Revolutionizing ALS Research: AI Models Predict Neural Network Degeneration
A groundbreaking study from the University of St Andrews, the University of Copenhagen, and Drexel University introduces AI computational models that can predict the degeneration of neural networks in Amyotrophic Lateral Sclerosis (ALS).
Published in Neurobiology of Disease, this research opens new avenues for using computational modeling as a complementary approach to traditional animal and in vitro methods.
ALS, a motor neuron disease, affects approximately 2 out of 100,000 individuals annually worldwide. In Scotland, this translates to around 200 diagnoses per year. The majority of ALS cases begin with spinal onset, impacting motor neurons and specific neural circuits in the spinal cord, leading to early symptoms like muscle weakness, stiffness, and cramps.
Traditional ALS research relies on animal models, such as genetically modified mice, to study disease progression. However, computational models offer a unique advantage by predicting disease progression between specific timepoints, providing insights into the impact of individual changes, and repeating experiments with single modifications. These models also enable researchers to forecast how neural circuits respond to treatment, guiding future preclinical studies in mice.
The study's key innovation lies in using biologically plausible neural networks, distinct from those used in everyday tasks like facial recognition or ChatGPT. These networks communicate via spike signals, mirroring the behavior of nerve cells in our nervous system. The networks are structured based on known spinal cord cell types and their connections, allowing researchers to develop models grounded in biological knowledge.
The models, created by the School of Psychology and Neuroscience, are mathematical systems calculating neuron excitability. When a neuron receives a spike (electrical impulse), its excitability changes, and if sufficient, it spikes, passing information to the next neuron. Neurons are grouped into populations and connected based on biological data to construct the network.
Co-author Beck Strohmer, a postdoctoral researcher from the University of Copenhagen, explains that during ALS, neurons die, and population communication breaks down. The models simulate this by removing affected neurons and reducing connections. This approach enables the modeling of disease progression and treatment strategies by saving or strengthening communication.
Co-author Dr. Ilary Alodi, a Reader in St Andrews School of Psychology and Neuroscience, emphasizes the need to test model hypotheses on animal models due to the complexity of biological systems. In this study, the researchers predicted a treatment strategy's effectiveness in saving a specific neuron population, which was confirmed in treated mice.
These findings highlight the value of models in guiding experimental research while exercising caution with predictions. This refinement allows for more targeted animal experimentation, providing researchers with a clearer understanding of where and when to look for changes in animal models.
Dr. Alodi further notes the expanding application of these models to specific brain areas, offering new insights into how neuronal communication changes during dementia, an exciting research direction for the lab.
