SELF-PACED | ONLINE | BEGINNER
🚨 NOTE 🚨: This course is offered only in self-paced mode. To access the course, enroll using the Enroll Now button and you will immediately get access to all course materials in your dashboard. There are no live cohort sessions. Please ignore any live start dates shown on the website. Support is available via Slack and email.
This course is your structured entry point into machine learning for small-molecule drug discovery. It teaches the fundamentals that most people skip, which is exactly why their models fail later.
You will learn the full workflow behind molecular ML, including the software stack, molecular data collection, preprocessing, feature engineering, and basic model building with proper quality control. The goal is not to memorize algorithms, the goal is to become competent at building reliable pipelines on chemical datasets.
This course is designed to prepare you for advanced predictive modeling and later generative AI work. If you want to build molecule generation systems in the future, this is where you start, because generative AI is useless without clean data, correct representations, and correct evaluation.
WHO THIS IS FOR
This course is for you if you are serious about drug discovery ML but you are not yet confident with the basics of molecular data workflows and model building.
Good fit if you are:
- Student, researcher, or professional entering molecular ML
- Chemist moving into data-driven discovery
- Computational chemist who wants ML foundations tailored to molecules
- Early-stage ML engineer entering biotech or cheminformatics
This course is also the right starting point if your end goal is generative AI for molecules, because it builds the foundations that generative modeling depends on: chemical data preparation, molecular representations, and model quality control.
Not for you if you want:
Deep learning architectures, advanced bias handling, or explainability tooling, that is covered in the Advanced MLDD course.
WHAT YOU WILL BE ABLE TO DO
By the end of the program, you will be able to build a correct beginner-to-intermediate molecular ML workflow instead of copying random notebooks that break in real use.
You will be able to:
- Set up the molecular machine learning software stack
- Collect and preprocess drug discovery datasets
- Engineer molecular features for ML, with practical feature choices for small molecules
- Train basic machine learning models for drug discovery tasks
- Apply quality control so you know when your model is real versus overfitting
