Corrigendum to: A Comprehensive Review of Machine Learning-based Clustering Methods for Single-Cell RNA Sequencing Data: Advantages and Challenges

In the published version of the article [1], the paragraph on page 90 (left column, second paragraph) appeared twice due to an inadvertent duplication during the production process. This correction has now been corrected. The original article can be found online at: https://www.eurekaselect.com/article/151342 Details of the error and the correction are provided below. ORIGINAL: The Rand Index (RI) is the unadjusted Rand index, which represents the ratio of consistent pairs between the clustering results and the true labels across all possible cell pairs. E[RI] is the expected value of RI, used to adjust for the influence of random assignment. ARI is commonly used to evaluate the performance of clustering algorithms on datasets with known labels. The Rand Index (RI) is the unadjusted Rand index, which represents the ratio of consistent pairs between the clustering results and the true labels across all possible cell pairs. E[RI] is the expected value of RI, used to adjust for the influence of random assignment. ARI is commonly used to evaluate the performance of clustering algorithms on datasets with known labels [38-40, 44, 48, 52, 72-77]. A higher ARI value indicates a high level of agreement between the clustering results and the true labels, suggesting that the clustering method performs well. CORRECTED: The Rand Index (RI) is the unadjusted Rand index, which represents the ratio of consistent pairs between the clustering results and the true labels across all possible cell pairs. E[RI] is the expected value of RI, used to adjust for the influence of random assignment. ARI is commonly used to evaluate the performance of clustering algorithms on datasets with known labels [38-40, 44, 48, 52, 72-77]. A higher ARI value indicates a high level of agreement between the clustering results and the true labels, suggesting that the clustering method performs well.