Curriculum Information

1) Computer Aided Drug Design (Computational Chemistry)
Following a revision of atomic / molecular orbitals, this topic will:
Introduce the idea of modelling / simulating molecular systems on computers
Introduce different simulation techniques used in computational chemistry (forcefields / semi-empirical descriptions, leading up to density functional theory and QM methods)
Introduce computational chemistry concepts useful in computer aided drug design (including but not necessarily limited to molecular docking, molecular dynamics, structure prediction, screening, enhanced sampling methods etc.)

2) Chemometrics
Following a revision of the underlying mathematical principles this topic will focus on data science and machine learning techniques applicable for use in experimental design and analysis in the pharmaceutical sciences, including but not limited to:
• Data Preprocessing (feature scaling, data transformations, feature encoding etc, with specific emphasis on techniques relevant to the chemical and pharmaceutical industries e.g. Savitzky-Golay filtering)
• Supervised Learning – regression, classification
• Unsupervised Learning – clustering, dimensionality reduction
• Model validation and tuning
• Introduction to Deep Learning – ANNs, CNNs, RNNs, autoencoders (brief, but important for wider context, especially in terms of advanced applications)

3) Artificial Intelligence Applications
This final topic will look at the cutting edge applications of artificial intelligence in the pharmaceutical industry – such topics are expected to include: AI in drug discovery, AI in protein structure prediction (e.g. AlphaFold), AI in molecular simulation, AI in spectra analysis / prediction.