Autoimmune diseases have a range of complex symptoms and are therefore typically hard to diagnose. Current diagnostic methods are often invasive, painful, and subjective. Additionally, the underlying mechanisms of these diseases are poorly understood.
Genetic sequencing can be used to profile the repertoire of immune cells in patients with autoimmune disease. Comparison of these repertoires to those of healthy controls has huge potential in improving our understanding of the immune system. However these datasets present an analytical challenge, consisting of hundreds of thousands of highly variable sequences per patient, with as little as 1% of sequences seen in multiple individuals.
In this project, the student will work closely with clinical collaborators and use large data sets to develop machine-learning algorithms which are capable of diagnosing autoimmune diseases and which are suitable for clinical use. An important feature of this is uncertainty quantification, so that diagnoses can be made with a degree of certainty. Automatic relevance determination will also be used to identify the important factors driving diagnosis with the potential to provide novel biomarkers of disease.
Coeliac disease is an autoimmune disease triggered by gluten, which has symptoms ranging from mild abdominal discomfort, to neurological problems. Current diagnosis methods involve patients consuming gluten (which is very painful for coeliac patients) for 6 weeks prior to a gut biopsy (an invasive procedure), which is then examined by a pathologist (subjectively). There is a clinical need for a new diagnostic method for coeliac disease which can improve on this current process. Therefore, we focus on coeliac disease as an area of need, for which we have a data from 100 patients, as well as 200 healthy controls, however the methods developed here will be applied to a range of other diseases.
The student will work in a multi-disciplinary environment, based in the statistical genetics group at the University of Liverpool, and working closely with expert clinicians based at Addenbrooks hospital, Cambridge. They will receive training across a range of fields, including artificial intelligence, genetics and statistics, and be given the opportunity to present at international conferences. Experience of programming in either R or python would be beneficial.
The University of Liverpool Doctoral Network in Artificial Intelligence (AI) for Future Digital Health aims to creating and maintaining a community of AI health care professionals that can apply the develop and apply AI research to medical problems, see https://www.liverpool.ac.uk/study/postgraduate-research/doctoral-training-programmes/ai-for-future-digital-health
The vision is to provide a high-quality doctoral training within the broad domain of AI (including Machine Learning, Data Science and Statistics) for medical applications from health care to drug design. The weekly 3-hour training sessions include various topics from Statistics and Linear Algebra to guest lectures on AI and healthcare, see http://kurlin.org/doctoral-network.php#training
. New students starting in October 2020 will join our first cohort of 8 PhD students who have started in October 2019.
Each PhD project has been carefully co-created in collaboration with a health care provider and/or a commercial partner working with medical data so that the outcomes of the PhD research will have immediate benefit. The network will provide students with regular training and internship opportunities at industry partners.
Applications are welcome from enthusiastic candidates with at least a 2:1 degree in Computer Science, Engineering, Mathematics, Biostatistics or in a similar area close to the proposed PhD research. The available funding is strictly limited to UK citizens.
To apply for this opportunity, please visit: https://www.liverpool.ac.uk/study/postgraduate-research/how-to-apply/
Applications should be made to a PhD in Biostatistics.