Freedom Space

Diving into the Freedom Space

The Freedom Space was created by Chemspace with the aim to provide an ultra-large collection of synthetically accessible molecules designed to facilitate hit discovery workflows.
To create the latest version of Freedom Space (4.0), our partners at Chemspace selected building blocks from reliable suppliers, prioritizing price and lead time.
Using 40 chemical transformations, Chemspace have designed custom SMARTS patterns to preselect building blocks that are suited for each reaction. Machine-learning-based (ML-based) filters refined these pools for high synthesizability, leading to high-quality synthons.
The approach has led to synthesis success rates as high as 80% and beyond.

Traits
  • Innovative ML-based filtering of building blocks
  • High chemical diversity
  • Synthetic accessibility
  • Fast delivery
Download
1.4 x 1011
Freedom Space

Diversity by Design

The Freedom Space features 40 reaction protocols of two- and three-component reactions to expand the variety of relevant compounds. Chemical diversity is achieved through functionally diverse building blocks as well as by robust key medicinal chemistry reactions such as amide formation, condensation, arylation, reductive amination, urea formation, and Suzuki couplings.

A Valuable Resource for Various Needs

Of the 142 billion compounds in the Freedom Space, two subsets were further analyzed in detail. These include molecules that comply with the Rule-of-Five (Ro5) as well as those belonging to the "beyond Ro5" (bRo5) category. The latter has been gaining increasing attention and popularity in recent years, making it the perfect resource for tangible chemistry in such scenarios.

The numbers below are valid for version 4.0 (February, 2025)
20 billion Ro5 compounds
  • MW: up to 500
  • H-bond donors: up to 5
  • H-bond acceptors: up to 10
  • logP: ≤ 5
68 billion beyond Ro5 compounds
  • MW: up to 800 (excluding the Ro5 compounds)
  • H-bond donors: up to 8
  • H-bond acceptors: up to 15
  • logP: ≤ 6
  • Rotatable bonds: up to 15

Innovational Machine-Learning-Based Filters

Achieving high synthesizability from a space requires selecting building blocks that perform well in reactions they undergo. Traditionally, this has been accomplished through iterative experiments and detailed documentation.
In the case of the Freedom Space, this process has now been automated using machine learning, combined with synthesis success data from past years of REAL Space operations.

This approach employs a custom synthon building block representation during training, enabling the model to accurately process building blocks that share the same synthons but differ in functional groups. Each building block pool is filtered by a dedicated model, resulting in the use of over 80 models for the creation of the new combinatorial Chemical Space.
Access with infiniSee

Access with infiniSee

The Freedom Space can be conveniently explored using BioSolveIT's Chemical Space navigation platform, infiniSee. Billions of entries can be searched for relevant chemistry within seconds. Various search algorithms are available to identify the best matches for the objectives of a drug discovery project.
Check out infiniSee
Want to Take It Into the 3D World?

Want to Take It Into the 3D World?

Chemical Space Docking™ also enables structure-based screening of the Freedom Space within your target of interest. Executed within our drug design dashboard SeeSAR, molecules forming the most favorable interactions in the binding site can be efficiently mined on standard hardware, and without a connection to the internet.

This allows in-house projects to be streamlined without the involvement of third parties; you will work in a user-friendly environment with full control over your results.
Read about C-S-D

Eager to learn more?

More details on Freedom Space