← All tools
Sequence prediction · Protein Design

LigandMPNN

Design protein sequences with ligand-, solubility-, or membrane-aware models.

Runs the official LigandMPNN run.py, ProteinMPNN's successor CLI covering protein, ligand-aware, soluble-only, and membrane-topology model types behind a single interface.

Input

Configure a small job

POST
Comma-separated chain IDs; blank designs every chain in the structure.
Sequences generated = batch_size x number_of_batches.
One-letter amino-acid codes to never sample, e.g. "CX".
Global per-amino-acid sampling bias, e.g. "A:-1.0,P:2.3".
JSON object keyed by chain+residue, e.g. {"C1": {"G": -0.3, "P": 10.8}}.
JSON object keyed by chain+residue, e.g. {"A1": "ACDEFG"}.
Space-separated "ChainResnum", e.g. "C1 C2 C3"; these residues are held fixed.
Space-separated "ChainResnum", the inverse of fixed_residues: only these are redesigned.
Space-separated "ChainResnum", e.g. "A1 A2 A3".
Space-separated "ChainResnum".
0 uses a single fast pack instead of resampling.
Ready
Response

JSON result

{
  "status": "Ready for a request"
}