Postdoctoral position advertised

Through the CompBioMed2 EU Centre of Excellence project I have funding to appoint a postdoctoral researcher to develop machine-learning models to predict whether an infection is susceptible to an antibiotic.

The need for predictive methods, such as these, will grow in the coming years as more of clinical microbiology transitions to using genetics to infer the antibiogram of an infection since all samples that contain new or rare mutations in genes associated with resistance will otherwise have no result attached to them. 

We have already shown that straightforward machine-learning models that include structural-, chemical- and evolutionary-features are sufficiently specific (and sensitive) to be used for pyrazinamide, the fluoroquinolones and the rifamycins (last two not yet published).

This post will lead the generalisation of the approach to M. tuberculosis generally and examine how to accredit and  deploy machine-learning models after the genetics processing steps in clinical microbiology genetics, such as used by Public Health England or through GPAS, which I am playing a central role in and is being developed by Oxford and others through a major donation made by ORACLE.

GPAS was only announced on Mon 17 May and, given the generosity of ORACLE, has the potential to dramatically accelerate the shift to a genetics-based clinical microbiology, not just for SARS-CoV-2 but other important pathogens, including M. tuberculosis.

Although the postholder would be expected to move and work at the John Radcliffe Hospital in Oxford in the long-term, obviously that might not be possible in the short-term and, given the nature of the work, remote working for a period would be possible and maybe even required.

The job advert is here and contains a link to the job description and essential and desirable characteristics of the post. Currently the post is funded until 30 Sept 2023. 

Deadline is 12 noon GMT+1 on Tuesday 1 June 2021.

Any questions please get in touch.

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.