alterlab-boltz

Featured

Co-fold biomolecular complexes with Boltz-2, an open AlphaFold3-style model — predict protein + ligand (SMILES/CCD), protein + nucleic-acid, and multi-chain structures in one pass, with binding-affinity prediction. Use when folding a protein together with a small-molecule ligand, predicting a holo (ligand-bound) complex or its binding affinity, or co-folding protein–DNA/RNA assemblies. For protein-only or protein–protein folding without ligands prefer alterlab-alphafold; for antibody–antigen complexes prefer alterlab-chai; to dock a ligand into a FIXED receptor structure prefer alterlab-diffdock; to look up an existing structure prefer alterlab-pdb. Part of the AlterLab Academic Skills suite.

AI & Automation 68 stars 13 forks Updated 3 days ago MIT

Install

View on GitHub

Quality Score: 91/100

Stars 20%
61
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Boltz-2 (open AlphaFold3-style co-folding) ## Overview **Boltz-2** (Passaro, Wohlwend et al. 2025; `jwohlwend/boltz`) is an open, commercially usable biomolecular structure model in the AlphaFold3 family: it **co-folds** proteins together with small-molecule **ligands**, nucleic acids, and multiple chains in a single prediction, and can predict **binding affinity** — capabilities AlphaFold2/ColabFold does not have. Use it when the biology is a *complex with a ligand or other molecule types*, not a bare protein. ## When to Use This Skill Use this skill when the user wants to: - Co-fold a protein **with a small-molecule ligand** (SMILES or CCD code) into a holo complex. - Predict a **binding affinity** alongside a co-folded pose. - Fold **protein–nucleic-acid** or multi-entity assemblies in one pass. - Get an open AlphaFold3-style prediction without proprietary access. ### Does NOT Trigger | Scenario | Use instead | |----------|-------------| | Protein-only or protein–protein folding, no ligand | `alterlab-alphafold` | | Antibody–antigen / general one-FASTA multi-entity complex | `alterlab-chai` | | Dock a ligand into an **existing, fixed** receptor structure | `alterlab-diffdock` | | Retrieve an experimentally determined structure | `alterlab-pdb` | | Design a binding-pocket sequence around a ligand | `alterlab-ligandmpnn` | ## Core Capabilities ### 1. Protein + ligand co-folding Describe the complex in a YAML spec (chains + ligand by SMILES or CCD), then predict: ...

Details

Author
AlterLab-IEU
Repository
AlterLab-IEU/AlterLab-Academic-Skills
Created
6 months ago
Last Updated
3 days ago
Language
Python
License
MIT

Integrates with

Bundled in these plugins

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Featured

alterlab-alphafold

Predict protein 3D structures with AlphaFold2 via ColabFold — MMseqs2-accelerated MSAs, monomer and AlphaFold2-Multimer complex folding, and confidence-based validation (pLDDT, pTM/ipTM, PAE). Use when folding a protein sequence or complex from FASTA, generating a predicted structure with confidence metrics, ranking models, or checking self-consistency of a design. For co-folding a protein WITH a small-molecule ligand or predicting binding affinity prefer alterlab-boltz; for antibody–antigen or one-FASTA multi-entity complexes prefer alterlab-chai; to LOOK UP an already-computed structure prefer alterlab-alphafold-db; for ESM embeddings or inverse folding prefer alterlab-esm. Part of the AlterLab Academic Skills suite.

68 Updated 3 days ago
AlterLab-IEU
AI & Automation Featured

alterlab-chai

Predict biomolecular complexes with Chai-1, an open AlphaFold3-style model that folds multi-entity assemblies (proteins, ligands, nucleic acids) from a single typed FASTA — strong on antibody–antigen and protein–ligand complexes, with optional MSA and restraint inputs. Use when predicting an antibody–antigen complex, folding a mixed protein/ligand/nucleic-acid assembly described in one FASTA, or generating a complex with experimental restraints. For binding-affinity prediction or a ligand-focused co-fold prefer alterlab-boltz; for protein-only or protein–protein folding prefer alterlab-alphafold; to dock into a fixed receptor prefer alterlab-diffdock. Part of the AlterLab Academic Skills suite.

68 Updated 3 days ago
AlterLab-IEU
AI & Automation Featured

alterlab-diffdock

Predicts protein-ligand binding poses with DiffDock diffusion-based molecular docking from PDB structures and SMILES, producing pose confidence scores for virtual screening and structure-based drug design. Use when docking ligands into a protein, generating binding poses, or screening compounds against a target; not for binding affinity prediction. Part of the AlterLab Academic Skills suite.

68 Updated 3 days ago
AlterLab-IEU