Dataset Information

Machine Learning Supports Long Noncoding RNAs as Expression Markers for Endometrial Carcinoma.

ABSTRACT: Uterine corpus endometrial carcinoma (UCEC) is the second most common type of gynecological tumor. Several research studies have recently shown the potential of different ncRNAs as biomarkers for prognostics and diagnosis in different types of cancers, including UCEC. Thus, we hypothesized that long noncoding RNAs (lncRNAs) could serve as efficient factors to discriminate solid primary (TP) and normal adjacent (NT) tissues in UCEC with high accuracy. We performed an in silico differential expression analysis comparing TP and NT from a set of samples downloaded from the Cancer Genome Atlas (TCGA) database, targeting highly differentially expressed lncRNAs that could potentially serve as gene expression markers. All analyses were performed in R software. The receiver operator characteristics (ROC) analyses and both supervised and unsupervised machine learning indicated a set of 14 lncRNAs that may serve as biomarkers for UCEC. Functions and putative pathways were assessed through a coexpression network and target enrichment analysis.

SUBMITTER: Mello AC

PROVIDER: S-EPMC7199595 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine Learning Supports Long Noncoding RNAs as Expression Markers for Endometrial Carcinoma.

Mello Ana Carolina AC Freitas Martiela M Coutinho Laura L Falcon Tiago T Matte Ursula U

BioMed research international 20200110

Uterine corpus endometrial carcinoma (UCEC) is the second most common type of gynecological tumor. Several research studies have recently shown the potential of different ncRNAs as biomarkers for prognostics and diagnosis in different types of cancers, including UCEC. Thus, we hypothesized that long noncoding RNAs (lncRNAs) could serve as efficient factors to discriminate solid primary (TP) and normal adjacent (NT) tissues in UCEC with high accuracy. We performed an in silico differential expres ...[more]

PMID: 32420338

Similar Datasets

Project description:Liver cancer is the most common cancer and is the epitome of a recalcitrant cancer. Increasing evidence shown that long noncoding RNAs (lncRNA) were associated with cancer-related death and could function as a competing endogenous RNA (ceRNA). To explore regulatory roles and potential prognostic biomarkers of lncRNA for liver cancer, RNA-sequencing expression data were downloaded from the TCGA database and GEO database. A total of 357 patients were randomly divided into a discovery group and a validation group, of which 313 patients can obtain clinical data. In discovery phrase, 58 lncRNAs, 16 miRNAs, and 34 mRNAs were screened to construct the ceRNA network based on 252 patients employed from discovery group. Univariate and multivariate Cox hazard regression analysis model revealed that five lncRNAs (AATK-AS1, C10orf91, LINC00162, LINC00200, and LINC00501) from 58 lncRNAs were formulated to predict the overall survival (OS). We used the value of gene expression and regression coefficients to construct a risk score based on the five lncRNAs. Next, we validated our model in the GSE116174 dataset (n = 64) and the validation group (n = 94) from TCGA database. Subgroup analysis suggest that the five lncRNAs played critical parts in early stage in cancer from both discovery and validation groups. The five lncRNAs were also found to be associated with immune cells infiltration including CD4+ memory activated, NK cells activated and mast cells activated, then the results were also validated according to the validation group. Furthermore, KEGG pathway enrichment analysis showed that these nine coexpressed modules using the method of WGCNA, and many of these pathways are associated with the development and progression of disease. At last, the transcription factor binding sites (TFBS) of the five lncRNAs were predicted, which help us to understand the potential mechanism that the TFBS adjusted the ceRNA network. In summary, the ceRNA regulatory network may contribute to a better understanding of liver cancer mechanism and provide potential prognostic biomarkers and therapeutic targets.

Dataset Information

Machine Learning Supports Long Noncoding RNAs as Expression Markers for Endometrial Carcinoma.

Publications

Machine Learning Supports Long Noncoding RNAs as Expression Markers for Endometrial Carcinoma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets