ABSTRACT Accurate prognosis in diffuse large B‐cell lymphoma (DLBCL) remains a clinical challenge. The International Prognostic Index (IPI) is the standard tool but relies solely on clinical variables and fails to capture the extensive molecular heterogeneity of DLBCL. Integrating transcriptomics has shown promise for improving patient stratification, yet most approaches lack biological interpretability and external validation. Here, we apply Cox‐PASNet, a pathway‐structured neural network survival model, to DLBCL, integrating gene expression with clinical features. Using a discovery cohort of 670 patients (GSE181063) and an independent external validation cohort of 233 R‐CHOP‐treated patients (GSE10846), we demonstrate that late fusion of pathway‐structured transcriptomics with IPI achieves a C ‐index of 0.700 ± 0.020 on the discovery cohort and 0.732 on external validation, statistically significantly outperforming the externally transferred IPI‐Cox baseline ( C ‐index 0.678; Δ = +0.054, bootstrap 95% confidence interval [CI] [+0.004, +0.104], p = 0.018). Incorporating cell‐of‐origin subtype further raised the external fused C ‐index to 0.745, though this additional gain over IPI‐Cox did not reach the pre‐specified significance threshold (bootstrap 95% CI [−0.0003, +0.130]). Pathway‐level explainability analysis identified apoptosis, hypoxia, IL6/JAK/STAT3 signaling, and interferon gamma response as consistently prognostic, with CDKN1A emerging as a recurrent hub gene across multiple pathways and GPX4 among the top‐ranked genes. These findings support the translational potential of pathway‐structured multimodal survival modeling in DLBCL.
ABSTRACT This review aims to explore the computational foundations of big data in cancer genomics and examine emerging pathways that support precision oncology and personalized cancer care. A narrative review approach was adopted to synthesize evidence from PubMed, Scopus, Web of Science, and IEEE Xplore. The literature search was conducted between January 10 and February 25, 2026, and 68 relevant studies were included in the final synthesis. Relevant studies were selected on the basis of their focus on computational methods, data integration strategies, and artificial intelligence (AI) applications in cancer genomics. Extracted data were organized into thematic categories and analyzed using an iterative synthesis framework. The findings indicate that high‐throughput sequencing and multi‐omics technologies have significantly expanded the volume and complexity of cancer‐related data. Advanced infrastructures, including cloud platforms, improve storage and access but raise privacy and interoperability concerns. Machine learning and AI support tumor classification, biomarker discovery, and treatment prediction. Integrative multi‐omics enhances biological insight and predictive accuracy. However, challenges such as data heterogeneity, limited model generalizability, and gaps in clinical integration remain. Big data in cancer genomics offer substantial potential to advance precision oncology by enabling more accurate and personalized treatment strategies. However, overcoming technical, ethical, and infrastructural barriers is essential to ensure effective translation into clinical practice and equitable healthcare outcomes.
ABSTRACT Breast cancer affects approximately one in every eight women globally, as reported by the World Health Organization. Among all female malignant tumors, breast cancer has the highest fatality rate, surpassed only by lung cancer. Advanced stages of this disease are almost always fatal, and despite the advancements in surgical techniques and carefully designed chemotherapy regimens, relapse remains nearly inevitable. Although there are various chemical therapies for the treatment of breast cancer that can destroy the tumor or inhibit its growth, they often come with a variety of side‐effects. The polyphenolic compound quercetin can be found in numerous food plants. Previous research strongly suggests quercetin's potential as a cancer therapy. Various types of cancer cell lines have demonstrated that quercetin can induce apoptosis and suppress the proliferation of cancer cells. Therefore, we conducted an integrative bioinformatics analysis to identify molecular signatures, signaling pathways, and lncRNA‐associated gene relationships potentially related to quercetin‐associated transcriptional changes in breast cancer. The identified candidates were subsequently explored using protein–protein interaction and public regulatory databases. These findings are intended to generate hypotheses regarding potential lncRNA‐associated mechanisms rather than establish direct causal quercetin–lncRNA interactions. We found several genes involved in different metabolic pathways in relation to breast cancer and quercetin treatment.
ABSTRACT Inherited factors account for a large share of breast cancer susceptibility, yet the biological consequences of most risk variants are still poorly understood. To address this gap, we studied 175 breast cancer risk variants confirmed by genome‐wide association studies and gathered the genes that lie near them. Two complementary gene sets were assembled. The first collected every gene immediately flanking each risk variant, regardless of distance. The second kept only the closest gene together with genes tagged by variants in strong linkage disequilibrium within a 100 kb interval. Across both sets, the clearest biological signal pointed to androgen receptor‐mediated signaling. Pathway mapping additionally implicated the Wnt/β‐catenin and Hedgehog cascades, and this pattern was most evident in the flanking‐gene set. With HaploReg, we annotated correlated variants at each locus and recovered features that mark active regulation. Enrichment testing returned a 4.8‐fold excess of DNase I hypersensitivity in a breast cancer cell line and a 15.7‐fold excess of enhancer motifs in a stem cell line. Together, these results indicate that breast cancer risk markers and their correlated variants influence the activity of neighboring genes and converge on a small number of signaling pathways central to mammary biology.
ABSTRACT Cadherin 1 ( CDH1 ) encodes E‐cadherin, a key epithelial adhesion molecule traditionally associated with tumor suppression and epithelial–mesenchymal transition (EMT). However, its roles across cancers remain incompletely understood, particularly within multilayer regulatory contexts involving genomic, epigenetic, transcriptional, and immune mechanisms. CDH1 expression, survival associations, EMT‐correlated gene profiles ( VIM , SNAI1 , and ZEB1 ), immune infiltration patterns, immune checkpoint correlations ( PDCD1 , CD274 , and CTLA4 ), promoter methylation, and genomic alterations were assessed across five epithelial cancers, breast invasive carcinoma (BRCA), colon adenocarcinoma (COAD), lung adenocarcinoma (LUAD), ovarian serous cystadenocarcinoma (OV), and stomach adenocarcinoma (STAD). Cross‐platform analysis was performed using The Cancer Genome Atlas (TCGA)/Genomic Data Commons (GDC) datasets, Gene Expression Profiling Interactive Analysis 2 (GEPIA2), UALCAN, TIMER, KM Plotter, cBioPortal, and g:Profiler. CDH1 was overexpressed but showed variable prognostic significance; TCGA/GDC analyses were nonsignificant, whereas KM Plotter showed better survival in COAD, LUAD, and STAD, worse survival in BRCA, and no association in OV. Classic inverse relationships between CDH1 and VIM or ZEB1 were evident only in STAD, and SNAI1 showed no consistent association. Immune infiltration patterns were tumor‐specific, ranging from cytotoxic T‐cell dominance in LUAD to macrophage‐rich profiles in OV; immune checkpoint correlations were similarly context‐dependent. Cancer‐specific enrichment revealed distinct trafficking‐ and adhesion‐related profiles. Promoter methylation patterns varied by cancer, whereas genomic alterations of CDH1 were rare. CDH1 does not function as a universal epithelial or EMT marker across epithelial cancers. Instead, its associations with EMT, immune contexture, methylation, and prognosis are context‐dependent, supporting a model of CDH1 as a heterogeneous regulator of epithelial plasticity. These findings challenge single‐function interpretations and support cancer‐specific CDH1 evaluation in translational research.
