Fastfold | Docs
Sign In
  • Home
  • Getting Started
    • Quickstart
    • News & Updates
  • LEARN ABOUT
    • Features
      • 1. Fold sequences
      • Steps - Fold
      • Results - Fold
      • 2. Properties prediction
      • Steps - Properties
      • Results - Properties
      • 3. Generation
      • Steps - Generation
      • Results - Generation
    • Use cases - Features
    • Aura
    • Use cases - Aura
    • Models
    • Glossary of terms
      • Predicted template modelling score (pTM)
      • Interface predicted template modelling (ipTM)
      • Predicted local distance difference test (pLDDT)
      • Predicted aligned error (PAE)
    • Account
  • Community & Support
Powered by GitBook
On this page

Was this helpful?

  1. LEARN ABOUT

Features

PreviousQuickstartNext 1. Fold sequences

Last updated 3 months ago

Was this helpful?

Fastfold enables the combination of its core capabilities—protein folding, property prediction, and structure generation—to adapt to various research use cases. By integrating these functions, users can optimize their workflows, exploring new strategies for biomolecular design and analysis.

This flexibility is key to addressing multiple scenarios in bioscientific research.

For example, a user can generate new structures with the De Novo Generation module, validate their stability through Properties Prediction, and then refine the design by adjusting the folding with Fold Proteins. By combining these capabilities, researchers can identify structural patterns, assess the impact of modifications, and accelerate the selection of optimal biomolecules for various applications, from designing therapeutic proteins to engineering enzymes.

This not only enhances workflow efficiency but also facilitates the discovery of new scientific applications by enabling continuous iteration between prediction, generation, and validation of biomolecular structures.

Below, you will find a detailed guide with all the features and key considerations of the Fold feature.

To become proficient with the tool, it's best to learn how to use each feature both manually and through automation with This will improve adoption and optimize the path to more efficient and accurate results.

Aura.