Back to projects

Computational and AI-Guided Drug Discovery

Using molecular modelling, docking, molecular dynamics, quantum chemistry and machine learning to explore therapeutic targets, predict molecular properties and support drug discovery workflows.

DockingMolecular dynamicsMachine learningQSAR

Overview

A case study in applying computational and data-driven methods to prioritise compounds, predict molecular properties and guide experimental decisions in early-stage discovery.

Scientific question

How can computational and machine-learning methods accelerate the identification and prioritisation of promising therapeutic molecules?

Why it matters

Computational methods can accelerate early-stage discovery, prioritise compounds and guide experimental decisions before committing laboratory resources.

Approach

Molecular docking, molecular dynamics, QSAR, quantum descriptors, machine learning, protein modelling and data-driven interpretation.

Relevance to biotech/pharma

Computational and AI-guided approaches are core to modern pharma R&D, reducing time and cost in hit identification, lead optimisation and property prediction.

Selected outputs / publications

Selected publications cover LRRK2 inhibitors, DPP-4 inhibitors, tyrosinase inhibitors, SARS-CoV-2 drug repurposing, QSAR studies and ElectroPredictor.