Detailed information about the course

[ Back ]

Machine Learning in Biology Summer School


17-20 June 2024

Lang EN Workshop language is English

Dr. Marco Kreuzer, UNIBE
Dr. David Francisco, UNIBE


Prof. Daniele Silvestro, UNIFR
Dr. Verena Schöning, UNIBE (not confirmed)
Dr. Alessandro Blasimme, ETHZ
Prof. Catherine Jutzeler, ETHZ
Prof. Fernando Racimo, University of Copenhagen (DK)


I. Summary: We present a proposal to host a comprehensive, four-day Machine Learning in Biology Summer School in 2024. This program is dedicated to equipping researchers, particularly those enrolled in PhD programs, with foundational knowledge and application skills in machine learning within the biological sciences. Set against the picturesque backdrop of Bern, Switzerland, this Summer School aims to bridge the knowledge gap, inspire application, and foster a collaborative environment for exchanging ideas in the realm of machine learning. II. Target Demographic: The Summer School is envisioned for PhD students with a keen interest in the interplay of biology and machine learning, but whose exposure to the subject has so far been limited. Our mission is to assist these individuals in gaining a sound understanding of the core concepts, learn about practical applications, and facilitate the integration of machine learning approaches into their current research endeavors. III. Program Duration and Outline: The Summer School will take place over four days. We aim to promote a culture of shared learning with all attendees participating in a common session. Experts from academia and industry will present insightful seminars, offering participants a glimpse into the diverse applications of machine learning. The summer school will have practical and accessible hands-on sessions, providing ample opportunity for participants to share their learnings, engage in enriching discussions with peers and lecturers, thereby stimulating the exploration of machine learning within their research interests. IV. Venue and Extracurricular Activities: Located in the charming city of Bern, Switzerland, the Summer School combines a world-class learning experience with an opportunity to unwind in a picturesque setting. To enhance the overall experience, recreational activities, including organized swimming sessions in the Aare river, will be woven into the program. This multifaceted approach will promote networking, relaxation, and cultural exploration, making the Summer School a truly memorable affair. V. Core Objectives: The Summer School has three central goals: Simplify Machine Learning: By presenting relatable content, we aim to strip away the complexity surrounding machine learning and make it more accessible for participants. We will ensure clarity in understanding the principles, terminologies, and methodologies that define this field. Promote Understanding and Utilization: The curriculum, balancing theoretical teaching with interactive discussions, will ensure a deep understanding of machine learning principles. Participants will gain insights into when, where, and how to apply machine learning techniques in their research while acknowledging their limitations and data prerequisites. Foster Collaboration and Application: Through active dialogue and presentations, we seek to spur curiosity about how machine learning can enhance individual research. Feedback and guidance from peers and lecturers will provide a platform for integrating machine learning approaches within their academic pursuits. VI. Conclusion: The proposed Machine Learning in Biology Summer School promises a comprehensive and enriching platform for PhD students to delve into the intricacies of machine learning and its applications. By ensuring a holistic learning environment, simplifying the complex subject matter, and promoting collaboration, we hope to empower our participants to harness the power of machine learning effectively in their research journey. VII. Day to day schedule Day 1: Introduction and General Concepts (Lectures); The Two Cultures: Statistics and Machine Learning in Science; Similarities and differences between ML and classical statistics; Hyperparameter tuning and model validation in machine learning; How to chose test, train and validation data & Overview over different classes of methods, models and algorithms. Day 2: Hands-on training (lectures and exercises): Detailed introduction of selected ML algorithms; Introduction to implementations (R / caret / tidymodels vs Python / SciKit learn ) & Group project: implementing your first ML pipeline, everybody uses same data-set, results will be presented / shared among students. Day 3: Mini-Symposium: Talks by invited speakers & Afternoon: social event where students get to interact with invited speakers Day 4: Developing a ML pipeline: from data preparation to model fitting and interpretation of results; Lectures about data preparation, potential issues such as data leakage and over-fitting; Group project: we provide a set of data-sets , students can choose an example data-set, come up with a question, implement a ML algorithm to answer question; Presentation of the results & Closing lecture: Exploring the societal impact of machine learning in biology and science: risks, challenges and opportunities.


More information in due time.




Reimbursements for CUSO StarOmics students: Train ticket, 2°class, half-fare from your institution to the place of the activity.

Reimbursement of your travel tickets can be asked online through your MyCUSO. See HERE for the procedure.

For any question concerning reimbursement please contact the CUSO StarOmics coordinator Corinne Dentan


Registration is CLOSE

Deadline for registration: TBA



Deadline for registration
short-url short URL

short-url URL onepage