Anne Hartebrodt

Anne Hartebrodt is a Postdoctoral Researcher at the Biomedical Network Science Lab in the Department of Artificial Intelligence in Biomedical Engineering at Friedrich-Alexander University Erlangen-Nürnberg (FAU), Germany. She has been working at FAU since March 2023, focusing on network-based embeddings and carbon-aware computing for bioinformatics following her PhD completion at the University of Southern Denmark.

Her research spans multiple cutting-edge domains at the intersection of AI and biomedical science:

• Bioinformatics and computational biology with emphasis on network science
• Federated learning and privacy-preserving computation for biomedical applications
• Single-cell omics analysis and gene regulatory network inference
• Carbon-aware computing for sustainable bioinformatics research
• Machine learning applications in proteomics and cancer research

Dr. Hartebrodt's publication record demonstrates expertise in developing computational methods that bridge theoretical machine learning with practical biomedical challenges, particularly in maintaining data privacy while enabling collaborative research across institutions. Her work on federated learning approaches has been published in high-impact journals including Nature Computational Science and Bioinformatics.

Her research leadership includes:

• Principal investigator for the 'Dimensionality reduction for molecular data based on explanatory power of differential regulatory networks' project (NetMap) funded by the Bundesministerium für Forschung, Technologie und Raumfahrt (2023-2026)
• Development of FedProt for privacy-preserving protein analysis
• Creation of Decoil for reconstructing extrachromosomal DNA structures
• Advancements in federated singular value decomposition methods

Dr. Hartebrodt actively supervises multiple graduate students working on gene regulatory networks, differential expression analysis, and carbon-aware optimization. Her laboratory work in the Biomedical Network Science Lab focuses on developing innovative approaches to analyze complex biological networks while addressing computational sustainability through carbon-aware computing methods.