Genetics of pregnancy loss through implementation of machine learning approaches to omics data
This studentship will dissect genetic and other omics factors related to maternal perinatal health with the focus on the pregnancy loss through miscarriage, stillbirth or other complications. The project will focus on big population-based datasets and electronic health records with implementation of machine learning and data fusion approaches to understand individual predisposition to such events and prevent them in future pregnancies.
Start date1 January 2023
Funding sourceInternal Faculty funds – Doctoral Training Programme in Pathogens and Host Defenses
- Stipend of £16,062 for 22/23, which will increase each year in line with the UK Research and Innovation (UKRI) rate
- Home rate fee allowance of £4,596 (with automatic increase to UKRI rate each year)
- For exceptional international candidates, there is the possibility of obtaining a scholarship to cover overseas fees.
This project will explore big omics data and apply efficient analytical and artificial intelligence (AI) approaches for identifying novel biomarkers for woman’s reproductive health conditions. Women’s reproductive health is the least systematically evaluated set of phenotypes in human genetics, contrary to its importance at individual level. The prevalence of women’s reproductive issues rapidly increases with ageing of human populations. The increasing age at conception leads to fertility problems, including miscarriage, pregnancy loss and stillbirth.
In-vitro fertilisation industry development and its popularisation exacerbate issues related to pregnancy losses (PL). Genetic studies demonstrated contribution of hereditable factors to susceptibility of PL but haven’t benefited from the recent technological development and availability of large datasets to the same extent as other common diseases. AI and machine learning approaches could be implemented for prediction of such outcomes. This project will provide insights into the genetics pregnancy loss and related conditions.
Overall objective: a large-scale genetic investigation into women’s reproductive health evaluated through miscarriage, pregnancy loss recurrence, stillbirth, and concomitant conditions.
- Evaluation of genome-wide DNA variability influencing susceptibility to miscarriage, idiopathic PL, stillbirth and related conditions within the single-trait and multi-phenotype genome-wide association study (MP-GWAS). These analyses will be done in the UK biobank (UKBB) and replicated in other large-scale datasets.
- Dissection of causal relationships between idiopathic PL and related conditions within the bi-directional Mendelian Randomization (MR) analysis. The student will use studies from WP1 and a number of publicly available trait-specific datasets for this analysis.
- Implementation of machine learning and data fusion approaches to combine multiple individual health data characteristics, genomic, metabolomic, blood biochemistry and other data for prediction of women’s reproductive health outcomes during pregnancy and development of prevention strategies for health systems.
You will need to meet the minimum entry requirements for our PhD programme.
Open to any UK or international candidates. All applicants should have (or expect to obtain) a first-class degree in a numerate discipline (mathematics, science or engineering) or MSc with Distinction (or 70% average) and a strong interest in pursuing research in this field. Additional experience which is relevant to the area of research is also advantageous.
How to apply
Applications should be submitted via the Biosciences and Medicine PhD programme page on the "Apply" tab. Please clearly state the studentship title and supervisor on your application.
Applicants should contract Prof Prokopenko with an enquiry upon the submission of their application documents using the standard application instructions.
Read our studentship FAQs to find out more about applying and funding.
Studentships at Surrey
We have a wide range of studentship opportunities available.