CHEM 487/542

Chemical Data Science

Chemical Data Science is designed for students and researchers from a broad range of backgrounds. The lectures give a careful explanation of technical details for people who want to understand or develop methods, while the hands-on sessions emphasize practical applications so you can use data science and machine learning in chemistry without needing every derivation on day one.

Lectures Theory and algorithms

Concepts, derivations, model assumptions, and technical depth.

Hands-on Practical applications

Coding, chemical datasets, model training, prediction, and interpretation.

CHEM 487/542 Chemical Data Science course logo
Offering

Offered every spring semester.

Format

Lectures and hands-on computational lab sessions.

Support

Supported by NAIRR Classroom, No. NAIRR250481.

Evaluation

20%

Class participation, including attending lectures and hands-on sessions and actively asking questions.

50%

Hands-on assignments with coding and computational tasks, along with analysis of results.

30%

Capstone project summarized as a project report and a 20-minute talk.

Schedule and Course Materials

Lecture notes and lab codes for the first 17 lectures are linked below. More materials will be added for Spring 2027. If you use any part of this content, please acknowledge the source.

Lecture 17

Crystal Structure Design with Transformer

Lab

Lecture 18

Equivariance Neural Networks

Lab

Laurence Giordano

Lecture 19

Self-Driving Lab and Agentic AI

Lab

Self-reading

Lecture 20

Help Session with Terminal, WSL, VSCode, and Git/GitHub

Lab

Lecture 21

Guest Lecture: Prof. York

Lab

Lecture 22

Guest Lecture: Prof. Khare

Lab

Lecture 23

Guest Lecture: Prof. Remsing

Lab