Course

Unit 1

Data types (Omics, networks); Dimensionality reduction methods (PCA, tSNE, UMAP); Mathematical models in biology ? Introduction, types of models, levels of modeling, specificity of modeling in biology. Concepts and working principles of System Biology – Practical applications of System Biology in Life Sciences – From molecules to pathway- Pathway to networks.

Unit 2

Model, Modeling. Modeling of biological systems: Metabolism, Cell Signaling, Aging, Evolution, Biological Oscillations, Modeling Dynamic Systems, Explainable AI (XAI) in Biology (Model interpretability, SHAP, LIME, biological validation);

Unit 3

Generative Models for Biology (GANs) Biological Network Inference and Graph AI (Gene Regulatory Network, GNN, ODE based modeling), Predictive biomarkers-based case study

Course Objective: This course explores how artificial intelligence (AI) techniques, particularly machine learning, deep learning, and data-driven modeling are revolutionizing systems biology. Students will learn key AI methods and apply them to biological networks, multi-omics data, dynamic system modeling, and biological discovery. Course outcome CO1: Understand the concept of systems biology. CO2: Analyze and interpret multi-omics datasets using AI methods. CO3: Design predictive models for biological networks and cellular behavior. CO4: Develop and present a project applying AI to a systems biology problem.

Textbooks and References “Machine Learning for the Life Sciences” by Andreas C. Mller & Alexander Hendorf “Systems Biology: A Textbook” by Edda Klipp et al. Selected journal articles (updated each year) Online resources: Tutorials (TensorFlow, PyTorch, Scikit-learn), NIH datasets