Application of spectrophores™ to map vendor chemical space using self-organising maps
2011
Mapping Chemical Space with Spectrophores
Sample size: 8600000
publication
Evidence: moderate
Author Information
Author(s): Thijs G, Langenaeker W, De Winter H
Primary Institution: Silicos NV
Hypothesis
Can Spectrophores™ effectively map vendor chemical space using self-organising maps?
Conclusion
The study demonstrates that vendor chemical space can be meaningfully organized using Spectrophores™.
Supporting Evidence
- Spectrophores™ are one-dimensional descriptors that represent the three-dimensional molecular field around a molecule.
- The self-organising map was trained from a large dataset of 8.6 million commercially available compounds.
- The resulting map shows meaningful organization of vendor chemical space based on Spectrophores™.
Takeaway
Scientists used a special method to group a huge number of chemicals based on their properties, helping to understand how they relate to each other.
Methodology
A self-organising map was trained using 8.6 million compounds to illustrate the capabilities of Spectrophores™.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website