Run Proteina-Complexa online

Pick Proteina-Complexa when you want de novo binders against a protein OR a small-molecule (ligand) target, scored by a full AF2 / RF3 / force-field reward stack, and you want to scale the search across many GPUs with the wallet as the only ceiling.

Proteina-Complexa (Geffner et al., NVIDIA 2025). A flow-matching generator wrapped in an inference-time search that filters designs through an AlphaFold2 / RoseTTAFold3 / force-field reward stack. It designs de novo binders against protein targets, small-molecule (ligand) targets, and enzyme / motif active sites. Runs here as a fund-and-drain campaign of independent seeded search shards, with global cross-shard top-K and post-hoc diversity clustering.

When it fits:

• You want de novo binders against a small-molecule target, not just a protein.
• You want an inference-time search filtered by an AF2 / RF3 / force-field reward, not raw generation.
• You want to scale the search across many GPUs with the prepaid wallet as the only ceiling.
• You want diverse high-reward designs (global top-K + diversity clustering) rather than near-duplicates.

Use the score legend below to read results. Each tool reports a subset of these depending on whether it does design, sequence recovery, or structure prediction.

ipTM

Predicted confidence in the binder to target interface. Higher is better. Aim above roughly 0.7 on a tractable target.

pLDDT

Per-residue confidence in the predicted fold. Higher means the model is more sure of that part of the structure.

i_pAE and pAE

Predicted alignment error, at the interface (i_pAE) or across the whole structure (pAE). Lower is better.

ProteinMPNN recovery

Fraction of native residues recovered when ProteinMPNN redesigns a known sequence on its native backbone. Higher is better; well calibrated above roughly 0.4 on diverse folds.

30 to 120 min to 1 to 3 min per run on a dedicated GPU. You pay only for the compute a job delivers, drawn from your wallet balance.

Can I run Proteina-Complexa online without a GPU cluster?

Yes. Ranomics Tools runs Proteina-Complexa as a fund-and-drain campaign of independent search shards on dedicated A100-80GB GPUs. Pick a protein or small-molecule target, choose how many designs you want, and shards fan out automatically. You only pay for compute that runs, and the campaign pauses if your balance runs low.

Can Proteina-Complexa design binders against a small molecule?

Yes. The ligand-binder variant takes a small-molecule target as an SDF and designs de novo binders scored by the RoseTTAFold3 reward. The protein-binder variant targets a protein PDB and is scored by AlphaFold2 confidence.

How are Proteina-Complexa designs scored and ranked?

Each search shard filters candidates through an AF2 / RF3 / force-field reward stack, and the hub then selects a global top-K across all shards with post-hoc structural diversity clustering, so you get diverse high-reward designs rather than near-duplicates.

Geffner et al., NVIDIA (2025)