Core Tools & Workflows
Foundational cheminformatics tools, tutorials, and key molecular databases.
Tutorials
Practical Cheminformatics
Jupyter / Colab
Fingerprints
Clustering
SAR
Active learning
TeachOpenCADD T001-T010
Jupyter
Molecular data
Fingerprints
Similarity
RDKit Cookbook
Documentation
RDKit fundamentals
Neural Networks for Chemists
Jupyter
NN fundamentals
Chemistry
Courses
AI4Chemistry Course
Covers molecular representations, GNNs, generative models, and reaction prediction.
Molecular representations
GNNs
Generative models
Reaction prediction
Practical Programming in Chemistry
Introduction to programming for chemists: Python, Git, RDKit, data analysis workflows.
Python
Git
RDKit
Cheminformatics Teaching Material
Molecular representations, fingerprints, and computational methods.
Molecular representations
Fingerprints
Tools
Core Cheminformatics Stack
RDKit
Core toolkit — the foundation of most chemistry ML
Datamol
RDKit wrapper optimized for data science workflows
OpenBabel
Format conversion, 3D generation
CDK
Java-based toolkit
Indigo
Libraries and utilities
cinfony
Common API to cheminformatics toolkits
SELFIES
Self-Referencing Embedded Strings representation
Database Wrappers
PubChemPy
Interact with PubChem in Python
ChemSpiPy
ChemSpider wrapper for searches
chembl-downloader
Automate downloading and querying ChEMBL
NistChemPy
NIST webbook data access
Visualization
nglview
Jupyter widget to view molecular structures
py3Dmol
3D molecular visualization in Jupyter
mols2grid
Interactive molecule grids
chemiscope
Interactive structure/property explorer
Datasets
MoleculeNet
Comprehensive benchmark suite with multiple tasks
TDC
Therapeutics Data Commons — drug discovery datasets
OCHEM
3.77M records for 689 chemical properties
ChEMBL
Bioactive molecules with drug-like properties
PubChem
Chemical information from 750+ data sources (116M compounds)
Awesome Lists
Tools & libraries
Python tools
ML-ready chemistry datasets
AI for chemistry papers
Drug discovery resources
Learning resources