This repository contains notebooks presentd at the MERCURY 2024 conference.
There are many options to run these notebooks. We recommend using JupyterLab instead of Jupyter notebook.
This repository is set up to run in a GitHub CodeSpace. Click the green "Code" button on this repository and choose "CodeSpaces". This will open a VSCode environment in GitHub CodeSpaces. Usage will be billed to your personal account, however, GitHub gives some free codespace hours to all accounts each month.
These notebooks are all compatible with chemcpompute.org.
An environment.yml file is included that you can use to create a conda environment for the notebooks if you have the conda package manager installed.
| Time | Topic | Notebook(s) |
|---|---|---|
| 9:30 AM - 10:45 AM | Introduction to molecular representations | 01_molecule_representation |
| 10:45 AM - 11:00 AM | Break | |
| 11:00 AM - 12:00 PM | Introduction to RDKit molecules | 02_rdkit_intro |
| 12:00 PM - 1:30 PM | Lunch | |
| 1:30 PM - 2:15 PM | Cheminformatics: Molecular Similarity Measures | 03_molecular_similarity |
| 2:15 PM - 3:00 PM | Cheminformatics: Molecular Descriptors | 03_molecular_similarity |
| 3:00 PM - 3:30 PM | Snack Break | |
| 3:30 PM - 4:45 PM | Exercise: Building a Dataset using RDKit | 04_RDKit_dataset |
| Time | Topic | Notebook(s) |
|---|---|---|
| 9:00 AM - 10:30 AM | Python Data Science Libraries: Pandas and Seaborn | 05_pandas_seaborn |
| 10:30 AM - 10:45 AM | Break | |
| 10:45 AM - 11:45 AM | Model Fitting with SciKit Learn: Part 1 | 06_sklearn_fitting_1 |
| 11:45 AM - 1:00 PM | Lunch | |
| 1:00 PM - 3:00 PM | Model Fitting with SciKit Learn: Part 2 | 07_ESOL_fitting |
| 3:00 PM - 3:30 PM | Snack Break | |
| 3:30 PM - 3:45 PM | Closing |
Exercise for Python Data Science Libraries is to load the file we wrote for the homework/wrap up yesterday and visualize the relationships using Seaborn.