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. 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: Modeling the impact of personal genome variation on molecular phenotypes

1 April 2026 5:30 p.m. - 6:30 p.m. Central European Time

Speaker: Nilah Ioannidis, University of California Santa Cruz

Abstract:

Understanding inter-individual variation in molecular, cellular, and other clinically-relevant phenotypes is an important challenge in precision medicine. Sequence-based genomic deep learning models that predict gene expression and other molecular phenotypes directly from DNA sequence have great potential to predict the genetic contribution to variation in such phenotypes. Despite their success in explaining variation in molecular phenotypes across the genome and across a variety of cell types, we and others recently found that current sequence-based genomic deep learning models have limited ability to explain variation in gene expression across different individuals based on their personal genome sequences. I will discuss our work to characterize the cross-individual performance of such models on gene expression and other molecular phenotypes, with resulting insights into their understanding of regulatory variation. I will also discuss our efforts to develop models with improved understanding of variation across individuals using several strategies, such as incorporating personal genome and transcriptome data during model training, modeling locally-regulated phenotypes such as chromatin accessibility, and augmenting models with additional molecular information.

Upcoming speakers

Previous speakers

The scientific committee