Chemistry & ADMET · AstraZeneca
RL-guided generative chemistry against a multi-objective scoring function.
No backend is configured for this model.
5–30min
Not runnable yet
This model isn't available to run right now.Run this model
About this model
REINVENT optimises molecules toward a composite objective — potency, selectivity, ADMET, synthesizability — using reinforcement learning over a SMILES generator. The industrial standard for de novo design, open-sourced by AstraZeneca.
Standardized I/O contract
Every model in the Hub speaks the same contract, which is what lets the Router and the agent call any of them without special-casing.
Inputs
Scaffold / seed SMILES
Objective
Molecules
Outputs
Molecules with objective scores.
