Thank you to everyone contributing to this great celebration! Promotor Marcel Reinders, paranymphs Kirti Biharie & Sander Goossens, the whole DBL lab ❤️, family+friends of Yasin, committee Aalt-Jan van Dijk, Boudewijn Lelieveldt, Jeroen de Ridder, Patrick Kemmeren, Wouter Kouw.

TL;DR
Part I: anti-cancer therapy target discovery, synthetic lethality prediction (ELISL) & stratification of oncogene-addicted cohorts (Oncostratifier, collab Iorio's lab).

Part II: mitigation of selection bias in ML via diversity-guided self-training (DCAST, Metric-DST).

Looking back on a most important event: Yasin Tepeli masterfully defended his PhD, 16 Jun 2025, on effective strategies for therapeutic target prediction & selection bias mitigation in ML edu.nl/hv4xt. Congratulations Dr. Tepeli!

Looking for his next move, snatch him.

SNMF: Integrated Learning of Mutational Signatures and Prediction of DNA Repair Deficiencies Motivation Many tumours show deficiencies in DNA damage response (DDR), which influence tumorigenesis and progression, but also expose vulnerabilities with therapeutic potential. Assessing which patie...

Paper by our Sander Goossens! Shows we can learn tumor-relevant mutational signatures of DDR deficiency from gene perturbation screens with mutation profiling after DNA damage. Check out SNMF (supervised NMF)! doi.org/10.1101/2024... #DDR #DNARepair #MachineLearning

DCAST: Diverse Class-Aware Self-Training Mitigates Selection Bias for Fairer Learning Fairness in machine learning seeks to mitigate model bias against individuals based on sensitive features such as sex or age, often caused by an uneven representation of the population in the training...

Paper by our Yasin Tepeli: How to train fairer ML models from data affected by selection bias? Diversity! DCAST learns from diverse vs. most confident samples to avoid confirmation bias via semi-supervised learning. #MachineLearning #FairnessML arxiv.org/abs/2409.20126