human her2-positive breast tumor (her2+) dataset  (Spatial Transcriptomics Inc)

Journal: Computational and Structural Biotechnology Journal

Article Title: Spatial domains identification in spatial transcriptomics using modality-aware and subspace-enhanced graph contrastive learning

doi: 10.1016/j.csbj.2024.10.029

Figure Lengend Snippet: GRAS4T accurately identified spatial domains in the HER2+ dataset. (a) Boxplot of ARI values across all sections of the HER2+ dataset for all compared methods. (b) The H&E image and manual annotation for the A1 section. (c) Spatial domains of HER2+ dataset in (b) detected by STAGATE, CCST, and GRAS4T.

Article Snippet: The efficacy of GRAS4T was further evaluated using the human HER2-positive breast tumor (HER2+) dataset , which used different spatial technologies (spatial transcriptomics) compared to the DLPFC dataset.

Techniques:

Journal: bioRxiv

Article Title: Deciphering Spatial Domains by Integrating Histopathological Image and Tran-scriptomics via Contrastive Learning

doi: 10.1101/2022.09.30.510297

Figure Lengend Snippet: Spatial domains and SVGs detected in the human HER2-positive breast tumor (HER2+) dataset and the invasive ductal carcinoma (IDC) dataset. (a) Boxplot of clustering accuracy in all sections of the HER2+ dataset in terms of ARI values for all methods. (b) Manually annotated regions of section E1 of the HER2+ dataset, spatial domains detected by Giotto and ConGI. (c) The histopathological image and manually annotated regions for the IDC data, spatial domains detected by STAGATE, SpaGCN, conST, BayesSpace, and ConGI, and the spatial expression patterns of SVGs for ConGI predicted spatial domains 0 (FAM234B) and 3 (MUC1).

Article Snippet: To evaluate the performance of our method, we employed four spatial transcriptomics datasets, including the human HER2-positive breast tumor dataset (HER2+) [ ], the human dorsolateral prefrontal cortex dataset (spatialLIBD) [ ], the human epidermal growth factor receptor (HER) 2-amplified (HER+) invasive ductal carcinoma (IDC) sample ( https://sup-port.10xgenomics.com/spatial-gene-expression/datasets ), and the mouse brain datasets ( https://www.10xgenomics.com/resources/datasets ).

Techniques: Expressing

Journal: bioRxiv

Article Title: Deciphering Spatial Domains by Integrating Histopathological Image and Tran-scriptomics via Contrastive Learning

doi: 10.1101/2022.09.30.510297

Figure Lengend Snippet: UMAP visualizations and PAGA graphs using representations generated by STAGATE, BayesSpace, and ConGI respectively (a) in the section E1 of the dataset HER2+ and (b) the section 151509 of the dataset spatialLIBD.

Article Snippet: To evaluate the performance of our method, we employed four spatial transcriptomics datasets, including the human HER2-positive breast tumor dataset (HER2+) [ ], the human dorsolateral prefrontal cortex dataset (spatialLIBD) [ ], the human epidermal growth factor receptor (HER) 2-amplified (HER+) invasive ductal carcinoma (IDC) sample ( https://sup-port.10xgenomics.com/spatial-gene-expression/datasets ), and the mouse brain datasets ( https://www.10xgenomics.com/resources/datasets ).

Techniques: Generated

Journal: bioRxiv

Article Title: Deciphering Spatial Domains by Integrating Histopathological Image and Tran-scriptomics via Contrastive Learning

doi: 10.1101/2022.09.30.510297

Figure Lengend Snippet: Ablation study for ConGI on the HER2+ dataset measured by ARI.

Article Snippet: To evaluate the performance of our method, we employed four spatial transcriptomics datasets, including the human HER2-positive breast tumor dataset (HER2+) [ ], the human dorsolateral prefrontal cortex dataset (spatialLIBD) [ ], the human epidermal growth factor receptor (HER) 2-amplified (HER+) invasive ductal carcinoma (IDC) sample ( https://sup-port.10xgenomics.com/spatial-gene-expression/datasets ), and the mouse brain datasets ( https://www.10xgenomics.com/resources/datasets ).

Techniques: