Applications of Artificial Intelligence in Drug Development

This course includes but not limited to the following main topics: The applications of machine learning as a part of artificial intelligence in drug development and delivery.

In this course, different types of supervised and un-supervised machine learning methods such as PCA, HCA and ANN, that were exploited in drug and nanoparticles formulation and delivery aspects and will be demonstrated and discussed. The cross-disciplinary integration of drug delivery and machine learning methods as a branch of artificial intelligence may shift the paradigm of pharmaceutical research from experience-dependent investigations to data-driven studies. Exploitation of these methods in the drug delivery field especially with the support from the pharmaceutical industry would lead to huge cuts in the resources expenses and would lead to large savings in efforts and time that are usually exerted in the wet-lab try-and-error experiments.

Design of Experiments (DoE) It is a branch of quality by design (QbD) as an emerging field that combines computer science, mathematics, and statistics in order to establish successful cause-effect correlations between factors and responses. Moreover, with the help of planned experiments, accurate predictions of outcomes based on the constructed models can be achieved. The huge development and advent of the computer software, especially those possessing user-friendly interfaces, could help in relaying the concepts of DoE as a crucial element of quality to the post-graduate students which would have futuristic beneficial impacts on the pharmaceutical industry. This course introduces a simple way of conveying the topic to the students using fish-bone diagrams and through conducting a step-by-step protocol of an experimental design used for modelling a drug carrier.