def one_slurm(list_smiles,
server,
unique_id,
name,
target='drd3',
parallel=True,
exhaustiveness=16,
mean=False,
load=False):
"""
:param list_smiles:
:param server:
:param unique_id:
:param name:
:param parallel:
:param exhaustiveness:
:param mean:
:param load:
:return:
"""
pythonsh, vina = set_path(server)
dirname = os.path.join(script_dir, 'results', name,
'docking_small_results')
dump_path = os.path.join(dirname, f"{unique_id}.csv")
header = ['smile', 'score']
with open(dump_path, 'w', newline='') as csvfile:
csv.writer(csvfile).writerow(header)
for smile in list_smiles:
score_smile = dock(smile,
target='drd3',
unique_id=unique_id,
parallel=parallel,
exhaustiveness=exhaustiveness,
mean=mean,
pythonsh=pythonsh,
vina=vina,
load=load)
# score_smile = 0
with open(dump_path, 'a', newline='') as csvfile:
list_to_write = [smile, score_smile]
csv.writer(csvfile).writerow(list_to_write)
def one_dock(smile,
server,
parallel=False,
exhaustiveness=16,
mean=False,
load=False,
target='drd3'):
pythonsh, vina = set_path(server)
score_smile = dock(smile,
unique_id=smile,
parallel=parallel,
exhaustiveness=exhaustiveness,
mean=mean,
pythonsh=pythonsh,
vina=vina,
load=load,
target=target)
return score_smile
# We load the data
if args.obj != 'docking':
X = np.loadtxt(
'../../data/latent_features_and_targets/latent_features.txt')
y = -np.loadtxt(
f'../../data/latent_features_and_targets/targets_{args.obj}.txt')
X = X[:args.n_init, ]
y = y[:args.n_init]
else:
X = np.loadtxt(
'../../data/latent_features_and_targets/latent_features_docking.txt')
# We want to minimize docking scores => no need to take (-scores)
y = -np.loadtxt(
f'../../data/latent_features_and_targets/targets_{args.obj}.txt')
PYTHONSH, VINA = set_path(args.server)
with open('250k_docking_scores.pickle', 'rb') as f:
docked = pickle.load(f)
def dock_one(enum_tuple):
""" Docks one smiles. Input = tuple from enumerate iterator"""
identifier, smiles = enum_tuple
if smiles in docked:
return docked[smiles]
else:
return dock(smiles,
identifier,
PYTHONSH,
VINA,
parallel=False,