Home » Notes » Datasets » Computational Chemistry Datasets

GDB-13

GDB-13: Chemical Universe Database (970M Molecules)

2025-08-16 · Hunter Heidenreich

Dataset Details
Authors	Lorenz C. Blum, Jean-Louis Reymond
Paper Title	970 Million Druglike Small Molecules for Virtual Screening in the Chemical Universe Database GDB-13
Institution	University of Berne
Published In	Journal of the American Chemical Society
Category	Computational Chemistry
Format	SMILES
Size	Molecules: 977,468,314
Date	August 2025
Year	2009
Links	📊 Dataset • 🔗 DOI • 📄 Paper

GDB-13 molecule structure showing CCCC(O)(CO)CC1CC1CN — Example GDB-13 molecule demonstrating the expanded chemical space with up to 13 atoms

Key Contribution

The main contribution is the creation and release of the 977.4 million-compound GDB-13, a massive expansion in molecular size (up to 13 atoms) and elemental diversity (including S and Cl) made possible by key algorithmic optimizations that significantly accelerated the enumeration process.

Dataset Information

Format

SMILES

Size

Type	Count
Molecules	977,468,314

Dataset Examples

Example GDB-13 molecule (SMILES: CCCC(O)(CO)CC1CC1CN)

Strengths

Systematic coverage of structures with up to 13 atoms
High drug-likeness: 100% Lipinski compliance
Structural novelty

Limitations

Limited to small molecules with up to 13 atoms of C, N, O, S, and Cl
Excludes highly strained molecules and some bond patterns
Excludes functional groups and highly polar molecules
Computer-generated structures, not experimentally validated compounds

Technical Notes

Differences from GDB-11

A fast elemental filter is used to auto reject structures, informed by analysis of extant molecular databases
Fluorine is removed from the list of allowed elements; sulfur and chlorine are added
MM2-based structure optimization is replaced with much faster geometry-based optimization

Related Datasets

Dataset	Relationship	Link
GDB-11	Predecessor	📄 View Details
GDB-17	Successor	📄 View Details