Deep Learning-based Characterisation of Protein Aggregation in amyotrophic lateral sclerosis (ALS)

Amyotrophic lateral sclerosis (ALS) is a rapidly debilitating neurodegenerative disease that affects motor neurons [1]. Patients develop progressive muscle weakness, leading to death due to respiratory failure, which typically occurs after 3–5 years of symptom onset. ALS affects 1.75 – 3 out of 100,000 individuals per year [2]. The existence of protein aggregates in affected motor neurons is still a poorly understood hallmark.

This project aims at increasing the understanding of these structures. To achieve this aim, the project intends to visualise them using super-resolution microscopy and apply different machine learning techniques to extend the understanding of the TDP-43 aggregates at an individual level. To approach this problem, a super-resolution image dataset was gathered at the University of Edinburgh from post-mortem tissue of ALS patients extracted from the Edinburgh Cognitive and Behavioural ALS Screen (ECAS) cohort [3].

Optical imaging is a powerful tool that can gain insights into TDP-43 aggregates' structure and assembly mechanisms. In particular, super-resolution microscopy can be used to observe the conformations of proteins in biological samples. However, their low concentration, high levels of heterogeneity, and the propensity to behave differently in cells compared to in vitro hinder their analytical study and general use [4]. This project aims at characterising in more detail how distinct species of aggregates and their distribution are presented in different cells and different patients.

References:
[1] Ravits, J. M., and La Spada, A. R. (2009). ALS motor phenotype heterogeneity, focality, and spread: deconstructing motor neuron degeneration. Neurology 73, 805–811. doi: 10.1212/wnl.0b013e3181b6bbbd
[2] Naruse, H., Ishiura, H., Mitsui, J., Takahashi, Y., Matsukawa, T., Tanaka, M., et al. (2019). Burden of rare variants in causative genes for amyotrophic lateral sclerosis (ALS) accelerates age at onset of ALS. J. Neurol. Neurosurg. Psychiatry 90, 537–542. doi: 10.1136/jnnp-2018-318568
[3] De Icaza Valenzuela, M.M., Bak, T.H., Thompson, H.E., Colville, S., Pal, S. and Abrahams, S., 2021. Validation of The Edinburgh Cognitive and Behavioural ALS Screen (ECAS) in behavioural variant Frontotemporal Dementia and Alzheimer's Disease. International Journal of Geriatric Psychiatry.
[4] Strohäker, T., Jung, B. C., Liou, S. H., Fernandez, C. O., Riedel, D., Becker, S., Halliday, G. M., Bennati, M., Kim, W. S., Lee, S. J. & Zweckstetter, M. (2019), ‘Structural heterogeneity of α-synuclein fibrils amplified from patient brain extracts’, Nature Communications 10(1), 1–12.

Supervisor name: 
Marta Vallejo
Supervisor and Deputy email addresses: 
m.vallejo@hw.ac.uk