Graph

• DST: Differentiable Scaffolding Tree (DST) enables gradient-based optimization on a chemical graph for molecule optimization, providing a novel approach for de novo molecule design.
  
• glownet: The main focus of this library (although it can do other things) is to construct graphs (e.g. graphs of atoms), which are constructed node by node.
  
• GRAPHINVENT: A platform for graph-based molecular generation using graph neural networks, emphasizing probabilistic generation one bond at a time.
  
• hgraph2graph: Hierarchical Generation of Molecular Graphs using Structural Motifs
  
• HyFactor (Hydrogen-count Labelled Graph-based Defactorization Autoencoder): An open-source architecture for structure generation using graph-based approaches, focusing on a new molecular graph type that considers hydrogen counts for enhanced molecular representation and generation.
  
• MoLeR: a generative model of molecular graphs which supports scaffold-constrained generation (generative chemistry) (standalone)
  
• NYAN (NotYetAnotherNightshade): A graph variational encoder designed for embedding molecules into a continuous latent space for molecular property prediction and high-throughput virtual screening in drug discovery.
  
• QADD: QADD is a novel de novo multi-objective quality assessment-based drug design approach that integrates an iterative refinement framework with a graph-based molecular quality assessment model to generate molecules with multiple desired properties.
  
• ScaffoldGVAE: ScaffoldGVAE is a variational autoencoder based on multi-view graph neural networks for scaffold generation and scaffold hopping of drug molecules, aiming to enhance molecular design by focusing on the scaffold components.