ABSTRACT
Background: The tumor microenvironment (TME) affected the prognosis of tumors. However, its effect on the outcomes of obese endometrial cancer (EC) patients had not been reported. Methods: This research performed a retrospective analysis of the transcriptome profiles and medical data of 503 EC patients. Immune scores were assessed by estimation algorithms. Cox and LASSO regression analyses were utilized to pinpoint key genes linked to prognosis, and the RPS was created to forecast the outcomes of obese EC patients. The relationship among genetic mutations and RPS was examined using CNV and somatic mutation information. ssGSEA and GSVA were employed to detect immune infiltration and immune pathway enrichment associated with key genes. The TIDE algorithm and GDSC database were utilized to forecast patients' responses of patients to immunotherapy and chemotherapy, respectively. Finally, we employed the 'rms' R software package to construct the nomogram. Results: The prognosis of obese EC patients was associated with immune scores. Three key genes (EYA4, MBOAT2 and SCGB2A1) were identified. The risk prognosis score (RPS) for obese EC patients was established by risk stratification and prognostic prediction using prognostic genes. The higher the RPS, the worse the prognosis, and the more malignant the genomic alterations. The high RPS group had a significantly reduced proportion of most immune cells in comparison to the low RPS group. The high RPS group was linked to G2M, MYC and E2F related pathways such as cell proliferation, cell cycle and cell death. Cisplatin, tamoxifen and topotecan had a greater effect on the low RPS group. Notably, the nomogram had a good predictive ability. Conclusion: Our study designed a reliable RPS for obese EC patients to forecast their prognosis, immune aggressiveness, and responses to immunotherapy and drug treatments.
ABSTRACT
Combination therapy is a promising strategy for cancers, increasing therapeutic options and reducing drug resistance. Yet, systematic identification of efficacious drug combinations is limited by the combinatorial explosion caused by a large number of possible drug pairs and diseases. At present, machine learning techniques have been widely applied to predict drug combinations, but most studies rely on the response of drug combinations to specific cell lines and are not entirely satisfactory in terms of mechanism interpretability and model scalability. Here, we proposed a novel network propagation-based machine learning framework to predict synergistic drug combinations. Based on the topological information of a comprehensive drug-drug association network, we innovatively introduced an affinity score between drug pairs as one of the features to train machine learning models. We applied network-based strategy to evaluate their therapeutic potential to different cancer types. Finally, we identified 17 specific-, 21 general- and 40 broad-spectrum antitumor drug combinations, in which 69% drug combinations were validated by vitro cellular experiments, 83% drug combinations were validated by literature reports and 100% drug combinations were validated by biological function analyses. By quantifying the network relationships between drug targets and cancer-related driver genes in the human protein-protein interactome, we show the existence of four distinct patterns of drug-drug-disease relationships. We also revealed that 32 biological pathways were correlated with the synergistic mechanism of broad-spectrum antitumor drug combinations. Overall, our model offers a powerful scalable screening framework for cancer treatments.