The Junior Research Associate (JRA) scheme is a program run by the University to give undergraduate students who are interested in post-graduate research hands-on experience. Students participate over the summer and receive a stipend to aid in living and research costs. At the end of the summer, students participate in an Undergraduate Research Poster Exhibition to demonstrate their research skills and synthesise their findings. Applications for the scheme open in the spring and are open to students in their middle year at Sussex who are willing to join a project or begin a project overseen by a faculty member.
Here, two students who participated in the scheme this summer, Rora Wilsby and Elliot Massen, have provided their experiences and some details about their projects.
My project is about how we can explain the predictions made by machine learning algorithms.
For example, if we have an algorithm that tells us whether an image contains a polar bear, it’s important to know whether it detects the polar bear itself or just snow (which is likely to be included in most images of polar bears).
My research is centered around creating my own implementation of a technique that, given any machine learning algorithm, can provide an explanation about how the input would need to be changed to completely alter the prediction.
This has many uses, such as in a loan approval system, where someone who is declined a loan could request an explanation as to how they should change their application to get approved – it could suggest that they wait a few more years or that they build a credit history.
During my time as a JRA I worked around others from the Predictive Analytics Lab and the Text Analytics Group and have been able to attend their symposiums and reading groups. In fact on my final day I presented on the key paper from my research at the lab’s reading group!
These opportunities have given me openings to topics that I would’ve never known of from lectures alone.
I heard about the scheme from previous JRAs and was interested in doing one in machine learning. Part way through spring term I spoke to my lecturer, Dr. Novi Quadrianto, and asked about the possibility of doing a JRA with him as my supervisor.
After hearing about the different areas of his work, we decided on my project title and I drafted up a project proposal which was roughly 1,000 words. After that it was just the case of getting a reference from a previous lecturer and then I was able to submit my application.
I’ve found my experience as a JRA to be really enriching! I’ve had the chance to learn about interesting developments in machine learning.
Alongside this the events put on by the Undergraduate Research Office allowed me to meet JRAs from other subject areas. It was great to find out about what other projects people were working on and to make new friends.
For my project I worked on amyloid beta 42 (AB42), a protein associated with the development and progression of Alzheimer’s disease – the major form of Dementia. AB42 readily forms aggregates and it has been established that the oligomer aggregates of this protein are toxic to neuronal cells (Marshall et al., 2016).
The researchers working in Louise Serpell’s lab have developed an amyloid beta variant (ABv), which less readily aggregates due to two different amino acids in the protein sequence. ABv oligomers have been found to be non-toxic to cells.
The formation of dityrosine bonds has also shown to play a role in Alzheimer’s disease. For my project I have been focusing on inducing dityrosine cross-linking via UV radiation in the ABv oligomers to establishing whether the ABv oligomers become toxic to cells when these covalent bonds are present. This research will contribute towards the knowledge of what molecular structures are responsible for the neuronal death that occurs with the disease. If the ABv oligomers (normally non-toxic), become toxic when the dityrosine bonds are present then we will have a molecular target to aim for in the treatment of the disease.
The JRA is a process that has the potential to be quite daunting and also overwhelming, learning from Mahmoud Maina, one of the post docs in the lab, has been a thoroughly enjoyable process and my confidence in the lab has grown exponentially in a very short space of time. I have been trained in confocal microscopy, transmission electron microscopy, western blotting, circular dichroism and I am looking forward to being trained in dot blotting and tissue cell culture.
These skills are invaluable and will provide me with the credentials and confidence to go on and fulfill my ambition of working in neuroscience research.