Jump to content

NeurIPS 2026

Sydney, AU
December 6–12, 2026

Meet Genedata at the NeurIPS 2026 in Sydney and connect with our experts to learn how Genedata Screener® accelerates image-based drug discovery through automated data analysis, quality assessment, and enterprise-wide data integration. By transforming complex high-content screening and imaging data into actionable insights, Genedata Screener empowers scientists to make faster, more confident decisions and advance AI-driven research programs. 

To get more information about our software or to arrange a meeting, please contact screener(at)genedata.com.

Presentations

DICE-SynBa: Addressing Synergy Shortcut Learning via Disentangled and Compressed Embeddings
Daniel Siegismund, Scientist, Genedata, Basel, Switzerland

Drug combinations are central to modern cancer therapies, and drug synergy prediction models have demonstrated strong performance on benchmark datasets. However, recent evidence suggests that many approaches may rely on shortcut learning. To address this challenge, we propose DICE-SynBa, a framework built upon DeepSynBa that incorporates feature compression, permutation-invariant representations, and disentangled parameter prediction. We evaluate DICE-SynBa in leave-cell-line-out and leave-drug-out scenarios that assess generalisation to unseen entities. Across both settings, DICE-SynBa outperforms existing methods, demonstrating improved generalisation and reduced shortcut learning.


Learn More