Marianna Rapsomaniki

Overview

Marianna Rapsomaniki

Pronouns

She/Her/Hers

Title

Staff Research Scientist

Location

IBM Research Europe - Zurich Zurich, Switzerland

Bio

Marianna is leading the AI for single-cell research team at IBM Research Europe in Zurich. The overarching goal of her team is modeling spatiotemporal tumor heterogeneity across different scales of biological organization, and understanding how it affects cancer initiation, progression, and response to treatment. To achieve that, her team combines machine learning and deep learning approaches to develop computational methods able to extract biologically meaningful patterns from large-scale, heterogeneous, and noisy single-cell data, with or without spatial resolution. Marianna holds a Diploma in Computer Science and Engineering and a Master's in Bioinformatics, both from the University of Patras, Greece. Her PhD research was carried out working jointly in the Cell Cycle lab of the University of Patras and the Automatic Control Lab of ETH Zurich and involved stochastic hybrid modeling of biological systems, with applications in protein mobility within the nucleus, DNA re-replication, and parameter inference from live-cell imaging data. Her research has been supported by a Swiss Government Excellence Scholarship, the State Scholarships Foundation of Greece, and the Swiss National Science Foundation (SNSF).  

Check our team's Publications, and collection of open-source tools!

News:

  • Our team's paper ChromFormer: A transformer-based model for 3D genome structure prediction selected as a spotlight talk at the Learning Meaningful Representations of Life workshop in NeurIPS - watch
  • Presentation of our team’s work in Applied Machine Learning Days (AMLD) - watch
  • Our team was awarded an SNSF Sinergia grant PROMETEX (collab with the Kruithof-de Julio Urogenus lab, University of Bern, and the Alexandrov Spatial Metabolomics lab, EMBL).
  • Read about our latest work on deciphering breast cancer heterogeneity here, or watch the related video from ReutersTV.

Publications

Patents

Projects

AI methods for precision therapies.png

AI methods for precision therapies

Developing AI methods for heterogeneity-aware precision therapies.
  • Healthcare
  • Accelerated Discovery
  • Machine Learning
CellCycleTRACER.png

CellCycleTRACER

A novel computational method to quantify cell cycle and cell volume variability.
  • Healthcare
Quantifying biological heterogeneity from single-cell data.png

Quantifying biological heterogeneity from single-cell data

Understanding, modeling and quantifying different sources of heterogeneity from single-cell measurements.
  • Healthcare
  • Accelerated Discovery
  • Machine Learning
AI methods for precision therapies

AI for single-cell research

Understanding spatiotemporal heterogeneity across different scales of biological organization.
  • Healthcare
  • Accelerated Discovery
  • Machine Learning
Modeling the 4D genome.png

Modeling the 4D genome

Modeling the 4D genome with deep learning and stochastic simulations.
  • Healthcare
  • Accelerated Discovery
  • Machine Learning
Modeling the Spatial Heterogeneity of the Tumor Microenvironment.png

Modeling spatial heterogeneity of the tumor microenvironment

Combining spatial single-cell omics with AI to model the complexity of the tumor micorenvironment and enable novel spatial biomarker discovery.
  • Healthcare
  • Accelerated Discovery
  • Machine Learning