Internship in drug discovery/computational biology at LHI/CPC, Helmholtz Munich

Are you interested in translational drug discovery and development? Burgstaller lab is working on development of antifibrotics against Idiopathic Pulmonary Fibrosis and we are looking for a master student for a computational/hybrid internship!

Lab background: Overproduction of extracellular matrix (ECM) by activated myofibroblasts as a result of cytokines like transforming growth factor β (TGFβ) is a key feature of IPF. Novel antifibrotics are urgently needed since the approved therapies only slow down disease progression. We took a top-down approach to drug discovery, conducting high-content drug screenings & structure-activity relationship (SAR) studies leading to the discovery of a new class of potent antifibrotics N23Ps. For lead development, we conducted a comprehensive SAR analysis on N23P-derivatives using high-content ECM deposition assays with primary IPF-derived lung fibroblasts. We are currently continuing lead optimization while also conducting target identification and mode-of-action studies. Read Gerckens, et. al. (2023) for more background information!

When and how long: Start as soon as possible and for a period of 2 months (flexible / with possibility of extension).

Project background: One of the key steps of preclinical drug discovery is lead optimization which involves structure-activity relationship (SAR) analysis. Here, trends between the changes to structural components and activity (like potency, toxicity, etc.) are studied to improve and optimize the lead compound. We have developed an automated pipeline that helps us process our lab-generated data and perform SAR for potency data. To improve the compounds further, we are now looking to explore stability and other ADMET- related properties using AI models to not only identify under-explored combinations but also synthesize new compounds based on these results. Initial steps would involve benchmarking cutting-edge AI predictions against real-world ADMET data followed by identifying best residues through SAR to suggest new molecules.

Who we are looking for: A master's student from life sciences who knows how to do basic coding and is interested in a computational/hybrid (80% comp, 20% lab) project that will primarily involve data engineering, statistical modelling, and cheminformatics. Extensive knowledge in AI/ML is not necessary, since this project involves application, not development of AI models. Background in Python programming and willingness to explore AI in drug discovery literature would be ideal.
Exploration, inquisitiveness, and new ideas will be encouraged.

What you learn:
- Principles of small-molecule drug discovery and development research
- Concepts and application of cheminformatics and AI for property prediction
- Preprocessing data and deploying statistical and AI models.
- Analyzing & interpreting the same and validating these inferences in the lab.
- Coding in Python (handling dataframes, plotting, cheminformatics (RDKit package), and statistics (scikit-learn))

This is a great opportunity to understand the complexities of small-molecule drug development while getting a firsthand experience of a multidisciplinary effort involving biologists, MDs, computational biologists and medicinal chemists. If interested, please send an email with a short cover letter and CV to [email protected].