NECSTFridayTalk – Bootstrap Your Own Chemical Compound
Presenter: Leonardo De Grandis
PHD Student in Information Technology
DEIB - NECSTLab Meeting Room (Bld. 20)
Online by Zoom
November 22nd, 2024 | 11.30 am
Contact: Prof. Marco Santambrogio
PHD Student in Information Technology
DEIB - NECSTLab Meeting Room (Bld. 20)
Online by Zoom
November 22nd, 2024 | 11.30 am
Contact: Prof. Marco Santambrogio
Sommario
On November 22nd, 2024 at 11.30 am a new appointment of NECSTFridayTalk series titled "Bootstrap Your Own Chemical Compound" will take place at DEIB NECSTLab Meeting Room (Building 20) and on line by Zoom.
During this talk, we will have, as speaker, Leonardo De Grandis, PhD student at Dipartimento di Elettronica, Informazione e Bioingegneria.
Predicting interactions between proteins and ligands is a highly challenging task due to the limited availability of labeled data, which is costly to obtain through experimental methods or physical simulations. To address this, exploiting pre-training phases with unsupervised and self-supervised techniques has shown promising results, allowing models to learn rich chemical representations from vast, unlabeled datasets. In this talk we will explore how methods from the field of Computer Vision can be adapted to generate graph embeddings for chemical compounds, offering a powerful alternative to language-based techniques.
During this talk, we will have, as speaker, Leonardo De Grandis, PhD student at Dipartimento di Elettronica, Informazione e Bioingegneria.
Predicting interactions between proteins and ligands is a highly challenging task due to the limited availability of labeled data, which is costly to obtain through experimental methods or physical simulations. To address this, exploiting pre-training phases with unsupervised and self-supervised techniques has shown promising results, allowing models to learn rich chemical representations from vast, unlabeled datasets. In this talk we will explore how methods from the field of Computer Vision can be adapted to generate graph embeddings for chemical compounds, offering a powerful alternative to language-based techniques.
The NECSTLab is a DEIB laboratory, with different research lines on advanced topics in computing systems: from architectural characteristics, to hardware-software codesign methodologies, to security and dependability issues of complex system architectures.
Every week, the “NECSTFridayTalk” invites researchers, professionals or entrepreneurs to share their work experiences and projects they are implementing in the “Computing Systems”.
