Dataset Information

Exploration of predictive and prognostic alternative splicing signatures in lung adenocarcinoma using machine learning methods.

ABSTRACT:

Background

Alternative splicing (AS) plays critical roles in generating protein diversity and complexity. Dysregulation of AS underlies the initiation and progression of tumors. Machine learning approaches have emerged as efficient tools to identify promising biomarkers. It is meaningful to explore pivotal AS events (ASEs) to deepen understanding and improve prognostic assessments of lung adenocarcinoma (LUAD) via machine learning algorithms.

Method

RNA sequencing data and AS data were extracted from The Cancer Genome Atlas (TCGA) database and TCGA SpliceSeq database. Using several machine learning methods, we identified 24 pairs of LUAD-related ASEs implicated in splicing switches and a random forest-based classifiers for identifying lymph node metastasis (LNM) consisting of 12 ASEs. Furthermore, we identified key prognosis-related ASEs and established a 16-ASE-based prognostic model to predict overall survival for LUAD patients using Cox regression model, random survival forest analysis, and forward selection model. Bioinformatics analyses were also applied to identify underlying mechanisms and associated upstream splicing factors (SFs).

Results

Each pair of ASEs was spliced from the same parent gene, and exhibited perfect inverse intrapair correlation (correlation coefficient?=?-?1). The 12-ASE-based classifier showed robust ability to evaluate LNM status of LUAD patients with the area under the receiver operating characteristic (ROC) curve (AUC) more than 0.7 in fivefold cross-validation. The prognostic model performed well at 1, 3, 5, and 10 years in both the training cohort and internal test cohort. Univariate and multivariate Cox regression indicated the prognostic model could be used as an independent prognostic factor for patients with LUAD. Further analysis revealed correlations between the prognostic model and American Joint Committee on Cancer stage, T stage, N stage, and living status. The splicing network constructed of survival-related SFs and ASEs depicts regulatory relationships between them.

Conclusion

In summary, our study provides insight into LUAD researches and managements based on these AS biomarkers.

SUBMITTER: Cai Q

PROVIDER: S-EPMC7720605 | biostudies-literature | 2020 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Exploration of predictive and prognostic alternative splicing signatures in lung adenocarcinoma using machine learning methods.

Cai Qidong Q He Boxue B Zhang Pengfei P Zhao Zhenyu Z Peng Xiong X Zhang Yuqian Y Xie Hui H Wang Xiang X

Journal of translational medicine 20201207 1

<h4>Background</h4>Alternative splicing (AS) plays critical roles in generating protein diversity and complexity. Dysregulation of AS underlies the initiation and progression of tumors. Machine learning approaches have emerged as efficient tools to identify promising biomarkers. It is meaningful to explore pivotal AS events (ASEs) to deepen understanding and improve prognostic assessments of lung adenocarcinoma (LUAD) via machine learning algorithms.<h4>Method</h4>RNA sequencing data and AS data ...[more]

PMID: 33287830

Similar Datasets

Project description:BackgroundDisulfidptosis is a newly identified variant of cell death characterized by disulfide accumulation, which is independent of ATP depletion. Accordingly, the latent influence of disulfidptosis on the prognosis of lung adenocarcinoma (LUAD) patients and the progression of tumors remains poorly understood.MethodsWe conducted a multifaceted analysis of the transcriptional and genetic modifications in disulfidptosis regulators (DRs) specific to LUAD, followed by an evaluation of their expression configurations to define DR clusters. Harnessing the differentially expressed genes (DEGs) identified from these clusters, we formulated an optimal predictive model by amalgamating 10 distinct machine learning algorithms across 101 unique combinations to compute the disulfidptosis score (DS). Patients were subsequently stratified into high and low DS cohorts based on median DS values. We then performed an exhaustive comparison between these cohorts, focusing on somatic mutations, clinical attributes, tumor microenvironment, and treatment responsiveness. Finally, we empirically validated the biological implications of a critical gene, KYNU, through assays in LUAD cell lines.ResultsWe identified two DR clusters and there were great differences in overall survival (OS) and tumor microenvironment. We selected the "Least Absolute Shrinkage and Selection Operator (LASSO) + Random Survival Forest (RFS)" algorithm to develop a DS based on the average C-index across different cohorts. Our model effectively stratified LUAD patients into high- and low-DS subgroups, with this latter demonstrating superior OS, a reduced mutational landscape, enhanced immune status, and increased sensitivity to immunotherapy. Notably, the predictive accuracy of DS outperformed the published LUAD signature and clinical features. Finally, we validated the DS expression using clinical samples and found that inhibiting KYNU suppressed LUAD cells proliferation, invasiveness, and migration in vitro.ConclusionsThe DR-based scoring system that we developed enabled accurate prognostic stratification of LUAD patients and provides important insights into the molecular mechanisms and treatment strategies for LUAD.

Dataset Information

Exploration of predictive and prognostic alternative splicing signatures in lung adenocarcinoma using machine learning methods.

Background

Method

Results

Conclusion

Publications

Exploration of predictive and prognostic alternative splicing signatures in lung adenocarcinoma using machine learning methods.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets