plant_tribes_gene_family_scaffold_loader: gene_family_scaffold

comparison gene_family_scaffold_loader.py @ 6:9a4b0ae3d408 draft

Uploaded

author	greg
date	Tue, 05 Jun 2018 14:27:50 -0400
parents	cb986be6355e
children	3841f7252b1d

comparison

equal deleted inserted replaced

-:cb986be6355e
+:9a4b0ae3d408
 # Strip the version from the species_code.
 species_code = species_code[0:5]
 # Get the species_name from self.species_ids_dict.
 species_name = self.species_ids_dict[species_code]
 # Create a key for self.species_genes_dict, with the format:
-# <clustering_method>^^<species_code>
+# <clustering_method>^^<species_name>
-species_genes_dict_key = "%s^^%s" % (clustering_method, species_code)
+species_genes_dict_key = "%s^^%s" % (clustering_method, species_name)
 # Add an entry to self.species_genes_dict, where the value
 # is a list containing species_name and num_genes.
 if species_genes_dict_key in self.species_genes_dict:
 tup = self.species_genes_dict[species_genes_dict_key]
 tup[1] += 1
 continue
 # Example line: Populus trichocarpa\tSalicaceae\tMalpighiales\tRosids\tCore Eudicots
 items = line.split("\t")
 species_name = items[0]
 i = 0
-for species_genes_dict_key in sorted(self.species_genes_dict.keys()):
+for clustering_method in self.clustering_methods:
-# The format of species_genes_dict_key is <clustering_method>^^<species_code>.
+species_genes_dict_key = "%s^^%s" % (clustering_method, species_name)
+# The format of species_genes_dict_key is <clustering_method>^^<species_name>.
 species_genes_dict_key_items = species_genes_dict_key.split("^^")
-clustering_method = species_genes_dict_key_items[0]
-species_code = species_genes_dict_key_items[1]
 # Get the scaffold_rec for the current scaffold_id and clustering_method.
 # The list is [<scaffold_id_db>, <scaffold_id>, <clustering_method>]
 for scaffold_rec in self.scaffold_recs:
 if scaffold_id in scaffold_rec and clustering_method in scaffold_rec:
 scaffold_id_db = scaffold_rec[0]
 def process_orthogroup_fasta_files(self):
 """
 1. Analyze all of the scaffold .fna and .faa files for each clustering
 method to populate the aa_dict and dna_dict sequence dictionaries.
 2. Use the populated sequence dictionaries to populate the plant_tribes_gene
-and gene_scaffold_orthogroup_association tables.
+and gene_scaffold_orthogroup_taxon_association tables.
 """
 scaffold_id = os.path.basename(self.args.scaffold_path)
 aa_dict = {}
 dna_dict = {}
 # Populate aa_dict and dna_dict.
 # above will be the sequence associated with that gene until
 # the next gene id line is encountered.
 sequence = adict[combined_id]
 sequence = "%s%s" % (sequence, line)
 adict[combined_id] = sequence
-# Populate the plant_tribes_gene and gene_scaffold_orthogroup_association tables
+# Populate the plant_tribes_gene and gene_scaffold_orthogroup_taxon_association tables
 # from the contents of aa_dict and dna_dict.
-self.log("Populating the plant_tribes_gene and gene_scaffold_orthogroup_association tables.")
+self.log("Populating the plant_tribes_gene and gene_scaffold_orthogroup_taxon_association tables.")
 gi = 0
 for gsoai, combined_id in enumerate(sorted(dna_dict.keys())):
 # The dictionary keys combine the orthogroup_id, clustering method and
 # gene id using the format <orthogroup_id>^^<clustering_method>^^<gene_id>.
 items = combined_id.split("^^")
 sql = "SELECT id FROM plant_tribes_orthogroup WHERE orthogroup_id = '%s';" % orthogroup_id
 cur = self.conn.cursor()
 cur.execute(sql)
 orthogroup_id_db = cur.fetchone()[0]
 # If the plant_tribes_gene table contains a row that has the gene_id,
-# then we'll add a row only to the gene_scaffold_orthogroup_association table.
+# then we'll add a row only to the gene_scaffold_orthogroup_taxon_association table.
 # Get the taxon_id  for the species_name from the plant_tribes_taxon table.
 sql = "SELECT id FROM plant_tribes_taxon WHERE species_name = '%s';" % species_name
 cur = self.conn.cursor()
 cur.execute(sql)
 taxon_id_db = cur.fetchone()[0]
 # If the plant_tribes_gene table contains a row that has the gene_id,
-# then we'll add a row only to the gene_scaffold_orthogroup_association table.
+# then we'll add a row only to the gene_scaffold_orthogroup_taxon_association table.
 sql = "SELECT id FROM plant_tribes_gene WHERE gene_id = '%s';" % gene_id
 cur = self.conn.cursor()
 cur.execute(sql)
 try:
 gene_id_db = cur.fetchone()[0]
 self.flush()
 gene_id_db = cur.fetchone()[0]
 gi += 1
 if gi % 1000 == 0:
 self.log("Inserted 1000 more rows into the plant_tribes_gene table.")
-# Insert a row into the gene_scaffold_orthogroup_association table.
+# Insert a row into the gene_scaffold_orthogroup_taxon_association table.
 # Get the scaffold_rec for the current scaffold_id and clustering_method.
 # The list is [<scaffold_id_db>, <scaffold_id>, <clustering_method>]
 for scaffold_rec in self.scaffold_recs:
 if scaffold_id in scaffold_rec and clustering_method in scaffold_rec:
 scaffold_id_db = scaffold_rec[0]
 VALUES (nextval('gene_scaffold_orthogroup_taxon_association_id_seq'), %s, %s, %s, %s);
 """
 cur = self.update(sql, tuple(args))
 self.flush()
 if gsoai % 1000 == 0:
-self.log("Inserted 1000 more rows into the gene_scaffold_orthogroup_association table.")
+self.log("Inserted 1000 more rows into the gene_scaffold_orthogroup_taxon_association table.")
 self.log("Inserted a total of %d rows into the plant_tribes_gene table." % gi)
-self.log("Inserted a total of %d rows into the gene_scaffold_orthogroup_association table." % gsoai)
+self.log("Inserted a total of %d rows into the gene_scaffold_orthogroup_taxon_association table." % gsoai)
 if __name__ == '__main__':
 scaffold_loader = ScaffoldLoader()
 scaffold_loader.run()
 scaffold_loader.shutdown()

Mercurial > repos > greg > plant_tribes_gene_family_scaffold_loader

comparison gene_family_scaffold_loader.py @ 6:9a4b0ae3d408 draft