Postdoctoral computer scientist – Algorithms for high-performance genomic data fusion
Do you know how to tackle large data sets? Do you know how to leverage high-performance computing for machine learning in computational biology?
We are looking for a motivated postdoctoral researcher who can help us to scale up machine learning algorithms for data fusion of genomic data.
How to mine multiple heterogeneous sources of genomic data in an integrated fashion is still an open problem. Researchers need to analyse and integrate sequences and their variants, expression data, protein-protein interactions, functional annotations, biomedical literature, and so on – all at the same time. Genomic data fusion (Moreau and Tranchevent, 2012; Aerts et al., 2006) offers a range of approaches to tackle this challenge. Among such methods, the University of Leuven has been a pioneer in the use of kernel methods to integrate heterogeneous omics data (De Bie et al., 2007; Yu et al., 2009). The key advantage of kernel methods for mining heterogeneous data is that when multiple data sets are available, they all lead to kernel similarity matrices independently of the original type of data. Those kernels can then be efficiently integrated using Multiple Kernel Learning (De Bie et al., 2007; Yu et al., 2009). The goal of the project is to develop simple, efficient, and scalable kernel methods for genomic data fusion using low-rank approximation, random projections, or ensemble methods and implement them in a large-scale parallel execution environment.
We offer a competitive package and a fun, dynamic environment as part of the Exascience Lab, a world-class collaboration with Intel (intel.eu), Janssen Pharmaceuticals (janssenpharmaceuticalsinc.com), and IMEC (imec.be). The University of Leuven is one of Europe’s leading research universities, with English as the working language for research. Leuven lies just east of Brussels, at the heart of Europe.
The ideal candidate holds a PhD degree in computer science or computational biology. Experience with efficient algorithms for machine learning and scale-up of such algorithms to large genomic data sets via high-performance, cloud, or grid computing are core assets. Programming and data analysis experience is essential. Willingness to interact with genomics experts is mandatory. Good communication skills are important for this role. The candidate will collaborate closely with researchers across the consortium and contribute to the reporting of the project. Qualified candidates will be offered the opportunity to work semi-independently under the supervision of a senior investigator, mentor PhD students, and contribute to the acquisition of new funding. A two-year commitment is expected from the candidate. Preferred start date as soon as possible.
Moreau Y, Tranchevent LC. Computational tools for prioritizing candidate genes: boosting disease gene discovery. Nat Rev Genet. 2012 Jul 3;13(8):523-36.
Yu S, Falck T, Daemen A, Tranchevent LC, Suykens JA, De Moor B, Moreau Y. L2-norm multiple kernel learning and its application to biomedical data fusion. BMC Bioinformatics. 2010 Jun 8;11:309.
De Bie T, Tranchevent LC, van Oeffelen LM, Moreau Y. Kernel-based data fusion for gene prioritization. Bioinformatics. 2007 Jul 1;23(13):i125-32.
Aerts S, Lambrechts D, Maity S, Van Loo P, Coessens B, De Smet F, Tranchevent LC, De Moor B, Marynen P, Hassan B, Carmeliet P, Moreau Y. Gene prioritization through genomic data fusion. Nat Biotechnol. 2006 May;24(5):537-44.
How to apply
Please send in PDF before November 30, 2013:
1. CV including education, research experience, and bibliography
2. Three references (with phone and email)
3. A statement of purpose describing why you are qualified for the position and what your contribution could be
to Ms. Mimi Deprez (email@example.com), cc Prof. Yves Moreau (firstname.lastname@example.org) and Ms. Ida Tassens (email@example.com).
Pre-application inquiries can be sent to Yves.Moreau@esat.kuleuven.be.