Inter-patient heterogeneity complicates predicting treatment response in ovarian cancer (OC). We developed OMICS-FUSE, an early-fusion multi-omics predictive model integrating proteomic, transcriptomic, and methylomic data from OC patients, evaluated across five machine learning algorithms with SHapley Additive exPlanations (SHAP) and experimental validation. The early-fusion Random Forest model achieved excellent predictive accuracy (AUC = 0.939, accuracy = 0.896, F1 = 0.939), with performance comparable to or surpassing that of the best-performing single-omics models. Nevertheless, the multi-omics framework yielded superior balance across accuracy and F1 score. SHAP analysis identified key determinants of treatment response, including CLEC2A, MYH4, and methylation of SYT12_1, with functional enrichment implicating immune regulation, metabolic pathways, and drug resistance signaling. Experimental validation confirmed six hub genes (CASP8, AQP8, CAV1, FN1, CREB1, KDR), exhibiting expression patterns associated with drug resistance, immune regulation, and prognosis. This multi-omics machine learning model enables robust, interpretable prediction, uncovering molecular signatures for therapeutic stratification and precision oncology in OC.
Background: Prostate cancer (PCa) is a leading cause of cancer-related mortality worldwide, highlighting the need for improved prognostic tools. The integration of artificial intelligence (AI) and machine learning (ML) with multi-omics data offers new opportunities for biomarker discovery and risk stratification. Methods: We integrated bulk transcriptomic data from GSE116918 (training, n = 248) and three cross-cohort consistency evaluation cohorts (TCGA-PRAD, GSE70769, GSE46602), focusing on 1087 epithelial–mesenchymal transition (EMT)-associated genes. Using consensus clustering, weighted gene co-expression network analysis (WGCNA), and 91 machine learning algorithm combinations (including Random Forest, Lasso, and CoxBoost), we constructed a prognostic signature. SHAP analysis was used for model interpretability. Single-cell RNA sequencing (scRNA-seq, GSE268307, 10,672 cells) and spatial transcriptomics (10× Genomics Visium FFPE) provided hypothesis-generating evidence; spatial analysis was based on one tissue section. Results: A three-gene signature (INHBA, FAP, ITGBL1) effectively stratified patients into high- and low-risk groups, with the high-risk group showing significantly worse metastasis-free survival (HR = 1.61, 95% CI: 1.39–1.87; 4-year AUC = 0.93 in the training cohort; external AUCs ranged from 0.62 to 0.77). CytoTRACE inferred high differentiation potential of COMP+ fibroblasts, and Monocle3 inferred a transcriptional transition from COMP+ toward NELL2+ fibroblasts. BayesPrism deconvolution suggested that high inferred COMP+ fibroblast abundance was associated with poor prognosis and advanced T stage. NicheNet analysis prioritized BMP7 as a key upstream ligand, with downstream targets enriched in TGF-β signaling and stem cell pluripotency pathways. Conclusions: This study presents a machine learning-based multi-omics framework for prostate cancer risk stratification. The three-gene signature provides a new exploratory prognostic model while inferring a COMP+ to NELL2+ transcriptional transition. These findings may inform future hypothesis-driven studies of treatment sensitivity, pending experimental validation, and demonstrate the value of AI-driven multi-omics integration for precision oncology.
Xueqian Zhang, Wei Zhang, Zheng Wang et al.· Genes· 0 citations
An interpretable three-stage machine learning framework integrating mRNA, microRNA, DNA methylation, copy number variation, and protein expression data from The Cancer Genome Atlas that couples improved prognostic estimation with biological interpretability supporting multi-omics biomarker discovery in ovarian cancer.
This study introduces a top-down framework for evaluating the utility of multi-omics features to predict the response of 309 drugs in cancer cell lines. This was done by taking a multi-omics approach where data from proteomic, transcriptomic, genomic, metabolomic, and miRNA were integrated with drug sensitivity (area under the curve, AUC) data. We performed modular dimensionality reduction using t-SNE (t-distributed Stochastic Neighbor Embedding), followed by K-Means clustering to stratify cell lines into data-driven molecular subgroups, and applied a Random Forest model to refine the drug list, selecting only those with a prediction accuracy exceeding 75%. Our findings show that among the evaluated single-omics features, transcriptomics is the most informative; however, multi-omics integration significantly enhances predictive capability compared to single-omics analysis, with a combination of transcriptomic, proteomic, and miRNA data achieving the best predictive performance across both primary and validation datasets. Cluster analysis showed the importance of well-defined clusters, indicating that while silhouette scores were linked to prediction success, biological variability also played a critical role. This study advances personalized oncology treatment strategies and provides a foundation for future studies focused on ranking omics features based on their predictive capabilities, eventually contributing to better therapeutic outcomes. Predictive performance is used here to evaluate omics feature strength, rather than as an objective to optimize predictive models.
Unknown authors· Current Issues in Molecular...· 0 citations
Pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) in breast cancer remains a clinically important endpoint, but accurate prediction before treatment is challenging. We developed an attention-based multi-omics framework that integrates pretreatment genomics, transcriptomics, proteomics, epigenomics, and clinical variables to predict pCR in early-stage breast cancer. The model was trained on the I-SPY2 neoadjuvant cohort and externally evaluated using The Cancer Genome Atlas Breast Cancer and independent NAC datasets. Performance was assessed using discrimination, calibration, and subtype-specific analyses, while explainability was examined using SHAP-based feature importance and pathway enrichment testing. In the I-SPY2 test set, the multi-omics model achieved an area under the receiver operating characteristic curve of 0.81 and outperformed clinical-only and single-omics baselines across subtypes. Improvements were most apparent in triple-negative and HER2-positive disease. The model showed acceptable calibration and maintained performance in external and transfer analyses, in which higher predicted risk scores were associated with poorer recurrence-related outcomes. Explainability analyses identified proliferation, immune activity, and PI3K/AKT signaling as major contributors to prediction. These findings indicate that integrating pretreatment multi-omics data with clinical variables improves prediction of NAC response while producing interpretable outputs. Further prospective validation is required before clinical application.
J. Fakoya, Catherine Falayi, M. Ajinaja· Cureus Journal of Computer S...· 0 citations
Uterine Corpus Endometrial Carcinoma (UCEC) is the most common gynecologic malignancy, with molecular heterogeneity influencing prognosis and treatment response. Although TCGA-defined molecular subtypes and multi-omics datasets have improved biological understanding of UCEC, externally evaluated computational frameworks for molecular stratification remain limited. To address this, we developed EMMA-STRAT, a supervised multi-omics machine learning framework integrating mRNA expression, miRNA expression, and DNA methylation data to classify UCEC genomic subtypes and microsatellite instability (MSI) status. Using the TCGA cohort (N = 433) for model development and internal validation, we benchmarked six classifiers and evaluated final model performance on two independent Clinical Proteomic Tumor Analysis Consortium (CPTAC) cohorts (N = 95 and N = 108). Multi-omics integration consistently outperformed single-omics models, with RNA expression as the strongest standalone modality. For MSI-H versus MSS classification, a LightGBM model trained on 20 SVM-selected features per omics layer achieved an internal balanced accuracy of 98.1% and external balanced accuracies of 93.1–94.9%. For four-class genomic subtyping, a Multi-Layer Perceptron trained on 50 LASSO-selected features per omics layer achieved an internal balanced accuracy of 89.1% and external balanced accuracies of 84.7–86.2%. Both models showed favorable discrimination and probability calibration relative to reference baselines, although calibration estimates for low-prevalence classes including POLE should be interpreted cautiously. SHapley Additive exPlanations (SHAP)-based interpretability analysis identified model-selected features including MLH1, CDKN2A, PPP4R4, and hsa-miR-378a, with downstream analyses supporting their biological plausibility. All results are openly accessible via an interactive browser at https://naisarg14.github.io/EMMA-STRAT-web-viewer/index.html. EMMA-STRAT provides an externally evaluated, research-grade computational framework for multi-omics molecular stratification of endometrial carcinoma. Integration of mRNA, miRNA, and DNA methylation data supported prediction of MSI-H versus MSS status and TCGA-defined genomic subtypes across independent cohorts. However, since EMMA-STRAT requires multi-omics data and was not directly compared with established clinical classifiers, it should currently be interpreted as a research-oriented molecular stratification framework rather than a clinically deployable decision-making model. The developed framework provides a basis for future prospective validation, incorporation of clinicopathological variables, and direct comparison with ProMisE-based or integrated clinical risk models.
Naisarg Patel, A. Salumets, V. Modhukur· BioData Mining· 1 citation
This study demonstrates that multi-omics integration via machine learning enhances survival prediction and reveals actionable biomarkers in breast cancer and outperformed mutation-based models.
G. Mestrallet, Alexandre Pierga, P. Frémont et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
