Skip to main content

Table 3 Evaluation metrics for marker sets on experimental data. The “Average precision” metric is a weighted average of precision over the clusters. The Matthews correlation coefficient is a summary statistic that incorporates all information from the confusion matrix. See [22] for more information about the classification metrics and [23] for more information about the clustering metrics

From: A rank-based marker selection method for high throughput scRNA-seq data

General procedure

Methods

Metrics

Supervised classification

Nearest centroid classifier (NCC)Random forests classifier (RFC)

Classification error (1 - accuracy)

  

Average precision

  

Matthews correlation coefficient

Unsupervised clustering

Louvain clustering

Adjusted rand index (ARI)

  

Adjusted mutual information (AMI)

  

Fowlkes-Mallows score (FMS)