Tumorigenesis arises from the dysfunction of cancer genes, leading to uncontrolled cell proliferation through various mechanisms. Establishing a complete cancer gene catalogue will make precision oncology possible. Although existing methods based on graph neural networks (GNN) are effective in identifying cancer genes, they fall short in effectively integrating data from multiple views and interpreting predictive outcomes. To address these shortcomings, an interpretable representation learning framework IMVRL-GCN is proposed to capture both shared and specific representations from multiview data, offering significant insights into the identification of cancer genes. Experimental results demonstrate that IMVRL-GCN outperforms state-of-the-art cancer gene identification methods and several baselines. Furthermore, IMVRL-GCN is employed to identify a total of 74 high-confidence novel cancer genes, and multiview data analysis highlights the pivotal roles of shared, mutation-specific, and structure-specific representations in discriminating distinctive cancer genes. Exploration of the mechanisms behind their discriminative capabilities suggests that shared representations are strongly associated with gene functions, while mutation-specific and structure-specific representations are linked to mutagenic propensity and functional synergy, respectively. Finally, our in-depth analyses of these candidates suggest potential insights for individualized treatments: afatinib could counteract many mutation-driven risks, and targeting interactions with cancer gene SRC is a reasonable strategy to mitigate interaction-induced risks for NR3C1, RXRA, HNF4A, and SP1.

Accurate detection of enhancer-promoter loops from genome-wide chromatin interaction data is critical for understanding gene regulation. Standard normalization methods, such as matrix balancing approaches, are widely used to correct biases in chromatin contact data prior to chromatin loop detection. However, while these methods preserve structural loop signals, they often attenuate enhancer-promoter interaction signals, making these regulatory loops more difficult to detect. To address this limitation, we develop Raichu, a normalization method for chromatin contact data. Raichu identifies nearly twice as many loops as conventional normalization approaches, recovering almost all previously detected loops while uncovering thousands of additional enhancer-promoter interactions that are otherwise missed. With its improved sensitivity for regulatory loops, Raichu detects more biologically meaningful differential interactions, including those between conditions within the same cell type. Moreover, Raichu performs robustly across a wide range of sequencing depths, resolutions, species, and experimental platforms, making it a versatile tool for revealing insights into three-dimensional genome organization and transcriptional regulation.

The prevalence of rheumatoid arthritis (RA) subtypes, including seropositive and seronegative, is influenced by lifestyle factors and exhibits high heterogeneity, resulting in reduced drug efficacy. This study aims to identify cytokines mediating the effects of different lifestyles on RA subtypes and to discover new drugs for personalized treatment. Mendelian randomization revealed that three cytokines (MIP1b, SCGFb, and TRAIL) partially mediated the effects of different lifestyles on RA overall or its subtypes. The pretrained model, i.e., DrugBAN, predicted the probability of 723,000 small molecule drugs binding to these three targets. In molecules with high binding rates, we calculated the structural similarity between known drugs for RA and other drugs to screen for new drugs, followed by molecular docking and molecular dynamics simulations for validation. The results indicate that these targets had promising binding affinity with known drugs and other drugs with high similarity. Our findings may guide therapeutic approaches for heterogeneous RA patients with specific lifestyle habits.

The identification of cancer prognostic biomarkers is crucial for predicting disease progression, optimizing personalized therapies, and improving patient survival. Molecular biomarkers are increasingly being identified for cancer prognosis estimation. However, existing studies and databases often focus on single-type molecular biomarkers, deficient in comprehensive multi-omics data integration, which constrains the comprehensive exploration of biomarkers and underlying mechanisms. To fill this gap, we conducted a systematic prognostic analysis using over 10,000 samples across 33 cancer types from The Cancer Genome Atlas (TCGA). Our study integrated nine types of molecular biomarker-related data: single-nucleotide polymorphism (SNP), copy number variation (CNV), alternative splicing (AS), alternative polyadenylation (APA), coding gene expression, DNA methylation, lncRNA expression, miRNA expression, and protein expression. Using log-rank tests, univariate Cox regression (uni-Cox), and multivariate Cox regression (multi-Cox), we evaluated potential biomarkers associated with four clinical outcome endpoints: overall survival (OS), disease-specific survival (DSS), disease-free interval (DFI), and progression-free interval (PFI). As a result, we identified 4,498,523 molecular biomarkers significantly associated with cancer prognosis. Finally, we developed SurvDB, an interactive online database for data retrieval, visualization, and download, providing a comprehensive resource for biomarker discovery and precision oncology research.