MedUni Vienna successful in WWTF Life Sciences 2023 call ’Understanding Biology with AI/ML’

- EN - DE

MedUni Vienna was successful with several submissions to the Life Sciences 2023 Call "Understanding Biology with AI/ML" of the Vienna Science, Research and Technology Fund WWTF. Diana Mechtcheriakova, Marjan Slak Rupnik and Juliane Winkler were able to acquire highly endowed funding for their research projects.

The WWTF Life Sciences 2023 call "Understanding Biology with AI/ML" was aimed at researchers in Vienna who want to carry out an excellent and interdisciplinary research project (2 - 4 years) in biology, biomedicine or clinical sciences that applies innovative methods of artificial intelligence (AI) or machine learning (ML) to large data sets. The funding volume per project is between ¤400,000 and ¤800,000.

Funded projects at MedUni Vienna:

LS23’006 Diana Mechtcheriakova (MedUni Vienna, Institute of Pathophysiology and Allergy Research)
LymphoidStructureMiner: AI-based exploration of the immunological contexture of lymphoid structures in translational research
Duration: 24 months, funding amount: € 480,236
Co-PI: Amirreza Mahbod (Danube Private University), Anastasia Meshcheryakova (MedUni Vienna) Lymphoid structures are highly organized multicellular units of the immune system that can recognize and respond to a variety of pathogens and cancer cells. In cancer patients, lymphoid structures are analyzed using tissue image cytometry. The aim of this project is to develop novel deep learning-based methods to recognize lymphoid structures in digital microscopic images and enable accurate analysis of their cellular composition. The project is part of translational research in the field of immuno-oncology and aims to nominate new biomarkers and identify new strategies for patient stratification.

LS23’026 Marjan Slak Rupnik (MedUni Vienna, Institute of Physiology)
Understanding pancreas biology with AI/ML
Duration: 48 months, funding amount: € 879,647
Co-PI: Gasper Tkacik (ISTA), Manami Hara (University of Chicago) The pancreas measures the nutrient content of the blood and secretes hormones accordingly. While research to date has focused on the molecular processes in individual cells, it is still unclear how these cells work together to coordinate response functions. This project will record the activity of multiple pancreatic cells simultaneously at high temporal resolution under different conditions. ML methods will be used to identify subpopulations of different cell types, infer cell-cell interactions and predict optimal interactions to maintain healthy blood glucose levels.

LS23’067 Juliane Winkler (MedUni Vienna, Center for Cancer Research)
Multiscale discovery of cellular and microanatomical determinants of metastasis
Duration: 48 months, funding amount: € 799,960
Co-PI: André Rendeiro (CeMM), Zsuzsanna Bagó-Horváth (MedUni Vienna) Metastases occur in about 30% of breast cancer patients. While some tumor cell-specific determinants of metastasis have been identified, the role of the tissue environment is still largely unknown. This project will use xenograft models to identify the microenvironmental factors that are critical for metastasis. Imaging technologies will be combined with ML models to assemble multi-layered information into a detailed map of metastasis. The project will help to better understand the spread of cancer and identify patients at high risk of metastasis.

Further funding as part of the WWTF Life Sciences 2023 Call "Understanding Biology with AI/ML"

LS23’028 Giulio Superti-Furga (CeMM - Research Center for Molecular Medicine of the Austrian Academy of Sciences)
mlDIAMANT: machine learning decodes interaction archetypes of membrane proteins to predict the effect of genetic variants
Duration: 36 months, funding amount: € 707,724

LS23’002 Jonas Ries (University of Vienna)
Dynamic nanoscale reconstruction of endocytosis with high-throughput superresolution microscopy and machine-learning
Duration: 36 months, funding amount: € 799,809

LS23’014 Marisa Hoeschele (ÖAW - Austrian Academy of Sciences)
Analysis of Nonhuman Intercommunication with Machine Learning
Duration: 48 months, funding amount: € 799,885

LS23’024 Angela Stöger-Horwath (ÖAW - Austrian Academy of Sciences)
Decoding elephant communication with AI
Duration: 48 months, funding amount: € 876,188

LS23’053 Ivo Hofacker (University of Vienna)
Determinants of mRNA Lifetime and Translation Efficiency
Duration: 48 months, funding amount: € 799,100

LS23’070 Manuel Zimmer (University of Vienna)
An interdisciplinary approach to learn and test the causal mapping between neural network dynamics and behavior
Duration: 48 months, funding amount: € 799.998