ExamplesStructure: Boltz-2 Affinity

Structure: Boltz-2 Affinity

Sequence-only protein–ligand structure and binding-affinity prediction using Boltz-2 v2.0.2. Provide a protein amino-acid sequence and a ligand SMILES, get back a predicted complex plus binding probability and pIC50.

What it simulates

  • Joint structure and affinity prediction from sequence-only inputs.
  • Pinned boltz[cuda]==2.0.2 driven by the upstream Boltz CLI on a GPU runner.
  • Diffusion + recycling pipeline with optional MSA via the configured server.
  • Bundled example protein and tyrosine-derivative ligand so a fresh run produces a renderable complex without setup.

Run it on the Hub

  1. Open the Boltz: Boltz2AffinityPredictor Lab on the public Hub.
  2. Click Run. The bundled defaults predict the example complex without any parameter editing.

Inputs you can tune

InputMeaning
protein_sequenceAmino-acid sequence string.
ligand_smilesSMILES string for the ligand.
msa_pathOptional path to a pre-computed MSA (.a3m). When unset and use_msa_server: true, Boltz queries the configured MSA server.
run_options.recycling_stepsRecycling iteration count.
run_options.sampling_stepsDiffusion sampling steps.
run_options.diffusion_samplesNumber of diffusion samples.
run_options.acceleratorCompute accelerator (gpu recommended; CPU is plumbing-only).

What results to expect

  • 3D structure view: predicted protein–ligand complex assembled from the top-ranked Boltz output. Sanity-check that the ligand lands in a plausible pocket on the predicted fold.
  • Affinity summary: binding probability (0–1) and predicted affinity in pIC50. Useful for ranking related candidates against the same target; less useful as absolute numbers.
  • Confidence summary: pTM and ipTM (global / interface fold confidence, 0–1) and pLDDT (per-residue confidence, 0–100). Low ipTM with reasonable pTM usually means the fold is fine but ligand placement is uncertain.
  • Run metadata: Boltz version, output directory, truncated stdout/stderr, and status: ok / status: error.

Reference

Boltz-2 v2.0.2.

Source on GitHub: models-boltz. Boltz-2 is GPU-bound: remote runs use the GPU-enabled runtime image; local runs need a CUDA device.