Artificial Intelligence in Drug Discovery
Syllabus, Master's level, 3FF036
- Education cycle
- Second cycle
- Main field(s) of study and in-depth level
- Pharmaceutical Sciences A1F
- Grading system
- Fail (U), Pass (G), Pass with distinction (VG)
- Finalised by
- The Educational Board of Pharmacy, 21 October 2021
- Responsible department
- Department of Pharmaceutical Biosciences
For students within:
Master's Program in Drug Discovery and Development: admitted and complied prior courses within the program
The programme in Master of Science in Chemical Engineering: at least 150 credits within the programme is required, including knowledge corresponding to at least 60 credits in the subjects chemistry, biology, biochemistry, pharmaceutical science or medicine.
Freestanding course: at least 150 credits is required, including knowledge corresponding to at least 60 credits in the subjects chemistry, biology, biochemistry, pharmaceutical science or medicine. In addition: Knowledge corresponding to English 6 is required (this requirement is fulfilled with a Swedish bachelor degree).
After completing the course, the student should be able to:
- Account for the basics of machine learning and artificial intelligence
- Explain different AI methods, their advantages and disadvantages, and how they can be used in the drug discovery process
- Reflect over and critically judge validation and documentation of AI models
- Use AI models practically and analyze, interpret and summarize results in English writing of good standards
- Perform basic training and validation of AI models relevant to drug discovery and evaluate the results.
Introduction to the use of artificial intelligence (AI) and machine learning (ML) in drug discovery. Basic concepts for AI / ML, commonly used methods for tabular data and different types of deep neural networks. The importance of data for modeling. Various application areas in drug development where AI can be used, such as ligand-based methods for virtual screening and prediction of properties based on chemical structure, structure-based methods, image-based methods, de novo drug design and network / graph-based methods. The primary focus is on making predictions and interpreting the results, but the course also includes the steps for training and validation of AI / ML models.
The course is given in its entirety remotely via the Internet and access to a computer with an Internet connection is mandatory. Instruction via self-studies where interaction with teachers and other students take place via the education platform and online meetings. Theoretical parts are intermixed with computer exercises and assignments. The course does not require previous experience in programming. The course is given in English on part-time (50%).
Written examination at the end of the course. To pass the course is required a passed written exam (5 hp) and passed compulsory assignments (2,5 hp). If there are special reasons for doing so, an examiner may make an exception from the method of assessment indicated and allow a student to be assessed by another method. An example of special reasons might be a certificate regarding special pedagogical support from the University's disability coordinator.
No reading list found.