stderr.write("Linking to gene id failed for %s. There is gene_symbol, %s, in gene_symbol2gene_id_set but it's empty.\n"%(gene_symbol, gene_symbol))
			else:
				sys.stderr.write("not supposed to happen: original_name=%s, gene_symbol=%s, gene_id_set=%s\n."%(gene_symbol, gene_symbol, gene_id_set))
			counter += 1
		
		for gene_id, pathway_id in gene_id_pathway_id_set:
			rows = FTGene.query.filter_by(gene_id=gene_id).filter_by(pathway_id=pathway_id)
			if rows.count()>0:
				row = rows.first()
				sys.stderr.write('gene_id %s, pathway_id %s already in db with id=%s.\n'%(gene_id, pathway_id, row.id))
				continue
			ft_gene = FTGene(gene_id=gene_id, pathway_id=pathway_id)
			session.save_or_update(ft_gene)
			session.flush()
		if self.commit:
			session.commit()
Exemplo n.º 4
0
	def run(self):
		"""
		2008-08-19
		"""
		if self.debug:
			import pdb
			pdb.set_trace()
		db = Stock_250kDB(drivername=self.drivername, username=self.db_user,
				   password=self.db_passwd, hostname=self.hostname, database=self.dbname, schema=self.schema)
		db.setup(create_tables=False)
		import MySQLdb
		mysql_conn = MySQLdb.connect(db=self.dbname, host='banyan.usc.edu', user = self.db_user, passwd = self.db_passwd)
		mysql_curs = mysql_conn.cursor()
		from pymodule import get_gene_symbol2gene_id_set
		gene_symbol2gene_id_set = get_gene_symbol2gene_id_set(mysql_curs, 3702, table='genome.gene_symbol2id', upper_case_gene_symbol=1)	#3702 is At's tax id
		
		session = db.session
		session.begin()
		self.putGeneListIntoDb(self.input_fname, self.list_type_id, self.list_type_name, gene_symbol2gene_id_set, db, self.skip_1st_line)
		if self.commit:
			session.commit()
Exemplo n.º 5
0
    def run(self):
        if self.debug:
            import pdb
            pdb.set_trace()
        import MySQLdb
        mysql_conn = MySQLdb.connect(db=self.dbname,
                                     host='banyan.usc.edu',
                                     user=self.db_user,
                                     passwd=self.db_passwd)
        mysql_curs = mysql_conn.cursor()
        from pymodule import get_gene_symbol2gene_id_set
        gene_symbol2gene_id_set = get_gene_symbol2gene_id_set(
            mysql_curs,
            3702,
            table='genome.gene_symbol2id',
            upper_case_gene_symbol=1)  #3702 is At's tax id

        from variation.src.DrawSNPRegion import DrawSNPRegion
        DrawSNPRegion_ins = DrawSNPRegion(db_user=self.db_user, db_passwd=self.db_passwd, hostname=self.hostname, database=self.dbname,\
               input_fname='/tmp/dumb', output_dir='/tmp', debug=0) #input_fname and output_dir are just random stuff
        gene_annotation = DrawSNPRegion_ins.dealWithGeneAnnotation(
            self.gene_annotation_picklef, cls_with_db_args=DrawSNPRegion_ins)
        self.improveTAIRGeneGFF(self.input_fname, gene_symbol2gene_id_set,
                                gene_annotation, self.output_fname)
    def run(self):
        """
		2008-08-19
		"""
        db = Stock_250kDB(drivername=self.drivername,
                          username=self.db_user,
                          password=self.db_passwd,
                          hostname=self.hostname,
                          database=self.dbname,
                          schema=self.schema)
        db.setup(create_tables=False)
        session = db.session
        session.begin()

        import MySQLdb
        mysql_conn = MySQLdb.connect(db=self.dbname,
                                     host='banyan.usc.edu',
                                     user=self.db_user,
                                     passwd=self.db_passwd)
        mysql_curs = mysql_conn.cursor()
        from pymodule import get_gene_symbol2gene_id_set
        gene_symbol2gene_id_set = get_gene_symbol2gene_id_set(
            mysql_curs,
            3702,
            table='genome.gene_symbol2id',
            upper_case_gene_symbol=1)  #3702 is At's tax id

        reader = csv.reader(open(self.input_fname), delimiter=self.delimiter)
        reader.next()
        counter = 0
        success_counter = 0
        gene_id_pathway_id_set = Set()
        for row in reader:
            gene_symbol = row[0].upper()
            pathway_id = int(row[1])
            gene_id_set = gene_symbol2gene_id_set.get(gene_symbol)
            if gene_id_set == None:
                sys.stderr.write(
                    "Linking to gene id failed for %s. No such gene_symbol, %s, in gene_symbol2gene_id_set.\n"
                    % (gene_symbol, gene_symbol))
            elif len(gene_id_set) == 1:
                gene_id = list(gene_id_set)[0]
                gene_id_pathway_id_set.add((gene_id, pathway_id))
                success_counter += 1
            elif len(gene_id_set) > 1:
                sys.stderr.write("Too many gene_ids: %s, %s.\n" %
                                 (gene_symbol, gene_id_set))
            elif len(gene_id_set) == 0:
                sys.stderr.write(
                    "Linking to gene id failed for %s. There is gene_symbol, %s, in gene_symbol2gene_id_set but it's empty.\n"
                    % (gene_symbol, gene_symbol))
            else:
                sys.stderr.write(
                    "not supposed to happen: original_name=%s, gene_symbol=%s, gene_id_set=%s\n."
                    % (gene_symbol, gene_symbol, gene_id_set))
            counter += 1

        for gene_id, pathway_id in gene_id_pathway_id_set:
            rows = FTGene.query.filter_by(gene_id=gene_id).filter_by(
                pathway_id=pathway_id)
            if rows.count() > 0:
                row = rows.first()
                sys.stderr.write(
                    'gene_id %s, pathway_id %s already in db with id=%s.\n' %
                    (gene_id, pathway_id, row.id))
                continue
            ft_gene = FTGene(gene_id=gene_id, pathway_id=pathway_id)
            session.save_or_update(ft_gene)
            session.flush()
        if self.commit:
            session.commit()