Developing prognostic gene panel of survival time in lung adenocarcinoma patients using machine learning
Ontology highlight
ABSTRACT: Background
Transcriptome data generates massive amounts of information that can be used for characterization and prognosis of patient outcomes for many diseases. The goal of our research is to predict the survival time of lung adenocarcinoma patients and improve the accuracy of classifying the long-survival cohort and short-survival cohort. Methods
We filtered prognostic features related with survival time of lung adenocarcinoma patients by the method of Relief and predicted whether survival time of the patient is >3 years or not—using eight machine learning algorithms (Support Vector Machines, Random Forests, Logistic Regression, Naïve Bayes, Linear Regression, Support Vector Regression (kernel Poly), Support Vector Regression (kernel Linear), and Ridge Regression). Then the best-performed algorithm was chosen to build a predictive model of survival time of lung adenocarcinoma patients. Further, another dataset was used to verify the stability and suitability of this model. We explored the underlying mechanisms of RNA expression changes with the corresponding DNA mutations and DNA methylation patterns in the 22 selected genetic features. Results
The best machine learning algorithm was Naïve Bayes (accuracy=75%, AUC =0.81) using the top 22 genetic features, and this algorithm had the stable and great performance on another dataset as well. The coupled mutation number of the long-survival group (>6 years) was less than the short-survival group (<1 year) in 22 genes (P=0.031). Conclusions
The expression of gene panel can predict the survival time of lung adenocarcinoma patients using Naïve Bayes. These 22 genes do affect the survival time of lung adenocarcinoma.
SUBMITTER: Liu Y
PROVIDER: S-EPMC8799101 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
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.
| S-EPMC7720605 | biostudies-literature
Project description: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.
| S-EPMC6959071 | biostudies-literature
Project description:Epithelial ovarian cancer patients usually relapse after primary management. We utilized the support vector machine algorithm to develop a model for the chemo-response using the Cancer Cell Line Encyclopedia (CCLE) and validated the model in The Cancer Genome Atlas (TCGA) and the GSE9891 dataset. Finally, we evaluated the feasibility of the model using ovarian cancer patients from our institute. The 10-gene predictive model demonstrated that the high response group had a longer recurrence-free survival (RFS) (log-rank test, p = 0.015 for TCGA, p = 0.013 for GSE9891 and p = 0.039 for NTUH) and overall survival (OS) (log-rank test, p = 0.002 for TCGA and p = 0.016 for NTUH). In a multivariate Cox hazard regression model, the predictive model (HR: 0.644, 95% CI: 0.436⁻0.952, p = 0.027) and residual tumor size < 1 cm (HR: 0.312, 95% CI: 0.170⁻0.573, p < 0.001) were significant factors for recurrence. The predictive model (HR: 0.511, 95% CI: 0.334⁻0.783, p = 0.002) and residual tumor size < 1 cm (HR: 0.252, 95% CI: 0.128⁻0.496, p < 0.001) were still significant factors for death. In conclusion, the patients of high response group stratified by the model had good response and favourable prognosis, whereas for the patients of medium to low response groups, introduction of other drugs or clinical trials might be beneficial.
| S-EPMC6406249 | biostudies-literature
Project description:Lung cancer is the second most common cancer in the United States and the leading cause of mortality in cancer patients. Biomarkers predicting survival of patients with lung cancer have a profound effect on patient prognosis and treatment. However, predictive biomarkers for survival and their relevance for lung cancer are not been well known yet. The objective of this study was to perform machine learning with data from The Cancer Genome Atlas of patients with lung adenocarcinoma (LUAD) to find survival-specific gene mutations that could be used as survival-predicting biomarkers. To identify survival-specific mutations according to various clinical factors, four feature selection methods (information gain, chi-squared test, minimum redundancy maximum relevance, and correlation) were used. Extracted survival-specific mutations of LUAD were applied individually or as a group for Kaplan-Meier survival analysis. Mutations in MMRN2 and GMPPA were significantly associated with patient mortality while those in ZNF560 and SETX were associated with patient survival. Mutations in DNAJC2 and MMRN2 showed significant negative association with overall survival while mutations in ZNF560 showed significant positive association with overall survival. Mutations in MMRN2 showed significant negative association with disease-free survival while mutations in DRD3 and ZNF560 showed positive associated with disease-free survival. Mutations in DRD3, SETX, and ZNF560 showed significant positive association with survival in patients with LUAD while the opposite was true for mutations in DNAJC2, GMPPA, and MMRN2. These gene mutations were also found in other cohorts of LUAD, lung squamous cell carcinoma, and small cell lung cancer. In LUAD of Pan-Lung Cancer cohort, mutations in GMPPA, DNAJC2, and MMRN2 showed significant negative associations with survival of patients while mutations in DRD3 and SETX showed significant positive association with survival. In this study, machine learning was conducted to obtain information necessary to discover specific gene mutations associated with the survival of patients with LUAD. Mutations in the above six genes could predict survival rate and disease-free survival rate in patients with LUAD. Thus, they are important biomarker candidates for prognosis.
| S-EPMC6231670 | biostudies-literature
Project description:This paper identifies prognosis factors for survival in patients with acute myeloid leukemia (AML) using machine learning techniques. We have integrated machine learning with feature selection methods and have compared their performances to identify the most suitable factors in assessing the survival of AML patients. Here, six data mining algorithms including Decision Tree, Random Forrest, Logistic Regression, Naive Bayes, W-Bayes Net, and Gradient Boosted Tree (GBT) are employed for the detection model and implemented using the common data mining tool RapidMiner and open-source R package. To improve the predictive ability of our model, a set of features were selected by employing multiple feature selection methods. The accuracy of classification was obtained using 10-fold cross-validation for the various combinations of the feature selection methods and machine learning algorithms. The performance of the models was assessed by various measurement indexes including accuracy, kappa, sensitivity, specificity, positive predictive value, negative predictive value, and area under the ROC curve (AUC). Our results showed that GBT with an accuracy of 85.17%, AUC of 0.930, and the feature selection via the Relief algorithm has the best performance in predicting the survival rate of AML patients.
| S-EPMC8294525 | biostudies-literature
Project description:Applying the knowledge that methyltransferases and demethylases can modify adjacent cytosine-phosphorothioate-guanine (CpG) sites in the same DNA strand, we found that combining multiple CpGs into a single block may improve cancer diagnosis. However, survival prediction remains a challenge. In this study, we developed a pipeline named "stacked ensemble of machine learning models for methylation-correlated blocks" (EnMCB) that combined Cox regression, support vector regression (SVR), and elastic-net models to construct signatures based on DNA methylation-correlated blocks for lung adenocarcinoma (LUAD) survival prediction. We used methylation profiles from the Cancer Genome Atlas (TCGA) as the training set, and profiles from the Gene Expression Omnibus (GEO) as validation and testing sets. First, we partitioned the genome into blocks of tightly co-methylated CpG sites, which we termed methylation-correlated blocks (MCBs). After partitioning and feature selection, we observed different diagnostic capacities for predicting patient survival across the models. We combined the multiple models into a single stacking ensemble model. The stacking ensemble model based on the top-ranked block had the area under the receiver operating characteristic curve of 0.622 in the TCGA training set, 0.773 in the validation set, and 0.698 in the testing set. When stratified by clinicopathological risk factors, the risk score predicted by the top-ranked MCB was an independent prognostic factor. Our results showed that our pipeline was a reliable tool that may facilitate MCB selection and survival prediction.
| S-EPMC7894106 | biostudies-literature
Project description:BACKGROUND:Prognostication is an essential tool for risk adjustment and decision making in the intensive care unit (ICU). Research into prognostication in ICU has so far been limited to data from admission or the first 24 hours. Most ICU admissions last longer than this, decisions are made throughout an admission, and some admissions are explicitly intended as time-limited prognostic trials. Despite this, temporal changes in prognostic ability during ICU admission has received little attention to date. Current predictive models, in the form of prognostic clinical tools, are typically derived from linear models and do not explicitly handle incremental information from trends. Machine learning (ML) allows predictive models to be developed which use non-linear predictors and complex interactions between variables, thus allowing incorporation of trends in measured variables over time; this has made it possible to investigate prognosis throughout an admission. METHODS AND FINDINGS:This study uses ML to assess the predictability of ICU mortality as a function of time. Logistic regression against physiological data alone outperformed APACHE-II and demonstrated several important interactions including between lactate & noradrenaline dose, between lactate & MAP, and between age & MAP consistent with the current sepsis definitions. ML models consistently outperformed logistic regression with Deep Learning giving the best results. Predictive power was maximal on the second day and was further improved by incorporating trend data. Using a limited range of physiological and demographic variables, the best machine learning model on the first day showed an area under the receiver-operator characteristic curve (AUC) of 0.883 (σ = 0.008), compared to 0.846 (σ = 0.010) for a logistic regression from the same predictors and 0.836 (σ = 0.007) for a logistic regression based on the APACHE-II score. Adding information gathered on the second day of admission improved the maximum AUC to 0.895 (σ = 0.008). Beyond the second day, predictive ability declined. CONCLUSION:This has implications for decision making in intensive care and provides a justification for time-limited trials of ICU therapy; the assessment of prognosis over more than one day may be a valuable strategy as new information on the second day helps to differentiate outcomes. New ML models based on trend data beyond the first day could greatly improve upon current risk stratification tools.
| S-EPMC6241126 | biostudies-other
Project description:Background: Although immunotherapy with checkpoint inhibitors is changing the face of lung adenocarcinoma (LUAD) treatments, only limited patients could benefit from it. Therefore, we aimed to develop an immune-relevant-gene-based signature to predict LUAD patients' prognosis and to characterize their tumor microenvironment thus guiding therapeutic strategy. Methods and Materials: Gene expression data of LUAD patients from Gene Expression Omnibus (GEO) and The Cancer Genome Atlas (TCGA) were systematically analyzed. We performed Cox regression and random survival forest algorithm to identify immune-relevant genes with potential prognostic value. A risk score formula was then established by integrating these selected genes and patients were classified into high- and low-risk score group. Differentially expressed genes, infiltration level of immune cells, and several immune-associated molecules were further compared across the two groups. Results: Nine hundred and fifty-four LUAD patients were enrolled in this study. After implementing the 2-steps machine learning screening methods, 12 immune-relevant genes were finally selected into the risk-score formula and the patients in high-risk group had significantly worse overall survival (HR = 10.6, 95%CI = 3.21-34.95, P < 0.001). We also found the distinct immune infiltration patterns in the two groups that several immune cells like cytotoxic cells and immune checkpoint molecules were significantly enriched and upregulated in patients from the high-risk group. These findings were further validated in two independent LUAD cohorts. Conclusion: Our risk score formula could serve as a powerful and accurate tool for predicting survival of LUAD patients and may facilitate clinicians to choose the optimal therapeutic regimen more precisely.
| S-EPMC7267039 | biostudies-literature
Project description:BackgroundLung adenocarcinoma (LUAD) stands as the most prevalent histological subtype of lung cancer, exhibiting heterogeneity in outcomes and diverse responses to therapy. CD8 T cells are consistently present throughout all stages of tumor development and play a pivotal role within the tumor microenvironment (TME). Our objective was to investigate the expression profiles of CD8 T cell marker genes, establish a prognostic risk model based on these genes in LUAD, and explore its relationship with immunotherapy response.MethodsBy leveraging the expression data and clinical records from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) cohorts, we identified 23 consensus prognostic genes. Employing ten machine-learning algorithms, we generated 101 combinations, ultimately selecting the optimal algorithm to construct an artificial intelligence-derived prognostic signature named riskScore. This selection was based on the average concordance index (C-index) across three testing cohorts.ResultsRiskScore emerged as an independent risk factor for overall survival (OS), progression-free interval (PFI), disease-free interval (DFI), and disease-specific survival (DSS) in LUAD. Notably, riskScore exhibited notably superior predictive accuracy compared to traditional clinical variables. Furthermore, we observed a positive correlation between the high-risk riskScore group and tumor-promoting biological functions, lower tumor mutational burden (TMB), lower neoantigen (NEO) load, and lower microsatellite instability (MSI) scores, as well as reduced immune cell infiltration and an increased probability of immune evasion within the TME. Of significance, the immunophenoscore (IPS) score displayed significant differences among risk subgroups, and riskScore effectively stratified patients in the IMvigor210 and GSE135222 immunotherapy cohort based on their survival outcomes. Additionally, we identified potential drugs that could target specific risk subgroups.ConclusionsIn summary, riskScore demonstrates its potential as a robust and promising tool for guiding clinical management and tailoring individualized treatments for LUAD patients.
| S-EPMC11319961 | biostudies-literature
Project description:BackgroundLung cancer is the most frequently diagnosed carcinoma and the leading cause of cancer-related mortality. Although molecular targeted therapy and immunotherapy have made great progress, the overall survival (OS) is still poor due to a lack of accurate and available prognostic biomarkers. Therefore, in this study we aimed to establish a multiple-gene panel predicting OS for lung adenocarcinoma.MethodsWe obtained the mRNA expression and clinical data of lung adenocarcinoma (LUAD) from TCGA database for further integrated bioinformatic analysis. Lasso regression and Cox regression were performed to establish a prognosis model based on a multi-gene panel. A nomogram based on this model was constructed. The receiver operating characteristic (ROC) curve and the Kaplan-Meier curve were used to assess the predicted capacity of the model. The prognosis value of the multi-gene panel was further validated in TCGA-LUAD patients with EGFR, KRAS and TP53 mutation and a dataset from GEO. Gene set enrichment analysis (GSEA) was performed to explore potential biological mechanisms of a novel prognostic gene signature.ResultsA four-gene panel (including DKK1, GNG7, LDHA, MELTF) was established for LUAD prognostic indicator. The ROC curve revealed good predicted performance in both test cohort (AUC = 0.740) and validation cohort (AUC = 0.752). Each patient was calculated a risk score according to the model based on the four-gene panel. The results showed that the risk score was an independent prognostic factor, and the high-risk group had a worse OS compared with the low-risk group. The nomogram based on this model showed good prediction performance. The four-gene panel was still good predictors for OS in LUAD patients with TP53 and KRAS mutations. GSEA revealed that the four genes may be significantly related to the metabolism of genetic material, especially the regulation of cell cycle pathway.ConclusionOur study proposed a novel four-gene panel to predict the OS of LUAD, which may contribute to predicting prognosis accurately and making the clinical decisions of individual therapy for LUAD patients.
| S-EPMC7720456 | biostudies-literature