𝐏𝐨𝐬𝐭𝐝𝐨𝐜: 𝐀𝐩𝐩𝐥𝐲𝐢𝐧𝐠 𝐌𝐋/𝐀𝐈 𝐭𝐨 𝐡𝐢𝐠𝐡-𝐝𝐢𝐦𝐞𝐧𝐬𝐢𝐨𝐧𝐚𝐥 𝐛𝐢𝐨𝐦𝐞𝐝𝐢𝐜𝐚𝐥 𝐝𝐚𝐭𝐚 (Julia preferred/Python)

Are you looking for a postdoc position that bridges AI and clinical research? Would you like to work between institutions to work on an impactful project with highly granular cohort data? Do you have a background or interest in molecular epidemiology, bioinformatics or biostatistics, and want to apply machine learning methods to multi-omics data?

Medical Centre Mainz and TU Kaiserslautern might be the right place for you, with a project on the application of AI methods to understand the cardiovascular illness and Sars-CoV-2.

𝐓𝐡𝐞𝐫𝐞 𝐚𝐫𝐞 𝐚𝐥𝐬𝐨 𝐨𝐭𝐡𝐞𝐫 𝐨𝐩𝐩𝐨𝐫𝐭𝐮𝐧𝐢𝐭𝐢𝐞𝐬 𝐚𝐯𝐚𝐢𝐥𝐚𝐛𝐥𝐞; 𝐬𝐞𝐞 𝐚𝐥𝐬𝐨 𝐨𝐮𝐫 𝐡𝐨𝐦𝐞𝐩𝐚𝐠𝐞 𝐡𝐭𝐭𝐩𝐬://𝐬𝐞𝐛𝐚𝐬𝐭𝐢𝐚𝐧.𝐯𝐨𝐥𝐥𝐦𝐞𝐫.𝐦𝐬/𝐣𝐨𝐛𝐬/

More details:
The postdoc will be affiliated with University Medical Center Mainz and TU Kaiserslautern and could be physically based in either institution, as preferred by the postdoc. The research will be supported by an interdisciplinary team with expertise in Systems Medicine (Prof. Philipp Wild, University Medical Center Mainz) and Artificial Intelligence (Prof. Dr. Sebastian Vollmer, DFKI/TU Kaiserslautern).

The project involves highly granular data collected as part of the Gutenberg Health Study—a prospective cohort study of a representative sample (N=15,000) of the population of Mainz — including genotyping, DNA methylation, transcriptomics, proteomics and extensive time-varying clinical information.

A key aim is to investigate mechanisms and effects of Covid-19 among some 500 participants who tested positive for the virus. How does the molecular profile (especially the proteomic profile) change following Sars-CoV-2 infection? What mechanisms distinguish symptomatic and asymptomatic infections? Which trajectories and processes are associated with severe disease outcomes or long-term effects?

In collaboration with partners, we will also investigate the role of auto-immunity in Sars-CoV-2 infection. In the longer term, we are interested in cardiac events, such as atherosclerosis and atherothrombosis. To this end, multidimensional datasets at protein, lipid and metabolite levels together with bioinformatics workflows, machine learning and multi-OMICS data integration enable comprehensive characterization of clinical samples and deciphering of complex pathophysiological mechanisms in different disease settings. The latter will involve partners such as Biotech and TRON.

An ideal candidate has a background or an interest in molecular epidemiology, bioinformatics or biostatistics, allowing direct interpretation of the results. They should have experience or interest in high-dimensional data analysis, especially applying ML methods to multi-omics data.