Protenix

What is Protenix?

Protenix is ByteDance Research's open-source biomolecular structure prediction model. It predicts 3D structures of complexes containing proteins, DNA, RNA, small molecule ligands, and metal ions from sequence or structural inputs, all in a single run.

Protenix follows the AlphaFold 3 all-atom structure-prediction architecture. ProteinIQ runs the Protenix v1 base checkpoint by default, with additional base, constraint, mini, and tiny variants available for comparison or faster exploratory runs.

How to use Protenix online

ProteinIQ runs Protenix on GPU infrastructure with no local installation. Add one or more molecules, optionally configure seeds and model, then submit. Results arrive as downloadable CIF files ranked by confidence score, viewable directly in the 3D structure viewer. Each ranked prediction also includes the Protenix summary-confidence JSON, and you can optionally export atom-level confidence JSON for deeper inspection. MSA search is off by default; enabling it can add several minutes but may improve protein predictions that benefit from evolutionary context.

Inputs

Each molecule is added as a separate entity. Up to 10 entries of each type are supported.

Input	Accepted formats
Protein	FASTA sequence, PDB file, or 4-letter RCSB PDB ID
Ligand	SMILES string, CCD code (e.g. ATP), SDF/MOL file, or PubChem compound ID
DNA	FASTA sequence (A, T, G, C)
RNA	FASTA sequence (A, U, G, C)
Ion	CCD code (e.g. ZN, MG, CA, FE)
Paired MSA	Optional uploaded or pasted .a3m alignment attached to a protein chain label
Unpaired MSA	Optional uploaded or pasted .a3m alignment attached to a protein chain label
RNA MSA	Optional uploaded or pasted .a3m alignment attached to an RNA chain label

For ligand files, Protenix requires a 3D conformer. 2D SDF files (flat structure with no z-coordinates) will fail at featurization.

Precomputed alignments attach to the chain letters shown on the main protein or RNA molecule cards. If there is only one eligible protein or RNA chain, you can leave the MSA target label blank and ProteinIQ will attach it automatically. Paired MSA and Unpaired MSA are separate native inputs; RNA only supports unpaired RNA-MSA in this pass. Template files are still out of scope here.

Settings

Setting	Description
Model seeds	Number of random seeds (1-5, default 1). Each seed independently samples the diffusion trajectory and produces a distinct set of structures.
Model	Model variant. Protenix v1 base is the default. See model options below.
Use MSA	Whether to run multiple sequence alignment for protein chains (default off). Adds 2-5 minutes but can improve accuracy, especially for proteins with many homologs.
Samples per seed	Structures generated per seed (1-5, default 5). Higher values increase output diversity.
Training-Free Guidance	Applies physical constraints (steric, torsion, distance) during diffusion sampling to improve geometric plausibility. Off by default; adds compute overhead.
Export atom confidence JSON	Saves the full_data JSON for each prediction. Useful for debugging or downstream analysis, but larger than the default summary metrics.

Model options

Model	Parameters	Training cutoff	When to use
Protenix v1 base	368M	2021-09-30	Default model for general structure prediction.
Protenix v1 base (2025 data)	368M	2025-06-30	Targets with templates deposited after 2021.
Protenix mini	135M	2021-09-30	Rapid screening, large sequences, or quick estimates before a full run. Roughly 40% faster.

How does Protenix work?

Protenix implements the AlphaFold 3 architecture, which replaces the iterative refinement of AlphaFold 2 with a diffusion-based structure generation process. Prediction starts from randomly initialized atom coordinates and progressively denoises them into a coherent structure over multiple cycles.

Multiple Sequence Alignment

For protein inputs, Protenix queries external MSA databases to find evolutionarily related sequences. Conserved residues and co-evolving residue pairs reveal spatial constraints that guide the structure prediction. The MSA step connects to an external server and is the primary source of runtime variability, typically adding 2-5 minutes per prediction.

If you already have alignments, ProteinIQ can use precomputed .a3m files instead of forcing a new search. Protein chains can receive separate paired and unpaired MSAs, while RNA chains can receive an unpaired RNA-MSA. These uploads are written to temporary files and referenced through the pairedMsaPath and unpairedMsaPath JSON fields used by Protenix.

Confidence estimation

Protenix outputs per-atom and per-residue confidence estimates derived from the same network that produces the structure. These are not validated against experimental data for each prediction; they reflect the model's internal consistency. A high-confidence prediction that matches an incorrect prior (e.g. a homolog with a different binding mode) may score well while being physically wrong.

Understanding the results

Protenix outputs ranked CIF files together with the native summary-confidence JSON for each prediction.

Metric	Scope	Interpretation
pLDDT	Per-residue, 0-100	>90: high confidence. 70-90: backbone likely correct. 50-70: low confidence. <50: likely disordered or unreliable.
pTM	Whole structure, 0-1	>0.5 suggests the overall fold is correct.
ipTM	Inter-chain interfaces, 0-1	>0.7 indicates a reliable interface prediction. Particularly relevant for protein-protein and protein-ligand complexes.

ProteinIQ also preserves the additional native metrics and flags from summary_confidence, including ranking_score, gpde, per-chain confidence summaries, pairwise interface scores, clash flags, disorder estimates, and the recycle count used for the prediction.

When running multiple seeds, structural agreement across the top-ranked predictions is a better indicator of reliability than any single confidence score. Divergent predictions across seeds suggest the structure is genuinely uncertain.

When to use Protenix vs alternatives

The main differences are molecule scope, evolutionary inputs, guidance options, and whether the result describes one structure, an ensemble, or binding affinity.

Tool	Best for	Key distinction
Protenix	General all-atom complexes	Multiple model sizes, protein and RNA MSAs, optional atom confidence; no affinity prediction or user restraints.
Boltz-2	Protein-ligand structure and affinity	Returns binder probability and affinity estimates; supports templates, constraints, and CCD covalent bonds.
Chai-1	Guided complex prediction	Combines MSA and template search with contact, pocket, and modified-residue inputs.
OpenFold 3	Open AlphaFold 3 research workflows	Trainable research preview with automatic MSA generation and low-memory inference.
RosettaFold3	Alternative all-atom complex prediction	Handles proteins, DNA, RNA, and ligands with multi-model sampling.
IntelliFold 2	Fast multi-component prediction	Offers a fast Flash model, optional MSA generation, and ranked complex structures.
AlphaFold2	Protein monomers and multimers	Established protein-only workflow with single-sequence or MSA-assisted prediction.
ESMFold2	Protein chains and protein complexes	Language-model folding with no MSA search and optional PAE and pair-chain ipTM outputs.
ESMFold	Rapid single-sequence protein folding	Predicts protein structures without an MSA and returns PDB, pLDDT, and optional PAE.
AlphaFlow	Protein conformational ensembles	Samples multiple structures to represent flexibility rather than one static prediction.
HighFold	Cyclic peptide structures	Models head-to-tail cyclization and disulfide constraints with an AlphaFold2-derived method.

Protenix is a strong default for unconstrained complexes containing several molecule types. Boltz-2 is the clearer choice for ligand affinity or pocket guidance, while Chai-1 is useful when templates, known contacts, or modified residues should influence the model.

Folding models predict structures from sequences and chemical inputs. For docking into a prepared receptor, AutoDock Vina searches a defined box and reports scores in kcal/mol, while DiffDock predicts ligand poses without a predefined box.