Bridging Basic Chemistry and Cheminformatics: Jupyter-based Modules on Molecular Representation for Introductory Chemistry

Author: Prof. Kevin P. Greenman, Ph.D. (Catholic Institute of Technology, MolSSI ACT-CMS Faculty Fellow 2024-2026)

Note: These materials are under development and will be first piloted in a course in Fall 2025.

Learning Objectives

Predict the molecular geometry of simple molecules using VSEPR theory.
Describe hybridization and determine sp, sp², sp³, sp³d, and sp³d² states.
Identify and differentiate between ionic and covalent bonds based on electronegativity differences and electron transfer/sharing mechanisms.
Translate between chemical representations (formula, SMILES, graph, geometry, conformers).
Choose the appropriate representation for a given task and justify the choice.

Read and write chemical data as SMILES + property values from CSV using pandas.
Clean and visualize chemical datasets using pandas, RDKit, and other Python operations.
Use Colab GPU resources to train a basic Chemprop (graph neural-network) model.
Visualize ML regression results with matplotlib.

This work was supported by the MolSSI ACT-CMS Faculty Fellowship program, funded by the Office of Advanced Cyberinfrastructure (OAC) NSF Award OAC 2321044.

Name		Name	Last commit message	Last commit date
Latest commit History 19 Commits
colab-notebooks		colab-notebooks
images		images
.gitignore		.gitignore
1-chemistry_visualisation.ipynb		1-chemistry_visualisation.ipynb
2-conformers.ipynb		2-conformers.ipynb
3-digital_chemistry_representations.ipynb		3-digital_chemistry_representations.ipynb
4-hybridisation.ipynb		4-hybridisation.ipynb
5-vsepr_geometry.ipynb		5-vsepr_geometry.ipynb
6-bond_types.ipynb		6-bond_types.ipynb
7-chemistry_data.ipynb		7-chemistry_data.ipynb
8-chemprop_machine_learning.ipynb		8-chemprop_machine_learning.ipynb
LICENSE		LICENSE
README.md		README.md
environment.yml		environment.yml
lewis-test.ipynb		lewis-test.ipynb