Biomedical Network Science Lab

The Biomedical Network Science (BIONETS) Lab investigates molecular mechanisms, using techniques from network science, (graph-based) AI and combinatorial optimization. We develop algorithms, AI models, and software tools to mine omics data for such mechanisms, with the aim to better understand cellular pathways and, ultimately, pave the way for targeted and causally effective treatments of complex diseases. We also develop privacy-preserving decentralized biomedical AI solutions, which enable cross-institutional studies on sensitive data. Finally, we are interested in meta-scientific questions such as reproducibility and the impact of data bias on biomedical AI systems.

Our research

News

More news

We are excited to share that our paper “SignifiKANTE – efficient P-value computation for gene regulatory networks” has now been published in Bioinformatics. Permutation-based significance testing is a common approach for filtering edges in regression-based gene regulatory network inference, but so expensive that it is usually skipped on real-world gene expression data. We tackle this…Read more

Our GNExT paper is officially out in Nature Genetics! https://doi.org/10.1038/s41588-026-02708-6 GNExT (GWAS Network Exploration Tool) tries to make it as easy as possible to set up your own GWAS exploration platform from your GWAS summary statistics and scales well for large datasets. GNExT takes your raw GWAS dataset, preprocesses it with a custom Nextflow pipeline,…Read more

Last week, we got the happy news that our DFG-funded DyHealthNet research project will be extended by another 3 years! Our main goal in DyHealthNet is to make cohort data more explorable. In the first phase of the project, we developed prototype platforms, primarily for application to the Collaborative Health Research in South Tyrol (CHRIS)…Read more

On July 1st, Julius Stutz joined the BIONETS Lab as a new research associate. He will work on new methods for representing and evaluating decision trees.Read more

We went on a joint scientific retreat with the DaiSyBio group at TUM’s Science & Study Center in Raitenhaslach, Burghausen. The two days were packed with great scientific exchange that will keep us busy with new ideas for months to come! We kicked things off with a joint poster session, held focused discussions in a…Read more

Judith Bernett has been awarded the Best Scientific Contribution Award by the German Association for AI in Medicine (KIMED) at the BAIOSPHERE Medical 2026 conference in Erlangen for her publication Critical evaluation of drug response prediction models with DrEval. We had a strong presence at this year’s BAIOSPHERE Medical conference, where around 200 researchers and…Read more

“Critical evaluation of drug response prediction models with DrEval” has been published in Nature Communications. ML-based cancer cell line drug response models are well-motivated, and significant research effort has gone into developing complex modeling approaches (over 100 papers in 2025). The problem: under rigorous evaluation, we found none that actually works: Most are published based…Read more