Molecular generation by Fast Assembly of (Deep)SMILES fragments

Table 2 Comparison of several molecular generators in the GuacaMol [33] distribution learning benchmark

Benchmark	Random sampler	SMILES LSTM	Graph MCTS	AAE	ORGAN	VAE	FASMIFRA	Negative control
Validity	1.000	0.959	1.000	0.822	0.379	0.870	1.000	1.000
Uniqueness	0.997	1.000	1.000	1.000	0.841	0.999	0.994	0.959
Novelty	0.000	0.912	0.994	0.998	0.687	0.974	0.702	0.947
KL_divergence	0.998	0.991	0.522	0.886	0.267	0.982	0.959	0.855
FCD	0.929	0.913	0.015	0.529	0.000	0.863	0.814	0.397

Random sampler: baseline model; SMILES LSTM: Long-Short-Term Memory DNN for SMILES strings; Graph MCTS: Graph-based Monte Carlo Tree Search; AAE: Adversarial AutoEncoder; ORGAN: Objective-Reinforced Generative Adversarial Network; VAE: Variational AutoEncoder; FASMIFRA: Fast Assembly of SMILES Fragments (proposed method); Negative control: FASMIFRA without extended bond typing (any fragment can be connected to any other fragment)

ISSN: 1758-2946