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.

Pancreas (by batch)

RankF1 scoreMacro F1 scoreAccuracyMemory (GB)Runtime (min)CPU (%)NamePaperCodeYear
140.180.040.353.703.8713.80Majority Vote

v0.6.0

2022
130.220.070.213.703.0514.60Random Labels

v0.6.0

2022
10.960.930.966.503.83630.30Multilayer perceptron (log CPM)

v1.1.2

1990
30.960.910.966.601.80310.00Logistic regression (log CPM)

v1.1.2

2013
110.760.700.776.603.62255.40K-neighbors classifier (log CPM)

v1.1.2

1967
70.940.840.949.001.381,736.20XGBoost (log CPM)

v1.6.2

2016
90.950.590.956.1018.32625.60scArches+scANVI (Seurat v3 2000 HVG)

v0.17.1

2021
40.960.660.966.1059.101,338.50scANVI (Seurat v3 2000 HVG)

v0.17.1

2021
80.940.810.9423.3016.85313.70XGBoost (log scran)

v1.6.2

2016
60.950.650.959.6034.071,559.90scArches+scANVI (All genes)

v0.17.1

2021
120.840.580.8422.6013.83193.90K-neighbors classifier (log scran)

v1.1.2

1967
50.960.660.966.1063.421,510.10scANVI (All genes)

v0.17.1

2021
100.940.640.9422.6014.52196.20Logistic regression (log scran)

v1.1.2

2013
20.960.790.9622.6023.42651.20Multilayer perceptron (log scran)

v1.1.2

1990