Speaker: Leonardo De Grandis
May 19th, 2026 | 2:15 pm
DEIB, PT2 Meeting Room (Bld. 20A)
For further information please contact: Silvia Cascianelli | silvia.cascianelli@polimi.it
Abstract
Tuesday, May 19th, 2026 at 2:15 pm a new appointment of Data Science Seminars: Bioinformatics focus will take place in DEIB PT2 Meeting Room (Building 20A) organized by the Data Science for Bioinformatics group.The seminar will be held by Leonardo De Grandis, PHD Student in Information Technology, on the following subject: "A graph machine learning approach for multi-omics representation learning".
Graphs are a powerful way to represent heterogeneous biological entities and their interactions. As a result, Graph Machine Learning (GML) is increasingly used to study biological networks. This talk covers the key steps of applying GML in a multi-omics context, from raw data processing to model development. Since data aggregation and harmonization remain bottlenecks for large scale artificial intelligence applications, two methods for consistently collecting high-quality genomic variants and multi-omics data will be presented. Subsequently, two different approaches for multi-omics GML applications will be introduced: a tool for compound-protein interaction prediction leveraging graph matching networks and a framework for toxicity detection on RNA-seq data. The discussion will conclude with a graph-based model for mass spectrometry data annotation. This work integrates ideas from the previous approaches into a comprehensive multi-modal pipeline.