Kipoi - Seminar

The monthly virtual seminar series is designed as a platform for interested Kipoi users and developers and will host talks on the applications of deep learning on biological data. The seminar is held on every first Wednesday of the month at 5:30 p.m. - 6:30 p.m. CET/CEST. We are also happy to share the recordings of the seminar on YouTube.

How to take part

Our Virtual Seminar Series is hosted entirely online. To join, please subscribe to the mailing list below; we will send you a single recurring link that provides access to every lecture in the series.

Register

How to apply as a speaker

The seminar is a great opportunity to present your recent work to a large international audience. If you want to apply as a speaker, please use the contact in the registration confirmation email.

Next seminar

Title: Artificial intelligence for molecular discovery to illuminate the dark proteome

7 October 2026 5:30 p.m. - 6:30 p.m. CET/CEST

Speaker: Wout Bittremieux, Adrem Data Lab, University of Antwerp

Abstract:

Mass spectrometry-based proteomics has generated vast amounts of publicly available data, yet much of this information remains unexplored. In this talk, I will discuss how artificial intelligence can transform large-scale proteomics repositories into discovery platforms, revealing biological insights hidden within existing datasets. I will introduce a neural network-based embedding and clustering approach that learns representations across millions of mass spectra, enabling the discovery of molecular patterns and the exploration of the "dark proteome" beyond the limits of conventional database searches. Next, I will discuss how the Casanovo encoder–decoder model enables direct interpretation of mass spectra using de novo peptide sequencing, uncovering unexpected peptides and expanding our view of complex proteomes. Finally, I will describe our efforts to integrate these approaches with large language models that automatically extract metadata from public proteomics datasets and associated open-access scientific manuscripts. By combining spectral analysis, peptide sequence interpretation, and experimental context, we aim to build AI-driven systems that illuminate what has remained hidden within existing proteomics data. Together, these developments represent a shift toward data-driven discovery systems that can extract new biological knowledge from the ever-growing wealth of molecular data.

Upcoming speakers

Previous speakers

The scientific committee