Home

My research focuses on designing algorithms for efficient and robust adaptation under continuous distribution shifts with applications in genomics, perturbation biology and experimental design. I'm interested in representation learning, generative modeling and causal inference. Since my first appointment in 2014, I have had the pleasure of collaborating with several leading biomedical research institutions, including the Peter MacCallum Cancer Centre, Cancer Therapeutics CRC Australia, the Garvan Institute of Medical Research, Pfizer, Roche, the Broad Institute, Wellcome Sanger Institute, WEHI, and Helmholtz Munich, where I spent most of my time. I was named a Rising Star in Data Science by Stanford University in 2025.

LinkedIn Google Scholar CV

Research highlights

April 2026: Three papers accepted to ICLR 2026 MLGenX and Gen2 workshops. SCOPE was featured in Valence Labs blog post on Virtual Cell @ ICLR 2026.
April 2026: New preprint "Perturbation-guided mapping of colorectal cancer cell states to causal mechanisms" is out on bioRxiv.
Jan 2026: I organised and presented at the Perturbation Modeling Forum at Helmholtz Munich.
Jan 2026: I gave a talk at the Leopoldina Meeting (German National Academy of Sciences) at TUM on my work on linking observational and pertubation atlases.
Sep 2025: I was named a Rising Star in Data Science by Stanford University.

Selected Links

Publications

Below is a selected list of my publications.

Hediyeh-zadeh*, S., Toh*, T. S., Dufva, O., Serra, G., Jakhmola, R., Fourneaux, C., ... Garnett, M. J. Perturbation-guided mapping of colorectal cancer cell states to causal mechanisms. bioRxiv, 2026-03.
Zheng*, Z., Hediyeh-Zadeh*, S., Liu, J., Theis, F. J. Beyond single-axis designs: multi-objective optimization for complex perturbation atlases. ICLR 2026 MLGenX.
Pinto, G. R., Cho, S. H., Ozleyen, S. Y., Von Schack, D., Apruzzese, W., Hediyeh-Zadeh*, S., Theis*, F. J. Structured and interpretable patient embeddings from Single-Cell Foundation Models. ICLR 2026 Gen2. Co-last author.
Schunke, L., Hediyeh-Zadeh, S., Salas, S. M., Can, A. O., Munich, H., Theis, F. J. Generative Modeling of Spatial Transcriptomics via Gaussian Mixture Flow Matching. ICLR 2026 Gen2.
Litinetskaya, A., Shulman, M., Hediyeh-zadeh, S., Moinfar, A. A., Curion, F., Szalata, A., ... Theis, F. J. Multimodal weakly supervised learning to identify disease-specific changes in single-cell atlases. bioRxiv, 2024-07.
Xu*, Q., Halle*, L., Hediyeh-Zadeh, S., Kuijs, M., Riedweg, R., Kilik, U., ... Camp, J. G. An integrated transcriptomic cell atlas of human endoderm-derived organoids. Nature Genetics, 2025, 1-12.
Kuemmerle, L. B., Luecken, M. D., Firsova, A. B., Barros de Andrade e Sousa, L., Strasser, L., Mekki, I. I., ... Hediyeh-zadeh, S. (11/21), ... Theis, F. J. Probe set selection for targeted spatial transcriptomics. Nature Methods, 2024, 1-11.
Ali*, M., Kuijs*, M., Hediyeh-Zadeh, S., Treis, T., Hrovatin, K., Palla, G., ... Theis, F. J. GraphCompass: spatial metrics for differential analyses of cell organization across conditions. Bioinformatics, 40(Supplement_1), July 2024, i548-i557. DOI
Baldoni, P. L.*, Chen, Y.*, Hediyeh-Zadeh, S., Liao, Y., Dong, X., Ritchie, M. E., ... Smyth, G. K. Dividing out quantification uncertainty allows efficient assessment of differential transcript expression with edgeR. Nucleic Acids Research, 52(3), 2024, e13-e13.
De Donno, C., Hediyeh-Zadeh, S., Moinfar, A. A., Wagenstetter, M., Zappia, L., Lotfollahi, M., Theis, F. J. Population-level integration of single-cell datasets enables multi-scale analysis across samples. Nature Methods, 2023. Helmholtz Munich Best Paper Award.
Hediyeh-Zadeh, S., Webb, A. I., Davis, M. J. MsImpute: Estimation of missing peptide intensity data in label-free quantitative mass spectrometry. Molecular and Cellular Proteomics, 2023. Outstanding Technological Innovation article by MCP journal.
Heumos*, L., Schaar*, A. C., Lance, C., Litinetskaya, A., ... Hediyeh-Zadeh, S., ... Schiller, H., and Theis, F. J. Best practices for single-cell analysis across modalities. Nat Rev Gen, 2023.
Lotfollahi, M., Rybakov, S., Hrovatin, K., Hediyeh-Zadeh, S., Talavera-Lopez, C., Misharin, A. V., Theis, F. J. Biologically informed deep learning to query gene programs in single-cell atlases. Nature Cell Biology, 2023, 1-14.
Hediyeh-zadeh, S., Lotfollahi, M., Theis, F. J. Continual single-cell architecture surgery for reference mapping. ICML 2022 Workshop on Computational Biology.
Hediyeh-Zadeh, S., Fischer, T., Theis, F. Disentanglement via mechanism sparsity by replaying realizations of the past. ICLR 2024 Workshop on Machine Learning for Genomics Explorations.
Hediyeh-zadeh*, S., Whitfield*, H. J., Kharbanda, M., Curion, F., Bhuva, D. D., Theis, F. J., Davis, M. J. Identification of cell types, states and programs by learning gene set representations. bioRxiv, 2023-09.
Aliee, H., Kapl, F., Hediyeh-Zadeh, S., Theis, F. J. Conditionally Invariant Representation Learning for Disentangling Cellular Heterogeneity. arXiv preprint arXiv:2307.00558, 2023.

Home

Research highlights

Selected Links

Publications

Students

Mentoring/Co-supervision

Supervision

Contact