Structure prediction

Protenix-v2 API

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.

Web form Home page ↗ Source code ↗

Submit POST /api/protenix/

Queues a run and returns 202 with the job.

Schema GET /api/protenix/

Returns this tool's metadata and the fields below, as JSON.

Tasks

Pick a mode with `task`

Fields belonging to another task are ignored, so send only the ones for the task you chose.

task	Mode
`sequence` default	Sequence
`list`	Chain list
`molecules`	Molecules (JSON)

Request body

Fields

The same names the web form posts. See the field type table for what each kind means over HTTP.

Name	Type	Required	Default	Description
`job_name`	string text	no	`protenix-demo`	Job name
`sequence_molecules` sequence	string (JSON array) molecule_builder	yes	`[{"type": "protein", "sequence": "MSTNPKPQRKTKRNTNRRPQDVKFPGG", "cyclic": false, "modifica …`	Molecules 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 of: `protein`, `dna`, `rna`, `ligand`, `ion`. A JSON array, sent as a string. See molecule entries.
`proteins` list	string textarea	yes	`MSTNPKPQRKTKRNTNRRPQDVKFPGG`	Protein chains One protein chain sequence per line.
`dnas` list	string textarea	no	`—`	DNA chains (optional) One DNA chain sequence per line.
`rnas` list	string textarea	no	`—`	RNA chains (optional) One RNA chain sequence per line.
`molecules` molecules	string textarea	yes	`[{"type": "protein", "chain": "A", "sequence": "MSTNPKPQRKTKRNTNRRPQDVKFPGG"}]`	Molecules JSON list of {"type": "protein"\|"dna"\|"rna", "chain": "A", "sequence": "..."}.
`ligands` list molecules	string textarea	no	`—`	Ligands (optional) One ligand per line: a CCD code such as CCD_ATP, or a SMILES string.
`model`	string select	no	`protenix-v2`	Model Use protenix_base_constraint_v0.5.0 for pocket/contact restraints to have any effect on the prediction. One of: `protenix-v2`, `protenix_base_20250630_v1.0.0`, `protenix_base_constraint_v0.5.0`, `protenix_base_default_v0.5.0`, `protenix_base_default_v1.0.0`.
`num_samples`	number number	no	`5`	Samples minimum 1, maximum 25.
`num_seeds`	number number	no	`1`	Consecutive seeds Runs this many seeds (MSA computed once); total predictions = seeds x samples. minimum 1, maximum 10.
`seed`	number number	no	`101`	Starting random seed minimum 0, maximum 2147483647.
`num_recycles`	number number	no	`10`	Recycles minimum 1, maximum 30.
`diffusion_steps`	number number	no	`200`	Diffusion steps minimum 10, maximum 500.
`use_msa_server`	boolean checkbox	no	`false`	Use the public MSA server Opt in to a network call for better accuracy; off keeps the run local.
`use_template`	boolean checkbox	no	`false`	Search PDB for templates Network search; only supported by protenix-v2 and the v1.0.0 base models.
`use_rna_msa`	boolean checkbox	no	`false`	Use RNA MSA search Network search; only supported by protenix-v2 and the v1.0.0 base models.
`use_guidance`	boolean checkbox	no	`false`	Use physics-aware guidance Training-free guidance for improved ligand plausibility (chirality, planarity, stereochemistry); increases compute time.
`bonds`	string textarea	no	`—`	Covalent bonds (optional) JSON list, e.g. [{"atom1Chain":"A","atom1Idx":32,"atom1Atom":"C","atom2Chain":"B","atom2Idx":1,"atom2Atom":"N"}].
`pocket_restraints`	string textarea	no	`—`	Pocket restraint (optional) At most one, as a JSON list, e.g. [{"binderChain":"A","pocketChain":"B","pocketContacts":"5 6 7","maxDistance":6}].
`contact_restraints`	string textarea	no	`—`	Contact restraints (optional) JSON list, e.g. [{"chainA":"A","res_idxA":1,"chainB":"B","res_idxB":1,"max_distance_angstrom":6,"min_distance_angstrom":3}].

Molecule entry keys

Key	Meaning
`type`	Which of the field's molecule types this entry is.
`sequence`	The residues, for a protein, dna, or rna entry.
`ligand`	A SMILES string or a CCD_ code, for a ligand entry.
`ion`	An ion code, for an ion entry.
`cyclic`	Whether a polymer chain is cyclic. Tools that cannot model one reject it rather than ignoring it.
`modifications`	Substitutions, as {"position": <1-indexed integer>, "residue": "<CCD code>"} objects.

Example

A request that runs

These are the defaults, exactly as the web form would post them.

curl -X POST https://www.athanortools.com/api/protenix/ \
  -H 'Content-Type: application/json' \
  -d '{
  "task": "sequence",
  "job_name": "protenix-demo",
  "sequence_molecules": "[{\"type\": \"protein\", \"sequence\": \"MSTNPKPQRKTKRNTNRRPQDVKFPGG\", \"cyclic\": false, \"modifications\": []}]",
  "model": "protenix-v2",
  "num_samples": 5,
  "num_seeds": 1,
  "seed": 101,
  "num_recycles": 10,
  "diffusion_steps": 200,
  "use_msa_server": false,
  "use_template": false,
  "use_rna_msa": false,
  "use_guidance": false,
  "bonds": "",
  "pocket_restraints": "",
  "contact_restraints": ""
}'

The reply is 202 with a queued job; poll its status_url until status is succeeded or failed. See the quick start for the whole exchange.

Responses

What comes back

status	Meaning
`queued`	Accepted, waiting for the jobs ahead of it. `position` counts how many those are.
`running`	The tool is executing now.
`succeeded`	Finished; `result` holds the tool's output and `license` the terms it came under.
`failed`	Finished; `error` holds a code and a message.

Errors

code	Meaning
`invalid_input`	The client supplied invalid or incomplete input.
`tool_unavailable`	The requested third-party dependency is not available on this host.
`execution_failed`	A configured third-party process exited unsuccessfully.
`internal_error`	An adapter failed in a way it does not describe. The detail is in the server log, not the response.
`not_found`	No job has that id. Finished jobs are dropped eventually.