Sunday 11 September 2011

PhD position at Imperial College London


EPSRC 3-year PhD Studentship
Department of Surgery and Cancer
Imperial College London

Overcoming the Protein Crystallization Bottleneck by Machine Learning


Applications are invited for a 3-year PhD studentship funded by the Engineering and Physical Sciences Research Council commencing 2011 under the joint supervision of Prof. Naomi Chayen and Dr Tim Ebbels in the field of computational protein crystallization.

The Project
Protein crystallography plays a major role in modern biomedicine because proteins, being the major machinery of life, are often the targets of drugs. Protein functions are determined by their three-dimensional structure, hence detailed understanding of protein structure is essential for rational design of therapeutic treatments. The most powerful method for determining the structure of proteins is X-ray crystallography which is totally reliant on the availability of high quality crystals. However, producing useful crystals has always been the bottleneck to structure determination. With the advent of genomics/proteomics and hence the exponentially increasing number of potential drug target proteins, this problem is becoming increasingly acute. While conventional techniques effectively rely on trial and error to find the optimal crystallization conditions, statistical and machine learning approaches have the potential to significantly increase the efficiency and accuracy of the process. In this project we will explore the ability of such computational tools to improve the protein crystallization process. Specifically, the student will:

1.     Apply a multivariate Design of Experiments approach to optimise crystallisation conditions using fewer experiments than conventional methods.
2.     Investigate existing databases of crystallisation conditions and associated outcomes (crystal quality) to derive multivariate models able to predict crystallisation from a set of input conditions.

The project will investigate the use of a diverse array of machine learning tools such as genetic algorithms, partial least squares regression and kernel density approaches. While the project will be primarily computational in nature, the student will also have the opportunity to gain experience in the experimental side of protein crystallization. The final result will be a more efficient methodology for conducting crystallisation experiments and an in silico approach to prediction of crystallizability.

Studentship Details
Applicants should hold (or obtain soon) a masters degree (or equivalent overseas qualification) in a physical science, bioinformatics or otherwise numerate field. Outstanding candidates possessing an appropriate bachelors degree may also be considered. The studentship is ONLY open to students who hold settled status in the UK and have been 'ordinarily resident' in the UK for three years. Further eligibility details can be found at:

For informal enquiries and application please contact Prof. Naomi Chayen (n.chayen@imperial.ac.uk) or Dr Tim Ebbels (t.ebbels@imperial.ac.uk). Pleaase send a full CV, stating your nationality, and the full contact details of two academic referees.

No comments:

Post a Comment