Andreas Hellander

This work uses federated learning to predict compound mechanism of action from cell painting image data, showing its effectiveness in handling data heterogeneity across institutions.

This study uses a 3D cell-based computational model to show that oriented cell divisions and repulsive mechanical interactions drive columnar cartilage formation in embryos.

The paper develops a computational pipeline to evaluate inference accuracy across different model levels and parameter inference settings for negative feedback gene regulation.

The paper introduces the HASTE Toolkit, a cloud-native toolkit for intelligent data pipelines that prioritize resource usage based on data content, demonstrating it in microscopy imaging case studies.

The paper develops a human-in-the-loop semi-supervised learning workflow to efficiently explore stochastic gene regulatory network models and identify interesting behaviors.