Hasso-Plattner-InstitutSDG am HPI
Hasso-Plattner-InstitutDSG am HPI
Login
  • de
 

Hendrik Raetz, M.Sc

Doctoral student at Data Analytics and Computational Statistics Group

Supervisor: Dr. Christoph Schlaffner

Topic: Machine Learning in Clinical Proteomics and Metaproteomics

Contact

Office:K-E.09/10
Phone:+49 331 5509 - 4944
E-Mail:hendrik.raetz(at)hpi.de

 

Research

An Unbiased Explainable Deep Learning Approach for SARS-CoV-2 Infection Outcome Stratification and Prediction

In recent years, digital advances in bioinformatics allowed for the extensive gathering and processing of proteomics data. This data is usually obtained via mass spectrometry (MS) experiments that result in large amounts of high-dimensional data. Using current methods, this sheer mass of data is often hard to analyze due to time and resource restrictions. Thus, it is important to develop improved processing methods that are not only faster, but also possess adequate sensitivity, while keeping false discovery rates low. This is especially important as the SARS-CoV-2 pandemic brought on large-scale studies of unprecedented size for proteomics, which need to be analyzed thoroughly and efficiently.

Recently, methods from the field of machine learning have proven to be successful in the analysis of complex proteomics data, such as the detection and intensity estimation of peptide feature intensity. In this work, we want to apply machine learning methods to efficiently analyze large amounts of MS data and predict sample conditions, e.g., disease presence or progression, without sequence-dependent preprocessing. We will especially focus on the unbiased understanding of disease outcomes in SARS-CoV-2 infected patients and their prediction. For this, we will represent samples as image-like data structures so that they can be processed using fine-tuned deep-learning models from the computer vision domain. The pixels in these pseudo images represent the abundances of the detected peptides and thus provide unbiased raw features of proteins involved in the disease without prior knowledge of sequence or modification. This peptide information is the key to explaining the difference in course of disease and could lead to novel biomarkers.

With the help of our machine learning model, we hope to gain new insights into the SARS-CoV-2 disease, increase analysis efficiency and thus support the treatment of SARS-CoV-2 patients.

Sorting your recycling: Understanding lysosomal-storage diseases

In cells there is a constant turnover of macromolecules, such as proteins and lipids, meaning that they are continuously degraded and newly synthesized. This ensures that old, non-functioning proteins are broken down into smaller building blocks that can be used to synthesize new, functioning and different proteins. Lysosomes play an important role in this process as they are the main cell organelle that is responsible for degrading biomolecules. The impairment of their function will impact the cell function negatively since it will lead to an accumulation of waste products, which in turn can lead to the development of diseases. These are known as Lysosomal Storage Disorders (LSDs). Additionally, it has been shown that the lysosome is involved in diseases such as Alzheimer’s and Parkinson’s disease, as well as cancer.

Using special enrichment methods, our project partners at the University of Bonn assessed the naturally low-abundant lysosomal proteins in various perturbation experiments using quantitative mass spectrometry (MS) experiments. In our part of the project, we model the half-life times of individual proteins, which is the time needed to degrade half of the protein mass, to gain insights into the effects of perturbations on lysosomal function. We hope that these findings will help our understanding of the function of this important cell organelle and will help in developing new treatments for LSDs

 

Presentations

  • Talk at the Joint Workshop of the German Research Training Groups in Computer Science in Dagstuhl

Other Activities

  • Member of the faculty council of the Digital Engineering Faculty (since October 2023)
  • Member of the appointment comittee "Open Topic"

Teaching

Winter term 2023/2024

  • Bachelor's project on building a protein analysis platform

Summer term 2023

Winter term 2022/2023: