schliessen

Filtern

 

Bibliotheken

A three‐gene panel that distinguishes benign from malignant thyroid nodules

Reliable preoperative diagnosis of malignant thyroid tumors remains challenging because of the inconclusive cytological examination of fine‐needle aspiration biopsies. Although numerous studies have successfully demonstrated the use of high‐throughput molecular diagnostics in cancer prediction, the... Full description

Journal Title: International Journal of Cancer April 2015, Vol.136(7), pp.1646-1654
Main Author: Zheng, Bing
Other Authors: Liu, Jun , Gu, Jianlei , Lu, Yao , Zhang, Wei , Li, Min , Lu, Hui
Format: Electronic Article Electronic Article
Language:
Subjects:
ID: ISSN: 0020-7136 ; E-ISSN: 1097-0215 ; DOI: 10.1002/ijc.29172
Zum Text:
SendSend as email Add to Book BagAdd to Book Bag
Staff View
recordid: wj10.1002/ijc.29172
title: A three‐gene panel that distinguishes benign from malignant thyroid nodules
format: Article
creator:
  • Zheng, Bing
  • Liu, Jun
  • Gu, Jianlei
  • Lu, Yao
  • Zhang, Wei
  • Li, Min
  • Lu, Hui
subjects:
  • Thyroid Cancer
  • Prediction Model
  • Machine Learning
  • Diagnostic Panel
  • Biomarkers
ispartof: International Journal of Cancer, April 2015, Vol.136(7), pp.1646-1654
description: Reliable preoperative diagnosis of malignant thyroid tumors remains challenging because of the inconclusive cytological examination of fine‐needle aspiration biopsies. Although numerous studies have successfully demonstrated the use of high‐throughput molecular diagnostics in cancer prediction, the application of microarrays in routine clinical use remains limited. Our aim was, therefore, to identify a small subset of genes to develop a practical and inexpensive diagnostic tool for clinical use. We developed a two‐step feature selection method composed of a linear models for microarray data (LIMMA) linear model and an iterative Bayesian model averaging model to identify a suitable gene set signature. Using one public dataset for training, we discovered a three‐gene signature peptidase 4 (DPP4), secretogranin V (SCG5) and carbonic anhydrase XII (CA12). We then evaluated the robustness of our gene set using three other independent public datasets. The gene signature accuracy was 85.7, 78.8 and 85.7%, respectively. For experimental validation, we collected 70 thyroid samples from surgery and our three‐gene signature method achieved an accuracy of 94.3% by quantitative polymerase chain reaction (QPCR) experiment. Furthermore, immunohistochemistry in 29 samples showed proteins expressed by these three genes are also differentially expressed in thyroid samples. Our protocol discovered a robust three‐gene signature that can distinguish benign from malignant thyroid tumors, which will have daily clinical application. What's new? Today a key challenge in thyroid cancer research lies in distinguishing benign thyroid nodules from malignant tumors in order to avoid unnecessary surgery. While many researchers have focused on molecular classification based on oligonucleotide microarray gene‐expression patterns, the high cost and poor reproducibility are barriers for daily clinical application. Here, using a two‐step feature selection method, the authors constructed a small gene‐expression set that can distinguish benign from malignant thyroid tumors with high prediction accuracy. The three‐gene signature was validated experimentally. The prediction model is simpler and more affordable than microarray‐based gene‐expression patterns and more suitable for daily clinical application.
language:
source:
identifier: ISSN: 0020-7136 ; E-ISSN: 1097-0215 ; DOI: 10.1002/ijc.29172
fulltext: fulltext
issn:
  • 0020-7136
  • 00207136
  • 1097-0215
  • 10970215
url: Link


@attributes
ID840453094
RANK0.07
NO1
SEARCH_ENGINEprimo_central_multiple_fe
SEARCH_ENGINE_TYPEPrimo Central Search Engine
LOCALfalse
PrimoNMBib
record
control
sourcerecordid10.1002/ijc.29172
sourceidwj
recordidTN_wj10.1002/ijc.29172
sourcesystemPC
pqid1652450521
display
typearticle
titleA three‐gene panel that distinguishes benign from malignant thyroid nodules
creatorZheng, Bing ; Liu, Jun ; Gu, Jianlei ; Lu, Yao ; Zhang, Wei ; Li, Min ; Lu, Hui
ispartofInternational Journal of Cancer, April 2015, Vol.136(7), pp.1646-1654
identifier
subjectThyroid Cancer ; Prediction Model ; Machine Learning ; Diagnostic Panel ; Biomarkers
descriptionReliable preoperative diagnosis of malignant thyroid tumors remains challenging because of the inconclusive cytological examination of fine‐needle aspiration biopsies. Although numerous studies have successfully demonstrated the use of high‐throughput molecular diagnostics in cancer prediction, the application of microarrays in routine clinical use remains limited. Our aim was, therefore, to identify a small subset of genes to develop a practical and inexpensive diagnostic tool for clinical use. We developed a two‐step feature selection method composed of a linear models for microarray data (LIMMA) linear model and an iterative Bayesian model averaging model to identify a suitable gene set signature. Using one public dataset for training, we discovered a three‐gene signature peptidase 4 (DPP4), secretogranin V (SCG5) and carbonic anhydrase XII (CA12). We then evaluated the robustness of our gene set using three other independent public datasets. The gene signature accuracy was 85.7, 78.8 and 85.7%, respectively. For experimental validation, we collected 70 thyroid samples from surgery and our three‐gene signature method achieved an accuracy of 94.3% by quantitative polymerase chain reaction (QPCR) experiment. Furthermore, immunohistochemistry in 29 samples showed proteins expressed by these three genes are also differentially expressed in thyroid samples. Our protocol discovered a robust three‐gene signature that can distinguish benign from malignant thyroid tumors, which will have daily clinical application. What's new? Today a key challenge in thyroid cancer research lies in distinguishing benign thyroid nodules from malignant tumors in order to avoid unnecessary surgery. While many researchers have focused on molecular classification based on oligonucleotide microarray gene‐expression patterns, the high cost and poor reproducibility are barriers for daily clinical application. Here, using a two‐step feature selection method, the authors constructed a small gene‐expression set that can distinguish benign from malignant thyroid tumors with high prediction accuracy. The three‐gene signature was validated experimentally. The prediction model is simpler and more affordable than microarray‐based gene‐expression patterns and more suitable for daily clinical application.
source
version6
lds50peer_reviewed
links
openurl$$Topenurl_article
openurlfulltext$$Topenurlfull_article
search
creatorcontrib
0Zheng, Bing
1Liu, Jun
2Gu, Jianlei
3Lu, Yao
4Zhang, Wei
5Li, Min
6Lu, Hui
titleA three‐gene panel that distinguishes benign from malignant thyroid nodules
descriptionReliable preoperative diagnosis of malignant thyroid tumors remains challenging because of the inconclusive cytological examination of fine‐needle aspiration biopsies. Although numerous studies have successfully demonstrated the use of high‐throughput molecular diagnostics in cancer prediction, the application of microarrays in routine clinical use remains limited. Our aim was, therefore, to identify a small subset of genes to develop a practical and inexpensive diagnostic tool for clinical use. We developed a two‐step feature selection method composed of a linear models for microarray data (LIMMA) linear model and an iterative Bayesian model averaging model to identify a suitable gene set signature. Using one public dataset for training, we discovered a three‐gene signature peptidase 4 (DPP4), secretogranin V (SCG5) and carbonic anhydrase XII (CA12). We then evaluated the robustness of our gene set using three other independent public datasets. The gene signature accuracy was 85.7, 78.8 and 85.7%, respectively. For experimental validation, we collected 70 thyroid samples from surgery and our three‐gene signature method achieved an accuracy of 94.3% by quantitative polymerase chain reaction (QPCR) experiment. Furthermore, immunohistochemistry in 29 samples showed proteins expressed by these three genes are also differentially expressed in thyroid samples. Our protocol discovered a robust three‐gene signature that can distinguish benign from malignant thyroid tumors, which will have daily clinical application. What's new? Today a key challenge in thyroid cancer research lies in distinguishing benign thyroid nodules from malignant tumors in order to avoid unnecessary surgery. While many researchers have focused on molecular classification based on oligonucleotide microarray gene‐expression patterns, the high cost and poor reproducibility are barriers for daily clinical application. Here, using a two‐step feature selection method, the authors constructed a small gene‐expression set that can distinguish benign from malignant thyroid tumors with high prediction accuracy. The three‐gene signature was validated experimentally. The prediction model is simpler and more affordable than microarray‐based gene‐expression patterns and more suitable for daily clinical application.
subject
0Thyroid Cancer
1Prediction Model
2Machine Learning
3Diagnostic Panel
4Biomarkers
general
010.1002/ijc.29172
1Wiley Online Library
sourceidwj
recordidwj10.1002/ijc.29172
issn
00020-7136
100207136
21097-0215
310970215
rsrctypearticle
creationdate2015
addtitle
0International Journal of Cancer
1Int. J. Cancer
searchscope
0wj
1wiley
scope
0wj
1wiley
lsr30VSR-Enriched:[pages, pqid]
sort
titleA three‐gene panel that distinguishes benign from malignant thyroid nodules
authorZheng, Bing ; Liu, Jun ; Gu, Jianlei ; Lu, Yao ; Zhang, Wei ; Li, Min ; Lu, Hui
creationdate20150400
facets
frbrgroupid-635621926893104411
frbrtype5
creationdate2015
topic
0Thyroid Cancer
1Prediction Model
2Machine Learning
3Diagnostic Panel
4Biomarkers
collectionWiley Online Library
prefilterarticles
rsrctypearticles
creatorcontrib
0Zheng, Bing
1Liu, Jun
2Gu, Jianlei
3Lu, Yao
4Zhang, Wei
5Li, Min
6Lu, Hui
jtitleInternational Journal of Cancer
toplevelpeer_reviewed
delivery
delcategoryRemote Search Resource
fulltextfulltext
addata
aulast
0Zheng
1Liu
2Gu
3Lu
4Zhang
5Li
aufirst
0Bing
1Jun
2Jianlei
3Yao
4Wei
5Min
6Hui
au
0Zheng, Bing
1Liu, Jun
2Gu, Jianlei
3Lu, Yao
4Zhang, Wei
5Li, Min
6Lu, Hui
atitleA three‐gene panel that distinguishes benign from malignant thyroid nodules
jtitleInternational Journal of Cancer
risdate201504
volume136
issue7
spage1646
epage1654
issn0020-7136
eissn1097-0215
genrearticle
ristypeJOUR
abstractReliable preoperative diagnosis of malignant thyroid tumors remains challenging because of the inconclusive cytological examination of fine‐needle aspiration biopsies. Although numerous studies have successfully demonstrated the use of high‐throughput molecular diagnostics in cancer prediction, the application of microarrays in routine clinical use remains limited. Our aim was, therefore, to identify a small subset of genes to develop a practical and inexpensive diagnostic tool for clinical use. We developed a two‐step feature selection method composed of a linear models for microarray data (LIMMA) linear model and an iterative Bayesian model averaging model to identify a suitable gene set signature. Using one public dataset for training, we discovered a three‐gene signature peptidase 4 (DPP4), secretogranin V (SCG5) and carbonic anhydrase XII (CA12). We then evaluated the robustness of our gene set using three other independent public datasets. The gene signature accuracy was 85.7, 78.8 and 85.7%, respectively. For experimental validation, we collected 70 thyroid samples from surgery and our three‐gene signature method achieved an accuracy of 94.3% by quantitative polymerase chain reaction (QPCR) experiment. Furthermore, immunohistochemistry in 29 samples showed proteins expressed by these three genes are also differentially expressed in thyroid samples. Our protocol discovered a robust three‐gene signature that can distinguish benign from malignant thyroid tumors, which will have daily clinical application. What's new? Today a key challenge in thyroid cancer research lies in distinguishing benign thyroid nodules from malignant tumors in order to avoid unnecessary surgery. While many researchers have focused on molecular classification based on oligonucleotide microarray gene‐expression patterns, the high cost and poor reproducibility are barriers for daily clinical application. Here, using a two‐step feature selection method, the authors constructed a small gene‐expression set that can distinguish benign from malignant thyroid tumors with high prediction accuracy. The three‐gene signature was validated experimentally. The prediction model is simpler and more affordable than microarray‐based gene‐expression patterns and more suitable for daily clinical application.
doi10.1002/ijc.29172
pages1646-1654
date2015-04