RDKit is the foundation of open cheminformatics and ML for small molecules. It handles everything from SMILES parsing to conformer generation.

Highlights

  • Fingerprints and descriptors for QSAR and ML featurization.
  • Substructure/SMARTS search, reactions and scaffold analysis.
  • 2D depiction and 3D conformer generation.

Example

1from rdkit import Chem
2from rdkit.Chem import Descriptors
3m = Chem.MolFromSmiles("CC(=O)Oc1ccccc1C(=O)O")
4print(Descriptors.MolWt(m), Descriptors.MolLogP(m))

Related tools

Liftoff.bio illustration — cat cheminformatics
Open source

Cheminformatics & Drug Discovery

Open Babel

The chemistry toolbox for converting molecular formats

Command linePython library
Liftoff.bio illustration — cat cheminformatics
Open source

Cheminformatics & Drug Discovery

DeepChem

Democratizing deep learning for the sciences

Python library
Liftoff.bio illustration — cat cheminformatics
Open source

Cheminformatics & Drug Discovery

Datamol

A friendly, modern molecular-processing library

Python library