'table_name': 'disease',
'where_clause': "dtype = 'UniProt'"
}, {
'dataset_id': dataset_id,
'table_name': 'feature'
}, {
'dataset_id': dataset_id,
'table_name': 'xref',
'where_clause': f"dataset_id = {dataset_id}"
}, {
'dataset_id': dataset_id,
'table_name': 'alias',
'where_clause': f"dataset_id = {dataset_id}"
}]
for prov in provs:
rv = dba.ins_provenance(prov)
assert rv, f"Error inserting provenance. See logfile {logfile} for details."
load_human(args, dba, dataset_id, eco_map, logger, logfile)
# Mouse and Rat proteins
# Dataset and Provenance
# As for human, we need the dataset id for xrefs and aliases
dataset_id = dba.ins_dataset({
'name': 'UniProt Mouse and Rat Proteins',
'source':
f"Mouse and Rat from UniProt XML file {UP_RODENT_FILE} from {UP_BASE_URL}",
'app': PROGRAM,
'app_version': __version__,
'url': 'https://www.uniprot.org'
})
assert dataset_id, f"Error inserting dataset See logfile {logfile} for details."
f'IDG generated data in file {IDG_LIST_FILE}.',
'app':
PROGRAM,
'app_version':
__version__,
'comments':
'IDG Target Flags are archived on GitHub in repo https://github.com/druggablegenome/IDGTargets.',
'url':
'https://github.com/druggablegenome/IDGTargets'
})
assert dataset_id, f"Error inserting dataset See logfile {logfile} for details."
# Provenance
provs = [{
'dataset_id': dataset_id,
'table_name': 'target',
'column_name': 'idg'
}, {
'dataset_id': dataset_id,
'table_name': 'target',
'column_name': 'fam',
'where_clause': 'idg = 1'
}]
#{'dataset_id': dataset_id, 'table_name': 'target', 'column_name': 'famext', 'where_clause': 'column_name == "fam"', 'where_clause': 'idg = 1'}
for prov in provs:
rv = dba.ins_provenance(prov)
assert rv, f"Error inserting provenance. See logfile {logfile} for details."
elapsed = time.time() - start_time
print("\n{}: Done. Elapsed time: {}\n".format(PROGRAM,
slmf.secs2str(elapsed)))
if type(rv) == int:
print(f"\nSet tdl to NULL for {rv} target rows")
else:
print(f"Error setting target.tdl values to NULL. See logfile {logfile} for details.")
exit(1)
rv = dba.del_dataset('TDLs')
if rv:
print(f"Deleted previous 'TDLs' dataset")
else:
print(f"Error deleting 'TDLs' dataset. See logfile {logfile} for details.")
exit(1)
load_tdls(dba, logfile, logger)
# Dataset
dataset_id = dba.ins_dataset( {'name': 'TDLs', 'source': 'IDG-KMC generated data by Steve Mathias at UNM.', 'app': PROGRAM, 'app_version': __version__, 'comments': 'TDLs are calculated by the loading app from data in TCRD.'} )
assert dataset_id, f"Error inserting dataset. See logfile {logfile} for details."
# Provenance
rv = dba.ins_provenance({'dataset_id': dataset_id, 'table_name': 'target', 'column_name': 'tdl'})
assert rv, f"Error inserting provenance. See logfile {logfile} for details."
# Add version number to filename and archive mapping file to old_versions dir
mmver = '.'.join( dbi['data_ver'].split('.')[:2] )
outfn = OUTFILE_PAT.format(mmver)
export_uniprot_mapping(dba, outfn)
shutil.copy(outfn, '/usr/local/apache2/htdocs/tcrd/download/PharosTCRD_UniProt_Mapping.tsv')
print(f"Copied {outfn} to /usr/local/apache2/htdocs/tcrd/download/PharosTCRD_UniProt_Mapping.tsv")
elapsed = time.time() - start_time
print("\n{}: Done. Elapsed time: {}\n".format(PROGRAM, slmf.secs2str(elapsed)))
dbi = dba.get_dbinfo()
logger.info(
"Connected to TCRD database {} (schema ver {}; data ver {})".format(
args['--dbname'], dbi['schema_ver'], dbi['data_ver']))
if not args['--quiet']:
print("Connected to TCRD database {} (schema ver {}; data ver {})".
format(args['--dbname'], dbi['schema_ver'], dbi['data_ver']))
start_time = time.time()
#do_glygen(dba, logger, logfile)
do_tiga(dba, logger, logfile)
# Dataset
dataset_id = dba.ins_dataset({
'name': 'ExtLinks',
'source': 'Tested links to target/protein info in external resources.',
'app': PROGRAM,
'app_version': __version__
})
assert dataset_id, f"Error inserting dataset. See logfile {logfile} for details."
# Provenance
rv = dba.ins_provenance({
'dataset_id': dataset_id,
'table_name': 'extlink'
})
assert rv, f"Error inserting provenance. See logfile {logfile} for details."
elapsed = time.time() - start_time
print("\n{}: Done. Elapsed time: {}\n".format(PROGRAM,
slmf.secs2str(elapsed)))
'logger_name': __name__
}
dba = DBAdaptor(dba_params)
dbi = dba.get_dbinfo()
logger.info(
"Connected to TCRD database {} (schema ver {}; data ver {})".format(
args['--dbname'], dbi['schema_ver'], dbi['data_ver']))
if not args['--quiet']:
print("Connected to TCRD database {} (schema ver {}; data ver {})".
format(args['--dbname'], dbi['schema_ver'], dbi['data_ver']))
start_time = time.time()
load(args, dba, logger, logfile)
# Dataset
dataset_id = dba.ins_dataset({
'name': 'DRGC Resources',
'source': 'RSS APIs at ',
'app': PROGRAM,
'app_version': __version__
})
assert dataset_id, f"Error inserting dataset See logfile {logfile} for details."
# Provenance
rv = dba.ins_provenance({
'dataset_id': dataset_id,
'table_name': 'drgc_resource'
})
assert rv, f"Error inserting provenance. See logfile {logfile} for details."
elapsed = time.time() - start_time
print("\n{}: Done. Elapsed time: {}\n".format(PROGRAM,
slmf.secs2str(elapsed)))
format(args['--dbname'], dbi['schema_ver'], dbi['data_ver']))
start_time = time.time()
load(args, dba, logger, logfile)
# Dataset
dataset_id = dba.ins_dataset({
'name': 'PubMed',
'source': 'NCBI E-Utils',
'app': PROGRAM,
'app_version': __version__,
'url': 'https://www.ncbi.nlm.nih.gov/pubmed'
})
assert dataset_id, "Error inserting dataset See logfile {} for details.".format(
logfile)
# Provenance
rv = dba.ins_provenance({'dataset_id': dataset_id, 'table_name': 'pubmed'})
assert rv, f"Error inserting provenance. See logfile {logfile} for details."
rv = dba.ins_provenance({
'dataset_id': dataset_id,
'table_name': 'protein2pubmed'
})
assert rv, "Error inserting provenance. See logfile {} for details.".format(
logfile)
elapsed = time.time() - start_time
print("\n{}: Done. Elapsed time: {}\n".format(PROGRAM,
slmf.secs2str(elapsed)))
# Use this to manually insert errors
# In [26]: t = dba.get_target(18821, include_annotations=True)
# In [27]: p = target['components']['protein'][0]