def print_all_proteins():
"""
Print all the proteins to stdout
:return: nothing
"""
con = connect_to_db(phagedb)
protein_to_fasta(con)
disconnect(con)
def list_all_genomes():
"""
Print all the proteins to stdout
:return: nothing
"""
con = connect_to_db(phagedb)
exc = con.cursor().execute("select description from genome")
for d in exc.fetchall():
print(f"{d[0]}")
disconnect(con)
Create a full text search virtual table on the protein products
:param conn: the database connection
:param verbose: more output
:return:
"""
if verbose:
sys.stderr.write(
f"{color.GREEN}Adding full text search capabilities{color.ENDC}\n")
c = conn.cursor()
c.execute(
"CREATE VIRTUAL TABLE protein_fts using FTS5(protein_rowid, product);")
c.execute(
"INSERT INTO protein_fts SELECT protein_rowid, product FROM protein;")
conn.commit()
if __name__ == '__main__':
parser = argparse.ArgumentParser(
description='Load genbank data into an SQLite table')
parser.add_argument('-f', help='GenBank file to parse', required=True)
parser.add_argument('-p', help='Phage SQLite database', required=True)
parser.add_argument('-v', help='verbose output', action='store_true')
args = parser.parse_args()
conn = connect_to_db(args.p, args.v)
load_genbank_file(args.f, conn, args.v)
create_full_text_search(conn, args.v)
disconnect(conn, args.v)
Convert a protein ID to a dict object of all function
:param proteinid: The protein md5 sum
:param clusterdb_cursor: the cursor to the cluster database
:param verbose: more output
:return: dict: the functions of the protein and their frequency
"""
global protein_functions
if proteinid not in protein_functions:
protein_functions[proteinid] = get_functions(proteinid, clusterdb_cursor, verbose)
return json.loads(protein_functions[proteinid][1])
if __name__ == '__main__':
parser = argparse.ArgumentParser(description=" ")
parser.add_argument('-i', help='protein id', required=True)
parser.add_argument('-c', help='cluster database', required=True)
parser.add_argument('-v', help='verbose output', action='store_true')
args = parser.parse_args()
c= connect_to_db(args.c, args.v)
fn = proteinid_to_function(args.i, c.cursor(), args.v)
fns = proteinid_to_all_functions(args.i, c.cursor(), args.v)
fnstr = "\n".join([f"{x} -> {str(y)}" for x,y in sorted(fns.items(), key=lambda item: item[1], reverse=True)])
disconnect(c, args.v)
print(f"The function of {args.i} is\n'{fn}'")
print(f'All the functions are:\n{fnstr}')
description="Create a database and load it with GenBank data")
parser.add_argument('-p', help='Phage SQL output database')
parser.add_argument('-c', help='clusters SQLite database')
parser.add_argument('-v', help='verbose output', action='store_true')
args = parser.parse_args()
if args.p:
sys.stderr.write(
f"{color.BOLD}{color.BLUE}Defining Phage Tables{color.ENDC}\n")
if not os.path.exists(args.p):
with open(args.p, 'w') as out:
True
phageconn = connect_to_db(args.p, args.v)
define_phage_tables(phageconn, args.v)
phageconn.commit() # final commit to make sure everything saved!
disconnect(phageconn, args.v)
if args.c:
sys.stderr.write(
f"{color.BOLD}{color.BLUE}Defining Cluster Tables{color.ENDC}\n")
if not os.path.exists(args.c):
with open(args.c, 'w') as out:
True
clconn = connect_to_db(args.c, args.v)
define_cluster_tables(clconn, args.v)
clconn.commit()
disconnect(clconn, args.v)
if not args.p and not args.c:
sys.stderr.write(f"{color.RED}Nothing to do!{color.ENDC}\n")
"""
"""
import os
import sys
import argparse
from pppf_databases import connect_to_db, disconnect
from pppf_clusters import read_mmseqs_clusters, add_functions_to_clusters, insert_cluster_metadata, insert_into_database
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Load the cluster information into the databases')
parser.add_argument('-p', '--phage', help='Phage SQL database', required=True)
parser.add_argument('-c', '--clusters', help='Clusters SQL database', required=True)
parser.add_argument('-t', '--tsv', help='Cluster tsv file', required=True)
parser.add_argument('-n', '--name', help='Cluster name (short text)', required=True)
parser.add_argument('-d', '--description', help='Cluster description (human readable text)', required=True)
parser.add_argument('-c', '--cli', help='Cluster command line (bash)', required=True)
parser.add_argument('-v', '--verbose', help='verbose output', action='store_true')
args = parser.parse_args()
phageconn = connect_to_db(args.phage, args.verbose)
clconn = connect_to_db(args.clusters, args.verbose)
clusters = read_mmseqs_clusters(args.tsv, args.verbose)
(clusters, protein_info) = add_functions_to_clusters(clusters, phageconn, args.verbose)
metadata_id = insert_cluster_metadata(clconn, args.name, args.description, args.cli, args.verbose)
insert_into_database(clusters, clconn, phageconn, metadata_id, protein_info, args.verbose)
disconnect(phageconn, args.verbose)
disconnect(clconn, args.verbose)