About Artificial Intelligence:

Artificial Intelligence (AI) is transforming the way we understand and interact with the world. It mimics human intelligence to solve complex problems, make predictions, and automate processes. From analysing massive datasets to recognizing patterns and optimizing systems, AI is at the forefront of scientific and technological advancement. In the context of Chemistry, AI enables smarter simulations, more accurate measurements, and deeper insights into the fundamental laws of nature.

About the Course – AI in Chemistry:

AI in Chemistry is an engaging and hands-on course that introduces undergraduate science students to the powerful world of AI as applied in various branches of chemistry. You’ll learn how to use tools like Python, RDKit, and Chemprop to predict molecular properties, design drugs, model reactions, and much more. The course combines theory with real-world datasets and interactive lab activities.

Who Should Join:

Science enthusiasts curious about the intersection of chemistry and AI

Learners with basic programming and chemistry background, eager to apply AI to solve real-world problems in the chemical domain

No prior experience in AI is required—just curiosity, passion, and a willingness to experiment with data and molecules!

Undergraduate students of B.Sc. (Chemistry, Physics, Computer Science, or related fields)

AI in Chemistry + Python - Overview

Week 1 — Chemistry Concepts & AI Tools

1. AI for Chemical Concepts & Visualisation — Workshop
2. Reaction Balancing & Numericals with AI — Lab + Worksheet
3. Spectroscopy Interpretation (AI-Assisted) — Activity
4. Lab Safety SOPs & AI-Generated Protocols — Exercise
5. Project Selection & Dataset Preparation — Planning Session

Week 2 — Python + RDKit in Colab

6. Python Basics for Chemists — Notebook (variables, loops, functions, CSV import)
7. RDKit: Molecules, SMILES, Properties — Notebook (draw molecules, compute MW)
8. Plotting Spectra with Pandas & Matplotlib — Notebook (IR/UV/NMR plotting)
9. Small ML: Property Prediction (scikit-learn) — Notebook (simple regression/classifier)
10. Final Mini-Project: Demo & Report — Project Submission + Peer Review

Suggested Colab Notebooks (host links):

• Intro_Python_for_Chemists.ipynb
• RDKit_Molecules_and_SMILES.ipynb
• Spectra_Analysis.ipynb
• QSAR_demo.ipynb

Learning Outcomes:

• Apply AI tools to chemistry education across levels (Class 10 → PG)
• Use Python & RDKit for molecular representations and simple computational tasks
• Visualise and interpret spectroscopy data programmatically
• Build and evaluate a small ML model for a chemical property