Fig. 4
From: A beginner’s approach to deep learning applied to VS and MD techniques
Overview of the workflow employed by Arshia et al. for the in silico compound generation of 3CLpro inhibitors. An LSTM RNN architecture was trained through DTL for the generation of 3CLpro binding molecules. Each generation step, the generated molecules were further validated and tested using traditional molecular docking methods. A genetic algorithm then selected a limited number of compounds for further finetuning of the RNN model. After ten generation steps, all molecules with high binding affinity for 3CLpro were clustered through a hierarchical clustering method, and the compounds with the highest binding affinity in each cluster were selected for further testing [53]