A Versatile Transformer-based Variational Autoencoder for Generating Novel Molecular Structures
The proposed Transformer-based Variational Autoencoder (VAE) model demonstrates state-of-the-art performance in generating novel molecular structures that are not present in the training dataset, while maintaining high validity and uniqueness of the generated molecules.
Adaptive 3D Molecule Generation: Leveraging Structural Variations to Expand the Scope of Diffusion-Based Models
The proposed Geometric Adaptive Diffusion Model (GADM) can adaptively generate 3D molecules with desired structural variations, such as scaffold and ring-structure, by leveraging an equivariant masked autoencoder to capture the structural-grained representations as domain supervisors for the diffusion-based generation process.
Mol-AIR: Adaptive Intrinsic Rewards for Efficient Goal-Directed Molecular Generation
Mol-AIR, a reinforcement learning framework with adaptive intrinsic rewards, enables efficient exploration of the vast chemical space to discover molecular structures with desired properties.
© 2024 by Linnk AI