DB_INPUT_ZV_protein

############################################################################
# Populating database with the content of ZoomVar Protein
# http://fraternalilab.kcl.ac.uk/ZoomVar/static/downloads/proteins.tar.gz
############################################################################

from sqlite3 import connect

DB_name = 'DB_JoRo_PRO'

############################################################################
conn = connect(DB_name)
curs = conn.cursor()

file = open('clinvar_protein.csv')
rows = [[line.rstrip().split(',')[0][1:-1]] + line.rstrip().split(',')[3:] for line in file]
if rows[0][0] == 'protein':
    del rows[0]
for rec in rows:
    curs.execute('INSERT INTO ZV_protein_clinvar (UniProt, length, snps, cdf, pval, qval) VALUES (?,?,?,?,?,?)', rec)

file = open('cosmic_protein.csv')
rows = [[line.rstrip().split(',')[0][1:-1]] + line.rstrip().split(',')[3:] for line in file]
if rows[0][0] == 'protein':
    del rows[0]
for rec in rows:
    curs.execute('INSERT INTO ZV_protein_cosmic (UniProt, length, snps, cdf, pval, qval) VALUES (?,?,?,?,?,?)', rec)

file = open('gnomad_common_protein.csv')
rows = [[line.rstrip().split(',')[0][1:-1]] + line.rstrip().split(',')[3:] for line in file]
if rows[0][0] == 'protein':
    del rows[0]
for rec in rows:
    curs.execute('INSERT INTO ZV_protein_gnomad_common (UniProt, length, snps, cdf, pval, qval) VALUES (?,?,?,?,?,?)', rec)

file = open('gnomad_rare_protein.csv')
rows = [[line.rstrip().split(',')[0][1:-1]] + line.rstrip().split(',')[3:] for line in file]
if rows[0][0] == 'protein':
    del rows[0]
for rec in rows:
    curs.execute('INSERT INTO ZV_protein_gnomad_rare (UniProt, length, snps, cdf, pval, qval) VALUES (?,?,?,?,?,?)', rec)


conn.commit()