Integrating multi-modal information to detect spatial domains of spatial transcriptomics by graph attention network.

Recent advances in spatially resolved transcriptomic technologies have enabled unprecedented opportunities to elucidate tissue architecture and function in situ. Spatial transcriptomics can provide multimodal and complementary information simultaneously, including gene expression profiles, spatial locations, and histology images. However, most existing methods have limitations in efficiently utilizing spatial information and matched high-resolution histology images. To fully leverage the multi-modal information, we propose a SPAtially embedded Deep Attentional graph Clustering (SpaDAC) method to identify spatial domains while reconstructing denoised gene expression profiles. This method can efficiently learn the low-dimensional embeddings for spatial transcriptomics data by constructing multi-view graph modules to capture both spatial location connectives and morphological connectives. Benchmark results demonstrate that SpaDAC outperforms other algorithms on several recent spatial transcriptomics datasets. SpaDAC is a valuable tool for spatial domain detection, facilitating the comprehension of tissue architecture and cellular microenvironment. The source code of SpaDAC is freely available at Github (https://github.com/huoyuying/SpaDAC.git).

Network embedding-based representation learning for single cell RNA-seq data.

Single cell RNA-seq (scRNA-seq) techniques can reveal valuable insights of cell-to-cell heterogeneities. Projection of high-dimensional data into a low-dimensional subspace is a powerful strategy in general for mining such big data. However, scRNA-seq suffers from higher noise and lower coverage than traditional bulk RNA-seq, hence bringing in new computational difficulties. One major challenge is how to deal with the frequent drop-out events. The events, usually caused by the stochastic burst effect in gene transcription and the technical failure of RNA transcript capture, often render traditional dimension reduction methods work inefficiently. To overcome this problem, we have developed a novel Single Cell Representation Learning (SCRL) method based on network embedding. This method can efficiently implement data-driven non-linear projection and incorporate prior biological knowledge (such as pathway information) to learn more meaningful low-dimensional representations for both cells and genes. Benchmark results show that SCRL outperforms other dimensional reduction methods on several recent scRNA-seq datasets.

Autoantibody Signatures Combined with Epstein-Barr Virus Capsid Antigen-IgA as a Biomarker Panel for the Detection of Nasopharyngeal Carcinoma.

Nasopharyngeal carcinoma (NPC) is prevalent in Southern China and Southeast Asia, and autoantibody signatures may improve early detection of NPC. In this study, serum levels of autoantibodies against a panel of six tumor-associated antigens (p53, NY-ESO-1, MMP-7, Hsp70, Prx VI, and Bmi-1) and Epstein-Barr virus capsid antigen-IgA (VCA-IgA) were tested by enzyme-linked immunosorbent assay in a training set (220 NPC patients and 150 controls) and validated in a validation set (90 NPC patients and 68 controls). We used receiver-operating characteristics (ROC) to calculate diagnostic accuracy. ROC curves showed that use of these 6 autoantibody assays provided an area under curve (AUC) of 0.855 [95% confidence interval (CI), 0.818-0.892], 68.2% sensitivity, and 90.0% specificity in the training set and an AUC of 0.873 (95% CI, 0.821-0.925), 62.2% sensitivity, and 91.2% specificity in the validation set. Moreover, the autoantibody panel maintained diagnostic accuracy for VCA-IgA-negative NPC patients [0.854 (0.809-0.899), 67.8%, and 90.0% in the training set; 0.879 (0.815-0.942), 67.4%, and 91.2% in the validation set]. Importantly, combination of the autoantibody panel and VCA-IgA improved diagnostic accuracy for NPC versus controls compared with the autoantibody panel alone [0.911 (0.881-0.940), 81.4%, and 90.0% in the training set; 0.919 (0.878-0.959), 78.9%, and 91.2% in the validation set), as well as for early-stage NPC (0.944 (0.894-0.994), 87.9%, and 94.0% in the training set; 0.922 (0.808-1.000), 80.0%, and 92.6% in the validation set]. These results reveal autoantibody signatures in an optimized panel that could improve the identification of VCA-IgA-negative NPC patients, may aid screening and diagnosis of NPC, especially when combined with VCA-IgA.