PhD Studentship: Machine Learning for predicting yeast phenotype from genotype for biotech applications

University of Nottingham


View All Vacancies
Mathematical Sciences
Location:  UK Other
Closing Date:  Tuesday 20 June 2023
Reference:  SCI2191

BBSRC Doctoral Training Partnership, Researcher Academy

Subject area: Statistics, Mathematics, Computer Science, Computational Biology, Computational Chemistry 

Supervisor: Markus Owen

Research Title: Machine Learning for predicting yeast phenotype from genotype for biotech applications

Project Summary: This project will apply artificial intelligence approaches to address this challenge: given data on yeast genotypes, growth conditions and phenotypes (traits), can we develop predictive models for the phenotype of novel yeast strains and hence ultimately predict strains that could out-perform any of those in the training data. Such novel strains could be produced using synthetic biology approaches and the model predictions tested. Yeast is an ideal platform for the manufacture of biomedically important protein products, such as life-saving medicines. The diversity of yeast genotypes and protein products means that the best strain for optimal yield of a given product is typically unknown – but ripe for identification using novel AI methods.

This project will work with published data from the group of Ed Louis (Chief Scientist, Phenotypeca, https://phenotypeca.com, industrial partner on this project), to develop the AI approaches and understanding of the context. These data include hundreds of genotypes with quantitative measurements of traits such as growth and response to various treatments. The developed approaches can then be applied to the context of Phenotypeca, which has the world’s largest collection of yeast strains for recombinant protein production. 

A range of non-parametric statistical tools and AI models will be explored for this prediction problem, from more traditional machine learning techniques, such as random forests and neural networks through to more innovative emerging approaches such as indefinite kernel-based support vector machines. 

Students would be expected to have a background in Statistics, Mathematics, Computer Science, Computational Biology, Computational Chemistry or a relevant discipline with a significant data analysis component. It is essential to have strong programming skills, e.g. in R and/or Python.

The student will be embedded in a thriving research environment at the interface between the Schools of Mathematical Sciences and Chemistry at the University of Nottingham and Phenotypeca (based at BioCity, in central Nottingham, with its vibrant biotech community). 

As a CASE studentship, the PhD will include a placement of at least three months with Phenotypeca, planned for the third year of the PhD and tailored to the student’s PhD research. The student will work on a commercially relevant research project within Phenotypeca’s R&D and IT groups, where they will also have the opportunity to gain skills in adjacent parts of the business, such as intellectual property and regulatory affairs, and appreciate how these compare to the academic setting. 

Award Start Date: October 2023

Duration of Award: 4 years 

Terms and Conditions: Home students are welcome to apply for this opportunity. Funding is available for four years from late September 2023. The award covers tuition fee (£4,712) at the home rate plus an annual stipend which was (£18,622) for 2023/24. This is set by the Research Councils. 

Applicant Qualification Requirements: To apply and check your eligibility, please click go to https://www.nottingham.ac.uk/bbdtp/apply/how-to-apply.aspx and you can find further information about how to apply to our programme. 

School/Faculty: Schools of Mathematical Sciences and Chemistry at the University of Nottingham

Informal enquiries may be addressed to [email protected] or [email protected] 

Closing date: Apply by noon on Tuesday 20th June 2023

View or Apply
To help us track our recruitment effort, please indicate in your cover/motivation letter where (globalvacancies.org) you saw this job posting.

Job Location