Skip to main content
Fig. 6 | Acta Neuropathologica Communications

Fig. 6

From: Unsupervised machine learning identifies distinct ALS molecular subtypes in post-mortem motor cortex and blood expression data

Fig. 6

Average performance metrics over all 10 cross-validation folds under three scenarios for KCL BrainBank Cluster 1 case-control analysis. The performance of the classifier supplied with all 131 informative genes in cluster 1 (A) was compared to the average performance when supplying ten classifiers with a random set of 131 genes from the full expression matrix (B). The x-axis represents each metric used to assess the discriminative performance of each model, with the average score represented on the y-axis. Each point represents the mean and standard deviation. The dotted line at 0.5 represents the performance value you would expect by chance

Back to article page