Connectionists: Experienced researcher in machine learning for personalized medicine

[Felix Agakov]

Experienced Researcher in “Machine Learning for Personalized Medicine”

Project title: Development of methods for patient stratification and disease subtyping for tailored medical interventions

Host Institution: Pharmatics Limited, Edinburgh BioQuarter, Edinburgh, UK.

Applications are invited for an Experienced Researcher (ER) fellowship in the field of Machine Learning for Personalized Medicine (MLPM), to be funded by the Marie Curie Initial Training Network MLPM2012 of the 7th Framework Programme of the European Commission. MLPM (http://mlpm.eu) is a consortium of several universities, research institutions and companies located in Belgium, France, Germany, the Netherlands, Spain, Switzerland, UK, and in the USA. MLPM offers an excellent training environment in the research field at the intersection of Machine Learning and Medicine. It includes several academic labs with expertise in Statistical Genetics or Machine Learning, and private companies that are active in this field. Its goal is to educate interdisciplinary experts who will develop analytical methods for tailoring medical interventions to individual patients based on their genetic and molecular profiles, and who will spur scientific and commercial developments in precision medicine. The recruited ER will be based at award-winning start-up company Pharmatics Limited in Edinburgh, UK. The ER will visit other nodes and attend training events of the network, in particular the annual summer schools on Machine Learning for Personalized Medicine. The immediately available position is fully funded (100% employment) until 31/12/2016 according to the Marie Curie programme, which offers a highly competitive and attractive salary.

Research project: The recruited ER will develop novel machine learning methods for disease subtyping and patient stratification based on heterogeneous high-dimensional molecular measurements and clinical/environmental variables. The methods may be extended to longitudinal (time series) phenotypes. Effects of possible shifts between training and test distributions will be considered. The methods will be investigated for several clinical datasets and build on the current understanding of targeted clinical indications. Specifically, the project will try to address the following questions:
(*) How can predictions of diseases be improved in high-dimensional real-world clinical settings?
(*) How should the methods be adapted to account for quantifiable differences between training and test datasets?
(*) How should existing biological and clinical knowledge be exploited to improve predictions?
(*) How can predictions of diseases and related complex traits be improved by stratifying patients into distinct groups based on heterogeneous molecular and clinical signatures?
(*) Which minimal sets of variables are needed to identify patient groups and make accurate clinically actionable predictions within each group?
If the new models outperform current clinical methods for stratification and prediction of diseases and related outcomes, they may be investigated further in a prospective clinical study.

Eligibility: Experienced researchers will have a PhD or more than 4 full-time years of research experience in machine learning, bioinformatics, statistical genetics, computational biology, or molecular epidemiology at the time of recruitment. To be eligible under FP7 ITN rules, they must have no more than 5 years of research experience, and must not have resided, worked, or studied in the country of their host organization (UK) for more than 12 months in the 3 years prior to the time of recruitment. The years of experience are measured from the time when the candidates obtained a degree that would entitle them to formally embark on a doctorate. Proficiency with R, Matlab, and/or Python is required. The successful candidate will have strong familiarity with at least three of: sparse predictive methods, kernel methods, ensemble methods, transfer learning, network modelling, semi-supervised learning, patient stratification, in vitro diagnostics, statistical genetics, molecular biology, molecular pathology, clinical trials, epidemiology.

Salary: The successful candidate will be paid at Marie Curie rates for experienced researchers (~£52,110 per anum, plus the mobility allowance of £7,400 - £10,495 per anum). Both allowances are in UK STERLINGs and subject to currency rate fluctuations.

Supervisor: Dr. Felix Agakov, director of Pharmatics Limited. Pharmatics is an award-winning start-up company founded by scientists from the University of Edinburgh, aiming to change the way high-dimensional medical data is analysed in biomarker studies, diagnostics, drug development, and stratified/precision medicine. The company is developing machine learning-based software and services for preclinical and clinical studies, and has expertise in machine learning, statistical genetics, molecular epidemiology, clinical trials, and a range of diseases and indications. Pharmatics is actively involved in biomarker studies of rheumatoid arthritis, cardiovascular diseases, and complications of diabetes, and is the leading SME of the European MIMOmics consortium developing statistical methods for analysis of multiple omics data.

Application process: Applicants should submit their applications material as a single PDF file to felix at pharmaticsltd.com with subject line “ITN MLPM Application” and the following information:
1. a curriculum vitae, including a list of publications, qualifications, and completed scientific or commercial research projects;
2. a two‐page statement of research interests;
3. names and e-mails of 2 referees;
4. a written statement by the applicant that the eligibility requirements are fulfilled. Please clarify in this statement in which countries you lived, worked and studied during the last 3 years.

Further documents may be required from short‐listed candidates. Job offers will be conditional on satisfying the eligibility criteria.

Applications should be submitted until Dec 31, 2014, but the position will remain open until filled. Please direct specific enquiries about the project to Dr. Felix Agakov (felix at pharmaticsltd.com). General enquiries about the ITN should be sent to mlpm at tuebingen.mpg.de.

> 
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20141209/6645e8b1/attachment.html>