The Atanackovic Lab focuses on developing cutting-edge machine learning methods for understanding and modeling natural (physical) systems from data. Our research spans multiple domains at the intersection of artificial intelligence and biology.

Machine Learning

Our work in machine learning focuses on developing novel approaches to model complex and high-dimensional systems from data.

Key Areas:

• Generative Modeling: Flow matching, diffusion models, generative flow networks (GFlowNets), and more
• Representation Learning: Learning to represent complex systems from data
• Causal Inference: Causal discovery and inference for (dynamical) systems

Systems Biology

We develop computational methods that help us decode and understand complex biological systems at multiple scales, from molecular interactions to cellular dynamics.

Key Areas:

• Single-Cell: Computational methods for single-cell RNA sequencing data
• Gene Regulatory Networks: Inference and modeling of gene interaction networks
• Cellular Dynamics: Modeling temporal changes in cellular states
• Perturbation Response Prediction and Modeling: Understanding how interventions affect biological systems

Interested in our research? Check out our publications or learn how to join our lab!