Dataset Information

Developing a Prognostic Gene Panel of Epithelial Ovarian Cancer Patients by a Machine Learning Model.

ABSTRACT: 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.

SUBMITTER: Lu TP

PROVIDER: S-EPMC6406249 | biostudies-literature | 2019 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Developing a Prognostic Gene Panel of Epithelial Ovarian Cancer Patients by a Machine Learning Model.

Lu Tzu-Pin TP Kuo Kuan-Ting KT Chen Ching-Hsuan CH Chang Ming-Cheng MC Lin Hsiu-Ping HP Hu Yu-Hao YH Chiang Ying-Cheng YC Cheng Wen-Fang WF Chen Chi-An CA

Cancers 20190225 2

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 s ...[more]

PMID: 30823599

Similar Datasets

Project description:IntroductionIntegrating additional factors into the International Federation of Gynecology and Obstetrics (FIGO) staging system is needed for accurate patient classification and survival prediction. In this study, we tested machine learning as a novel tool for incorporating additional prognostic parameters into the conventional FIGO staging system for stratifying patients with epithelial ovarian carcinomas and evaluating their survival.Material and methodsCancer-specific survival data for epithelial ovarian carcinomas were extracted from the Surveillance, Epidemiology, and End Results (SEER) program. Two datasets were constructed based upon the year of diagnosis. Dataset 1 (39 514 cases) was limited to primary tumor (T), regional lymph nodes (N) and distant metastasis (M). Dataset 2 (25 291 cases) included additional parameters of age at diagnosis (A) and histologic type and grade (H). The Ensemble Algorithm for Clustering Cancer Data (EACCD) was applied to generate prognostic groups with depiction in dendrograms. C-indices provided dendrogram cutoffs and comparisons of prediction accuracy.ResultsDataset 1 was stratified into nine epithelial ovarian carcinoma prognostic groups, contrasting with 10 groups from FIGO methodology. The EACCD grouping had a slightly higher accuracy in survival prediction than FIGO staging (C-index = 0.7391 vs 0.7371, increase in C-index = 0.0020, 95% confidence interval [CI] 0.0012-0.0027, p = 1.8 × 10-7 ). Nevertheless, there remained a strong inter-system association between EACCD and FIGO (rank correlation = 0.9480, p = 6.1 × 10-15 ). Analysis of Dataset 2 demonstrated that A and H could be smoothly integrated with the T, N and M criteria. Survival data were stratified into nine prognostic groups with an even higher prediction accuracy (C-index = 0.7605) than when using only T, N and M.ConclusionsEACCD was successfully applied to integrate A and H with T, N and M for stratification and survival prediction of epithelial ovarian carcinoma patients. Additional factors could be advantageously incorporated to test the prognostic impact of emerging diagnostic or therapeutic advances.

Project description:BackgroundMelanoma is a common tumor characterized by a high mortality rate in its late stage. After metastasis, current treatment methods are relatively ineffective. Many studies have shown that long noncoding RNA (lncRNA) may participate in gene mutation and genomic instability in cancer.MethodsWe downloaded transcriptome data, mutation data, and clinical follow-up data of melanoma patients from The Cancer Genome Atlas. We divided samples into groups according to the number of somatic cell mutations and then performed a differential analysis to screen out the differentially expressed genes. We then divided samples into genomic unstable and genomic stable groups. We compared lncRNA expression profiles in these groups and constructed a protein-coding genes network coexpressed with selected lncRNA to analyze the pathways enriched by these genes. Two machine learning methods, least absolute shrinkage and selector operation (LASSO) and support vector machine-recursive feature elimination (SVM-RFE), were applied to conduct the lncRNA-related prognostic model. Afterward, we performed survival analysis, risk correlation analysis, independent prognostic analysis, and clinical subgroup model validation. Finally, through wound healing assay and transwell assay, the function of AATBC was verified by A375 cell lines.ResultsWe screened 61 prognostic-related lncRNAs and constructed an lncRNA-mRNA coexpression network based on these lncRNAs. Seven lncRNAs were selected as common characteristic factors based on the two machine learning methods. The model formula was as follows: risk score = 0.085∗AATBC + 0.190∗ AC026689.1-0.117∗AC083799.1 + 0.036∗ AC091544.6-0.039∗ LINC01287-0.291∗ SPRY4.AS1 + 0.056∗ ZNF667.AS1. The seven lncRNAs in this formula are key candidates. Cell experiments have verified that knocking down AATBC in A375 cell lines can reduce the proliferation and invasion ability of melanoma cells.ConclusionThe lncRNA we identified provides a new way to study lncRNA's role in the genomic instability of melanoma. Our findings may provide essential candidate biomarkers for the diagnosis and treatment of melanoma.

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:Background Ovarian cancer is the most lethal gynaecological malignancy, and serous ovarian cancer (SOC) is one of the more important pathological subtypes. Previous studies have reported a significant association of epithelial tomesenchymal transition (EMT) with invasive metastasis and immune modulation of SOC, however, there is a lack of prognostic and immune infiltration biomarkers reported for SOC based on EMT. Methods Gene expression data for ovarian cancer and corresponding patient clinical data were collected from the TCGA database and the GEO database, and cell type annotation and spatial expression analysis were performed on single cell sequencing data from the GEO database. To understand the cell type distribution of EMT-related genes in SOC single-cell data and the enrichment relationships of biological pathways and tumour functions. In addition, GO functional annotation analysis and KEGG pathway enrichment analysis were performed on mRNAs predominantly expressed with EMT to predict the biological function of EMT in ovarian cancer. The major differential genes of EMT were screened to construct a prognostic risk prediction model for SOC patients. Data from 173 SOC patient samples obtained from the GSE53963 database were used to validate the prognostic risk prediction model for ovarian cancer. Here we also analysed the direct association between SOC immune infiltration and immune cell modulation and EMT risk score. and calculate drug sensitivity scores in the GDSC database.In addition, we assessed the specific relationship between GAS1 gene and SOC cell lines. Results Single cell transcriptome analysis in the GEO database annotated the major cell types of SOC samples, including: T cell, Myeloid, Epithelial cell, Fibroblast, Endothelial cell, and Bcell. cellchat revealed several cell type interactions that were shown to be associated with EMT-mediated SOC invasion and metastasis. A prognostic stratification model for SOC was constructed based on EMT-related differential genes, and the Kapan-Meier test showed that this biomarker had significant prognostic stratification value for several independent SOC databases. The EMT risk score has good stratification and identification properties for drug sensitivity in the GDSC database. Conclusions This study constructed a prognostic stratification biomarker based on EMT-related risk genes for immune infiltration mechanisms and drug sensitivity analysis studies in SOC. This lays the foundation for in-depth clinical studies on the role of EMT in immune regulation and related pathway alterations in SOC. It is also hoped to provide effective potential solutions for early diagnosis and clinical treatment of ovarian cancer.

Dataset Information

Developing a Prognostic Gene Panel of Epithelial Ovarian Cancer Patients by a Machine Learning Model.

Publications

Developing a Prognostic Gene Panel of Epithelial Ovarian Cancer Patients by a Machine Learning Model.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets