Prof Sara Zanivan, Prof Crispin Miller
Developing machine learning algorithms for early detection of hepatocellular carcinoma
As a world-leading cancer research centre, the CRUK Beatson Institute supports cutting edge work into the molecular mechanisms of cancer development. We provide an outstanding research environment, underpinned by state-of-the-art core services and advanced technologies with special emphasis on imaging and in vivo models.
We are looking for students with a very good degree in a Life Sciences subject and an aptitude for experimental work, who are also highly committed to pursuing a PhD and a career in cancer research. The Beatson has an excellent reputation and success record in training its graduate students. Students, whilst being trained at the Institute working within our research groups, will matriculate with the University of Glasgow.
Our PhD studentships are for a maximum of 4 years, and currently provide students with an annual stipend of £19,000 and matriculation fees for home, EU or overseas students.
Primary liver cancer is the third leading cause of cancer-related death worldwide. The most common type of liver cancer is hepatocellular carcinoma (HCC), which develops in the background of liver diseases, such as cirrhosis. HCC incidence is rising faster than other cancers worldwide. Given the only cure for HCC is surgery, which can only be used in patients with early-stage disease, there is urgent need to develop new methods for early HCC detection to reduce mortality by increasing the number of patients who can access curative interventions. Current HCC surveillance methodologies in routine clinical practice lack sensitivity and are of doubtful cost-effectiveness, posing a substantial problem for healthcare systems.
Recent breakthroughs in mass spectrometry (MS) technology have dramatically advanced the proteomic field, such that MS proteomics is considered the next massive investment opportunity in biomedical research (https://www.forbes.com/sites/stephenmcbride1/2021/06/23/proteomics-the-next-truly-massive-investing-opportunity/). Liver diseases are particularly well suited for plasma biomarker studies, because the liver is a highly secretory organ. Consequently, the majority of blood-secreted proteins comes from the liver, of which some are routinely assessed in the clinics as biomarkers. Single blood biomarkers used in the clinics to detect HCC lack sensitivity and specificity. However, recent mass spectrometry (MS)-based plasma proteomic studies have shown that subsets of plasma proteins can be used for predictive models for diagnosis, staging and to predict progression of liver disease and performed as well as existing diagnostic strategies or better.
This project aims at developing a proteomic classifier for risk of developing HCC for patients with liver diseases. To achieve this, the student will analyse proteomic data that will be generated at the Beatson using novel MS technology and will develop machine learning approaches for the analysis of proteomic data of plasma samples obtained from large cohorts of patients at risk of developing HCC and with early-stage HCC. This project is part of an interdisciplinary project that has recently been funded by CRUK Early Detection and Diagnosis Research Committee, which involves the Beatson Institute (Zanivan, Bird and Miller groups), the University of Oxford and University of Nottingham.