Generative & De Novo overview
Propose novel small molecules toward a target profile with REINVENT or GenMol, then plan a retrosynthesis route for what you decide to make.
When existing compounds don't fit, generate new ones. This section proposes novel molecules — or grows and decorates a fragment — toward a target profile, expanding chemical space beyond what's already been made. It pairs naturally with docking and ADMET to score what you generate.
Availability
These tools are metered by credits and gated by your plan — plans set your monthly credits, available model families, and which modal-app tools you can run. See Plans & tiers.
What you can achieve here
- Generate novel small molecules toward a target
- Grow or decorate a fragment
- Design toward a desired property profile
For which tool fits each, see What you can achieve.
Tools in this section
| Tool | What it does |
|---|---|
| REINVENT | Design molecules with REINVENT 4 reinforcement learning, scoring functions and diversity filters — soft-deprecated here in favour of GenMol. |
| GenMol | Generate novel molecules using masked discrete diffusion on SAFE representations. |
| AiZynthFinder | Break a target SMILES into purchasable starting materials with AiZynthFinder — Monte Carlo tree search over USPTO templates, scored against your… |
Recipes using these tools
Read next
Reading a result against the bench
Why every published generative figure is in silico, and how to check makeability.
What you can achieve
The outcomes these tools deliver — and which to pick when several do the same thing.
Which tool?
Match a scientific goal to a tool across every domain.
Concept clusters
How tools, jobs, and results fit together.
Workflows
Guided pipelines and copy-and-adapt prompt recipes for common goals.
Was this page helpful?