Course detail

Applied AI in Life Sciences

FEKT-MPA-AUIAcad. year: 2026/2027

The course focuses on modern methods of applied artificial intelligence and machine learning in the life sciences, particularly biomedicine, biology, and bioinformatics. Emphasis is placed on probabilistic approaches, working with uncertainty, model robustness, and their interpretability in real-world application scenarios. Teaching combines theoretical lectures with project-oriented computer exercises in which students solve practical tasks using real data from the fields of signals, images, and bioinformatics. The course also covers topics such as ethics, fairness, regulation, and clinical implementation of AI systems, with the aim of preparing students for the practical deployment of AI in real research.

Language of instruction

English

Number of ECTS credits

4

Mode of study

Not applicable.

Guarantor

prof. Ing. Valentýna Provazník, Ph.D.

Department

Department of Biomedical Engineering (UBMI)

Aims

Cílem předmětu je seznámit studenty s principy a metodami aplikované umělé inteligence v živých vědách a naučit je tyto metody kriticky používat v praxi. Studenti získají schopnost navrhovat, implementovat a hodnotit AI modely s ohledem na nejistotu, interpretovatelnost, robustnost a etické aspekty. Důraz je kladen na porozumění reálným datům, validačním postupům a omezením modelů v klinickém a biologickém kontextu, stejně jako na schopnost týmové práce a prezentace výsledků projektů.

Rules for evaluation and completion of the course

The conditions for successful completion of the course are set out in the annually updated course syllabus and include:

  • Full attendance and active participation in computer exercises.
  • Fulfilment of ongoing requirements arising from project work.
  • Completion of a mid-semester theoretical test.
  • Completion of a colloquium and discussion of project results.

To obtain a graded credit and pass the course, it is necessary to obtain at least 50 points from the above activities.

 

Study aids

Not applicable.

Prerequisites and corequisites

Not applicable.

Basic literature

CHRISTOPHER M. BISHOP. 2006. Pattern Recognition and Machine Learning. Springer Verlag. ISBN 978-0-387-31073-2. (EN)
KEVIN P. MURPHY. 2012. Machine Learning: A Probabilistic Perspective. Ilustrated ed. MIT Press. ISBN 9780262018029. (EN)

Recommended reading

Explainable AI: Interpreting, Explaining and Visualizing Deep Learning. 2019. Lecture Notes in Computer Science [online]. Cham: Springer International Publishing, 11700(1), 439 [accessed 2026-1-30]. DOI: 10.1007/978-3-030-28954-6. ISBN 9783030289539. ISSN 0302-9743. Available at: https://link.springer.com/content/pdf/10.1007/978-3-030-28954-6.pdf (EN)

Classification of course in study plans

  • Programme MPA-BTB Master's 2 year of study, winter semester, compulsory, profile core courses
  • Programme MPCN-BTB Master's 2 year of study, winter semester, compulsory-optional, profile core courses
  • Programme MPAN-BIO Master's 2 year of study, winter semester, compulsory

  • Programme MPCN-BIO Master's

    specialization MPC-BIO_TECH , 2 year of study, winter semester, compulsory-optional

Type of course unit

 

Lecture

13 hours, optionally

Teacher / Lecturer

prof. Ing. Valentýna Provazník, Ph.D.

Syllabus

  1. Introduction to applied artificial intelligence in life sciences, overview of methods, specifics of biological and clinical data.
  2. Bayesian modeling, working with uncertainty and principles of probabilistic decision making, Bayesian inference.
  3. Monte Carlo methods, stochastic simulations, and approximation inference.
  4. Bayesian optimization and optimization of costly and black-box functions, Gaussian processes and acquisition functions.
  5. Model hyperparameters and their optimization.
  6. Model explainability and interpretability, post-hoc methods, and clinical requirements.
  7. Bias, fairness, and ethical aspects of AI in the life sciences.
  8. Robustness, generalization, distribution shift, and reliability of models in real-world deployment.

Exercise in computer lab

52 hours, compulsory

Teacher / Lecturer

prof. Ing. Valentýna Provazník, Ph.D.

Syllabus

Practical exercises are designed as project-oriented teaching focused on specific areas of application of artificial intelligence in the life sciences. Each thematic block is addressed in the form of a separate project, the solution to which is gradually developed, implemented, and evaluated over the course of several hours. Emphasis is placed on linking theoretical knowledge from lectures with real data and practical tasks, as well as expert discussions of the results achieved in the context of biological, biomedical, or clinical applications.

Application of AI in the analysis of biomedical signals with a focus on event detection, classification, and prediction in clinical and research tasks.

Application of AI in the analysis of image data from medical imaging and microscopy, including segmentation, detection, classification, and deep learning methods.

Application of AI in the analysis of bioinformatic and omic data, including sequence analysis, prediction of biological functions, and integration of heterogeneous data.

Design and implementation of real-time AI systems with an emphasis on low latency, edge AI, online decision support, and continuous monitoring.

 

Individual preparation for excercises

13 hours, optionally

Teacher / Lecturer

prof. Ing. Valentýna Provazník, Ph.D.

Individual preparation for a final exam

26 hours, optionally

Teacher / Lecturer

prof. Ing. Valentýna Provazník, Ph.D.