Submission Details
Molecule(s):
Cc1ccc(C2CC(c3ccccc3)=NN2C(=O)CCl)cc1
CC(=O)Nc1ccc(N(C(=O)CCl)C(C(=O)NC2CCCCC2)c2ccccc2)cc1
COc1cc(C2CC(c3ccc(OC)c(OC)c3)=NN2C(=O)CCl)ccc1O
CN(C)c1ccc(C2CC(c3cccs3)=NN2C(=O)CCl)cc1
MAR-LAB-efb042c5-5
Duplicate of:
AAR-POS-d2a4d1df-27
Cc1ccc(S(=O)(=O)N2CCN(C(=O)CCl)CC2)cc1
O=C(O)c1ccc(N(Cc2ccccc2)C(=O)CCl)cc1
Design Rationale:
These molecules were generated by our de novo design neural network. Briefly, we trained a LSTM-based model to generate molecules on the same chemical space as SARS-CoV-1 Mpro inhibitors. We then used the learned features to train a classifier which we used to predict the activity of the generated molecules.