PR-GVAE: Property-Controllable Molecular Generation via Conditional Graph Variational Autoencoder

CCVAN Leverages Conditional Molecular Generation Through Conditional VAE and Wasserstein GAN.

This study integrated the conditional variational autoencoder with the Wasserstein generative adversarial network and effectively applied this hybrid architecture to molecular generation tasks, introducing a molecular generation framework with conditional generation capabilities known as CCVAN.

DF-S4: Disentangled FiLM-Conditioned Molecular Generation Using the S4 Architecture

DF-S4, a conditional molecular generation framework based on Structured State Space Models (S4), which addresses this limitation through a disentangled latent representation and hierarchical feature-wise linear modulation (FiLM) through a disentangled latent representation and hierarchical feature-wise linear modulation.

MolGraphGAN: a graph transformer–adversarial framework for target-specific molecule generation

MolGraphGAN provides a generalizable and experimentally usable pipeline for accelerating target-centric drug discovery in a variety of therapeutics, demonstrating scalability across multiple therapeutic classes, and embeds explainable AI protocols through the presentation of attention maps highlighting substructure having maximum influence on predicted binding.

GraphVAEBM: Graph Generation Combining Variational Autoencoders and Energy-Based Models

Conditional GraphGANFed: Optimizing Graph-Structured Molecule Generation in Federated Generative Adversarial Networks

Generative adversarial networks (GANs) have garnered considerable attention in molecular discovery for their ability to generate novel and high-quality molecules. To efficiently train a GAN model while preserving data privacy, GraphGANFed has been proposed to incorporate federated learning and graph convolutional networks into GAN. Yet, GraphGANFed cannot produce synthetic molecules that only optimize a user-defined metric(s) to facilitate the new drug discovery process. To address this issue, we introduce a novel extension to GraphGANFed, namely conditional GraphGANFed (cGraphGANFed), by incorporating the critic network to assess generated molecules using user-defined metric(s). The evaluation results from both the critic network and discriminator are integrated into the loss function of the generator, guiding it to generate novel molecules that maintain similar chemical properties to real ones while optimizing user-defined metrics. Extensive simulations are conducted in two scenarios. First, cGraphGANFed endeavors to optimize all seven commonly used metrics, and the results show that cGraphGANFed significantly outperforms GraphGANFed in Validity and LogP, with a slight advantage in QED, across different settings. Second, cGraphGANFed focuses solely on optimizing QED, and the results show that the synthetic molecules produced by cGraphGANFed can achieve more than 10% improvement in QED than GraphGANFed. Also, the results demonstrate cGraphGANFed has enhanced resilience against mode collapses and performance reduction caused by non-IID data.

Controllable molecular generation with fine-tuned flow-matching model

Three-dimensional molecular generative models have emerged that produce de novo molecules both unconditionally and conditionally, e.g., within protein pockets. However, steering those models in a specific region of the chemical space that satisfies a set of desired properties remains challenging. In this study, we introduce a flexible reinforcement learning method for flow-matching based generative models, allowing the velocity field to be refined according to a user-defined reward function. In contrast to a pure conditional generation setup, where the set of conditions must be decided a priori, this framework allows fine-tuning of any unconditional or conditional model, reflecting a more realistic scenario where the target properties to be optimized often vary and are typically case-specific. This also enables joint optimization of continuous and discrete features in flow-matching models for the first time. Through extensive experiments across diverse optimization scenarios, we demonstrate that models trained with this strategy (agents) consistently outperform baseline approaches (priors) when evaluated against the target design criteria. Three-dimensional molecular generative models can design novel molecules but guiding them to meet specific property requirements remains challenging. Here, the authors introduce a flexible reinforcement learning method for flow-matching generative models, enabling dynamic fine-tuning and joint optimization of features, outperforming baseline approaches in diverse optimization scenarios.