← All tools
Structure prediction

Protenix-v2

Predict protein or protein-ligand complex structures with Protenix.

Builds Protenix's AlphaFold3-style JSON input and runs the official `protenix pred` CLI, with MSA and PDB template search off by default.

Input

Configure a small job

POST
Add one box per chain: Protein, DNA, RNA, Ligand, or Ion. Ligands take a SMILES string or a CCD_ code (e.g. CCD_ATP); ions take a CCD ion code (e.g. NA, MG, ZN). A modification applies a CCD residue code at a given position; "Cyclic" bonds the chain's first and last residue.
One protein chain sequence per line.
One DNA chain sequence per line.
One RNA chain sequence per line.
JSON list of {"type": "protein"|"dna"|"rna", "chain": "A", "sequence": "..."}.
One ligand per line: a CCD code such as CCD_ATP, or a SMILES string.
Use protenix_base_constraint_v0.5.0 for pocket/contact restraints to have any effect on the prediction.
Runs this many seeds (MSA computed once); total predictions = seeds x samples.
JSON list, e.g. [{"atom1Chain":"A","atom1Idx":32,"atom1Atom":"C","atom2Chain":"B","atom2Idx":1,"atom2Atom":"N"}].
At most one, as a JSON list, e.g. [{"binderChain":"A","pocketChain":"B","pocketContacts":"5 6 7","maxDistance":6}].
JSON list, e.g. [{"chainA":"A","res_idxA":1,"chainB":"B","res_idxB":1,"max_distance_angstrom":6,"min_distance_angstrom":3}].
Ready
Response

JSON result

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