Fig. 5: Illustration of the model architecture of DeepICL.
From: 3D molecular generative framework for interaction-guided drug design
a The training phase of DeepICL, where two losses ℓreg and ℓrecon are denoted. b In the generation phase of DeepICL, z is sampled from the standard normal distribution instead of using the encoder. c The encoder module (qϕ) is trained to encode a whole protein–ligand complex (L, P) and corresponding interaction condition, I, into a latent vector z that follows a prior distribution. d The decoder module (pθ) is trained to reconstruct the ligand structure from the given protein pocket and an interaction condition with an autoregressive process. Note that the decoder of the figure describes a single atom addition step, where a type and a position of the tth ligand atom are determined from the protein–ligand complex of step t−1. e The embedding module is included in front of the encoder and decoder, incorporates interaction conditions to protein atoms, and updates protein and ligand atom features via interaction layers.
