Artificial Intelligence for Drug Discovery MSc

Program Overview

The Artificial Intelligence for Drug Discovery MSc at Queen Mary University of London is a one-year program that equips students with the essential concepts of drug discovery and artificial intelligence (AI). The program trains students in advanced computational skills required to apply AI techniques to drug discovery, preparing them for careers in this rapidly growing field. Graduates will be well-prepared for roles such as Computational Drug Discovery Scientist, AI Research Scientist, and Computational Chemist.

Program Outline

Artificial Intelligence for Drug Discovery MSc

Degree Overview:

The Artificial Intelligence for Drug Discovery MSc is a one-year, full-time program designed to equip you with the essential concepts of drug discovery and artificial intelligence (AI). The program will train you in advanced computational skills required to apply AI techniques to drug discovery. This program is ideal for graduates in Chemistry, Pharmaceutical Chemistry, Medicinal Chemistry, Biochemistry, Pharmacy, or a related discipline, who wish to pursue a career in this rapidly growing field.

Objectives:

• Provide advanced training in drug discovery and AI
• Equip students with the skills to apply AI techniques to drug discovery
• Train students in advanced computational skills required for drug discovery
• Prepare graduates for careers in AI-driven drug discovery

Outline:

The program consists of seven compulsory modules and a research project. The program begins in September and ends in September the following year.

Compulsory Modules:

• Project - Artificial Intelligence for Drug Discovery
• The students work on research topics in one of the areas of Artificial Intelligence for Drug Discovery set by their project supervisors.
Computational work is the principal component of the projects. The work also involves critical evaluation of previously published results. A dissertation is prepared.
• Fine-Tuning Lead Compounds
• This module is designed to teach students about the process of lead compound optimization in drug discovery.
Lead compounds are compounds that show promising activity against a specific target, but often require further modification to improve their efficacy, safety, and pharmacokinetic properties. Students will learn how to fine-tune lead compounds through various chemical modifications, to improve their potency, selectivity, pharmacokinetics, and toxicity profiles. The module will cover topics such as structure-activity relationships, chemical modifications, synthetic viability, ligand efficiency, bioisosteres, prodrugs, and ADME/Tox profiling.
• Computational Ligand-based Drug Discovery
• This module covers the main principles of in silico ligand-based approaches to drug discovery, with a programming component that builds upon the programming skills developed in CHE709.
Topics include molecular representations, descriptors and fingerprints, molecular similarity, database searches, application of machine learning to QSAR and ADMET prediction. Tools for the critical assessment of method performance will also be presented.
• Data-driven Drug Discovery
• The module covers advanced deep learning techniques applied to drug discovery.
Topics include chemical datasets for machine learning benchmarking, deep learning for protein structure prediction, binding affinity prediction and virtual screening, and generative models for de novo drug design. Students will learn both how to use existing applications based on machine learning and how to develop deep learning pipelines in the context of drug discovery through hands-on computational sessions.
• Molecular Modelling for Drug Discovery
• This module covers the main molecular modelling techniques used in drug discovery, with emphasis on structure-based approaches.
Topics include protein structure, protein-ligand interactions, classical force fields, homology modelling, molecular docking, structure-based virtual screening and molecular dynamics simulations. Practical lab sessions will complement face-to-face teaching and provide the students with the opportunity to use a range of popular modelling tools for drug discovery and assess their performance.
• Fundamentals of Medicinal Chemistry
• The discovery and development of new drugs is critical for improving human health and treating a wide range of diseases.
Students will develop the skills necessary to design and optimize drugs with improved efficacy and safety profiles. By the end of the module, students will be able to critically evaluate the impact of medicinal chemistry on drug discovery.
• Scientific Programming for Drug Discovery
Face-to-face teaching will be followed by practical sessions in the computer lab, where student will have the opportunity to build their coding skills and apply them to data analysis and visualisation in the context of drug discovery using an integrated development environment such as JupyterLab.

Assessment:

Assessment methods vary depending on the module. Typical methods include:

• Written examinations
• Project reports
• Presentations
• Essays
• Coursework
• Group work

Teaching:

The program is taught through a combination of lectures, tutorials, hands-on sessions in the computational lab, seminars, and student-led presentations. The program is taught by a team of world-leading researchers and professionals in the field of drug discovery and AI.

Careers:

Graduates of the program will be well-prepared for careers in drug discovery and development, including:

• Computational Drug Discovery Scientist
• AI Research Scientist
• Computational Chemist
• Data Scientist
• Molecular Modelling Specialist

Other:

The program is designed to be flexible and can be tailored to your individual interests and career goals. You will have the opportunity to gain hands-on experience in a variety of cutting-edge research techniques. The program is taught in a supportive and collaborative environment.

Entry Requirements:

To be eligible for the program, you must have a 2:1 or above at undergraduate level in Chemistry, Pharmaceutical Chemistry, Medicinal Chemistry, Biochemistry, Pharmacy, or a related discipline.