Dataset Information

Identification of a Sixteen-gene Prognostic Biomarker for Lung Adenocarcinoma Using a Machine Learning Method.

ABSTRACT: Objectives: Lung adenocarcinoma (LUAD) accounts for a majority of cancer-related deaths worldwide annually. The identification of prognostic biomarkers and prediction of prognosis for LUAD patients is necessary. Materials and Methods: In this study, LUAD RNA-Seq data and clinical data from the Cancer Genome Atlas (TCGA) were divided into TCGA cohort I (n = 338) and II (n = 168). The cohort I was used for model construction, and the cohort II and data from Gene Expression Omnibus (GSE72094 cohort, n = 393; GSE11969 cohort, n = 149) were utilized for validation. First, the survival-related seed genes were selected from the cohort I using the machine learning model (random survival forest, RSF), and then in order to improve prediction accuracy, the forward selection model was utilized to identify the prognosis-related key genes among the seed genes using the clinically-integrated RNA-Seq data. Second, the survival risk score system was constructed by using these key genes in the cohort II, the GSE72094 cohort and the GSE11969 cohort, and the evaluation metrics such as HR, p value and C-index were calculated to validate the proposed method. Third, the developed approach was compared with the previous five prediction models. Finally, bioinformatics analyses (pathway, heatmap, protein-gene interaction network) have been applied to the identified seed genes and key genes. Results and Conclusion: Based on the RSF model and clinically-integrated RNA-Seq data, we identified sixteen key genes that formed the prognostic gene expression signature. These sixteen key genes could achieve a strong power for prognostic prediction of LUAD patients in cohort II (HR = 3.80, p = 1.63e-06, C-index = 0.656), and were further validated in the GSE72094 cohort (HR = 4.12, p = 1.34e-10, C-index = 0.672) and GSE11969 cohort (HR = 3.87, p = 6.81e-07, C-index = 0.670). The experimental results of three independent validation cohorts showed that compared with the traditional Cox model and the use of standalone RNA-Seq data, the machine-learning-based method effectively improved the prediction accuracy of LUAD prognosis, and the derived model was also superior to the other five existing prediction models. KEGG pathway analysis found eleven of the sixteen genes were associated with Nicotine addiction. Thirteen of the sixteen genes were reported for the first time as the LUAD prognosis-related key genes. In conclusion, we developed a sixteen-gene prognostic marker for LUAD, which may provide a powerful prognostic tool for precision oncology.

SUBMITTER: Ma B

PROVIDER: S-EPMC6959071 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Identification of a Sixteen-gene Prognostic Biomarker for Lung Adenocarcinoma Using a Machine Learning Method.

Ma Baoshan B Geng Yao Y Meng Fanyu F Yan Ge G Song Fengju F

Journal of Cancer 20200101 5

<b>Objectives</b>: Lung adenocarcinoma (LUAD) accounts for a majority of cancer-related deaths worldwide annually. The identification of prognostic biomarkers and prediction of prognosis for LUAD patients is necessary. <b>Materials and Methods</b>: In this study, LUAD RNA-Seq data and clinical data from the Cancer Genome Atlas (TCGA) were divided into TCGA cohort I (n = 338) and II (n = 168). The cohort I was used for model construction, and the cohort II and data from Gene Expression Omnibus (G ...[more]

PMID: 31956375

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.

Project description:Disulfidptosis represents a novel cell death mechanism triggered by disulfide stress, with potential implications for advancements in cancer treatments. Although emerging evidence highlights the critical regulatory roles of long non-coding RNAs (lncRNAs) in the pathobiology of lung adenocarcinoma (LUAD), research into lncRNAs specifically associated with disulfidptosis in LUAD, termed disulfidptosis-related lncRNAs (DRLs), remains insufficiently explored. Using The Cancer Genome Atlas (TCGA)-LUAD dataset, we implemented ten machine learning techniques, resulting in 101 distinct model configurations. To assess the predictive accuracy of our model, we employed both the concordance index (C-index) and receiver operating characteristic (ROC) curve analyses. For a deeper understanding of the underlying biological pathways, we referred to the Kyoto Encyclopedia of Genes and Genomes (KEGG) and Gene Ontology (GO) for functional enrichment analysis. Moreover, we explored differences in the tumor microenvironment between high-risk and low-risk patient cohorts. Additionally, we thoroughly assessed the prognostic value of the DRLs signatures in predicting treatment outcomes. The Kaplan-Meier (KM) survival analysis demonstrated a significant difference in overall survival (OS) between the high-risk and low-risk cohorts (p < 0.001). The prognostic model showed robust performance, with an area under the ROC curve exceeding 0.75 at one year and maintaining a value above 0.72 in the two and three-year follow-ups. Further research identified variations in tumor mutational burden (TMB) and differential responses to immunotherapies and chemotherapies. Our validation, using three GEO datasets (GSE31210, GSE30219, and GSE50081), revealed that the C-index exceeded 0.67 for GSE31210 and GSE30219. Significant differences in disease-free survival (DFS) and OS were observed across all validation cohorts among different risk groups. The prognostic model offers potential as a molecular biomarker for LUAD prognosis.

Project description:BackgroundAlternative 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.MethodRNA 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).ResultsEach 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.ConclusionIn summary, our study provides insight into LUAD researches and managements based on these AS biomarkers.

Project description:Accurate prognostic prediction is crucial for treatment decision-making in lung papillary adenocarcinoma (LPADC). The aim of this study was to predict cancer-specific survival in LPADC using ensemble machine learning and classical Cox regression models. Moreover, models were evaluated to provide recommendations based on quantitative data for personalized treatment of LPADC. Data of patients diagnosed with LPADC (2004-2018) were extracted from the Surveillance, Epidemiology, and End Results database. The set of samples was randomly divided into the training and validation sets at a ratio of 7:3. Three ensemble models were selected, namely gradient boosting survival (GBS), random survival forest (RSF), and extra survival trees (EST). In addition, Cox proportional hazards (CoxPH) regression was used to construct the prognostic models. The Harrell's concordance index (C-index), integrated Brier score (IBS), and area under the time-dependent receiver operating characteristic curve (time-dependent AUC) were used to evaluate the performance of the predictive models. A user-friendly web access panel was provided to easily evaluate the model for the prediction of survival and treatment recommendations. A total of 3615 patients were randomly divided into the training and validation cohorts (n = 2530 and 1085, respectively). The extra survival trees, RSF, GBS, and CoxPH models showed good discriminative ability and calibration in both the training and validation cohorts (mean of time-dependent AUC: > 0.84 and > 0.82; C-index: > 0.79 and > 0.77; IBS: < 0.16 and < 0.17, respectively). The RSF and GBS models were more consistent than the CoxPH model in predicting long-term survival. We implemented the developed models as web applications for deployment into clinical practice (accessible through https://shinyshine-820-lpaprediction-model-z3ubbu.streamlit.app/ ). All four prognostic models showed good discriminative ability and calibration. The RSF and GBS models exhibited the highest effectiveness among all models in predicting the long-term cancer-specific survival of patients with LPADC. This approach may facilitate the development of personalized treatment plans and prediction of prognosis for LPADC.

Project description:BackgroundLung cancer is the leading cause of cancer-related death, and adenocarcinoma is the most common type of lung cancer. Although emerging evidence implicates the role of several aldehyde dehydrogenases in cancer progression, the expression and clinical significance of aldehyde dehydrogenase 3B1 in lung adenocarcinoma has never been studied.MaterialsIn our study, the expression of aldehyde dehydrogenase 3B1 in 250 cases of lung adenocarcinoma was detected with immunohistochemistry, and the patients were further divided into subgroups with different aldehyde dehydrogenase 3B1 expression. Using real-time polymerase chain reaction, we investigated the aldehyde dehydrogenase 3B1 messenger RNA in 20 lung adenocarcinoma and paired normal lung tissues. With the χ2 test, we evaluated the clinical significance of aldehyde dehydrogenase 3B1 by analyzing its correlation with the clinicopathological factors. Propensity score matching was performed to balance the baseline of cohort. With univariate and multivariate analyses, we screened the prognostic factors of lung adenocarcinoma and identified the independent prognostic factors before and after the propensity score matching.ResultsAldehyde dehydrogenase 3B1 expression was significantly associated with the sex and age of patients, tumor size, and histological grade. High expression of aldehyde dehydrogenase 3B1 predicted the poor prognosis (P = .003). Moreover, male patients (P = .020), large tumor size (P = .009), advanced T stage (P = .001), positive lymphatic invasion (P < .001), and advanced tumor-node-metastasis stage (P < .001) were all the prognostic factors for unfavorable outcome. Aldehyde dehydrogenase 3B1 was an independent prognostic biomarker of lung adenocarcinoma, indicating the poor prognosis. In addition, after balancing the baseline characteristics by propensity score matching, we also demonstrated that aldehyde dehydrogenase 3B1 was an independent prognostic biomarker of lung adenocarcinoma (P = .007).ConclusionsAldehyde dehydrogenase 3B1 was an independent prognostic biomarker of lung adenocarcinoma, indicating the unfavorable prognosis. Postoperative detection of aldehyde dehydrogenase 3B1 would help stratify the high-risk patients with lung adenocarcinoma and guide individual treatment.

Dataset Information

Identification of a Sixteen-gene Prognostic Biomarker for Lung Adenocarcinoma Using a Machine Learning Method.

Publications

Identification of a Sixteen-gene Prognostic Biomarker for Lung Adenocarcinoma Using a Machine Learning Method.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets