Innovative super-resolution in spatial transcriptomics: a transformer model exploiting histology images and spatial gene expression.

Spatial transcriptomics technologies have shed light on the complexities of tissue structures by accurately mapping spatial microenvironments. Nonetheless, a myriad of methods, especially those utilized in platforms like Visium, often relinquish spatial details owing to intrinsic resolution limitations. In response, we introduce TransformerST, an innovative, unsupervised model anchored in the Transformer architecture, which operates independently of references, thereby ensuring cost-efficiency by circumventing the need for single-cell RNA sequencing. TransformerST not only elevates Visium data from a multicellular level to a single-cell granularity but also showcases adaptability across diverse spatial transcriptomics platforms. By employing a vision transformer-based encoder, it discerns latent image-gene expression co-representations and is further enhanced by spatial correlations, derived from an adaptive graph Transformer module. The sophisticated cross-scale graph network, utilized in super-resolution, significantly boosts the model's accuracy, unveiling complex structure-functional relationships within histology images. Empirical evaluations validate its adeptness in revealing tissue subtleties at the single-cell scale. Crucially, TransformerST adeptly navigates through image-gene co-representation, maximizing the synergistic utility of gene expression and histology images, thereby emerging as a pioneering tool in spatial transcriptomics. It not only enhances resolution to a single-cell level but also introduces a novel approach that optimally utilizes histology images alongside gene expression, providing a refined lens for investigating spatial transcriptomics.

Characterization of B cell-mediated PD-1/PD-L1 interaction in pancreatic cancer patients.

Pancreatic ductal adenocarcinoma (PDAC) is a common type of pancreatic cancer with one of the worst survival rate of all malignancies. Recent studies have identified that immunosuppressive B cells could employ the PD-1/PD-L1 pathway to suppress antitumour T cell responses; hence, we examined the expression and function of PD-L1 in B cells. We found that the PD-L1 expression was significantly enriched in tumour-infiltrating (TI) B cells than in peripheral blood (PB) B cells from the same patients. Additionally, the PB B cells from stage III and stage IV PDAC patients presented significantly higher PD-L1 than the PB B cells from healthy controls. High PD-L1 expression in PB B cells could be achieved by stimulation via CpG and less effectively via anti-BCR plus CD40L, but not by coculture with pancreatic cancer cell lines in vitro. Also, STAT1 and STAT3 inhibition significantly suppressed PD-L1 upregulation in stimulated B cells. CpG-stimulated PB B cells could inhibit the IFN-γ expression and proliferation of CD8 T cells in a PD-L1-dependent manner. Also, TI CD8 T cells incubated with whole TI B cells presented significantly lower IFN-γ expression and lower proliferation, than TI CD8 T cells incubated with PD-L1+  cell-depleted TI B cells, suggesting that PD-L1+  B cells could also suppress CD8 T cells in the tumour. Overall, this study identified that B cells could suppress CD8 T cells via PD-L1 expression, indicating a novel pathway of immuno-regulation in pancreatic cancer.

A 3D Convolutional Encapsulated Long Short-Term Memory (3DConv-LSTM) Model for Denoising fMRI Data.

Function magnetic resonance imaging (fMRI) data are typically contaminated by noise introduced by head motion, physiological noise, and thermal noise. To mitigate noise artifact in fMRI data, a variety of denoising methods have been developed by removing noise factors derived from the whole time series of fMRI data and therefore are not applicable to real-time fMRI data analysis. In the present study, we develop a generally applicable, deep learning based fMRI denoising method to generate noise-free realistic individual fMRI volumes (time points). Particularly, we develop a fully data-driven 3D convolutional encapsulated Long Short-Term Memory (3DConv-LSTM) approach to generate noise-free fMRI volumes regularized by an adversarial network that makes the generated fMRI volumes more realistic by fooling a critic network. The 3DConv-LSTM model also integrates a gate-controlled self-attention model to memorize short-term dependency and historical information within a memory pool. We have evaluated our method based on both task and resting state fMRI data. Both qualitative and quantitative results have demonstrated that the proposed method outperformed state-of-the-art alternative deep learning methods.