Machine learning for analysis of gene expression data in fast- and slow-progressing amyotrophic lateral sclerosis murine models

Amyotrophic lateral sclerosis is a fatal motor neuron disease characterised by degenerative changes in both upper and lower motor neurons. Current treatment options in the general cohort of ALS patients have only a minimal impact on survival. Only two approved medications are available today, just addressing the management of symptoms and supporting the respiration. In this work, gene expression data from genetically modified murine motor neurons have been analysed with machine learning techniques, with the scope of distinguishing between mice developing a fast progression of the disease, and mice showing a slower progression. Results showed high accuracy (above 80%) in all tasks, with peaks of accuracy for specific ones – such as distinguishing between fast and slow progression. In the above mentioned task the best performing algorithm reached an accuracy of 100%. This research group is currently working on three more investigations on data from mice, using similar approaches and methodology, focusing on thoracic and lumbar metabolomic data as well as microbiome data. We believe that, based on the findings in the murine models, machine learning could be used to discover ALS progression markers in humans by looking at features related to the immune response. This could pave the path for the discovery of druggable targets and disease biomarkers for homogeneous ALS patient subgroups.