Table 4. Nucleus accumbens classification performance.

Cell sex classification of the nucleus accumbens dataset was performed using two non-ML and four ML models trained with the ventral tegmental area (VTA) training partition. Model performance was assessed by accuracy and AUC-ROC. Model: Name of classification model; Predictors: the set of predictor variables in the model; Overall: performance measured across all cells.

		Overall
Model	Predictors	AUC-ROC	Accuracy
Xist	ENSRNOG00000065796 (Xist)	0.781	0.767
Chr Y	All detected Y Chromosome genes	0.881	0.886
Logistic Regression (LR)	285 Selected features	0.964	0.894
Support Vector Machine (SVM)	285 Selected features	0.960	0.889
Random Forest (RF)	285 Selected features	0.968	0.896
Multi-Layer-Perceptron (MLP)	285 Selected features	0.942	0.870