internscience/scp/boltz2-binding-affinity
Trust tier 2
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Predict protein-ligand binding affinity using Boltz-2 model to assess molecular interactions and binding probability for drug discovery.
Install
npx vskill@latest install internscience/scp/boltz2-binding-affinitySKILL.md
Boltz-2 Protein-Ligand Binding Affinity Prediction
Usage
1. MCP Server Definition
2. Boltz-2 Binding Affinity Workflow
This workflow predicts protein-ligand binding affinity using the Boltz-2 deep learning model, providing affinity probabilities and 3D complex structures.
Workflow Steps:
- Prepare Input - Define protein sequence and SMILES list for ligands
- Run Boltz-2 Prediction - Calculate binding affinity probability for each ligand
- Analyze Results - Extract affinity scores and structure files
Implementation:
Tool Descriptions
DrugSDA-Model Server:
boltz_binding_affinity: Predict protein-ligand binding affinity using Boltz-2- Args:
protein(list): List of protein chains with sequence information- Each chain:
{'chain': str, 'sequence': str} smiles_list(list): List of ligand SMILES strings- Returns:
boltz_res(list): List of binding predictionssmiles(str): Ligand SMILES stringaffinity_probability(float): Binding affinity probability (0-1)cif_file(str): Path to predicted complex structure
Input/Output
Input:
protein: List of protein chainschain: Chain identifier (e.g., 'A', 'B')sequence: Amino acid sequence in single-letter codesmiles_list: List of SMILES strings for ligand molecules
Output:
- List of binding predictions, each containing:
smiles: Ligand SMILES stringaffinity_probability: Binding probability (0-1, higher is better)cif_file: Path to predicted protein-ligand complex structure in CIF format
Affinity Interpretation
- Probability > 0.5: Strong binding likelihood
- Probability 0.3-0.5: Moderate binding potential
- Probability < 0.3: Weak or no binding expected
Use Cases
- Virtual screening of compound libraries
- Lead optimization in drug discovery
- Protein-ligand binding mode prediction
- Structure-based drug design
- Comparative binding analysis across ligands
Performance Notes
- Execution time: 30-120 seconds per ligand depending on protein size
- Protein length: Best for proteins <1000 amino acids
- Multiple ligands: Processes sequentially, allow sufficient time
- Structure output: CIF files can be visualized in PyMOL, ChimeraX, or similar tools
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/boltz2-binding-affinity/SKILL.md
Popularity
- Repository stars
- 150
- Repository forks
- 10
- 7-day trend score
- 25
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 19 Mar 2026, 7 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/internscience/scp/boltz2-binding-affinity)