Postdoctoral researcher in machine-learning for multi-omics

• Apply interpretable machine learning approaches to identify multi-omic signatures and build predictive models for Treatment response.
• Establish and maintain centralized storage infrastructure for processed multi-omic datasets from consortium partners And community use.
• Collaborate with clinical and experimental partners across multiple countries.

• PhD in Bioinformatics, Computational Biology, Statistics, Computer Science, or related field
• Experience with high-throughput genomic data analysis
• Experience in machine learning and statistical modeling for genomic data
• Excellent English communication skills and team work skills
• Experience with multi-omics data integration and cancer genomics would be a plus

Heidelberg University is a comprehensive university with a strong focus on research and international standards. With around 31,300 students and 8,400 employees, including numerous top researchers, it is a globally respected institution that also has outstanding economic significance for the Rhine-Neckar metropolitan region. The department of Bioinformatics at the Institute of Pharmacy and Molecular Biotechnology (IPMB) of Heidelberg University is offering a 3-year full-time (100%; 39,5 h/week) postdoc position in Multiomics Data Integration and Machine-Learning for therapy response prediction in metastatic cancer. This position is funded by the European Partnership in Personalized Medicine (EP PerMed) within a trans-national consortium involving research groups from Spain, Italy, France and Germany, focusing on metastatic papillary renal carcinoma. The consortium will perform multi-omic characterization of metastatic pRCC samples across four European countries, integrating real-world drug response data with preclinical model testing to create the world′s largest metastatic pRCC database. Heidelberg University leads the multidimensional data integration task, focusing on centralized data management and machine learning-based integration of multi-omic datasets. Our goal is to identify predictive signatures and develop treatment response models to enable biomarker-guided clinical trials.