We are looking for Masters Students!

We are currently looking for Master’s students in the field of Bioinformatics for the following topics

Analyzing cell-free DNA fragmentation patterns in clinical samples

This project aims to improve diagnosis and prognosis through liquid biopsies in cancer and various other diseases. Cell-free DNA (cfDNA) carries information on the epigenetics of distal tissues and organs. We discern epigenetic signatures from cfDNA-sequencing data and connect those to diagnoses and patient outcomes. The student should have basic experience with Unix systems, some experience with at least one scripting language (e.g. Python or R), a strong understanding of biostatistics and a basic understanding of machine learning algorithms. Depending on the experience and interest of the student we offer projects focusing on either:

• Feature extraction from cfDNA-sequencing data using bioinformatic tools and comparison to nucleosome coverage or methylation data or
• Representation learning from high-dimensional cfDNA-sequencing data

Data integration in Cancer Genomics

The project’s aim is to characterize the effects of transcriptional and epigenetic processes on mutational patterns in cancer. The student should have basic experience with Unix systems and some experience with at least one scripting language (e.g. Python or R). Prior experience with genomics software and data formats is an advantage.

We are currently looking for Master’s students in Clinical Data Science for the following topics

Information extraction from German Radiology Report

Large, labeled datasets have driven deep learning methods to achieve expert-level performance on a variety of medical imaging tasks. There are some English radiology report datasets that have been labeled automatically to detect in presence of 14 observations by capturing uncertainties inherent in radiograph interpretation. We would like to investigate different approaches such as the information extraction paradigm to label radiology reports in another language such as German. We plan to explore the possibility of incorporating domain knowledge such as http://radlex.org/ and evaluate the effectiveness of it in the proposed framework. Since a radiology report comes with radiology images, we also would like to investigate the multi-modal approaches in our study.

Trait prediction using Big data and machine learning

Genome-wide association studies rely on big cohorts of hundreds of thousands of participants with gene sequences amounting to TB of information. This project is interested in predicting relevant traits like disease risk and identifying this risk’s genetic component. We also are interested in resolving possible confounders in this kind of data, like pairwise interactions.

The model and data reading are already implemented, objectives of a short project would be to:

• Accelerate data reading and training
• Perform experiments on performance and hyperparameter tuning.
• Select the best performing predictor and test in an external cohort.

The student should have experience with Unix Systems, good experience with Python and ML frameworks (preferably TF 2). Additional experience with quantitative genetic tools like plink would be advantageous.

Applications can be done by sending a CV to this e-mail along with a short description of the student’s motivation to join our lab.