A contrastive learning approach to integrate spatial transcriptomics and histological images.

The rapid growth of spatially resolved transcriptomics technology provides new perspectives on spatial tissue architecture. Deep learning has been widely applied to derive useful representations for spatial transcriptome analysis. However, effectively integrating spatial multi-modal data remains challenging. Here, we present ConGcR, a contrastive learning-based model for integrating gene expression, spatial location, and tissue morphology for data representation and spatial tissue architecture identification. Graph convolution and ResNet were used as encoders for gene expression with spatial location and histological image inputs, respectively. We further enhanced ConGcR with a graph auto-encoder as ConGaR to better model spatially embedded representations. We validated our models using 16 human brains, four chicken hearts, eight breast tumors, and 30 human lung spatial transcriptomics samples. The results showed that our models generated more effective embeddings for obtaining tissue architectures closer to the ground truth than other methods. Overall, our models not only can improve tissue architecture identification's accuracy but also may provide valuable insights and effective data representation for other tasks in spatial transcriptome analyses.

Epstein-Barr Virus Orchestrates Spatial Reorganization and Immunomodulation within the Classic Hodgkin Lymphoma Tumor Microenvironment.

Classic Hodgkin Lymphoma (cHL) is a tumor composed of rare malignant Hodgkin and Reed-Sternberg (HRS) cells nested within a T-cell rich inflammatory immune infiltrate. cHL is associated with Epstein-Barr Virus (EBV) in 25% of cases. The specific contributions of EBV to the pathogenesis of cHL remain largely unknown, in part due to technical barriers in dissecting the tumor microenvironment (TME) in high detail. Herein, we applied multiplexed ion beam imaging (MIBI) spatial pro-teomics on 6 EBV-positive and 14 EBV-negative cHL samples. We identify key TME features that distinguish between EBV-positive and EBV-negative cHL, including the relative predominance of memory CD8 T cells and increased T-cell dysfunction as a function of spatial proximity to HRS cells. Building upon a larger multi-institutional cohort of 22 EBV-positive and 24 EBV-negative cHL samples, we orthogonally validated our findings through a spatial multi-omics approach, coupling whole transcriptome capture with antibody-defined cell types for tu-mor and T-cell populations within the cHL TME. We delineate contrasting transcriptomic immunological signatures between EBV-positive and EBV-negative cases that differently impact HRS cell proliferation, tumor-immune interactions, and mecha-nisms of T-cell dysregulation and dysfunction. Our multi-modal framework enabled a comprehensive dissection of EBV-linked reorganization and immune evasion within the cHL TME, and highlighted the need to elucidate the cellular and molecular fac-tors of virus-associated tumors, with potential for targeted therapeutic strategies.

Rupture-Related Features of Cerebral Arteriovenous Malformations and Their Utility in Predicting Hemorrhage.

BACKGROUND: Evaluating rupture risk in cerebral arteriovenous malformations currently lacks quantitative hemodynamic and angioarchitectural features necessary for predicting subsequent hemorrhage. We aimed to derive rupture-related hemodynamic and angioarchitectural features of arteriovenous malformations and construct an ensemble model for predicting subsequent hemorrhage. METHODS: This retrospective study included 3 data sets, as follows: training and test data sets comprising consecutive patients with untreated cerebral arteriovenous malformations who were admitted from January 2015 to June 2022 and a validation data set comprising patients with unruptured arteriovenous malformations who received conservative treatment between January 2009 and December 2014. We extracted rupture-related features and developed logistic regression (clinical features), decision tree (hemodynamic features), and support vector machine (angioarchitectural features) models. These 3 models were combined into an ensemble model using a weighted soft-voting strategy. The performance of the models in discriminating ruptured arteriovenous malformations and predicting subsequent hemorrhage was evaluated with confusion matrix-related metrics in the test and validation data sets. RESULTS: A total of 896 patients (mean±SD age, 28±14 years; 404 women) were evaluated, with 632, 158, and 106 patients in the training, test, and validation data sets, respectively. From the training set, 9 clinical, 10 hemodynamic, and 2912 pixel-based angioarchitectural features were extracted. A logistic regression model was built using 4 selected clinical features (age, nidus size, location, and venous aneurysm), whereas a decision-tree model was constructed from 4 hemodynamic features (outflow time, stasis index, cerebral blood flow, and outflow volume ratio). A support vector machine model was designed using 5 pixel-based angioarchitectural features. In the validation data set, the accuracy, sensitivity, specificity, and area under the curve of the ensemble model for predicting subsequent hemorrhages were 0.840, 0.889, 0.823, and 0.911, respectively. CONCLUSIONS: The ensemble model incorporating clinical, hemodynamic, and angioarchitectural features showed favorable performance in predicting subsequent hemorrhage of cerebral arteriovenous malformations.

Graph Fourier transform for spatial omics representation and analyses of complex organs.

Spatial omics technologies are capable of deciphering detailed components of complex organs or tissue in cellular and subcellular resolution. A robust, interpretable, and unbiased representation method for spatial omics is necessary to illuminate novel investigations into biological functions, whereas a mathematical theory deficiency still exists. We present SpaGFT (Spatial Graph Fourier Transform), which provides a unique analytical feature representation of spatial omics data and elucidates molecular signatures linked to critical biological processes within tissues and cells. It outperformed existing tools in spatially variable gene prediction and gene expression imputation across human/mouse Visium data. Integrating SpaGFT representation into existing machine learning frameworks can enhance up to 40% accuracy of spatial domain identification, cell type annotation, cell-to-spot alignment, and subcellular hallmark inference. SpaGFT identified immunological regions for B cell maturation in human lymph node Visium data, characterized secondary follicle variations from in-house human tonsil CODEX data, and detected extremely rare subcellular organelles such as Cajal body and Set1/COMPASS. This new method lays the groundwork for a new theoretical model in explainable AI, advancing our understanding of tissue organization and function.

Prediction of Venous Trans-Stenotic Pressure Gradient Using Shape Features Derived From Magnetic Resonance Venography in Idiopathic Intracranial Hypertension Patients.

OBJECTIVE: Idiopathic intracranial hypertension (IIH) is a condition of unknown etiology associated with venous sinus stenosis. This study aimed to develop a magnetic resonance venography (MRV)-based radiomics model for predicting a high trans-stenotic pressure gradient (TPG) in IIH patients diagnosed with venous sinus stenosis. MATERIALS AND METHODS: This retrospective study included 105 IIH patients (median age [interquartile range], 35 years [27-42 years]; female:male, 82:23) who underwent MRV and catheter venography complemented by venous manometry. Contrast enhanced-MRV was conducted under 1.5 Tesla system, and the images were reconstructed using a standard algorithm. Shape features were derived from MRV images via the PyRadiomics package and selected by utilizing the least absolute shrinkage and selection operator (LASSO) method. A radiomics score for predicting high TPG (≥ 8 mmHg) in IIH patients was formulated using multivariable logistic regression; its discrimination performance was assessed using the area under the receiver operating characteristic curve (AUROC). A nomogram was constructed by incorporating the radiomics scores and clinical features. RESULTS: Data from 105 patients were randomly divided into two distinct datasets for model training (n = 73; 50 and 23 with and without high TPG, respectively) and testing (n = 32; 22 and 10 with and without high TPG, respectively). Three informative shape features were identified in the training datasets: least axis length, sphericity, and maximum three-dimensional diameter. The radiomics score for predicting high TPG in IIH patients demonstrated an AUROC of 0.906 (95% confidence interval, 0.836-0.976) in the training dataset and 0.877 (95% confidence interval, 0.755-0.999) in the test dataset. The nomogram showed good calibration. CONCLUSION: Our study presents the feasibility of a novel model for predicting high TPG in IIH patients using radiomics analysis of noninvasive MRV-based shape features. This information may aid clinicians in identifying patients who may benefit from stenting.

TREM2 mediates MHCII-associated CD4+ T cell response against gliomas.

BACKGROUND: Myeloid cells comprise up to 50% of the total tumor mass in glioblastoma (GBM) and have been implicated in promoting tumor progression and immunosuppression. Modulating the response of myeloid cells to the tumor has emerged as a promising new approach for cancer treatment. In this regard, we focus on the Triggering Receptor Expressed on Myeloid cells 2 (TREM2), which has recently emerged as a novel immune modulator in peripheral tumors. METHODS: We studied the TREM2 expression profile in various patient tumor samples and conducted single-cell transcriptomic analysis in both glioblastoma patients and the GL261 mouse glioma model. We utilized multiple mouse glioma models and employed state-of-the-art techniques such as in vivo two-photon imaging, spectrum flow cytometry, and in vitro co-culture assays to study TREM2 function in myeloid cell-mediated phagocytosis of tumor cells, antigen presentation, and response of CD4+ T cells within the tumor hemispheres. RESULTS: Our research revealed significantly elevated levels of TREM2 expression in brain tumors compared to other types of tumors in patients. TREM2 was predominantly localized in tumor-associated myeloid cells and was highly expressed in nearly all microglia, as well as various subtypes of macrophages. Surprisingly, in pre-clinical glioma models, TREM2 deficiency did not confer a beneficial effect; instead, it accelerated glioma progression. Through detailed investigations, we determined that TREM2 deficiency impaired the ability of tumor-myeloid cells to phagocytose tumor cells and led to reduced expression of MHCII. This deficiency further significantly decreased the presence of CD4+ T cells within the tumor hemispheres. CONCLUSIONS: Our study unveiled a previously unrecognized protective role of tumor-myeloid TREM2. Specifically, we found TREM2 enhance the phagocytosis of tumor cells and promote an immune response by facilitating MHCII-associated CD4+ T cell responses against gliomas.

Dimension-agnostic and granularity-based spatially variable gene identification using BSP.

Identifying spatially variable genes (SVGs) is critical in linking molecular cell functions with tissue phenotypes. Spatially resolved transcriptomics captures cellular-level gene expression with corresponding spatial coordinates in two or three dimensions and can be used to infer SVGs effectively. However, current computational methods may not achieve reliable results and often cannot handle three-dimensional spatial transcriptomic data. Here we introduce BSP (big-small patch), a non-parametric model by comparing gene expression pattens at two spatial granularities to identify SVGs from two or three-dimensional spatial transcriptomics data in a fast and robust manner. This method has been extensively tested in simulations, demonstrating superior accuracy, robustness, and high efficiency. BSP is further validated by substantiated biological discoveries in cancer, neural science, rheumatoid arthritis, and kidney studies with various types of spatial transcriptomics technologies.

High-resolution magnetic resonance imaging-based radiomic features aid in selecting endovascular candidates among patients with cerebral venous sinus thrombosis.

OBJECTIVES: Cerebral venous sinus thrombosis (CVST) can cause sinus obstruction and stenosis, with potentially fatal consequences. High-resolution magnetic resonance imaging (HRMRI) can diagnose CVST qualitatively, although quantitative screening methods are lacking for patients refractory to anticoagulation therapy and who may benefit from endovascular treatment (EVT). Thus, in this study, we used radiomic features (RFs) extracted from HRMRI to build machine learning models to predict response to drug therapy and determine the appropriateness of EVT. MATERIALS AND METHODS: RFs were extracted from three-dimensional T1-weighted motion-sensitized driven equilibrium (MSDE), T2-weighted MSDE, T1-contrast, and T1-contrast MSDE sequences to build radiomic signatures and support vector machine (SVM) models for predicting the efficacy of standard drug therapy and the necessity of EVT. RESULTS: We retrospectively included 53 patients with CVST in a prospective cohort study, among whom 14 underwent EVT after standard drug therapy failed. Thirteen RFs were selected to construct the RF signature and CVST-SVM models. In the validation dataset, the sensitivity, specificity, and area under the curve performance for the RF signature model were 0.833, 0.937, and 0.977, respectively. The radiomic score was correlated with days from symptom onset, history of dyslipidemia, smoking, fibrin degradation product, and D-dimer levels. The sensitivity, specificity, and area under the curve for the CVST-SVM model in the validation set were 0.917, 0.969, and 0.992, respectively. CONCLUSIONS: The CVST-SVM model trained with RFs extracted from HRMRI outperformed the RF signature model and could aid physicians in predicting patient responses to drug treatment and identifying those who may require EVT.

Identifying predictors of glioma evolution from longitudinal sequencing.

Clonal evolution drives cancer progression and therapeutic resistance. Recent studies have revealed divergent longitudinal trajectories in gliomas, but early molecular features steering posttreatment cancer evolution remain unclear. Here, we collected sequencing and clinical data of initial-recurrent tumor pairs from 544 adult diffuse gliomas and performed multivariate analysis to identify early molecular predictors of tumor evolution in three diffuse glioma subtypes. We found that CDKN2A deletion at initial diagnosis preceded tumor necrosis and microvascular proliferation that occur at later stages of IDH-mutant glioma. Ki67 expression at diagnosis was positively correlated with acquiring hypermutation at recurrence in the IDH-wild-type glioma. In all glioma subtypes, MYC gain or MYC-target activation at diagnosis was associated with treatment-induced hypermutation at recurrence. To predict glioma evolution, we constructed CELLO2 (Cancer EvoLution for LOngitudinal data version 2), a machine learning model integrating features at diagnosis to forecast hypermutation and progression after treatment. CELLO2 successfully stratified patients into subgroups with distinct prognoses and identified a high-risk patient group featured by MYC gain with worse post-progression survival, from the low-grade IDH-mutant-noncodel subtype. We then performed chronic temozolomide-induction experiments in glioma cell lines and isogenic patient-derived gliomaspheres and demonstrated that MYC drives temozolomide resistance by promoting hypermutation. Mechanistically, we demonstrated that, by binding to open chromatin and transcriptionally active genomic regions, c-MYC increases the vulnerability of key mismatch repair genes to treatment-induced mutagenesis, thus triggering hypermutation. This study reveals early predictors of cancer evolution under therapy and provides a resource for precision oncology targeting cancer dynamics in diffuse gliomas.

Quantitative evaluation of the subsequent hemorrhage with arteriography-derived hemodynamic features in patients with untreated cerebral arteriovenous malformation.

Background: Patients with untreated cerebral arteriovenous malformations (AVMs) are at risk of intracerebral hemorrhage. However, treatment to prevent AVM hemorrhage carries risks. Objective: This study aimed to analyze the AVM nidus-related hemodynamic features and identify the risk factors for subsequent hemorrhage. Methods: We retrospectively identified patients with untreated AVMs who were assessed at our institution between March 2010 and March 2021. Patients with ≥6 months of treatment-free and hemorrhage-free follow-up after diagnosed by digital subtraction angiography were included in subsequent examinations. The hemodynamic features were extracted from five contrast flow-related parameter maps. The Kaplan-Meier analyses and Cox proportional hazards regression models were used to find the potential risk factors for subsequent hemorrhage. Results: Overall, 104 patients with a mean follow-up duration of 3.37 years (median, 2.42 years; range, 6-117 months) were included in study, and the annual risk of rupture was 3.7%. Previous rupture (hazard ratio [HR], 4.89; 95% confidence interval [CI], 1.16-20.72), deep AVM location (HR, 4.02; 95% CI, 1.01-15.99), higher cerebral blood volume (HR, 3.35; 95% CI, 1.15-9.74) in the nidus, and higher stasis index (HR, 1.54; 95% CI, 1.06-2.24) in the nidus were associated with subsequent hemorrhage in untreated AVMs. Conclusion: Higher cerebral blood volume and stasis index in the nidus suggest increased blood inflow and stagnant blood drainage. The combination of these factors may cause subsequent hemorrhage of AVMs.

Single-cell profiling of murine bladder cancer identifies sex-specific transcriptional signatures with prognostic relevance.

Bladder cancer (BLCA) is more common in men but more aggressive in women. Sex-based differences in cancer biology are commonly studied using a murine model with BLCA generated by N-butyl-N-(4-hydroxybutyl)-nitrosamine (BBN). While tumors in the BBN model have been profiled, these profiles provide limited information on the tumor microenvironment. Here, we applied single-cell RNA sequencing to characterize cell-type specific transcriptional differences between male and female BBN-induced tumors. We found proportional and gene expression differences in epithelial and non-epithelial subpopulations between male and female tumors. Expression of several genes predicted sex-specific survival in several human BLCA datasets. We identified novel and clinically relevant sex-specific transcriptional signatures including immune cells in the tumor microenvironment and it validated the relevance of the BBN model for studying sex differences in human BLCA. This work highlights the importance of considering sex as a biological variable in the development of new and accurate cancer markers.

TREM2 mediates MHCII-associated CD4+ T cell response against gliomas.

Triggering receptor expressed on myeloid cells 2 (TREM2) was recently highlighted as a novel immune suppressive marker in peripheral tumors. The aim of this study was to characterize TREM2 expression in gliomas and investigate its contribution in glioma progression by using Trem2-/- mouse line. Our results showed that higher TREM2 expression was correlated with poor prognosis in glioma patients. Unexpectedly, TREM2 deficiency did not have a beneficial effect in a pre-clinical model of glioma. The increased TREM2 expression in glioma was likely due to increased myeloid cell infiltration, as evidenced by our single-cell analysis showing that almost all microglia and macrophages in gliomas were TREM2+. Furthermore, we found that deficiency of TREM2 impaired tumor-myeloid phagocytosis and MHCII presentation, and significantly reduced CD4+ T cells in tumor hemispheres. Our results revealed a previously unrecognized protective role of tumor-myeloid TREM2 in promoting MHCII-associated CD4+ T cell response against gliomas.

Dimension-agnostic and granularity-based spatially variable gene identification.

Identifying spatially variable genes (SVGs) is critical in linking molecular cell functions with tissue phenotypes. Spatially resolved transcriptomics captures cellular-level gene expression with corresponding spatial coordinates in two or three dimensions and can be used to infer SVGs effectively. However, current computational methods may not achieve reliable results and often cannot handle three-dimensional spatial transcriptomic data. Here we introduce BSP (big-small patch), a spatial granularity-guided and non-parametric model to identify SVGs from two or three-dimensional spatial transcriptomics data in a fast and robust manner. This new method has been extensively tested in simulations, demonstrating superior accuracy, robustness, and high efficiency. BSP is further validated by substantiated biological discoveries in cancer, neural science, rheumatoid arthritis, and kidney studies with various types of spatial transcriptomics technologies.

Dimension-agnostic and granularity-based spatially variable gene identification.

Identifying spatially variable genes (SVGs) is critical in linking molecular cell functions with tissue phenotypes. Spatially resolved transcriptomics captures cellular-level gene expression with corresponding spatial coordinates in two or three dimensions and can be used to infer SVGs effectively. However, current computational methods may not achieve reliable results and often cannot handle three-dimensional spatial transcriptomic data. Here we introduce BSP (big-small patch), a spatial granularity-guided and non-parametric model to identify SVGs from two or three-dimensional spatial transcriptomics data in a fast and robust manner. This new method has been extensively tested in simulations, demonstrating superior accuracy, robustness, and high efficiency. BSP is further validated by substantiated biological discoveries in cancer, neural science, rheumatoid arthritis, and kidney studies with various types of spatial transcriptomics technologies.

Pipeline embolization devices for the treatment of nonsaccular aneurysms in pediatric patients.

Objective: Pediatric nonsaccular aneurysms are rare but challenging lesions; pipeline embolization devices (PEDs) are their potential treatment option. In this study, we aimed to evaluate the safety and efficacy of PEDs for treatment of these aneurysms. Methods: We retrospectively selected pediatric patients with nonsaccular aneurysms treated using PEDs between June 2015 and July 2021 from our prospectively maintained database. For each patient, demographics, aneurysm characteristics, procedure details, and clinical and angiographic follow-up data were collected and summarized. Results: This study included 16 pediatric patients with 16 nonsaccular aneurysms treated with PEDs. A median clinical follow-up time of 1,376 days was achieved in 93.75% of the patients. The complication rate of the included patients was 25%, with two patients developing mass effect, one patient undergoing major ischemic stroke, and one patient experiencing stent foreshortening after the procedure. The complete occlusion rate of aneurysms without any neurologic sequelae was 93.33%, with a median angiographic follow-up period of 246 days. The mortality rate was 6.25%. Conclusions: The use of PEDs to treat pediatric nonsaccular aneurysms is feasible, with a high rate of complete occlusion of the aneurysm and favorable follow-up outcomes.

Single-cell biological network inference using a heterogeneous graph transformer.

Single-cell multi-omics (scMulti-omics) allows the quantification of multiple modalities simultaneously to capture the intricacy of complex molecular mechanisms and cellular heterogeneity. Existing tools cannot effectively infer the active biological networks in diverse cell types and the response of these networks to external stimuli. Here we present DeepMAPS for biological network inference from scMulti-omics. It models scMulti-omics in a heterogeneous graph and learns relations among cells and genes within both local and global contexts in a robust manner using a multi-head graph transformer. Benchmarking results indicate DeepMAPS performs better than existing tools in cell clustering and biological network construction. It also showcases competitive capability in deriving cell-type-specific biological networks in lung tumor leukocyte CITE-seq data and matched diffuse small lymphocytic lymphoma scRNA-seq and scATAC-seq data. In addition, we deploy a DeepMAPS webserver equipped with multiple functionalities and visualizations to improve the usability and reproducibility of scMulti-omics data analysis.

Recent advances of bioactive proteins/polypeptides in the treatment of breast cancer.

Proteins do not only serve as nutrients to fulfill the demand for food, but also are used as a source of bioactive proteins/polypeptides for regulating physical functions and promoting physical health. Female breast cancer has the highest incidence in the world and is a serious threat to women's health. Bioactive proteins/polypeptides exert strong anti-tumor effects and exhibit inhibition of multiple breast cancer cells. This review discussed the suppressing effects of bioactive proteins/polypeptides on breast cancer in vitro and in vivo, and their mechanisms of migration and invasion inhibition, apoptosis induction, and cell cycle arrest. This may contribute to providing a basis for the development of bioactive proteins/polypeptides for the treatment of breast cancer.

A Bayesian multivariate mixture model for high throughput spatial transcriptomics.

High throughput spatial transcriptomics (HST) is a rapidly emerging class of experimental technologies that allow for profiling gene expression in tissue samples at or near single-cell resolution while retaining the spatial location of each sequencing unit within the tissue sample. Through analyzing HST data, we seek to identify sub-populations of cells within a tissue sample that may inform biological phenomena. Existing computational methods either ignore the spatial heterogeneity in gene expression profiles, fail to account for important statistical features such as skewness, or are heuristic-based network clustering methods that lack the inferential benefits of statistical modeling. To address this gap, we develop SPRUCE: a Bayesian spatial multivariate finite mixture model based on multivariate skew-normal distributions, which is capable of identifying distinct cellular sub-populations in HST data. We further implement a novel combination of Pólya-Gamma data augmentation and spatial random effects to infer spatially correlated mixture component membership probabilities without relying on approximate inference techniques. Via a simulation study, we demonstrate the detrimental inferential effects of ignoring skewness or spatial correlation in HST data. Using publicly available human brain HST data, SPRUCE outperforms existing methods in recovering expertly annotated brain layers. Finally, our application of SPRUCE to human breast cancer HST data indicates that SPRUCE can distinguish distinct cell populations within the tumor microenvironment. An R package spruce for fitting the proposed models is available through The Comprehensive R Archive Network.