Identification of Human Cell Cycle Phase Markers Based on Single-Cell RNA-Seq Data by Using Machine Learning Methods

<div>IFS curves of four classification algorithms on the feature list yielded by the SHAP by LightGBM. The highest MCC values for four classification algorithms are 0.784, 0.800, 0.875, and 0.875, respectively. Such performance is obtained by using top 103, 18, 87, and 222 features in the list.</div>

BioMed Research International

fig5

Figure 5

Figure 5: Identification of Human Cell Cycle Phase Markers Based on Single-Cell RNA-Seq Data by Using Machine Learning Methods 