LICHEN
Heavy-chain-conditioned light-chain generation, including bispecific-oriented sequence workflows.
Developer: Oxford Protein Informatics Group; Capel et al.
Overview
- Developer
- Oxford Protein Informatics Group; Capel et al.
- Category
- antibody-specific design
- Commercial rights
- Unverified
- License fee
- Unverified
- Open weights
- Yes
- Last verified
- 2026-10-18
- Added
- 2026-10-18
Capabilities
Generates candidate immunoglobulin light-chain sequences conditioned on an input heavy-chain sequence and optional germline constraints. Repository documents conditional light-chain sampling, scoring, and bispecific-related modes.
When to use it
Prototype light-chain pairing/design for an existing VH or dual-heavy-chain strategy; test VH/VL pairing, expression, binding and aggregation experimentally.
Compute
Compute category: cpu. See original installation instructions or platform terms for specific hardware costs and runtime.
Example use cases
- Prototype light-chain pairing/design for an existing VH or dual-heavy-chain strategy; test VH/VL pairing, expression, binding and aggregation experimentally.
Source-based workflow description. No experimental performance ranking is implied.
Known limitations
- Model weights are distributed via Zenodo. Commercial license coverage for checkpoints, model data and every third-party component has not been fully checked.
Check the original linked sources and the terms of every model dependency.
Commercial licensing
Commercial permission — Unverified
BSD-3-Clause repository code; separately hosted checkpoint and dependency terms need verification.
Model weights are distributed via Zenodo. Commercial license coverage for checkpoints, model data and every third-party component has not been fully checked.
Commercial fee — Unverified
No complete model + checkpoint + cloud compute + service charges have been verified. Public research software or downloadable weights do not imply a free commercial deployment.
Official references
Validate your designed binder.
Seq2Study coordinates expression, affinity, stability and developability testing for AI-designed antibodies and proteins.