Skip to main content
The Sandbox is the best place to start running your first predictions in Boltz Lab. Here, you can quickly test hypotheses, validate binding poses, explore protein structures - all in a private workspace where you can experiment freely before committing to larger screening campaigns. Image

​
Why Use Sandbox?

Quick Validation

Test a binding hypothesis in minutes

Full Flexibility

Iterate quickly setting different constraints

Private by Default

Your predictions are visible only to you

​
What Can You Predict?

Sandbox supports the prediction of the structure of arbitrary biomolecular complexes. Common use cases include:
System TypeExample Use Cases
Protein-LigandValidate docking poses, predict binding modes, assess ligand affinity
Protein-ProteinModel complex interfaces, predict interaction sites
Protein-RNA/DNAExplore nucleic acid binding proteins
Apo StructuresPredict protein conformations
Covalent BindersModel irreversible inhibitors with bond constraints
Sandbox is ideal for one-off predictions - validating a single compound, checking a crystal structure hypothesis, or exploring a new target before setting up a full Design Project.

​
Your Prediction History

Image All your Sandbox predictions are stored and searchable. Use the table view to:
  • Search predictions by name
  • Filter by status or date
  • Sort columns to find what you need
  • Duplicate previous predictions as starting points
Image Hover over any row to display the three-dot menu for quick actions:
  • Duplicate prediction - Clone all inputs to start a new prediction
  • Download results - Export structures and data for offline analysis

​
What’s Next?

Submit Your First Prediction

Step-by-step guide to creating predictions

Understanding Results

Interpret confidence scores, view structures, and analyze binding