Topic 1 - Representing molecules in the computer

In this part you will learn how molecules are stored and manipulated by the computer. You will learn about the different formats, and you will write your first chemo-informatics code.

Prepare yourself:

It is highly recommended that you prepare yourselves by first having a look at this movie:

• String-based representations of molecules: SMILES, SMARTS and SELFIES [YouTube - 15’00”]

Then you should have a good read of this paper:

• A review of molecular representations in the age of machine learning [pdf]

Course manuals:

• Chapter 2: Representing molecules in the computer [pdf]
• Chapter 3: Chemical informatics with RDKit [pdf]

Slides:

• Lecture slides of topic 01 [pdf]

Exercises:

With the following Google Colab sessions, you can bring to practice all that has been learned in this lessons:

• Chemical informatics with RDKit [Google Colab]
• Extra exercises [Google Colab]

Finished?

Then it is time to move to the second topic of this course:

• Topic 2: Clustering and machine learning

However, if you feel that your Python skills are still somewhat behind, then it might be wise to repeat the intro session again.