Dataset Information

A prognostic nomogram integrating novel biomarkers identified by machine learning for cervical squamous cell carcinoma.

ABSTRACT: BACKGROUND:Cervical cancer (CC) represents the fourth most frequently diagnosed malignancy affecting women all over the world. However, effective prognostic biomarkers are still limited for accurately identifying high-risk patients. Here, we provided a combination machine learning algorithm-based signature to predict the prognosis of cervical squamous cell carcinoma (CSCC). METHODS AND MATERIALS:After utilizing RNA sequencing (RNA-seq) data from 36 formalin-fixed and paraffin-embedded (FFPE) samples, the most significant modules were highlighted by the weighted gene co-expression network analysis (WGCNA). A candidate genes-based prognostic classifier was constructed by the least absolute shrinkage and selection operator (LASSO) and then validated in an independent validation set. Finally, based on the multivariate analysis, a nomogram including the FIGO stage, therapy outcome, and risk score level was built to predict progression-free survival (PFS) probability. RESULTS:A mRNA-based signature was developed to classify patients into high- and low-risk groups with significantly different PFS and overall survival (OS) rate (training set: p?

SUBMITTER: Li Y

PROVIDER: S-EPMC7275455 | biostudies-literature | 2020 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A prognostic nomogram integrating novel biomarkers identified by machine learning for cervical squamous cell carcinoma.

Li Yimin Y Lu Shun S Lan Mei M Peng Xinhao X Zhang Zijian Z Lang Jinyi J

Journal of translational medicine 20200605 1

<h4>Background</h4>Cervical cancer (CC) represents the fourth most frequently diagnosed malignancy affecting women all over the world. However, effective prognostic biomarkers are still limited for accurately identifying high-risk patients. Here, we provided a combination machine learning algorithm-based signature to predict the prognosis of cervical squamous cell carcinoma (CSCC).<h4>Methods and materials</h4>After utilizing RNA sequencing (RNA-seq) data from 36 formalin-fixed and paraffin-embe ...[more]

PMID: 32503630

Similar Datasets

Project description:The immune response within the tumor microenvironment plays a key role in tumorigenesis and determines the clinical outcomes of head and neck squamous cell carcinoma (HNSCC). However, to date, a paucity of robust, reliable immune-related biomarkers has been identified that are capable of estimating prognosis in HNSCC patients. High-throughput RNA sequencing was performed in tumors and matched adjacent tissues from five HNSCC patients, and the immune signatures expression of 730 immune-related transcripts selected from the nCounter PanCancer Immune Profiling Panel were assessed. Survival analyzes were performed in a training cohort, consisting of 416 HNSCC cases, retrieved from The Cancer Genome Atlas (TCGA) database. A prognostic signature was built, using elastic net-penalized Cox regression and backward, stepwise Cox regression analyzes. The outcomes were validated by an independent cohort of 115 HNSCC patients, using tissue microarrays and immunohistochemistry staining. Cell-type identification by estimating relative subsets of RNA transcripts (CIBERSORT) was also used to estimate the relative fractions of 22 immune-cell types and their correlations coefficients with prognostic biomarkers. Collectively, 248 immune-related genes were differentially expressed in paired tumors and normal tissues using RNA sequencing. After process screening in the training TCGA cohort, four immune-related genes (PVR, TNFRSF12A, IL21R, and SOCS1) were significantly associated with overall survival (OS). Integrating these genes with Path_N stage, a multiplex model was built and suggested better performance in determining 5 years OS (receiver operating characteristic (ROC) analysis, area under the curve (AUC)=0.709) than others. Further protein-based validation was conducted in 115 HNSCC patients. Similarly, high expression of PVR and TNFRSF12A were associated with poor OS (Kaplan-Meier p=0.017 and 0.0032), while high expression of IL21R and SOCS1 indicated favorable OS (Kaplan-Meier p<0.0001 and =0.0018). The integrated model with Path_N stage still demonstrated efficacy in OS evaluation (Kaplan-Meier p<0.0001, ROC AUC=0.893). Besides, the four prognostic genes were significantly correlated with activated CD8+ T cells, CD4+ T cells, follicular helper T cells and regulatory T cells, implying the possible involvement of these genes in the immunoregulation and development of HNSCC. The well-established model encompassing both immune-related biomarkers and clinicopathological factor might serve as a promising tool for the prognostic prediction of HNSCC.

Project description:BackgroundA plethora of prognostic biomarkers for esophageal squamous cell carcinoma (ESCC) that have hitherto been reported are challenged with low reproducibility due to high molecular heterogeneity of ESCC. The purpose of this study was to identify the optimal biomarkers for ESCC using machine learning algorithms.MethodsBiomarkers related to clinical survival, recurrence or therapeutic response of patients with ESCC were determined through literature database searching. Forty-eight biomarkers linked to recurrence or prognosis of ESCC were used to construct a molecular interaction network based on NetBox and then to identify the functional modules. Publicably available mRNA transcriptome data of ESCC downloaded from Gene Expression Omnibus (GEO) and The Cancer Genome Atlas (TCGA) datasets included GSE53625 and TCGA-ESCC. Five machine learning algorithms, including logical regression (LR), support vector machine (SVM), artificial neural network (ANN), random forest (RF) and XGBoost, were used to develop classifiers for prognostic classification for feature selection. The area under ROC curve (AUC) was used to evaluate the performance of the prognostic classifiers. The importances of identified molecules were ranked by their occurrence frequencies in the prognostic classifiers. Kaplan-Meier survival analysis and log-rank test were performed to determine the statistical significance of overall survival.ResultsA total of 48 clinically proven molecules associated with ESCC progression were used to construct a molecular interaction network with 3 functional modules comprising 17 component molecules. The 131,071 prognostic classifiers using these 17 molecules were built for each machine learning algorithm. Using the occurrence frequencies in the prognostic classifiers with AUCs greater than the mean value of all 131,071 AUCs to rank importances of these 17 molecules, stratifin encoded by SFN was identified as the optimal prognostic biomarker for ESCC, whose performance was further validated in another 2 independent cohorts.ConclusionThe occurrence frequencies across various feature selection approaches reflect the degree of clinical importance and stratifin is an optimal prognostic biomarker for ESCC.

Project description:Background: Microglia plays complex and crucial roles in multiple sclerosis (MS). This study aimed to explore the biological significance of microglia-associated genes in experimental autoimmune encephalomyelitis (EAE) . Methods: Differentially expressed genes (DEGs) were screened with six machine learning (ML) methods, which were also utilized to validate the microglia-associated DEGs in three public databases. ceRNA and Protein–protein interaction (PPI) network analyses were utilized to identify the interaction of the 6 novel biomarkers with other molecules. Then, CIBERSORT and single-sample gene set enrichment analysis (ssGSEA) were employed to quantify the relative abundance of each immune cell infiltration, respectively. qRT-PCR was performed to test the expression of key DEGs in murine models. Results: A total of 247 DEmRNA, 499 DElncRNAs and 269 DEcircRNAs were identified. With screening strategy of five ML algorithms, 6 DEmRNAs were obtained including NGP, HIST1H2BJ, PBLD1, MBLN3, CD180 and F10. Then the 6 DEmRNAs were used as a multigene signature to construct models to differentiate EAE from normal microglia, and AUC value for each model was greater than 0.8. The diagnostic value of these 6 DEmRNAs were identified and further verified by qRT-PCR. Then, differential expression for five out of these 6 DEmRNAs, namely NGP, HIST1H2BJ, PBLD1, MBLN3, and F10 were confirmed. Using PPI analysis, DEmRNAs frequently interacting with transcription factors (TFs), potential drugs and RBPs were identified. With immune cell infiltration analyses, we found EAE microglia presented high levels of immune infiltration, especially Nature Killer (NK) cells and CD8+ T cells. We also reported circRNA (circRNA_00638) was predicted to bind to 76 RBPs. Conclusions: We identified and validated 6 novel microglia related genes and developed a multigene signature with ML methods to confirm their ability to accurately diagnose and characterize biological alterations in EAE microglia. The six key DEmRNAs might also be latent targets for immunoregulatory therapy.

Dataset Information

A prognostic nomogram integrating novel biomarkers identified by machine learning for cervical squamous cell carcinoma.

Publications

A prognostic nomogram integrating novel biomarkers identified by machine learning for cervical squamous cell carcinoma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets