The aim of the module is to expose the students to modern chemical informatics, machine learning (ML) and artificial intelligence (AI) driven approaches for computational modelling and prediction, illustrated with applications to research in to the discovery of new pharmaceuticals and materials. The module will introduce the basic techniques of applying AI and ML to chemistry and the opportunity to apply these ideas to specific examples as part of a mini-project.
Having successfully completed this module you will be able to:
a.Introduction to the representation of molecules in a computer readable and processible form, e.g. SMILES, mol files;
b.Chemical space and access to chemical data (databases);
c.Introduction to regression style statistical analysis: types of regression, quantitative structure-activity relationship (QSAR) and quantitative structure-property relationships (QSPR);
d.Introduction to Machine Learning and Artificial Intelligence;
e.dimensional reduction (PCA and non-linear approaches), classification (Support Vector Machines, Logistical models), clustering, neutral networks, Kernelisation;
f.Knowledge-based approaches (e.g. for synthesis prediction)
Taught lectures, workshops and independent study including a short self led project.
| Type | Hours |
|---|---|
| Lecture | 16 |
| Independent Study | 54 |
| Practical classes and workshops | 8 |
| Guided independent study | 17 |
| Completion of assessment task | 40 |
| Completion of assessment task | 15 |
| Total study time | 150 |
This is how we’ll formally assess what you have learned in this module.
| Method | Percentage contribution |
|---|---|
| Multiple choice question | 15% |
| Individual project | 70% |
| Individual Presentation | 15% |