Next-generation sequencing has made artificial intelligence vital for analysing, curating, and interpreting human genome data. The vast array of DNA sequences provides a means for identifying potential treatments for certain types of cancer. This tutorial will cover methods for working with such data, including traditional machine learning tools, deep learning, and language models designed to integrate various data types, with the goal of identifying DNA mutations in cancer that could be used for drug development.

Michal Kováč is an Associate Professor in Applied Informatics at the Faculty of Informatics and Information Technologies, Slovak University of Technology. He currently leads a research group BrainWorks, which focuses on knowledge discovery in precision genomic medicine. Previously, he held research positions at the University of Basel, University of Oxford, and the pharmaceutical company Roche. He holds a PhD in cancer genetics from Comenius University and an MSc in software engineering from the University of Oxford.

His research aims to provide a fundamental understanding of how DNA mutations relevant to therapy can be identified using a wide range of AI methods, and how this knowledge can be used for treatment recommendations. His publications include papers in Nature Genetics, Cancer Cell, Nature Ecology and Evolution, and Nature Communications.