GEN: highly efficient SMILES explorer using autodidactic generative examination networks

Table 1 Comparison architecture A and B and comparing LSTM to GRU

Architecture	Layer size	Best model epoch#	Validity%	Uniqueness%	Training%	Length match %^a	HAC match %^b
A: LSTM–LSTM	256/256	12, 17, 20	96.7 ± 0.4	99.9 ± 0.1	15.0 ± 0.7	98.2 ± 0.9	94.0 ± 1.8
A: GRU–GRU	256/256	15, 15, 15	91.8 ± 0.7	99.9 ± 0.1	12.6 ± 0.8	98.3 ± 0.4	94.6 ± 1.3
B: biLSTM–biLSTM	256/256	6, 7, 10	97.1 ± 0.4	99.9 ± 0.1	13.1 ± 0.5	98.2 ± 0.6	93.9 ± 0.8
B: biGRU–biGRU	256/256	11, 11, 11	95.6 ± 0.6	99.9 ± 0.1	15.0 ± 0.5	98.3 ± 0.3	93.1 ± 1.4

^aLength match for SMILES length distributions of the training set and generated set (See “Methods”)
^bHAC match for the atom count distributions of the generated set and training set (See “Methods”)

ISSN: 1758-2946