Skip to main content

Table 1 Benchmark tools and datasets

From: Benchmarking clustering, alignment, and integration methods for spatial transcriptomics

Algorithm

Task

Language

Resource

Output

Method

Link

BANKSY

Clustering

R

Singhal et al. 2024  [21]

Clustering Labels, Embedding

Azimuthal Gabor filter

https://github.com/prabhakarlab/Banksy

ADEPT

Clustering

Python

Hu et al. 2023 [28]

Clustering Labels, Embedding

Graph Autoencoder, Imputation, Differentially Expressed Genes

https://github.com/maiziezhoulab/ADEPT

GraphST

Clustering

Python

Long et al. 2022 [4]

Clustering Labels, Embedding

Graph Neural Network, Contrastive Learning

https://github.com/JinmiaoChenLab/GraphST

SpaceFlow

Clustering

Python

Ren et al. 2022 [27]

Clustering Labels, Embedding

Spatially Regularized Deep Graph Infomax

https://github.com/hongleir/SpaceFlow

conST

Clustering

Python

Zong et al. 2022 [25]

Clustering Labels, Embedding

Contrastive Learning, Masked Autoencoder

https://github.com/ys-zong/conST

ConGI

Clustering

Python

Zeng et al. 2022 [26]

Clustering Labels, Embedding

Contrastive Learning, Autoencoder

https://github.com/biomed-AI/ConGI

SpatialPCA

Clustering

R

Shang et al. 2022 [19]

Clustering Labels

Spatial Probabilistic PCA

https://github.com/shangll123/SpatialPCA

DR.SC

Clustering

R

Liu et al. 2022 [20]

Clustering Labels

Regression Analysis, Imputation

https://github.com/feiyoung/DR-SC.Analysis

STAGATE

Clustering

Python

Dong et al. 2022 [3]

Clustering Labels, Embedding

Graph Autoencoder, Attention Mechanism

https://github.com/QIFEIDKN/STAGATE_pyG

CCST

Clustering

Python

Li et al. 2022 [24]

Clustering Labels, Embedding

Graph Convolutional Network

https://github.com/xiaoyeye/CCST

SEDR

Clustering

Python

Fu et al. 2021 [23]

Clustering Labels, Embedding

Deep Autoencoder, Graph Variational Autoencoder

https://github.com/JinmiaoChenLab/SEDR

SpaGCN

Clustering

Python

Hu et al. 2021 [22]

Clustering Labels

Graph Convolutional Network

https://github.com/jianhuupenn/SpaGCN

BayesSpace

Clustering

R

Li et al. 2021 [17]

Clustering Labels

Markov chain Monte Carlo, Differentially Expressed Genes

https://github.com/edward130603/BayesSpace

STalign

Alignment

Python

Clifton et al. 2023 [36]

Refined Coordinates

Diffeomorphic Metric Mapping

https://github.com/JEFworks-Lab/STalign

GPSA

Alignment

Python

Jones et al. 2023 [37]

Refined Coordinates

Gaussian Process

https://github.com/andrewcharlesjones/spatial-alignment

SPIRAL

Integration

Python

Guo et al. 2023 [42]

Refined Coordinates, Embedding

GraphSAGE, Optimal Transport

https://github.com/guott15/SPIRAL

STAligner

Integration

Python

Zhou et al. 2023 [39]

Embedding

Graph Autoencoder, Attention Mechanism, Triplet Loss

https://github.com/zhanglabtools/STAligner

PASTE

Alignment Integration

Python

Zeira et al. 2022 [33]

Alignment Matrix, Integrated Slice, 3D Reconstruction

Fused Gromov-Wasserstein Optimal Transport, Generalized Procrustes Analysis

https://github.com/raphael-group/paste

PASTE2

Alignment Integration

Python

Xinhao et al. 2022 [34]

Partial Alignment Matrix, 3D Reconstruction

Partial Fused Gromov-Wasserstein Optimal Transport, Generalized Procrustes Analysis

https://github.com/raphael-group/paste2

PRECAST

Clustering Integration

R

Liu et al. 2023 [41]

Embedding

Gaussian Mixture Model, Discrete Hidden Markov Random Field

https://github.com/cran/PRECAST

SPACEL

Deconvolution Clustering Alignment

Python

Xu et al. 2023 [35]

Cell Type Composition, Refined Coordinates, 3D Reconstruction

Variational Autoencoder, Graph Convolutional Network, Adversarial Learning, Regression

https://github.com/QuKunLab/SPACEL

BASS

Clustering Integration

R

Li et al. 2022 [18]

Clustering Labels

Bayesian Analysis, Multi-sample Analysis

https://github.com/zhengli09/BASS

DeepST

Clustering Integration

Python

Xu et al. 2022 [40]

Embedding

Data Augmentation, Variational graph autoencoder

https://github.com/JiangBioLab/DeepST

ST dataset

ST type

Abbreviations

ST protocol

Spots/genes

Num. of used slices

Source

Dataset 1: Human Dorsal Lateral Prefrontal Cortex data [43]

Sequencing-based

DLPFC

10x Visium

3431-4788/33,538

12

http://spatial.libd.org/spatialLIBD/

Dataset 2: Human Breast Cancer Block A Section 1 [44]

Sequencing-based

HBCA1

10x Visium

3798/36,601

1

https://support.10xgenomics.com/spatial-gene-expression/datasets/1.1.0/V1_Breast_Cancer_Block_A_Section_1

Dataset 3: Mouse Brain Section 2 Sagittal Anterior [45]

Sequencing-based

MB2SA

10x Visium

2695/32,285

2

https://www.10xgenomics.com/resources/datasets/mouse-brain-serial-section-2-sagittal-anterior-1-standard

Dataset 4: HER2 Positive Breast Tumors [46]

Sequencing-based

HER2BT

Spatial Transcriptomics

177-692/ 14,861-15,701

8

https://github.com/almaan/her2st

Dataset 5: Mouse Hippocampus [47]

Sequencing-based

MHPC

Slide-seq v2

41,770/23,264

1

https://singlecell.broadinstitute.org/single_cell/study/SCP815

Dataset 6: MOSTA Embryo [48]

Sequencing-based

Embryo

Stereo-seq

30,124-51,365/26,854-27,810

2

https://db.cngb.org/stomics/mosta/resource/

Dataset 7: Mouse Visual Cortex [9]

Sequencing-based

MVC

STARmap

1207/1020

1

https://www.STARmapresources.com/data

Dataset 8: Mouse Prefrontal Cortex [9]

Sequencing-based

MPFC

STARmap

1049-1088/166

3

https://github.com/zhengli09/BASS-Analysis/blob/master/data/STARmap_mpfc.RData

Dataset 9: Mouse Hypothalamus [49]

Imaging-based

MHypo

MERFISH

5488-5926/155

5

https://datadryad.org/stash/dataset/doi:10.5061/dryad.8t8s248

Dataset 10: Mouse Brain [50]

Sequencing-based

MB

MERFISH

2033-7626/254

33

https://zenodo.org/records/8167488

  1. Top panel: Summary of clustering, alignment, and integration methods used in this work. The tool’s task, programming language, resource, tool output, the general method by each tool, and tool links are shown in the table. Bottom panel: Overview of the datasets benchmarked in this study. The ST type, datasets’ abbreviations, ST protocol, the range of number of spots and genes, number of slices, and source link for each dataset are shown in the table