Highly accurate two-gene classifier for differentiating gastrointestinal stromal tumors and leiomyosarcomas

Nathan D. Price, Jonathan Trent, Adel K. El-Naggar, David Cogdell, Ellen Taylor, Kelly K. Hunt, Raphael E. Pollock, Leroy Hood, Ilya Shmulevich, Wei Zhang

Research output: Contribution to journalArticle

123 Citations (Scopus)

Abstract

Gastrointestinal stromal tumor (GIST) has emerged as a clinically distinct type of sarcoma with frequent overexpression and mutation of the c-Kit oncogene and a favorable response to imatinib mesylate [also known as STI571 (Gleevec)] therapy. However, a significant diagnostic challenge remains in the differentiation of GIST from leiomyosarcomas (LMSs). To improve on the diagnostic evaluation and to complement the immunohistochemical evaluation of these tumors, we performed a whole-genome gene expression study on 68 well characterized tumor samples. Using bioinformatic approaches, we devised a two-gene relative expression classifier that distinguishes between GIST and LMS with an accuracy of 99.3% on the microarray samples and an estimated accuracy of 97.8% on future cases. We validated this classifier by using RT-PCR on 20 samples in the microarray study and on an additional 19 independent samples, with 100% accuracy. Thus, our two-gene relative expression classifier is a highly accurate diagnostic method to distinguish between GIST and LMS and has the potential to be rapidly implemented in a clinical setting. The success of this classifier is likely due to two general traits, namely that the classifier is independent of data normalization and that it uses as simple an approach as possible to achieve this independence to avoid overfitting. We expect that the use of simple marker pairs that exhibit these traits will be of significant clinical use in a variety of contexts.

Original languageEnglish
Pages (from-to)3414-3419
Number of pages6
JournalProceedings of the National Academy of Sciences of the United States of America
Volume104
Issue number9
DOIs
StatePublished - Feb 27 2007
Externally publishedYes

Fingerprint

Gastrointestinal Stromal Tumors
Leiomyosarcoma
Gene Expression
Genes
Computational Biology
Oncogenes
Sarcoma
Neoplasms
Genome
Polymerase Chain Reaction
Mutation
Imatinib Mesylate
Therapeutics

Keywords

  • Cancer
  • Classification
  • Diagnostic
  • Machine learning
  • Molecular signature

ASJC Scopus subject areas

  • Genetics
  • General

Cite this

Highly accurate two-gene classifier for differentiating gastrointestinal stromal tumors and leiomyosarcomas. / Price, Nathan D.; Trent, Jonathan; El-Naggar, Adel K.; Cogdell, David; Taylor, Ellen; Hunt, Kelly K.; Pollock, Raphael E.; Hood, Leroy; Shmulevich, Ilya; Zhang, Wei.

In: Proceedings of the National Academy of Sciences of the United States of America, Vol. 104, No. 9, 27.02.2007, p. 3414-3419.

Research output: Contribution to journalArticle

Price, ND, Trent, J, El-Naggar, AK, Cogdell, D, Taylor, E, Hunt, KK, Pollock, RE, Hood, L, Shmulevich, I & Zhang, W 2007, 'Highly accurate two-gene classifier for differentiating gastrointestinal stromal tumors and leiomyosarcomas', Proceedings of the National Academy of Sciences of the United States of America, vol. 104, no. 9, pp. 3414-3419. https://doi.org/10.1073/pnas.0611373104
Price, Nathan D. ; Trent, Jonathan ; El-Naggar, Adel K. ; Cogdell, David ; Taylor, Ellen ; Hunt, Kelly K. ; Pollock, Raphael E. ; Hood, Leroy ; Shmulevich, Ilya ; Zhang, Wei. / Highly accurate two-gene classifier for differentiating gastrointestinal stromal tumors and leiomyosarcomas. In: Proceedings of the National Academy of Sciences of the United States of America. 2007 ; Vol. 104, No. 9. pp. 3414-3419.
@article{966237c7bc16468fbf0ce77ec8144e29,
title = "Highly accurate two-gene classifier for differentiating gastrointestinal stromal tumors and leiomyosarcomas",
abstract = "Gastrointestinal stromal tumor (GIST) has emerged as a clinically distinct type of sarcoma with frequent overexpression and mutation of the c-Kit oncogene and a favorable response to imatinib mesylate [also known as STI571 (Gleevec)] therapy. However, a significant diagnostic challenge remains in the differentiation of GIST from leiomyosarcomas (LMSs). To improve on the diagnostic evaluation and to complement the immunohistochemical evaluation of these tumors, we performed a whole-genome gene expression study on 68 well characterized tumor samples. Using bioinformatic approaches, we devised a two-gene relative expression classifier that distinguishes between GIST and LMS with an accuracy of 99.3{\%} on the microarray samples and an estimated accuracy of 97.8{\%} on future cases. We validated this classifier by using RT-PCR on 20 samples in the microarray study and on an additional 19 independent samples, with 100{\%} accuracy. Thus, our two-gene relative expression classifier is a highly accurate diagnostic method to distinguish between GIST and LMS and has the potential to be rapidly implemented in a clinical setting. The success of this classifier is likely due to two general traits, namely that the classifier is independent of data normalization and that it uses as simple an approach as possible to achieve this independence to avoid overfitting. We expect that the use of simple marker pairs that exhibit these traits will be of significant clinical use in a variety of contexts.",
keywords = "Cancer, Classification, Diagnostic, Machine learning, Molecular signature",
author = "Price, {Nathan D.} and Jonathan Trent and El-Naggar, {Adel K.} and David Cogdell and Ellen Taylor and Hunt, {Kelly K.} and Pollock, {Raphael E.} and Leroy Hood and Ilya Shmulevich and Wei Zhang",
year = "2007",
month = "2",
day = "27",
doi = "10.1073/pnas.0611373104",
language = "English",
volume = "104",
pages = "3414--3419",
journal = "Proceedings of the National Academy of Sciences of the United States of America",
issn = "0027-8424",
number = "9",

}

TY - JOUR

T1 - Highly accurate two-gene classifier for differentiating gastrointestinal stromal tumors and leiomyosarcomas

AU - Price, Nathan D.

AU - Trent, Jonathan

AU - El-Naggar, Adel K.

AU - Cogdell, David

AU - Taylor, Ellen

AU - Hunt, Kelly K.

AU - Pollock, Raphael E.

AU - Hood, Leroy

AU - Shmulevich, Ilya

AU - Zhang, Wei

PY - 2007/2/27

Y1 - 2007/2/27

N2 - Gastrointestinal stromal tumor (GIST) has emerged as a clinically distinct type of sarcoma with frequent overexpression and mutation of the c-Kit oncogene and a favorable response to imatinib mesylate [also known as STI571 (Gleevec)] therapy. However, a significant diagnostic challenge remains in the differentiation of GIST from leiomyosarcomas (LMSs). To improve on the diagnostic evaluation and to complement the immunohistochemical evaluation of these tumors, we performed a whole-genome gene expression study on 68 well characterized tumor samples. Using bioinformatic approaches, we devised a two-gene relative expression classifier that distinguishes between GIST and LMS with an accuracy of 99.3% on the microarray samples and an estimated accuracy of 97.8% on future cases. We validated this classifier by using RT-PCR on 20 samples in the microarray study and on an additional 19 independent samples, with 100% accuracy. Thus, our two-gene relative expression classifier is a highly accurate diagnostic method to distinguish between GIST and LMS and has the potential to be rapidly implemented in a clinical setting. The success of this classifier is likely due to two general traits, namely that the classifier is independent of data normalization and that it uses as simple an approach as possible to achieve this independence to avoid overfitting. We expect that the use of simple marker pairs that exhibit these traits will be of significant clinical use in a variety of contexts.

AB - Gastrointestinal stromal tumor (GIST) has emerged as a clinically distinct type of sarcoma with frequent overexpression and mutation of the c-Kit oncogene and a favorable response to imatinib mesylate [also known as STI571 (Gleevec)] therapy. However, a significant diagnostic challenge remains in the differentiation of GIST from leiomyosarcomas (LMSs). To improve on the diagnostic evaluation and to complement the immunohistochemical evaluation of these tumors, we performed a whole-genome gene expression study on 68 well characterized tumor samples. Using bioinformatic approaches, we devised a two-gene relative expression classifier that distinguishes between GIST and LMS with an accuracy of 99.3% on the microarray samples and an estimated accuracy of 97.8% on future cases. We validated this classifier by using RT-PCR on 20 samples in the microarray study and on an additional 19 independent samples, with 100% accuracy. Thus, our two-gene relative expression classifier is a highly accurate diagnostic method to distinguish between GIST and LMS and has the potential to be rapidly implemented in a clinical setting. The success of this classifier is likely due to two general traits, namely that the classifier is independent of data normalization and that it uses as simple an approach as possible to achieve this independence to avoid overfitting. We expect that the use of simple marker pairs that exhibit these traits will be of significant clinical use in a variety of contexts.

KW - Cancer

KW - Classification

KW - Diagnostic

KW - Machine learning

KW - Molecular signature

UR - http://www.scopus.com/inward/record.url?scp=33847665105&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33847665105&partnerID=8YFLogxK

U2 - 10.1073/pnas.0611373104

DO - 10.1073/pnas.0611373104

M3 - Article

VL - 104

SP - 3414

EP - 3419

JO - Proceedings of the National Academy of Sciences of the United States of America

JF - Proceedings of the National Academy of Sciences of the United States of America

SN - 0027-8424

IS - 9

ER -