On the following pages you see a current overview. Questions regarding the research activities of our department can be directed to research@bioinf.med.uni-goettingen.de at any time.

CRU 5002

Desciphering genome dynamics for subtype specific therapie in pancreatic cancer.

PerMiCCion

Performing a comprehensive characterization of the tissue micro- and mycobiome of young CRC patients, identifying the oncogenic microbiome signature and understanding its influence on oncogenic signaling resulting in tumor development and progression. 

Resolve PCC

Long-/post COVID condition (PCC) is difficult to define due to clinical heterogeneity and limited understanding of its etiology. In RESOLVE-PCC, we aim at answering the questions: 1) Which symptoms are causally related to the infection? 2) Which risk factors determine severity and persistence? 3) Are there distinct subgroups with different underlying disease mechanisms and treatment requirements?

AutoBuSTeD stained pipeline steps

AutoBuSTeD

This project develops the hardware and image analysis software for an automated bubble sweat test diagnostics system developed with partners from the MHH in Hannover.

CandActCFTR

This project develops a generic software platform / toolbox to handle and annotate chemical structure libraries in a way that clinical researchers can organize chemical structures annotating a biological system.

Stracyfic

We aim at developing a usable common standard for the required experiments, the automated analysis via software and providing the experimental hardware setups for an easy dissemination of the technique to other sites.

FDLP

FDLP - Federated Learning in Lymphoma Pathology: Infrastructure, Models, Extension Algorithms, Detection of High-Risk Patients.

This poject supports the development of federated machine learning methods to develop models that enable the prediction of prognostic subtypes.

TRR 274 - Checkpoints of Central Nervous System Recovery

Our aim is to define the immunological, glial and neuronal checkpoints that faithfully predict the outcome of CNS injuries, and to develop intervention strategies targeting these checkpoints that guide an injured CNS tissue towards recovery.

FAIrPaCT I/ FAIrPaCT II

The FAIrPaCT I project develops a federated AI-based software system to harness big data from molecular analyses, imaging, and clinical cohorts in pancreatic cancer.  
In its second phase, FAIrPaCT II, robust multimodal models will be trained on multi-omics data and histopathology images to improve prediction of treatment responses. 

Counterfactual domain-adaptive machine learning for personalized drug recommendations in cancer treatment

In this project, we use cutting-edge AI methods to predict the effects of drugs and combination therapies against cancer. By integrating data from large-scale cell experiments and adapting our models to real tumors, we aim to discover new treatment options and enable personalized therapies.

OUTCAST-AI

Long- and Post-COVID remain poorly understood, with diverse symptoms persisting for weeks or months after infection. The OUTCAST-AI consortium leverages advanced data analysis to uncover disease subtypes, cellular mechanisms, and therapeutic targets, paving the way for improved treatment and care strategies.

PANDA

Personalized ANalysis for Drug Activity in Pancreatic Cancer

This project aims to analyze existing drug screening data from pancreatic cancer cell lines to identify personalized treatment strategies for patients.

MTB-Report

In this project we develop methods and tools to extract information relevant to the patient and present it to the clinician.

IMAGINE

IMAge Guided precIsion therapy NEtwork in Lower Saxony

An interdisciplinary project with the aim to develop develop and provide a digital support system for harmonized processes and workflows within the model region, accompanying the entire journey of cancer patients.

 

CKDNapp

The Chronic Disease Nephrologist's App (CKDNapp) is designed as a clinical decision support system to assist the practising nephrologist in the management of patients with chronic kidney didease. 

That might also interest you

Follow us