|Staff Category:||Postdoctoral Fellow|
|Contract Duration:||3 years|
|Closing Date:||7 April 2019|
A Postdoctoral position in machine learning and computational single-cell genomics is available in the Statistical Genomics and Systems Genetics group at our laboratory in the Genome Biology Unit at EMBL Heidelberg in Germany. Our research group is relocating from Cambridge to Heidelberg, where we bridge the excellence in molecular biology and biotechnology at EMBL Heidelberg with disease models and access to large biomedical datasets at the German Cancer Research Center Heidelberg. The position is funded via the recently awarded BMBF project MechML, which we are coordinating.The position will be jointly located at EMBL Heidelberg and
- develop novel machine learning models that integrate mechanistic prior information and knowledge in a principled manner
- apply these methods to large single-cell variation datasets with millions of cells, and to integrate spatial technologies with single-cell RNA-seq and epigenome methods
- contribute to the Human Cell Atlas, as a node in the analysis working group
- collaborate with partners in the MechML projects, the Human Cell Atlas, collaborators at EMBL, DKFZ and elsewhere
- build on previous developments and expertise in the group, including factor model, linear mixed models and deep learning methods
Recent relevant publications:
- Argelaguet, R., et al. (2018). Multi‐Omics Factor Analysis—a framework for unsupervised integration of multi‐omics data sets. Molecular Systems biology, 14, e8124.
- Svensson, V., et al. (2018) SpatialDE: Identification of spatially variable genes. Nature Methods, 343–346.
- Buettner, F., et al. (2017) f-scLVM: scalable and versatile factor analysis for single-cell RNA-seq.” Genome biology 18.1 (217): 212.
- Angermueller, Christof, et al. (2017) DeepCpG: accurate prediction of single-cell DNA methylation states using deep learning. Genome biology 18.1 (2017): 67.
- Buettner, F., et al. (2015). Computational analysis of cell-to-cell heterogeneity in single-cell RNA-sequencing data reveals hidden subpopulations of cells. Nature biotechnology, 33(2), 155.
- a doctoral degree or equivalent qualification in computer science, statistics, mathematics, physics, and/or engineering, or a degree in biological science
- previous experience in developing and applying computational methods applied to large datasets
- prior experience in developing statistical methodology in a genomics context, including gene expression analysis, factor models, GWAS and analysis of NGS data.
- previous usage of methods in any of the following fields is advantageous: statistics, machine learning, genetics, optimization and mathematical modeling
- proficiency with a high-level programming language (e.g., C++, Java) and/or appropriate scripting languages, and statistical data analysis tools such as R, MATLAB or Python
- ability to work independently and creatively
- excellent communications skills and be able to articulate clearly the scientific and technical needs, set clear goals and work within an interdisciplinary setting, communicating with other partners within the MechML project and within the Human Cell Atlas project
You might also have
- expertise in analysis and integration of multiomics data, statistical genetics, statistical interpretation and analysis of next-generation sequencing datasets and an ability to communicate results in scientific conferences and papers
- a background in molecular biology, or previous experience tackling biological questions