Prognostic classification of endometrial cancer using a molecular approach based on a twelve-gene NGS panel

Endometrial Cancer (EC) is one of the most common malignancies in women in developed countries. Molecular characterization of different biotypes may improve clinical management of EC. The Cancer Genome Atlas (TCGA) project has revealed four prognostic EC subgroups: POLE, MSI; Copy Number Low (CNL) a...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports 2019-12, Vol.9 (1), p.18093-9, Article 18093
Main Authors: López-Reig, Raquel, Fernández-Serra, Antonio, Romero, Ignacio, Zorrero, Cristina, Illueca, Carmen, García-Casado, Zaida, Poveda, Andrés, López-Guerrero, José Antonio
Format: Article
Language:English
Subjects:
45
45/22
45/23
692/4017
692/4028/67/1517/1931
692/53/2422
Artificial Intelligence
Biotypes
Cancer
Classification
Copy number
Developed countries
Endometrial cancer
Endometrial Neoplasms - diagnosis
Endometrial Neoplasms - genetics
Endometrium
Female
Genetic markers
Genomes
Humanities and Social Sciences
Humans
Microsatellite Instability
Microsatellites
multidisciplinary
Mutation
Mutation Rate
Paraffin
Prognosis
Science
Science (multidisciplinary)
Survival
Tumors
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Endometrial Cancer (EC) is one of the most common malignancies in women in developed countries. Molecular characterization of different biotypes may improve clinical management of EC. The Cancer Genome Atlas (TCGA) project has revealed four prognostic EC subgroups: POLE, MSI; Copy Number Low (CNL) and Copy Number High (CNH). The goal of this study was to develop a method to classify tumors in any of the four EC prognostic groups using affordable molecular techniques. Ninety-six Formalin-Fixed Paraffin-embedded (FFPE) samples were sequenced following a NGS TruSeq Custom Amplicon low input (Illumina) protocol interrogating a multi-gene panel. MSI analysis was performed by fragment analysis using eight specific microsatellite markers. A Random Forest classification algorithm (RFA), considering NGS results, was developed to stratify EC patients into different prognostic groups. Our approach correctly classifies the EC patients into the four TCGA prognostic biotypes. The RFA assigned the samples to the CNH and CNL groups with an accuracy of 0.9753 (p 
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-019-54624-x