Skip to main content
QUB NILab Logo

Detection Learning for Discovering and Detecting Virus Signatures

This project is a 4-year PhD project with enhanced training and 3+ month placement, which is funded by UKRI BBSRC, delivered by Queen’s University Belfast and Ulster University. Details of the enhanced training will be available later.

The emergence of novel pathogens poses significant global health challenges. Rapid and accurate detection of viruses and bacteria is essential for effective diagnostics and timely interventions. Machine learning approaches are commonly used; however, they often struggle with limited data scenarios and environmental variability. This limitation hinders their robustness and applicability in real-world settings. Building upon the EPSRC-funded VIPIRS project, which demonstrated the potential of combining low-cost near-infrared (NIR) spectroscopy with machine learning for virus detection, there remains a critical need to develop methods that generalise across different media, pathogens, and disease states.

This project studies machine learning that can discover unique signatures from limited data and ensure their reliable detection across diverse environments. The student will design a new mathematical formulation of the detection problem to characterise object-specific patterns, and develop novel machine learning algorithms for detection purposes. The student will also conduct experimental evaluations using datasets from the VIPIRS project, including NIR data from viruses such as Respiratory Syncytial Virus (RSV) and Sendai Virus (SeV). The student will have opportunities to collect new data from other medically significant viruses like influenza, rhinovirus, and pox viruses in various media. The student will also have opportunities to collaborate with other students to validate the new methods in diagnostic applications, aiming to improve early health detection.

The student will receive comprehensive interdisciplinary training in both artificial intelligence and biosciences. This includes advanced machine learning, chemometric and spectroscopic data analysis, leadership and entrepreneurship. Additionally, the student will develop transferable skills in research methodologies, scientific communication, and project management. Opportunities for placements with academic and industry partners will provide experiential learning and foster innovation. This training will equip the student to address complex challenges in bioscience and AI, supporting career advancement in academia, industry, and beyond.

Click here to access the application form