Prof. Jan Baumbach

Hybrid Meeting (Register here for the on-site event and networking afterwards: https://indico.desy.de/event/34770/)

June 8th, 2022

4 pm

Chair: Prof. Kay Grünewald

We are very happy to welcome Prof. Jan Baumbach (Computational Systems Biology, Universität Hamburg) as speaker in our series. In his talk, he will introduce recent data science challenges in the field of systems biology. The title of the presentation is "Privacy-preserving clinical omics data profiling".

Abstract

Artificial intelligence (AI) offers game-changing opportunities to healthcare. However, it also harbors risks to patient privacy in particular when dealing with sensitive clinical data stored in critical healthcare IT infrastructure. Specifically, data exchange over the internet is perceived insurmountable, posing a roadblock hampering big -data-based medical innovations. We created a novel AI platform, the FeatureCloud AI app store that is based on the idea of federated learning where only model parameters are communicated. To maximize privacy, sensitive datasets remain stored locally and are analysed behind safe firewalls. We will investigate the power of FeatureCloud apps exemplarily for decentralized genome-wide association studies (GWAS). We then quickly introduce related apps for gene expression data mining and time-to-event analysis, to demonstrate how FeatureCloud may enhance worldwide collaboration, accelerate innovation, and democratize scientific data usage.

Networking

We are looking forward to further discussions after the talk with some snacks and drinks. Please register by June 3rd, 2022 if you want to join: https://indico.desy.de/event/34770/

We additionally offer a childcare service for the event. If you want to make use of this offer, please contact dashh-office@desy.de.

At 6 pm, the Center for Data and Computing also organized a Mini-Hackathon and invites interested researchers to register here: https://indico.desy.de/event/34266/

See below for further information and contact or subscribe to our mailing list using the link https://bit.ly/3hTStBa