Norwich Research Park Featured PhD Programmes
Aberdeen University Featured PhD Programmes
University of Cambridge Featured PhD Programmes

Understanding the Reliability and Transferability of Machine Learning Methods Used in High Throughput Reaction Discovery and Optimisation


   Department of Pure and Applied Chemistry

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities
  Dr David Nelson, Dr M Reid, Dr David Palmer  No more applications being accepted  Funded PhD Project (European/UK Students Only)

About the Project

Background:
Efficient organic synthesis enables pharmaceutical products to be produced in a scalable, robust, safe, and cost-effective way; significant resource is expended to optimise the yield and purity of the products obtained. Currently, Design of Experiments (DoE), underpinned by regression techniques, provides a structured, logical way to determine optimal reaction conditions and test their robustness. The resource requirements of DoE increase rapidly as more factors are added, and the treatment of discontinuous (i.e. categorical) factors (e.g. solvent, ligand) is difficult. Smarter, faster, and complementary ways to optimise reactions will allow the delivery of target molecules more quickly and at lower cost. Indeed, integration of modelling in chemistry research is estimated to provide up to 9:1 return on investment.


Project Details:
This project is a collaboration between Dr Marc Reid, Dr David Nelson, and Dr David Palmer (University of Strathclyde) and Dr Andrew Dominey (Process Chemistry at GSK in Stevenage). The student will undertake experimental and computational work to predict the outcomes of emerging and industrially-relevant C-H functionalisation reactions catalysed by transition metals. This will include two placements at GSK Stevenage, where they will utilise state-of-the-art high throughput experimentation apparatus and engage with colleagues in process development.

The research and training will include: organic and organometallic synthetic chemistry; executing catalytic reactions under inert atmospheres; careful analysis of reaction outcomes using a range of techniques; and the construction, validation, and testing of machine learning methods. This project would suit a student with strong interests in synthetic chemistry and physical organic chemistry, and in the use of state-of-the-art data analysis techniques. The student will benefit from working within teams of researchers approaching challenges in machine learning, catalysis, and physical organic chemistry.


Applications:
To be considered for this position, students must have (or be on track to obtain) a first or upper second class degree in chemistry and have a passion for research. The following would be advantageous: work experience in the chemical industry; research experience in catalysis and synthesis in industrial or academic laboratories; experience in coding/scripting (any language).

To apply for this position, please send a CV and cover letter to Dr David Nelson (email address below). Applications must be recieved by 6 pm on Wednesday 8th January 2020 in order to be considered.


Supervisory Team:
Dr Marc Reid is a GSK/Leverhulme Trust fellow with a background in catalysis, physical organic chemistry, computational chemistry, and new enabling technologies for synthesis; he is also the founder of Pre-Site Safety, which uses virtual reality to embed safe working practices in organisations that carry out essential high-risk work in the chemical industry. Dr David Nelson is a Senior Lecturer with a research programme that spans catalysis, organometallic chemistry, physical organic chemistry, and computational chemistry. Dr David Palmer is a Senior Lecturer who leads a team with interests including computational modelling and machine learning; he is also co-founder and Chief Data Officer at ClinSpecDx, a recently-established spin out company that uses machine learning in the diagnosis of brain cancer from blood serum analysis.

Funding Notes

Funding has been secured through an EPSRC ICASE Studentship for 48 months. This includes a stipend (ca. £15k p.a., untaxed) and all tuition fees. A 1st October start date is preferred.

There are specific eligibility requirements for this studentship; please see https://epsrc.ukri.org/skills/students/help/eligibility/. For exceptional non-UK candidates it may be possible to relax these requirements.
Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.