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)

Rank	F1 score	Macro F1 score	Accuracy	Memory (GB)	Runtime (min)	CPU (%)	Name	Code	Year
14	0.18	0.04	0.35	3.70	3.87	13.80	Majority Vote	v0.6.0	2022
13	0.22	0.07	0.21	3.70	3.05	14.60	Random Labels	v0.6.0	2022
1	0.96	0.93	0.96	6.50	3.83	630.30	Multilayer perceptron (log CPM)	v1.1.2	1990
3	0.96	0.91	0.96	6.60	1.80	310.00	Logistic regression (log CPM)	v1.1.2	2013
11	0.76	0.70	0.77	6.60	3.62	255.40	K-neighbors classifier (log CPM)	v1.1.2	1967
7	0.94	0.84	0.94	9.00	1.38	1,736.20	XGBoost (log CPM)	v1.6.2	2016
9	0.95	0.59	0.95	6.10	18.32	625.60	scArches+scANVI (Seurat v3 2000 HVG)	v0.17.1	2021
4	0.96	0.66	0.96	6.10	59.10	1,338.50	scANVI (Seurat v3 2000 HVG)	v0.17.1	2021
8	0.94	0.81	0.94	23.30	16.85	313.70	XGBoost (log scran)	v1.6.2	2016
6	0.95	0.65	0.95	9.60	34.07	1,559.90	scArches+scANVI (All genes)	v0.17.1	2021
12	0.84	0.58	0.84	22.60	13.83	193.90	K-neighbors classifier (log scran)	v1.1.2	1967
5	0.96	0.66	0.96	6.10	63.42	1,510.10	scANVI (All genes)	v0.17.1	2021
10	0.94	0.64	0.94	22.60	14.52	196.20	Logistic regression (log scran)	v1.1.2	2013
2	0.96	0.79	0.96	22.60	23.42	651.20	Multilayer perceptron (log scran)	v1.1.2	1990