LIFE SCIENCES & MATERIALS
De novo protein sequence design
De novo protein sequence design is an OpenEnv-compatible reinforcement learning environment in our Life Sciences & Materials catalog. An agent acts through the tools below, and a deterministic verifier scores every episode, so the reward can be used for GRPO or other RLVR post-training.
Task and verification
Generate candidate amino acid sequences for target 3D backbone structures and binding pockets. Downstream structural validation via ColabFold and ESMFold determines folding stability, target TM-score, and interface binding free energy.
Tools and runtime
Sequence generation + ColabFold/ESMFold structural validation & TM-score
OPENENV / PROTEIN
Related Life Sciences & Materials gyms
- Opentrons bio-lab protocol execution
- X-ray diffraction (XRD) materials suite
- Crystal structure prediction & DFT
- CRISPR guide RNA design & off-target checks
- Multi-step organic retrosynthesis
- Small molecule drug discovery & docking
- Autonomous experimental design (DoE)
- Molecular structure visualization & render (PyMOL)
- Clinical quality measures (FHIR & CQL)
See how these environments are run privately on the custom RL environments page, and how their rewards are made hard to game in our verifier design guide.
Plan a training run
Check the environment’s availability, compatible models and compute in Studio. A catalog entry does not guarantee that hosted training is enabled for your workspace.