Contents
Description
How can networks help us identify critical relationships in biomedical systems? How can we uncover hidden connections between genes and predict disease pathways? How can visualizing medical data improve diagnostics and treatment outcomes? How can machine learning and deep learning models help process and analyze complex medical data?
This course provides participants with the theoretical knowledge and practical tools to apply network science, data visualization, and machine learning techniques to solve pressing biomedical challenges. The curriculum focuses on four key areas:
- Biomedical Network Science – Learn how networks can model relationships between genes, proteins, diseases, and patient data to uncover patterns and predict interactions.
- Processing and Visualizing Medical Data – Explore practical methods for creating clear, interactive visualizations of complex medical datasets, improving interpretability and decision-making.
- Machine Learning on Tabular Medical Data – Apply machine learning techniques to structured datasets, such as electronic health records, to predict outcomes and identify risk factors.
- Deep Learning on Unstructured Medical Data – Gain hands-on experience with deep learning models to analyze unstructured data, including medical images, text, and genomic sequences.
Participants will learn how to recognize when a network-based approach is beneficial in biomedical contexts, interpret different network types, and model real-world medical systems. They will explore dynamic processes such as disease progression and treatment responses through Python and R programming exercises.
This hands-on course empowers participants to apply cutting-edge computational techniques to real-world biomedical data, bridging the gap between theory and practice in the rapidly evolving field of medical data science.
Programme
• Day 1: Biomedical network science
• Day 2-3: Processing and visualizing medical data
• Day 4-5: Machine learning on tabular medical data
• Day 6-7: Deep learning on unstructured medical data
Entry requirements
Participants are expected to have a good command of both spoken and written English. They should be comfortable programming in either Python or R, as both languages will be used throughout the course. A basic knowledge of algebra, probability, and statistics is also required. For those familiar with only one of the two programming languages, it is highly recommended to complete an introductory online course in the other language prior to attending.
Teaching methods/learning formats
Each day is divided into a morning and an afternoon session. Each session begins with an introduction to a specific method, emphasizing its conceptual foundations and practical applications. This is followed by a hands-on practical session, where participants apply the newly learned method to real-world data from socioeconomic (e.g. income levels, employment rates) or biological (e.g. age, gender) contexts.
During these practical sessions, participants will have the chance to discuss how the methods can be tailored to their own datasets and research questions.
Participants are required to bring their own laptops, with all necessary software, available for free download online.
Data Science specialisation
Our summer course can be further enriched by a three-day professional workshop organized by our institute immediately following the Summer School. This workshop provides an excellent opportunity for participants to present their own research, either through oral presentations or poster sessions.
During the workshop, attendees will have the chance to hear keynote speeches from renowned experts, focusing on the latest scientific advancements and practical applications in biomedical network science, medical data visualization, machine learning on tabular medical data, and deep learning on unstructured medical data.
The workshop will feature dedicated sessions for student presentations related to the topics covered in the Summer School, fostering a deeper understanding of the subject matter, promoting professional discussions, and encouraging networking. Participants will have the opportunity to learn about other researchers’ work, discuss challenges in their own projects, and establish new collaborations with professionals who share similar research interests.
Target audience
Participants with a technical background and a strong motivation to deepen their knowledge in network science.
Aim of the course
By the end of the summer school, participants will be able to:
- Comprehend the core principles of network science and identify situations where a network-based approach offers unique advantages;
- Differentiate between various types of network analyses and select appropriate methods for specific research questions;
- Calculate and interpret key descriptive statistics that characterize networks;
- Assess and choose the most suitable centrality measures to identify influential nodes within a network;
- Recognize and apply appropriate statistical methods for analysing social network data;
- Utilize the relational event model to examine the temporal dynamics of social interactions;
- Apply probabilistic graphical models to reconstruct networks from partial or incomplete data;
- Compare and implement various link prediction techniques to infer missing or future connections in networks;
- Design and build network models to test hypotheses about structural properties and relational dynamics;
- Detect and analyse community structures or clusters within networks;
- Investigate the spread of information, behaviors, or diseases by modeling contagion processes in dynamic networks.
Study load
The program spans seven full days. Each day runs from 9:00 AM to 5:00 PM, with scheduled breaks for coffee, tea, and lunch.
Participants will receive a certificate of completion at the end of the course. Please note that the course does not include graded assignments or assessments; as such, we are unable to issue an official transcript of grades.
Costs
- Course fee: 850€
- Included: Course + course materials + lunch + social programmes
The price does not include accommodation, breakfast and dinner, but it does include the cost of lunch and coffee breaks, study materials, and two exclusive community programmes. The first programme features a guided city tour, including a visit to the Saint Stephen Hall and Matthias Church. The second programme is a day trip to the historic town of Visegrád, combined with a museum visit and cultural activities, offering participants an immersive experience in Hungary’s rich history.
If you apply to our Workshop, we can provide a discount on the participation fees.
The combined price of the Summer School and Workshop is 1100 Euros.
See details about the Workshop here.
Deadlines
Additional information
- Please fill out the application form and send it back to the email address below, to which you must also attach your current CV.
- If you wish to finance your participation in our event(s) through your university, department, or a European Union grant, and require an official confirmation, please indicate this in the “Additional Information” section at the bottom of the registration form. (Official confirmation for grant application: is a formal document prepared with our institute’s letterhead, signed and stamped by the head of our institute.)
Contact
Email: biostat@semmelweis.hu