EDUCATION
AI4LifeSciences & MEDICINE
KAUST. On-campus
The course is a division-wide lecture course that goes beyond the boundaries of the different programs. Story-driven, by examples, to show what you can do (and not) by using AI in life sciences and medicine. It is not a coding-based course but rather one that teaches the basic ideas in AI and how these are used in practice, using examples across the biosciences and medical field. We emphasize innovations and business opportunities where illustrative examples exist. The course is designed to be accessible to master’s and PhD students with a bioscience/medical profile without a computer science/quantitative background. Quantitative students are most welcome, and the course provides a first-hand, in-depth take on the most successful examples of AI in Life Sciences.
➤ The learning objectives include:
The course has three parts. First, we work through the main ideas, concepts, and architectures in modern AI. These include (mainly) AE, VAE, GNN, CNN, and Transformers. Next, we have a block of student-led presentations and discussion of key success stories papers. Finally, we conclude with practical exercises, a survey of available tools, business opportunities, generative and agent-based AI, and ethical and future perspectives.
➤ The learning objectives include:
- Provide a broad overview of how to deploy AI in Life Sciences and Medicine
- Illustrate key ideas for research and innovation through story-driven examples
- Share an overview of resources and tools
- Stimulate critical thinking of possibilities and limitations of AI in Life Sciences & Medicine and relevant ethical considerations.
- Inspire students with stories and examples so that they can use these ideas and tools in their current and future work
- 40.00% – Present one paper and lead the discussion on a second paper.
- 40.00% – Quiz(zes)
- 20.00% – Final exam.
The course has three parts. First, we work through the main ideas, concepts, and architectures in modern AI. These include (mainly) AE, VAE, GNN, CNN, and Transformers. Next, we have a block of student-led presentations and discussion of key success stories papers. Finally, we conclude with practical exercises, a survey of available tools, business opportunities, generative and agent-based AI, and ethical and future perspectives.
FUNDAMENTAL SKILLS IN BIOINFORMATICS
KAUST. On-campus
The course provides a broad and mainly practical overview of very fundamental skills for the area of bioinformatics. Topics are selected to be relevant for the biologist / biomedical scientist with limited or none background in programming or quantitative analysis. The aim is to support the simultaneous development of quantitative and programming skills for biological and biomedical students. Through the course, the student will develop the necessary practical skills to conduct fundamental data analysis and develop the framework to establish advanced programming and analytical skills in the next courses. A particular aim is to provide the participants with long-term skill on programming and the guidelines for improving their knowledge on it. Read more
UNDERSTANDING AND CONSTRUCTING BIOINFORMATICS PIPELINES
KAUST. On-campus
This course introduces students to the design, implementation, and interpretation of computational pipelines used in genomics. Starting with RNA-seq analysis, participants progressively explore a range of data types—including ATAC-seq, single-cell RNA-seq, multi-omics, and DNA methylation—developing a solid foundation in both the theoretical and practical aspects of pipeline construction. Emphasis is placed on reproducibility, code management (e.g., GitHub), and statistical considerations underlying count data. Finally, It culminates in group projects focused on developing pipelines for specialized data types such as Hi-C, CITE-seq, or CyTOF.
FUNDAMENTAL SKILLS IN BIOINFORMATICS
Coursera. Online
The course provides a broad and mainly practical overview of fundamental skills for bioinformatics (and, in general, data analysis). The aim is to support the simultaneous development of quantitative and programming skills for biological and biomedical students with little or no background in programming or quantitative analysis. Read more
COMPUTATIONAL BIOSCIENCE AND MACHINE LEARNING
KAUST. On-campus
The course provides a broad and practical overview of selected techniques and concepts in rapidly developing areas such as bioinformatics, computational biology, systems biology, systems medicine, network biology, data analytics, predictive modelling, and machine learning. Topics are selected to be of relevance for the computer scientist, working biologist, computational scientist, and applied investigator (Biotechnology and engineering).
The aim is to support the development of bilingual students. With a background in bioscience or computer science, providing a firm foundation in their area of expertise, the student will develop practical and conceptual language skills, enabling them to communicate and collaborate efficiently with experts outside their domain.
➤ Specific themes and topics include:
The aim is to support the development of bilingual students. With a background in bioscience or computer science, providing a firm foundation in their area of expertise, the student will develop practical and conceptual language skills, enabling them to communicate and collaborate efficiently with experts outside their domain.
➤ Specific themes and topics include:
- Genome Alignment (+Lab), Bioinformatics Pipelines – RNA (bulk) sequence analysis (+Lab), and Single Cell Genomics (+Lab), Transcriptional, metabolic, and protein-protein interaction networks.
- Bioinformatics, Computational Biology, and Machine Learning: concepts, techniques, tools, and resources. For example: differential analysis (time, samples), enrichment and pathway analysis, and exploratory data analysis.
- Multiple testing, cross-validation, bootstrapping, normalization, uni/multivariate statistics, networks, supervised and unsupervised learning, classification – support vector machines, regression, loss function, clustering techniques and dimension reductions (PCA, SVM, ICA, MDS, UMAP, and t-SNE).
- Working knowledge of R.
- Recommend to have completed B204 -Genomics course.
MACHINE LEARNING IN GENOMICS AND HEALTH
KAUST On-campus
Recent progress in machine learning and artificial intelligence is currently transforming genomics, translational medical research, healthcare, and wellness. Huge data-sets are produced at an increasing rate. This include recordings of smart living augmented by sensor devices, medical images, text data in healthcare and social media, and genomics profiling of a range of different biomolecular data. Concurrent with these developments there has over the last 5 years been a stunning production of open source machine learning tools and powerful computational platforms. These advances are currently advancing bioinformatics, computational biology, systems biology, where an area which could be referred to as Digital Medicine in a broad sense is emerging. We expect students with a background in computer science, mathematics, bioscience, and engineering to learn how to use, develop, and to think on how to use ML/AI techniques in what can broadly be referred to as Digital Technologies for Medicine and Health. Read more
GEOMETRIC MACHINE LEARNING AND NETWORK SCIENCE
KAUST On-campus
Progress in machine learning, particularly in deep convolutional neural networks, has advanced areas such as the analysis of images, audio, and languages. Yet, several areas in biology, chemistry, and physics are dealing with problems that can be represented as interactions between many parts, i.e., domain-specific networks, or more generally, as graphs.
➤ Requisites:
➤ Requisites:
- Familiar with probability theory, linear algebra, Fourier-Laplace operators, algorithms and machine learning.
- Working knowledge of programming: Python, MATLAB
- Required courses to have completed: CS 220 Data Analytics and CS 229 Machine Learning.
- AMCS 201 Applied Mathematics I
- AMCS 202 Applied Mathematics II