domains / families / science / generative-design

generative-design

separate

Designs novel molecules using REINVENT 4 (de novo, scaffold decoration, linker design, R-group, molecular optimization), MolMIM, Diffusion-based generators (DiGress, DiffSMol), and JT-VAE with explicit handling of multi-parameter optimization (MPO), goal-directed scoring functions, transfer/reinforcement/curriculum learning, synthetic accessibility scoring, and chemical space exploration vs exploitation. Use when designing new chemical matter against a target, decorating a scaffold, linking fragments, or optimizing a hit for multiple ADMET / activity properties simultaneously.

When to use

• de novo molecular design
• scaffold decoration
• linker design
• R-group replacement
• molecular optimization
• multi-parameter optimization (MPO)
• goal-directed scoring functions
• chemical space exploration

When not to use

• QSAR/scoring model development
• retrosynthesis
• library enumeration

Skill page

Source