Artificial Intelligent Deep Learning Molecular Generative Modeling of Scaffold-Focused and Cannabinoid CB2 Target-Specific Small-Molecule Sublibraries
Yuemin Bian | Xiang-Qun Xie | Xiang-Qun
From the training molecules, generative models study and summarize a probability distribution to sample new molecules that are similar to the training data [24,25]. The training process results in a probability distribution of the next SMILES character given the input string. The validity, uniqueness, and novelty of sampled indole molecules under different epochs and sampling temperatures of the g-DeepMGM. Table S3: The validity, uniqueness, and novelty of sampled purine molecules under different epochs and sampling temperatures of the g-DeepMGM. Generative chemistry: Drug discovery with deep learning generative models.