Table 1 Molecules sampled during training
From: Multiobjective de novo drug design with recurrent neural networks and nondominated sorting
Iteration | Generated example | Valid |
|---|---|---|
0 | LCtACFS5AF@t-rl(= sL#) | False |
100 | CN1C(=O)CCCNc2cccnc2N2CCN(C)3=O | False |
500 | CO1)C(= O)NC2CCN(CCN3[C@@H](C(=O)CCC4)c3c1CSC(= O)= C)C(= O)O | False |
1000 | CCCC=C(c1ccc(OCCCC(C)(C)C(=O)O)c(Sc2ccccc2)c1)C(=O)O | True |
10,000 | CC(C)(C)OC(=O)N[C@@H](Cc1c[nH]c2ccccc12)C(=O)N[C@@H](Cc3ccccc3)C(= O)N | True |
100,000 | COc1ccccc1NC(= S)NC2CC(C)(C)Oc3ccc(F)cc23 | True |