Pancreas (by batch)

Human pancreatic islet scRNA-seq data from 6 datasets across technologies (CEL-seq, CEL-seq2, Smart-seq2, inDrop, Fluidigm C1, and SMARTER-seq). Split into train/test by experimental batch. Dimensions: 16382 cells, 18771 genes. 14 cell types (avg. 1170±1703 cells per cell type).
Raw Scaled
RankNameMean scoreAccuracyAccuracyF1 scoreF1 scoreMacro F1 scoreMacro F1 scoreMemory (GB)Runtime (min)CPU (%)PaperYearLibrary
1Multilayer perceptron (log CP10k)0.950.960.950.960.950.940.932.303.05704.801990v1.1.3
2Logistic regression (log CP10k)0.920.970.960.970.960.860.852.304.28374.302013v1.1.3
3XGBoost (log CP10k)0.910.940.920.940.920.910.902.7011.87294.102016v1.6.2
4Seurat reference mapping (SCTransform)0.910.960.950.960.950.850.84445.5013.77125.402021v4.3.0
5Multilayer perceptron (log scran)0.870.950.940.950.940.760.748.3012.12936.001990v1.1.3
6XGBoost (log scran)0.870.930.920.930.920.790.778.5012.03328.402016v1.6.2
7scANVI (All genes)0.840.960.950.960.940.660.644.5043.482,440.002021v0.20.0
8scANVI (Seurat v3 2000 HVG)0.840.960.950.960.950.660.636.9032.872,380.402021v0.20.0
9scArches+scANVI (All genes)0.830.950.940.950.940.650.625.8024.172,612.902021v0.20.0
10K-neighbors classifier (log CP10k)0.820.880.840.880.840.790.772.302.75298.101967v1.1.3
11Logistic regression (log scran)0.810.940.920.940.920.630.608.5016.78131.202013v1.1.3
12scArches+scANVI (Seurat v3 2000 HVG)0.780.950.940.940.930.520.484.0021.871,358.502021v0.20.0
13K-neighbors classifier (log scran)0.720.840.800.840.800.580.558.308.77118.701967v1.1.3
14Majority Vote0.040.350.190.18-0.030.04-0.030.691.0819.902022v0.7.0