Dataset Information

EMT network-based feature selection improves prognosis prediction in lung adenocarcinoma.

ABSTRACT: Various feature selection algorithms have been proposed to identify cancer prognostic biomarkers. In recent years, however, their reproducibility is criticized. The performance of feature selection algorithms is shown to be affected by the datasets, underlying networks and evaluation metrics. One of the causes is the curse of dimensionality, which makes it hard to select the features that generalize well on independent data. Even the integration of biological networks does not mitigate this issue because the networks are large and many of their components are not relevant for the phenotype of interest. With the availability of multi-omics data, integrative approaches are being developed to build more robust predictive models. In this scenario, the higher data dimensions create greater challenges. We proposed a phenotype relevant network-based feature selection (PRNFS) framework and demonstrated its advantages in lung cancer prognosis prediction. We constructed cancer prognosis relevant networks based on epithelial mesenchymal transition (EMT) and integrated them with different types of omics data for feature selection. With less than 2.5% of the total dimensionality, we obtained EMT prognostic signatures that achieved remarkable prediction performance (average AUC values >0.8), very significant sample stratifications, and meaningful biological interpretations. In addition to finding EMT signatures from different omics data levels, we combined these single-omics signatures into multi-omics signatures, which improved sample stratifications significantly. Both single- and multi-omics EMT signatures were tested on independent multi-omics lung cancer datasets and significant sample stratifications were obtained.

SUBMITTER: Shao B

PROVIDER: S-EPMC6354965 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Glutamine (Gln) metabolism has been reported to play an essential role in cancer. However, a comprehensive analysis of its role in lung adenocarcinoma is still unavailable. This study established a novel system of quantification of Gln metabolism to predict the prognosis and immunotherapy efficacy in lung cancer. Further, the Gln metabolism in tumor microenvironment (TME) was characterized and the Gln metabolism-related genes were identified for targeted therapy. We comprehensively evaluated the patterns of Gln metabolism in 513 patients diagnosed with lung adenocarcinoma (LUAD) based on 73 Gln metabolism-related genes. Based on differentially expressed genes (DEGs), a risk model was constructed using Cox regression and Lasso regression analysis. The prognostic efficacy of the model was validated using an individual LUAD cohort form Shandong Provincial Hospital, an integrated LUAD cohort from GEO and pan-cancer cohorts from TCGA databases. Five independent immunotherapy cohorts were used to validate the model performance in predicting immunotherapy efficacy. Next, a series of single-cell sequencing analyses were used to characterize Gln metabolism in TME. Finally, single-cell sequencing analysis, transcriptome sequencing, and a series of in vitro experiments were used to explore the role of EPHB2 in LUAD. Patients with LUAD were eventually divided into low- and high-risk groups. Patients in low-risk group were characterized by low levels of Gln metabolism, survival advantage, “hot” immune phenotype and benefit from immunotherapy. Compared with other cells, tumor cells in TME exhibited the most active Gln metabolism. Among immune cells, tumor-infiltrating T cells exhibited the most active levels of Gln metabolism, especially CD8 T cell exhaustion and Treg suppression. EPHB2, a key gene in the model, was shown to promote LUAD cell proliferation, invasion and migration, and regulated the Gln metabolic pathway. Finally, we found that EPHB2 was highly expressed in macrophages, especially M2 macrophages. It may be involved in the M2 polarization of macrophages and mediate the negative regulation of M2 macrophages in NK cells. This study revealed that the Gln metabolism-based model played a significant role in predicting prognosis and immunotherapy efficacy in lung cancer. We further characterized the Gln metabolism of TME and investigated the Gln metabolism-related gene EPHB2 to provide a theoretical framework for anti-tumor strategy targeting Gln metabolism.

Project description:BackgroundAfter curative surgical resection, about 30-75% lung adenocarcinoma (LUAD) patients suffer from recurrence with dismal survival outcomes. Identification of patients with high risk of recurrence to impose intense therapy is urgently needed.Materials and methodsGene expression data of LUAD were obtained from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) databases. Differentially expressed genes (DEGs) were calculated by comparing the recurrent and primary tissues. Prognostic genes associated with the recurrence-free survival (RFS) of LUAD patients were identified using univariate analysis. LASSO Cox regression and multivariate Cox analysis were applied to extract key genes and establish the prediction model.ResultsWe detected 37 DEGs between primary and recurrent LUAD tumors. Using univariate analysis, 31 DEGs were found to be significantly associated with RFS. We established the RFS prediction model including thirteen genes using the LASSO Cox regression. In the training cohort, we classified patients into high- and low-risk groups and found that patients in the high-risk group suffered from worse RFS compared to those in the low-risk group (P < 0.01). Concordant results were confirmed in the internal and external validation cohort. The efficiency of the prediction model was also confirmed under different clinical subgroups. The high-risk group was significantly identified as the risk factor of recurrence in LUAD by the multivariate Cox analysis (HR = 13.37, P = 0.01). Compared to clinicopathological features, our prediction model possessed higher accuracy to identify patients with high risk of recurrence (AUC = 96.3%). Finally, we found that the G2M checkpoint pathway was enriched both in recurrent tumors and primary tumors of high-risk patients.ConclusionsOur recurrence-specific gene-based prognostic prediction model provides extra information about the risk of recurrence in LUAD, which is conducive for clinicians to conduct individualized therapy in clinic.

Dataset Information

EMT network-based feature selection improves prognosis prediction in lung adenocarcinoma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets