Fig. 6
From: Randomized SMILES strings improve the quality of molecular generative models
Kernel Density Estimates (KDEs) of the Molecule negative log-likelihoods (NLLs) of the ChEMBL models for the canonical SMILES variant (left) and the randomized SMILES variant (right). Each line symbolizes a different subset of 50,000 molecules from: Training set (green), validation set (orange), randomized SMILES model (blue) and canonical SMILES model (yellow). Notice that the Molecule NLLs for the randomized SMILES model (right) are obtained from the sum of all the probabilities of the randomized SMILES for each of the 50,000 molecules (adding up to 320 million randomized SMILES), whereas those from the canonical model are the canonical SMILES of the 50,000 molecules