Search

Motivation Spatial clustering is essential and challenging for spatial transcriptomics' data analysis to unravel tissue microenvironment and biological function. Graph neural networks are promising to address gene expression profiles and spatial location information in spatial transcriptomics to generate latent representations. However, choosing an appropriate graph deep learning module and graph neural network necessitates further exploration and investigation. Results In this article, we present GRAPHDeep to assemble a spatial clustering framework for heterogeneous spatial transcriptomics data. Through integrating 2 graph deep learning modules and 20 graph neural networks, the most appropriate combination is decided for each dataset. The constructed spatial clustering method is compared with state-of-the-art algorithms to demonstrate its effectiveness and superiority. The significant new findings include: (i) the number of genes or proteins of spatial omics data is quite crucial in spatial clustering algorithms; (ii) the variational graph autoencoder is more suitable for spatial clustering tasks than deep graph infomax module; (iii) UniMP, SAGE, SuperGAT, GATv2, GCN, and TAG are the recommended graph neural networks for spatial clustering tasks; and (iv) the used graph neural network in the existent spatial clustering frameworks is not the best candidate. This study could be regarded as desirable guidance for choosing an appropriate graph neural network for spatial clustering. Availability and implementation The source code of GRAPHDeep is available at https://github.com/narutoten520/GRAPHDeep. The studied spatial omics data are available at https://zenodo.org/record/8141084. [ABSTRACT FROM AUTHOR]

With the development of spatially resolved transcriptomics technologies, it is now possible to explore the gene expression profiles of single cells while preserving their spatial context. Spatial clustering plays a key role in spatial transcriptome data analysis. In the past 2 years, several graph neural network-based methods have emerged, which significantly improved the accuracy of spatial clustering. However, accurately identifying the boundaries of spatial domains remains a challenging task. In this article, we propose stAA, an adversarial variational graph autoencoder, to identify spatial domain. stAA generates cell embedding by leveraging gene expression and spatial information using graph neural networks and enforces the distribution of cell embeddings to a prior distribution through Wasserstein distance. The adversarial training process can make cell embeddings better capture spatial domain information and more robust. Moreover, stAA incorporates global graph information into cell embeddings using labels generated by pre-clustering. Our experimental results show that stAA outperforms the state-of-the-art methods and achieves better clustering results across different profiling platforms and various resolutions. We also conducted numerous biological analyses and found that stAA can identify fine-grained structures in tissues, recognize different functional subtypes within tumors and accurately identify developmental trajectories. [ABSTRACT FROM AUTHOR]

Advancing spatially resolved transcriptomics (ST) technologies help biologists comprehensively understand organ function and tissue microenvironment. Accurate spatial domain identification is the foundation for delineating genome heterogeneity and cellular interaction. Motivated by this perspective, a graph deep learning (GDL) based spatial clustering approach is constructed in this paper. First, the deep graph infomax module embedded with residual gated graph convolutional neural network is leveraged to address the gene expression profiles and spatial positions in ST. Then, the Bayesian Gaussian mixture model is applied to handle the latent embeddings to generate spatial domains. Designed experiments certify that the presented method is superior to other state-of-the-art GDL-enabled techniques on multiple ST datasets. The codes and dataset used in this manuscript are summarized at https://github.com/narutoten520/SCGDL. [ABSTRACT FROM AUTHOR]

We investigate the physical properties, such as star-forming activity, disc versus bulge nature, galaxy size, and obscuration of 3811 SRG/ eROSITA -detected AGNs at 0.2 < z < 0.8 in the eFEDS field. Using Subaru Hyper Suprime-Cam imaging data in the grizy bands, we measure the structural and stellar properties for their host galaxies by performing a 2D AGN-host image decomposition. We find that (1) AGNs can contribute significantly to the total optical light down to |${\rm log}\, L_{\rm X}\sim 42.5\ \rm erg\ s^{-1}$|⁠ , thus ignoring the AGN component can significantly bias the structural measurements; (2) AGN hosts are predominately star-forming galaxies at |${\rm log}\, \mathcal {M}_\star \lesssim 11.3\, \mathrm{M}_\odot$|⁠ ; (3) the bulk of AGNs (64 per cent) reside in galaxies with significant stellar discs (⁠|$\rm S\acute{e}rsic$|  index n < 2), while their host galaxies become increasingly bulge dominated (n ∼ 4) and quiescent at |${\rm log}\, \mathcal {M}_\star \gtrsim 11.0\, \mathrm{M}_\odot$|⁠ ; (4) the size–stellar mass relation of AGN hosts tends to lie between that of inactive (i.e. non-AGN) star-forming, and quiescent galaxies, suggesting that the physical mechanism responsible for building the central stellar density also efficiently fuel the black hole growth; (5) the hosts of X-ray unobscured AGNs are biased towards face-on systems, suggesting that some of the obscuration of the nuclei could come from galaxy-scale gas and dust. This will bias against the detection of unobscured AGNs in gas-rich star-forming galaxies, which may partly account for the deficiency of star-forming discs as host galaxies for the most massive AGNs (missing star-forming fraction up to |$\sim 40{{\ \rm per\ cent}}$|⁠). Our results are consistent with a scenario in which the black hole and galaxy transform in structure and star-forming activity while grow in mass, as desired to establish the local |$\mathcal {M}_{\rm BH}-\mathcal {M}_{\rm bulge}$| relation. [ABSTRACT FROM AUTHOR]