Hands-on Tutorials

13 coding sessions on Google Colab — from molecular fingerprints and GNNs to Bayesian optimization and chemistry agents. Click any card to open the tutorial.

Week 1 · Foundations of ML & Representations

Tutorial
Molecular Property Prediction
Building a pipeline using RDKit, feature engineering, training and performance evaluation
Jules Schleinitz
Open in Colab →
Tutorial
Model Training & Performance Evaluation
Train/val/test splitting, data leakage, chemically-relevant splits, baselines
S. Wahler
Open in Colab →
Tutorial
Neural Networks in Practice
MLP layers, backpropagation, learning curves, and fixed held-out test evaluation
Jules Schleinitz
Open in Colab →
Tutorial
Machine Learning Interatomic Potentials
Train & test a MACE potential on molecular liquids, then model water's density and try to freeze/boil it
Madeline Murphy | A. Gurajapu
Open in Colab →
Tutorial
Explaining ML Predictions
Permutation importance, ICE/PDP, SHAP, and LIME on a blood–brain barrier model
Michael Yusov
Open in Colab →
Tutorial
Few-Shot Learning
Transfer learning, application, failure modes of limited-data regimes
Jules Schleinitz
Open in Colab →
Tutorial
Molecular Generation
Encode/decode molecules, latent space exploration, validity checks
Jules Schleinitz
Open in Colab →

Week 2 · Dataset Design & LLMs

Tutorial
Data Stewardship
Organizing research data, metadata standards, and reproducible sharing practices
Alix Schmidt
Open in Colab →
Tutorial
Design of Experiments in Practice
Factorial screening, response surface setup, and experiment planning workflows
Alix Schmidt
Open in Colab →
Tutorial
Active Learning on DFT Descriptors
8,528 carboxylic acids, Chemprop D-MPNN, 600-label budget, hidden test set
Jules Schleinitz
Open in Colab →
Tutorial
Reaction Yield Optimization with BO
Suzuki coupling dataset, BoTorch, EI vs. UCB convergence comparison
Jules Schleinitz
Open in Colab →
Tutorial
Chemistry RAG Assistant
Index papers, Q&A on reactions, RDKit tool calls
S. Wahler
Open in Colab →
Tutorial
Does This Chemistry Task Need an LLM?
Manual parser vs. LLM predictor vs. self-optimizing DSPy Flex
B. Reiner | J. Wade
Open in Colab →