Dear all,

We are pleased to announce our upcoming online course: Machine Learning for Computational Cancer Genomics

Dates: 1–5 February | Online

Modern cancer genomics increasingly relies on computational models to extract biological insights from complex datasets. However, understanding the assumptions behind these methods is essential for correctly interpreting their results.

This 5-day course is designed for biologists and researchers who want to move beyond treating machine learning approaches as black boxes and develop a deeper understanding of the models driving modern computational cancer genomics.

Throughout the course, participants will explore the principles, implementation, and real-world applications of:

• Hidden Markov Models for copy-number inference

• Mixture models for tumour subclonal deconvolution

• Hierarchical models for mutation signal extraction

• Autoencoders for single-cell data analysis

The course combines theoretical concepts with hands-on exercises using real datasets. Participants will learn how these models work, how they are applied in practice, when their results can be trusted, and how to critically evaluate computational analyses.

No PhD in statistics is required — participants only need curiosity and some experience running R code in a programming environment.

Join us for a practical journey into computational cancer genomics and gain the confidence to understand and critically assess the machine learning approaches shaping modern cancer research.

More information and registration: https://www.physalia-courses.org/courses-workshops/cancer-genomics

Best regards,

Carlo

Carlo Pecoraro, Ph.D

Physalia-courses DIRECTOR

info@physalia-courses.org