def main(fragment_file, lead_file):
fragment_mols = read_file(fragment_file)
lead_mols = read_file(lead_file)
fragment_mols += lead_mols
logging.info("Read %s molecules for fragmentation library",
len(fragment_mols))
logging.info("Read %s lead moleculs", len(lead_mols))
fragments, used_mols = get_fragments(fragment_mols)
logging.info("Num fragments: %s", len(fragments))
logging.info("Total molecules used: %s", len(used_mols))
assert len(fragments)
assert len(used_mols)
encodings, decodings = get_encodings(fragments)
save_decodings(decodings)
logging.info("Saved decodings")
lead_mols = np.asarray(
fragment_mols[-len(lead_mols):])[used_mols[-len(lead_mols):]]
X = encode_list(lead_mols, encodings)
logging.info("Building models")
actor, critic = build_models(X.shape[1:])
X = clean_good(X, decodings)
logging.info("Training")
history = train(X, actor, critic, decodings)
logging.info("Saving")
np.save("History/history.npy", history)
def main(fragment_file, lead_file):
fragment_mols = read_file(fragment_file)
lead_mols = read_file(lead_file)
fragment_mols += lead_mols
logging.info("Read %s molecules for fragmentation library",
len(fragment_mols))
logging.info("Read %s lead molecules", len(lead_mols))
fragments, used_mols = get_fragments(fragment_mols)
logging.info("Num fragments: %s", len(fragments))
logging.info("Total molecules used: %s", len(used_mols))
assert len(fragments)
assert len(used_mols)
# =============================================================================
# encodings, decodings = get_encodings(fragments)
# save_encodings(encodings)
# save_decodings(decodings)
# logging.info("Saved encodings and decodings")
# =============================================================================
lead_mols = np.asarray(
fragment_mols[-len(lead_mols):])[used_mols[-len(lead_mols):]]
decodings = read_decodings()
encodings = read_encodings()
logging.info("Loaded encodings and decodings")
X = encode_list(lead_mols, encodings)
#print(X.shape)
if X.shape[0] == 0:
return -1
logging.info("Building models")
actor, critic = build_models(X.shape[1:])
# X = clean_good(X, decodings)
# logging.info("Remaining molecules after clean good: %s",X.shape[0])
if X.shape[0] == 0:
return -1
logging.info("Training")
history = train(X, actor, critic, decodings)
logging.info("Saving")
np.save("History/history.npy", history)
actor.save('./saved_models/generation')
critic.save('./saved_models/critic')
def main(fragment_file, lead_file):
fragment_mols = read_file(fragment_file)
lead_mols = read_file(lead_file)
fragment_mols += lead_mols
fragments, used_mols = get_fragments(fragment_mols)
encodings, decodings = get_encodings(fragments)
save_decodings(decodings)
lead_mols = np.asarray(fragment_mols[-len(lead_mols):])[used_mols[-len(lead_mols):]]
X = encode_list(lead_mols, encodings)
actor, critic = build_models(X.shape[1:])
X = clean_good(X, decodings)
history = train(X, actor, critic, decodings)
np.save("History/history.npy", history)
def main(epoch,gen):
if gen == 1:
lead_file = "Data/trial.csv"
fragment_file = "Data/molecules.smi"
fragment_mols = read_file(fragment_file)
lead_mols = read_file(lead_file)
fragment_mols += lead_mols
logging.info("Read %s molecules for fragmentation library", len(fragment_mols))
logging.info("Read %s lead molecules", len(lead_mols))
fragments, used_mols = get_fragments(fragment_mols)
logging.info("Num fragments: %s", len(fragments))
logging.info("Total molecules used: %s", len(used_mols))
assert len(fragments)
assert len(used_mols)
lead_mols = np.asarray(fragment_mols[-len(lead_mols):])[used_mols[-len(lead_mols):]]
decodings = read_decodings()
encodings = read_encodings()
logging.info("Loaded encodings and decodings")
X = encode_list(lead_mols, encodings)
modify_mols(X,decodings)
epoch=1000
file_name = './past outputs/out'+str(epoch)+'.csv'
logging.info("Collecting and storing all molecules in {}".format(file_name))
Show_Epoch.main(epoch,file_name)
df = pd.read_csv('./past outputs/out'+str(epoch)+'.csv',sep=";")
moli = []
molm = []
for i in range(len(df)):
if (Chem.MolFromSmiles(df.iloc[i,1])) is not None:
moli.append(Chem.MolFromSmiles(df.iloc[i,0]))
molm.append(Chem.MolFromSmiles(df.iloc[i,1]))
logging.info("Predicting pIC50 values of the initial molecules")
ini = get_pIC50(moli)
logging.info("Predicting pIC50 values of the predicted molecules")
mod = get_pIC50(molm)
ini = np.asarray(ini)
mod = np.asarray(mod)
changes = pd.DataFrame(np.transpose(np.asarray([ini,mod])),columns=['Initial_pIC','Modified_pIC'])
changes['Initial_mol'] = df.iloc[:,0]
changes['Modified_mol'] = df.iloc[:,1]
changes['Delta'] = changes['Modified_pIC'] - changes['Initial_pIC']
changes.sort_values(by='Delta',ascending=False,inplace=True)
inact_to_act = changes.loc[(changes['Modified_pIC']>7) & (changes['Initial_pIC']<7),['Modified_pIC','Initial_pIC','Delta']].sort_values(by='Delta',ascending=False)
changes.to_csv('./past outputs/out_pIC'+str(epoch)+'.csv',index=False)
inact_to_act.to_csv('./past outputs/act_pIC'+str(epoch)+'.csv',index=False)
print(inact_to_act.head())
print(changes.head())
from rdkit.Chem import Draw
moli = []
molm = []
for i in range(5):
moli.append(Chem.MolFromSmiles(changes.iloc[i,2]))
moli.append(Chem.MolFromSmiles(changes.iloc[i,3]))
plot = Draw.MolsToGridImage(moli, molsPerRow=2)
plot.show()
#plot.save('/past outputs/epoch.png')
bins = np.linspace(4,10,14)
#changes = changes.loc[changes.Delta>0]
plt.hist(changes['Initial_pIC'], bins, alpha=0.5, label='initial',color='blue')
plt.hist(changes['Modified_pIC'], bins, alpha=0.5, label='modified',color='green')
plt.legend(loc='upper right')
plt.show()
sp = changes.loc[changes['Delta']>0].sum()['Delta']
sn = changes.loc[changes['Delta']<0].sum()['Delta']
cp = changes.loc[changes['Delta']>0].count()['Delta']
cn = changes.loc[changes['Delta']<0].count()['Delta']
print('Sum of positive changes = {}\tNo. of +ves = {}\nSum of negative changes = {}\tNo. of -ves = {}'.format(sp,cp,sn,cn))
return 0