. Author manuscript; available in PMC: 2023 May 7.

Published in final edited form as: Nat Methods. 2019 Oct 7;16(11):1139–1145. doi: 10.1038/s41592-019-0576-7

Table 1:

A comparison of modularity (left) and silhouette (right) scores of each of the clustering algorithms on each dataset.

	SAUCIE	kmeans	Phenograph	scVI
GMM	0.7512/0.8162	0.8917/0.3097	0.9302/0.2662	0.9030/-0.0626
Shekhar et al	0.9662/-0.0602	0.8530/0.0753	0.8981/0.0868	0.93139/0.0593
Chevrier et al	0.9347/-0.3761	0.9517/0.0085	0.9258/-0.0452	0.9302/0.2662
Zeisel et al	0.8663/-0.1881	0.9138/0.1135	0.9209/0.1529	0.9085/-0.1238
Paul et al	0.8854/-0.3060	0.8930/0.0249	0.8819/0.1802	0.8839/-0.0540
Setty et al	0.6860/0.0425	0.8704/0.0377	0.8912/0.0147	0.8591/-0.0718