Mol Omics. 2025 Oct 1. doi: 10.1039/d5mo00221d. Online ahead of print.

ABSTRACT

BACKGROUND: cancer exhibits high molecular and clinical heterogeneity, making accurate subtyping essential for personalized treatment. Traditional single-omics approaches often fail to capture this complexity. Multi-omics integration offers a more holistic understanding, but many existing methods either lack interpretability or fail to model cross-omics correlations effectively.

METHODS: we developed MOFNet, a novel supervised deep learning framework for multi-omics integration, incorporating a similarity graph pooling (SGO) module and a view correlation discovery network (VCDN). MOFNet processes omics data-including mRNA expression, DNA methylation, and miRNA expression-via omics-specific graph learning and cross-omics label space fusion. Three cancer types-breast cancer (BRCA), low-grade glioma (LGG), and stomach adenocarcinoma (STAD)-were analyzed using datasets from the cancer genome atlas (TCGA). Statistical evaluation was performed using accuracy, weighted F1 score, and macro F1 score across stratified training/testing splits.

RESULTS: MOFNet achieved superior performance across all datasets. For BRCA, it obtained an accuracy of 85.17%, F1_weighted of 85.36%, and macro F1 of 80.93%, outperforming all baseline models by up to 18.25%. In LGG and STAD, MOFNet also showed robust gains, with maximum improvements of 23.72% and 21.56%, respectively. Omics ablation studies demonstrated enhanced performance with multi-omics integration. Functional enrichment analysis revealed that MOFNet-identified key features were involved in biologically relevant pathways such as cell cycle regulation, synaptic signaling, and ion transport.

CONCLUSIONS: MOFNet enables scalable and interpretable multi-omics data fusion for cancer subtype classification, significantly improving predictive accuracy while retaining only 25% of input features. The integration of SGO and VCDN modules offers both biological interpretability and computational efficiency. These results suggest MOFNet's promising application in precision oncology and biomarker discovery.

PMID:41031935 | DOI:10.1039/d5mo00221d

Nat Rev Clin Oncol. 2025 Oct 3. doi: 10.1038/s41571-025-01077-z. Online ahead of print.

ABSTRACT

Patients with advanced-stage pancreatic ductal adenocarcinoma (PDAC) predominantly receive chemotherapy, and despite initial responses in some patients, most will have disease progression and often dismal outcomes. This lack of clinical effectiveness partly reflects not only cancer cell-intrinsic factors but also the presence of a tumour microenvironment (TME) that precludes access of both systemic therapies and circulating immune cells to the primary tumour, as well as supporting the growth of PDAC cells. Combined with improved preclinical models of PDAC, advances in single-cell spatial multi-omics and machine learning-based models have provided novel methods of untangling the complexities of the TME. In this Review, we focus on the desmoplastic stroma and both the intratumoural and intertumoural heterogeneity of PDAC, with an emphasis on cancer-associated fibroblasts and their surrounding immune cell niches. We describe new approaches in converting the immunologically 'cold' PDAC TME into a 'hot' TME by priming T cell activation, overcoming T cell exhaustion and unravelling myeloid cell-mediated immunosuppression. Furthermore, we explore integrated targets involving the TME, such as points of convergence among tumour, stromal and immune cell metabolism as well as oncogenic KRAS signalling. Finally, building on our experience with failed clinical trials in the past, we consider how this evolving comprehensive understanding of the TME will ensure future success in developing more effective therapies for patients with PDAC.

PMID:41044427 | DOI:10.1038/s41571-025-01077-z