How to use Boltz: what you can do with it

3 use cases

• Predict a protein complex structure with Boltz

  Describe your biomolecules in a YAML file and let Boltz predict the structure of the complex.

  • REPO jwohlwend/boltz
  • Claude Code
  • Codex
  • Cursor
  • Gemini CLI
  • Security and science
  • Intermediate
  View prompt

  Using jwohlwend/boltz, install it in a fresh environment, write an input YAML for <protein sequences and ligands> following docs/prediction.md, and run `boltz predict input_path --use_msa_server`. Tell me where the predicted structures were written.

  Share Email me this

• Screen small molecules for likely binders

  Use Boltz-2's affinity output to separate likely binders from decoys in a hit-discovery screen.

  • REPO jwohlwend/boltz
  • Claude Code
  • Codex
  • Cursor
  • Gemini CLI
  • Security and science
  • Advanced
  View prompt

  With jwohlwend/boltz, build a directory of YAML inputs pairing <target protein> with each ligand in <list>, requesting affinity, and run `boltz predict input_path --use_msa_server` on it. Rank the ligands by affinity_probability_binary.

  Share Email me this

• Compare small changes to a lead molecule

  Use affinity_pred_value to see how small modifications change predicted binding during hit-to-lead work.

  • REPO jwohlwend/boltz
  • Claude Code
  • Codex
  • Cursor
  • Gemini CLI
  • Security and science
  • Advanced
  View prompt

  Using jwohlwend/boltz, predict affinity for my lead compound <SMILES> and these analogs <list> against <target>, then make a table of affinity_pred_value per analog with a note on which modifications helped.

  Share Email me this

Quick start with Boltz

1. Check you have what it needs: Python in a fresh environment and pip; An NVIDIA GPU for the [cuda] install; CPU-only works but is significantly slower; Input YAML files describing the biomolecules (format in docs/prediction.md).
2. Open jwohlwend/boltz on GitHub and read the README and license.
3. Create a fresh Python environment, as the README recommends
4. Install with pip install boltz[cuda] -U (drop [cuda] on CPU-only or non-CUDA GPU hardware)
5. Write an input YAML file describing the biomolecules you want to model, following docs/prediction.md
6. Run boltz predict input_path --use_msa_server with input_path pointing at the YAML file

These steps come from our top use case, Predict a protein complex structure with Boltz, which also has a copy-paste agent prompt.

Using the Deduped MCP, get the setup steps for jwohlwend/boltz

claude mcp add --transport http deduped https://dedupedai.com/mcp

Best AI repos for Security and science

About this repo

• Who it is forComputational biologists, structural biologists and drug discovery teams who want open structure and binding affinity predictions they can run themselves.
• Why it is hot4.3k stars, talked about in 2 AI sources we track
• LanguagePython
• Sourcegithub.com/jwohlwend/boltz · Back to Hot repos

Requirements

• Python in a fresh environment and pip
• An NVIDIA GPU for the [cuda] install; CPU-only works but is significantly slower
• Input YAML files describing the biomolecules (format in docs/prediction.md)
• Network access for the optional MSA server (--use_msa_server)

Related repos

• Trended earlier REPO sokrypton/ColabFold Colab Fold ColabFold makes protein structure prediction accessible through Google Colab notebooks for AlphaFold2 with MMseqs2, AlphaFold3 (OpenFold3), ESMFold, batch runs and beta models such as RoseTTAFold2, Boltz and BioEmu. It also runs locally: colabfold_search builds multiple sequence alignments against the ColabFold databases (with optional GPU-accelerated MMseqs2-GPU search) and colabfold_batch predicts structures, and both can export MSAs as AlphaFold3-compatible JSON.
• Trended earlier REPO google-deepmind/alphafold3 Alphafold3 AlphaFold 3 is Google DeepMind's inference pipeline for predicting the structure of biomolecular complexes. You describe the complex in a JSON input file and run run_alphafold.py, usually inside the provided container, with separate flags for the CPU heavy data pipeline and the GPU inference step. Model parameters are not in the repo: you must request them from Google and follow their terms of use.
• Trended earlier REPO Biohub/esm Esm The esm package from Biohub (EvolutionaryScale) ships ESMC, a protein language model trained on billions of protein sequences, ESMFold2, a structure prediction model built on ESMC 6B that predicts all atom 3D structures from sequence, and sparse autoencoders that decompose ESMC representations into interpretable features. Models run locally from Hugging Face weights or through the Biohub Platform with an API token.