Unsupervised cell type identification is crucial for uncovering and characterizing heterogeneous populations in single cell omics studies. Although a range of clustering methods have been developed, most focus exclusively on intrinsic cellular structure and ignore the pivotal role of cell-gene associations, which limits their ability to distinguish closely related cell types. To this end, we propose a Refinement Contrastive Learning framework (scRCL) that explicitly incorporates cell-gene interactions to derive more informative representations. Specifically, we introduce two contrastive distribution alignment components that reveal reliable intrinsic cellular structures by effectively exploiting cell-cell structural relationships. Additionally, we develop a refinement module that integrates gene-correlation structure learning to enhance cell embeddings by capturing underlying cell-gene associations. This module strengthens connections between cells and their associated genes, refining the representation learning to exploiting biologically meaningful relationships. Extensive experiments on several single-cell RNA-seq and spatial transcriptomics benchmark datasets demonstrate that our method consistently outperforms state-of-the-art baselines in cell-type identification accuracy. Moreover, downstream biological analyses confirm that the recovered cell populations exhibit coherent gene-expression signatures, further validating the biological relevance of our approach.

The development of single-cell RNA sequencing (scRNA-seq) technology has enabled the exploration of biological processes at the cellular level. A critical task in scRNA-seq data analysis is the unsupervised clustering of cells to distinguish different cell types. While various clustering methods have been successfully developed for scRNA-seq data, they still face limitations, particularly in terms of unstable clustering performance. This is often due to their inability to fully capture the intrinsic properties of cells, especially in the presence of high dropout rates and noise in the data. In this work, we propose a SEmantic-Aware contrastive Learning (SEAL) approach for scRNA-seq clustering. Specifically, we randomly mask the gene expression of each cell to generate two different augmentations of the cell data, and then apply semantic-aware contrastive learning to capture semantically invariant representations across these augmentations by leveraging semantic information from generated pseudo-labels. Experimental results demonstrate that our method effectively learns biologically meaningful representations and accurately identifies cell types.

Multi-view clustering has been empirically shown to improve learning performance by leveraging the inherent complementary information across multiple views of data. However, in real-world scenarios, collecting strictly aligned views is challenging, and learning from both aligned and unaligned data becomes a more practical solution. Partially View-aligned Clustering (PVC) aims to learn correspondences between misaligned view samples to better exploit the potential consistency and complementarity across views, including both aligned and unaligned data. However, most existing PVC methods fail to leverage unaligned data to capture the shared semantics among samples from the same cluster. Moreover, the inherent heterogeneity of multi-view data induces distributional shifts in representations, leading to inaccuracies in establishing meaningful correspondences between cross-view latent features and, consequently, impairing learning effectiveness. To address these challenges, we propose a Semantic MAtching contRasTive learning model (SMART) for PVC. The main idea of our approach is to alleviate the influence of cross-view distributional shifts, thereby facilitating semantic matching contrastive learning to fully exploit semantic relationships in both aligned and unaligned data. Specifically, we mitigate view distribution shifts by aligning cross-view covariance matrices, which enables the inference of a semantic graph for all data. Guided by the learned semantic graph, we further exploit semantic consistency across views through semantic matching contrastive learning. After the optimization of the above mechanisms, our model smoothly performs semantic matching for different view embeddings instead of the cumbersome view realignment, which enables the learned representations to enjoy richer category-level semantics and stronger robustness. Extensive experiments on eight benchmark datasets demonstrate that our method consistently outperforms existing approaches on the PVC problem. The code is available at https://github.com/THPengL/SMART.

Multi-view clustering (MVC) has shown that leveraging both consistency and complementary information across views enhances clustering performance. However, most existing methods focus on aligning features into the same dimension, often neglecting cross-view heterogeneity and introducing discrepancies. To address this, we propose a novel multi-view clustering framework that combines cross-view neighborhood contrastive learning with a cross-attention view-mixup feature learning mechanism. Specifically, the cross-attention view-mixup module learns view-invariant feature representations by capturing complementary and consistent information, while the neighborhood contrastive learning module uncovers semantic structures across views based on the learned mixup features. By implicitly performing feature mixup across views and effectively integrating cross-view neighborhood contrastive learning, our method alleviates cross-view discrepancies and enables more effective integration of complementary and consistent information, ultimately enhancing clustering performance. Experiments conducted on several real datasets demonstrate the effectiveness of our proposed method in comparision with several representative MVC approaches.

BACKGROUND: Polygenic risk score (PRS) have proved to offer robust risk prediction for coronary artery disease (CAD). However, the global CAD PRS summarizes the joint effects of all the markers in the genome, masking potential genetic heterogeneity that may be important for disease interpretation and targeted interventions. METHODS: Using summary-level data, we identified 43 significant CAD-related traits based on genetic correlations, and further classified them into eight pleiotropy clusters based on their biological functions. We then partitioned the genome into 2,353 near-independent regions. Variants in each region were assigned to the trait most genetically similar to CAD, and then were labeled with the corresponding pleiotropy cluster. We grouped variants without labels into a ninth, non-specific cluster. The Pleiotropy Decomposed (PD) PRSs for each of the nine clusters were calculated using variants assigned to each cluster for 407,903 samples of European ancestry from the UK Biobank (UKBB). RESULTS: We decomposed the CAD PRS into nine PD-PRSs and further stratified individuals with high CAD-PRS into nine subgroups. Each PD-PRS accounted for a higher proportion of the global CAD-PRS within its corresponding subgroup than in the remaining subjects with high CAD-PRS (e.g., 25.2% (0.07) vs. 10.06% (0.07) for lipids-PD-PRS). Additionally, these subgroups showed distinct clinical features. For example, in the lipids-related subgroup, lipoprotein(a) and LDL-cholesterol levels were 67.5% and 18.3% higher, respectively, compared to the remaining high-risk individuals. Furthermore, significant interactions were observed between blood pressure and BP PD-PRS, and between current smoking and respiratory system PD-PRS. CONCLUSION: Our findings suggest that PD-PRSs may reveal substantial genetic and phenotypic heterogeneity among individuals with high CAD-PRS. The unique PD-PRS compositions of each individual can highlight the relative importance of different pleiotropic regions.

Genetic correlation is the correlation of phenotypic effects by genetic variants across the genome on two phenotypes. It is an informative metric to quantify the overall genetic similarity between complex traits, which provides insights into their polygenic genetic architecture. Several methods have been proposed to estimate genetic correlation based on data collected from genome-wide association studies (GWAS). Due to the easy access of GWAS summary statistics and computational efficiency, methods only requiring GWAS summary statistics as input have become more popular than methods utilizing individual-level genotype data. Here, we present a benchmark study for different summary-statistics-based genetic correlation estimation methods through simulation and real data applications. We focus on two major technical challenges in estimating genetic correlation: marker dependency caused by linkage disequilibrium (LD) and sample overlap between different studies. To assess the performance of different methods in the presence of these two challenges, we first conducted comprehensive simulations with diverse LD patterns and sample overlaps. Then we applied these methods to real GWAS summary statistics for a wide spectrum of complex traits. Based on these experiments, we conclude that methods relying on accurate LD estimation are less robust in real data applications due to the imprecision of LD obtained from reference panels. Our findings offer guidance on how to choose appropriate methods for genetic correlation estimation in post-GWAS analysis.