4-Year PhD studentship: Towards efficient drug development modelling with machine learning

Ref Number

B02-07033

Professional Expertise

Research and Research Support

Department

School of Life & Medical Sciences (B02)

Location

London

Working Pattern

Full time

Salary

See advert text

Contract Type

Fixed-term

Working Type

Hybrid

Available for Secondment

No

Closing Date

14-Jun-2024

A four-year PhD Studentship in Pharmacometrics and Machine Learning funded by the UKRI EPSRC and GSK is available within the Institute for Global Health. The studentship will commence from 1st October 2024 onwards, under the supervision of Dr Frank Kloprogge with subsidiary supervision from Prof Joseph Standing and Nuria Buil-Bruna.

Project Title: Towards efficient drug development modelling with machine learning.

Background:
A large proportion of expensive Phase III trials fail. In recent years Phase III failure has declined, in part due to the integration of model-informed decision making in earlier phases. Pharmacometric (pharmacokinetic/pharmacodynamic (PK-PD)) models are used at all stages of pre-clinical and clinical development, but they are based on mathematical and statistical principles dating from the 1970s. Developing these pharmacometric models remains a laborious task where highly qualified staff spend large amounts of time.

Aims:
The overarching aim is to enhance drug effect understanding through improved PK/PD predictions using Machine Learning (ML) and leveraging standardised and centralised big data. The distinctive feature is the integration of nonlinear mixed effects (or multi-level) modelling of time-series (repeated measure) data in combination with ML and prior distributions, something that has seen limited exploration and adds a novel perspective to the field of PK/PD modelling. Existing Natural Language Processing (NLP) pipelines, developed at UCL, will be used to collate PK/PD parameter prior distributions and ML guided PK/PD prediction algorithms developed in house will be further advanced to enable accommodation of prior distributions.

Timeline:
The successful candidate will use the first 12 months, i.e. MPhil phase, to conduct a detailed review of the literature to build hypotheses and to define research questions and corresponding objectives. This time should also be used for feasibility testing through data collection at UCL and GSK using readily available NLP pipelines and subsequent preliminary analyses. After a successful upgrade to PhD student status the successful candidate will use the remaining three years to develop ML algorithms that incorporate prior distributions for the development of PK/PD models on various types of time series data that arise across the drug development pipeline from pre-clinical stages to Phase III. Developed ML-based algorithms will be benchmarked against conventional methods PK/PD modelling methods.

References:

• Ferran Gonzalez Hernandez, Quang Nguyen, Victoria C. Smith, José Antonio Cordero, Maria Rosa Ballester, Màrius Duran, Albert Solé, Palang Chotsiri, Thanaporn Wattanakul, Gill Mundin, Watjana Lilaonitkul, Joseph F. Standing, Frank Kloprogge. Named Entity Recognition of Pharmacokinetic parameters in the scientific literature. BioRxiv 2024.02.12.580001; doi: https://doi.org/10.1101/2024.02.12.580001
• Zhonghui Huang, Joseph F Standing, Frank Kloprogge. Development and exploration of exhaustive, stepwise, and heuristic algorithms for automated population pharmacokinetic modelling. PAGE 31 (2023) Abstr 10704 [www.page-meeting.org/?abstract=10704]
• Gonzalez Hernandez F, Carter SJ, Iso-Sipilä J, Goldsmith P, Almousa AA, Gastine S, Lilaonitkul W, Kloprogge F, Standing JF. An automated approach to identify scientific publications reporting pharmacokinetic parameters. Wellcome Open Res. 2021 Apr 21;6:88. doi: 10.12688/wellcomeopenres.16718.1. PMID: 34381873; PMCID: PMC8343403.

The student will be registered with Frank Kloprogge as primary supervisor at the Institute for Global Health pharmacokinetics-pharmacodynamics group. For more information visit:
https://www.ucl.ac.uk/global-health/research/pharmacokinetics-pharmacodynamics-group

The student will work with a wider group of PhD students and post-docs, led by secondary supervisor Joseph Standing, at UCL’s Great Ormond Street Institute for Child Health and with computer sciences specialists at UCL. The student will also spend blocks of three months at GSK Stevenage under an industrial supervision team led by Nuria Buil-Bruna for data collection and testing of development ML models on real world industrial regulatory data. GSK is a science-led global biopharma company that aims to unite science, technology, and talent to get ahead of disease together. GSK undertakes research and development in a broad range of innovative products in the primary areas of pharmaceuticals and vaccines. GSK is working to positively impact the health of 2.5 billion people by the end of 2030. For further information, please visit GSK’s website.

The student will learn about all aspects of nonlinear mixed effects modelling of PK/PD time-series data, and the application of ML and embedding of prior distributions within this domain.

This Studentship presents a unique opportunity to conduct supervised research within an academic and industrial environment and be a part of the research community and an integral part of the exciting and thriving research team.

We are looking for a successful candidate with, or is expected to receive, an upper second-class (or higher) Bachelor’s degree in mathematics/statistics/engineering/computer sciences or in pharmacy/(bio-)medical sciences (or an overseas qualification of an equivalent standard). Furthermore, the candidate should be familiar with analysis of time series data using mixed-effects models, this specific skill may also have been acquired with a Master’s degree or equivalent work experience.

This studentship provides a starting stipend of £25,237 per annum and covers the cost of tuition fees based on the UK (Home) rate. Additional funding for travel/conference fees is provided at £1,000 per annum and for consumables at £5,500 per annum.

Eligibility:
Non-UK students can apply but if they are not eligible for UK/Home fees status, will have to personally fund the difference between the UK (Home) rate and the Overseas rate. NB: You will be asked about your likely fee status at the interview so we would advise you to contact the UCL Graduate Admissions Office for advice, should you be unsure whether or not you meet the eligibility criteria for Home fee status. EU nationals should see this Student fee status page for information about eligibility for Home fees. See also to the UKCISA website (England: HE fee status).

How to Apply
Enquiries regarding the post can be made to Frank Kloprogge ([email protected])

To apply, please send 1.) a current two-page CV, 2.) a one-sided A4 motivation letter and 3.) the contact details of two professional referees to Frank Kloprogge ([email protected]). Please use the following subject line: PhD application “Towards efficient drug development modelling with machine learning”.

Closing deadline for applications: 17:00 14 June 2024 (GMT summer time)

Interview date/s: End of June/early July.

Applications that are submitted without following the correct application process, or those exceeding the page limits for CV’s and motivation letters will not be considered. The successful applicant will subsequently be required to apply to and register on the Global Health research degree to take up the studentship.

University College London and GSK are passionate about recruiting the best talent regardless of their background. All assessments are made on merit alone. We have support systems to protect the physical and mental well-being of all our staff and students and will make every effort to accommodate your personal circumstances by adopting a flexible working/study pattern to enable you to progress in your career while managing your circumstances.