Artificial Neural Networks and gene filtering distinguish between global gene expression profiles of Barrett's esophagus and esophageal cancer

Yan Xu, Florin M. Selaru, Jing Yin, Tong Tong Zou, Valentina Shustova, Yuriko Mori, Fumiaki Sato, Thomas C. Liu, Andreea Olaru, Suna Wang, Martha C. Kimos, Kellie Perry, Kena Desai, Bruce D. Greenwald, Mark J. Krasna, David Shibata, John M. Abraham, Stephen J. Meltzer

Research output: Contribution to journalArticle

113 Citations (Scopus)

Abstract

cDNA microarrays, combined with bioinformatics analyses, are becoming increasingly used in current medical research. Existing analytic methods, particularly those that are unsupervised, often have difficulty recognizing subtle differences among predefined subgroups. In contrast, supervised methods, such as Artificial Neural Networks (ANNs), are able to recognize subtly different biological entities. We applied ANNs in a proof-of-principle study of cDNA microarray data in esophageal cancer (CA) and premalignancy. cDNA microarrays, each containing 8064 clones, were hybridized to RNAs from 22 esophageal lesions, including 14 Barrett's esophagus (BA) metaplasias and 8 esophageal carcinomas (3 squamous cell carcinomas and 5 adenocarcinomas). Scanned cDNA microarray data were analyzed using the bioinformatics software Cluster/TreeView, Significance Analysis of Microarrays (SAM), and ANNs. Cluster analysis based on all 8064 clones on the microarrays was unable to correctly distinguish BA specimens from CA specimens. SAM then selected 160 differentially expressed genes between Barrett's and cancer. Cluster analysis based on this reduced set still misclassified 2 Barrett's as cancers. The ANN was trained on 12 samples and tested against the remaining 10 samples. Using the 160 selected genes, the ANN correctly diagnosed all 10 samples in the test set. Finally, the 160 genes selected by SAM may merit further study as biomarkers of neoplastic progression in the esophagus, as well as in elucidating pathological mechanisms underlying BA and CA.

Original languageEnglish (US)
Pages (from-to)3493-3497
Number of pages5
JournalCancer Research
Volume62
Issue number12
StatePublished - Jun 15 2002

Fingerprint

Barrett Esophagus
Gene Regulatory Networks
Esophageal Neoplasms
Oligonucleotide Array Sequence Analysis
Transcriptome
Microarray Analysis
Computational Biology
Cluster Analysis
Neoplasms
Clone Cells
Synthetic Genes
Metaplasia
Esophagus
Genes
Biomedical Research
Squamous Cell Carcinoma
Adenocarcinoma
Software
Biomarkers
RNA

All Science Journal Classification (ASJC) codes

  • Oncology
  • Cancer Research

Cite this

Xu, Y., Selaru, F. M., Yin, J., Zou, T. T., Shustova, V., Mori, Y., ... Meltzer, S. J. (2002). Artificial Neural Networks and gene filtering distinguish between global gene expression profiles of Barrett's esophagus and esophageal cancer. Cancer Research, 62(12), 3493-3497.

Artificial Neural Networks and gene filtering distinguish between global gene expression profiles of Barrett's esophagus and esophageal cancer. / Xu, Yan; Selaru, Florin M.; Yin, Jing; Zou, Tong Tong; Shustova, Valentina; Mori, Yuriko; Sato, Fumiaki; Liu, Thomas C.; Olaru, Andreea; Wang, Suna; Kimos, Martha C.; Perry, Kellie; Desai, Kena; Greenwald, Bruce D.; Krasna, Mark J.; Shibata, David; Abraham, John M.; Meltzer, Stephen J.

In: Cancer Research, Vol. 62, No. 12, 15.06.2002, p. 3493-3497.

Research output: Contribution to journalArticle

Xu, Y, Selaru, FM, Yin, J, Zou, TT, Shustova, V, Mori, Y, Sato, F, Liu, TC, Olaru, A, Wang, S, Kimos, MC, Perry, K, Desai, K, Greenwald, BD, Krasna, MJ, Shibata, D, Abraham, JM & Meltzer, SJ 2002, 'Artificial Neural Networks and gene filtering distinguish between global gene expression profiles of Barrett's esophagus and esophageal cancer', Cancer Research, vol. 62, no. 12, pp. 3493-3497.
Xu, Yan ; Selaru, Florin M. ; Yin, Jing ; Zou, Tong Tong ; Shustova, Valentina ; Mori, Yuriko ; Sato, Fumiaki ; Liu, Thomas C. ; Olaru, Andreea ; Wang, Suna ; Kimos, Martha C. ; Perry, Kellie ; Desai, Kena ; Greenwald, Bruce D. ; Krasna, Mark J. ; Shibata, David ; Abraham, John M. ; Meltzer, Stephen J. / Artificial Neural Networks and gene filtering distinguish between global gene expression profiles of Barrett's esophagus and esophageal cancer. In: Cancer Research. 2002 ; Vol. 62, No. 12. pp. 3493-3497.
@article{0411a542f6964842ac3b82d622395bc9,
title = "Artificial Neural Networks and gene filtering distinguish between global gene expression profiles of Barrett's esophagus and esophageal cancer",
abstract = "cDNA microarrays, combined with bioinformatics analyses, are becoming increasingly used in current medical research. Existing analytic methods, particularly those that are unsupervised, often have difficulty recognizing subtle differences among predefined subgroups. In contrast, supervised methods, such as Artificial Neural Networks (ANNs), are able to recognize subtly different biological entities. We applied ANNs in a proof-of-principle study of cDNA microarray data in esophageal cancer (CA) and premalignancy. cDNA microarrays, each containing 8064 clones, were hybridized to RNAs from 22 esophageal lesions, including 14 Barrett's esophagus (BA) metaplasias and 8 esophageal carcinomas (3 squamous cell carcinomas and 5 adenocarcinomas). Scanned cDNA microarray data were analyzed using the bioinformatics software Cluster/TreeView, Significance Analysis of Microarrays (SAM), and ANNs. Cluster analysis based on all 8064 clones on the microarrays was unable to correctly distinguish BA specimens from CA specimens. SAM then selected 160 differentially expressed genes between Barrett's and cancer. Cluster analysis based on this reduced set still misclassified 2 Barrett's as cancers. The ANN was trained on 12 samples and tested against the remaining 10 samples. Using the 160 selected genes, the ANN correctly diagnosed all 10 samples in the test set. Finally, the 160 genes selected by SAM may merit further study as biomarkers of neoplastic progression in the esophagus, as well as in elucidating pathological mechanisms underlying BA and CA.",
author = "Yan Xu and Selaru, {Florin M.} and Jing Yin and Zou, {Tong Tong} and Valentina Shustova and Yuriko Mori and Fumiaki Sato and Liu, {Thomas C.} and Andreea Olaru and Suna Wang and Kimos, {Martha C.} and Kellie Perry and Kena Desai and Greenwald, {Bruce D.} and Krasna, {Mark J.} and David Shibata and Abraham, {John M.} and Meltzer, {Stephen J.}",
year = "2002",
month = "6",
day = "15",
language = "English (US)",
volume = "62",
pages = "3493--3497",
journal = "Cancer Research",
issn = "0008-5472",
number = "12",

}

TY - JOUR

T1 - Artificial Neural Networks and gene filtering distinguish between global gene expression profiles of Barrett's esophagus and esophageal cancer

AU - Xu, Yan

AU - Selaru, Florin M.

AU - Yin, Jing

AU - Zou, Tong Tong

AU - Shustova, Valentina

AU - Mori, Yuriko

AU - Sato, Fumiaki

AU - Liu, Thomas C.

AU - Olaru, Andreea

AU - Wang, Suna

AU - Kimos, Martha C.

AU - Perry, Kellie

AU - Desai, Kena

AU - Greenwald, Bruce D.

AU - Krasna, Mark J.

AU - Shibata, David

AU - Abraham, John M.

AU - Meltzer, Stephen J.

PY - 2002/6/15

Y1 - 2002/6/15

N2 - cDNA microarrays, combined with bioinformatics analyses, are becoming increasingly used in current medical research. Existing analytic methods, particularly those that are unsupervised, often have difficulty recognizing subtle differences among predefined subgroups. In contrast, supervised methods, such as Artificial Neural Networks (ANNs), are able to recognize subtly different biological entities. We applied ANNs in a proof-of-principle study of cDNA microarray data in esophageal cancer (CA) and premalignancy. cDNA microarrays, each containing 8064 clones, were hybridized to RNAs from 22 esophageal lesions, including 14 Barrett's esophagus (BA) metaplasias and 8 esophageal carcinomas (3 squamous cell carcinomas and 5 adenocarcinomas). Scanned cDNA microarray data were analyzed using the bioinformatics software Cluster/TreeView, Significance Analysis of Microarrays (SAM), and ANNs. Cluster analysis based on all 8064 clones on the microarrays was unable to correctly distinguish BA specimens from CA specimens. SAM then selected 160 differentially expressed genes between Barrett's and cancer. Cluster analysis based on this reduced set still misclassified 2 Barrett's as cancers. The ANN was trained on 12 samples and tested against the remaining 10 samples. Using the 160 selected genes, the ANN correctly diagnosed all 10 samples in the test set. Finally, the 160 genes selected by SAM may merit further study as biomarkers of neoplastic progression in the esophagus, as well as in elucidating pathological mechanisms underlying BA and CA.

AB - cDNA microarrays, combined with bioinformatics analyses, are becoming increasingly used in current medical research. Existing analytic methods, particularly those that are unsupervised, often have difficulty recognizing subtle differences among predefined subgroups. In contrast, supervised methods, such as Artificial Neural Networks (ANNs), are able to recognize subtly different biological entities. We applied ANNs in a proof-of-principle study of cDNA microarray data in esophageal cancer (CA) and premalignancy. cDNA microarrays, each containing 8064 clones, were hybridized to RNAs from 22 esophageal lesions, including 14 Barrett's esophagus (BA) metaplasias and 8 esophageal carcinomas (3 squamous cell carcinomas and 5 adenocarcinomas). Scanned cDNA microarray data were analyzed using the bioinformatics software Cluster/TreeView, Significance Analysis of Microarrays (SAM), and ANNs. Cluster analysis based on all 8064 clones on the microarrays was unable to correctly distinguish BA specimens from CA specimens. SAM then selected 160 differentially expressed genes between Barrett's and cancer. Cluster analysis based on this reduced set still misclassified 2 Barrett's as cancers. The ANN was trained on 12 samples and tested against the remaining 10 samples. Using the 160 selected genes, the ANN correctly diagnosed all 10 samples in the test set. Finally, the 160 genes selected by SAM may merit further study as biomarkers of neoplastic progression in the esophagus, as well as in elucidating pathological mechanisms underlying BA and CA.

UR - http://www.scopus.com/inward/record.url?scp=0037096859&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037096859&partnerID=8YFLogxK

M3 - Article

VL - 62

SP - 3493

EP - 3497

JO - Cancer Research

JF - Cancer Research

SN - 0008-5472

IS - 12

ER -