Multiclass cancer diagnosis using tumor gene expression signatures

Sridhar Ramaswamy, Pablo Tamayo, Ryan Rifkin, Sayan Mukherjee, Chen Hsiang Yeang, Michael Angelo, Christine Marie Ladd-Acosta, Michael Reich, Eva Latulippe, Jill P. Mesirov, Tomaso Poggio, William Gerald, Massimo Loda, Eric S. Lander, Todd R. Golub

Research output: Contribution to journalArticle

Abstract

The optimal treatment of patients with cancer depends on establishing accurate diagnoses by using a complex combination of clinical and histopathological data. In some instances, this task is difficult or impossible because of atypical clinical presentation or histopathology. To determine whether the diagnosis of multiple common adult malignancies could be achieved purely by molecular classification, we subjected 218 tumor samples, spanning 14 common tumor types, and 90 normal tissue samples to oligonucleotide microarray gene expression analysis. The expression levels of 16,063 genes and expressed sequence tags were used to evaluate the accuracy of a multiclass classifier based on a support vector machine algorithm. Overall classification accuracy was 78%, far exceeding the accuracy of random classification (9%). Poorly differentiated cancers resulted in low-confidence predictions and could not be accurately classified according to their tissue of origin, indicating that they are molecularly distinct entities with dramatically different gene expression patterns compared with their well differentiated counterparts. Taken together, these results demonstrate the feasibility of accurate, multiclass molecular cancer classification and suggest a strategy for future clinical implementation of molecular cancer diagnostics.

Original languageEnglish (US)
Pages (from-to)15149-15154
Number of pages6
JournalProceedings of the National Academy of Sciences of the United States of America
Volume98
Issue number26
DOIs
StatePublished - Dec 18 2001
Externally publishedYes

Fingerprint

Transcriptome
Neoplasms
Gene Expression
Molecular Pathology
Expressed Sequence Tags
Oligonucleotide Array Sequence Analysis
Genes

ASJC Scopus subject areas

  • Genetics
  • General

Cite this

Ramaswamy, S., Tamayo, P., Rifkin, R., Mukherjee, S., Yeang, C. H., Angelo, M., ... Golub, T. R. (2001). Multiclass cancer diagnosis using tumor gene expression signatures. Proceedings of the National Academy of Sciences of the United States of America, 98(26), 15149-15154. https://doi.org/10.1073/pnas.211566398

Multiclass cancer diagnosis using tumor gene expression signatures. / Ramaswamy, Sridhar; Tamayo, Pablo; Rifkin, Ryan; Mukherjee, Sayan; Yeang, Chen Hsiang; Angelo, Michael; Ladd-Acosta, Christine Marie; Reich, Michael; Latulippe, Eva; Mesirov, Jill P.; Poggio, Tomaso; Gerald, William; Loda, Massimo; Lander, Eric S.; Golub, Todd R.

In: Proceedings of the National Academy of Sciences of the United States of America, Vol. 98, No. 26, 18.12.2001, p. 15149-15154.

Research output: Contribution to journalArticle

Ramaswamy, S, Tamayo, P, Rifkin, R, Mukherjee, S, Yeang, CH, Angelo, M, Ladd-Acosta, CM, Reich, M, Latulippe, E, Mesirov, JP, Poggio, T, Gerald, W, Loda, M, Lander, ES & Golub, TR 2001, 'Multiclass cancer diagnosis using tumor gene expression signatures', Proceedings of the National Academy of Sciences of the United States of America, vol. 98, no. 26, pp. 15149-15154. https://doi.org/10.1073/pnas.211566398
Ramaswamy, Sridhar ; Tamayo, Pablo ; Rifkin, Ryan ; Mukherjee, Sayan ; Yeang, Chen Hsiang ; Angelo, Michael ; Ladd-Acosta, Christine Marie ; Reich, Michael ; Latulippe, Eva ; Mesirov, Jill P. ; Poggio, Tomaso ; Gerald, William ; Loda, Massimo ; Lander, Eric S. ; Golub, Todd R. / Multiclass cancer diagnosis using tumor gene expression signatures. In: Proceedings of the National Academy of Sciences of the United States of America. 2001 ; Vol. 98, No. 26. pp. 15149-15154.
@article{ea6522ffe8c942238fb985347c245a25,
title = "Multiclass cancer diagnosis using tumor gene expression signatures",
abstract = "The optimal treatment of patients with cancer depends on establishing accurate diagnoses by using a complex combination of clinical and histopathological data. In some instances, this task is difficult or impossible because of atypical clinical presentation or histopathology. To determine whether the diagnosis of multiple common adult malignancies could be achieved purely by molecular classification, we subjected 218 tumor samples, spanning 14 common tumor types, and 90 normal tissue samples to oligonucleotide microarray gene expression analysis. The expression levels of 16,063 genes and expressed sequence tags were used to evaluate the accuracy of a multiclass classifier based on a support vector machine algorithm. Overall classification accuracy was 78{\%}, far exceeding the accuracy of random classification (9{\%}). Poorly differentiated cancers resulted in low-confidence predictions and could not be accurately classified according to their tissue of origin, indicating that they are molecularly distinct entities with dramatically different gene expression patterns compared with their well differentiated counterparts. Taken together, these results demonstrate the feasibility of accurate, multiclass molecular cancer classification and suggest a strategy for future clinical implementation of molecular cancer diagnostics.",
author = "Sridhar Ramaswamy and Pablo Tamayo and Ryan Rifkin and Sayan Mukherjee and Yeang, {Chen Hsiang} and Michael Angelo and Ladd-Acosta, {Christine Marie} and Michael Reich and Eva Latulippe and Mesirov, {Jill P.} and Tomaso Poggio and William Gerald and Massimo Loda and Lander, {Eric S.} and Golub, {Todd R.}",
year = "2001",
month = "12",
day = "18",
doi = "10.1073/pnas.211566398",
language = "English (US)",
volume = "98",
pages = "15149--15154",
journal = "Proceedings of the National Academy of Sciences of the United States of America",
issn = "0027-8424",
number = "26",

}

TY - JOUR

T1 - Multiclass cancer diagnosis using tumor gene expression signatures

AU - Ramaswamy, Sridhar

AU - Tamayo, Pablo

AU - Rifkin, Ryan

AU - Mukherjee, Sayan

AU - Yeang, Chen Hsiang

AU - Angelo, Michael

AU - Ladd-Acosta, Christine Marie

AU - Reich, Michael

AU - Latulippe, Eva

AU - Mesirov, Jill P.

AU - Poggio, Tomaso

AU - Gerald, William

AU - Loda, Massimo

AU - Lander, Eric S.

AU - Golub, Todd R.

PY - 2001/12/18

Y1 - 2001/12/18

N2 - The optimal treatment of patients with cancer depends on establishing accurate diagnoses by using a complex combination of clinical and histopathological data. In some instances, this task is difficult or impossible because of atypical clinical presentation or histopathology. To determine whether the diagnosis of multiple common adult malignancies could be achieved purely by molecular classification, we subjected 218 tumor samples, spanning 14 common tumor types, and 90 normal tissue samples to oligonucleotide microarray gene expression analysis. The expression levels of 16,063 genes and expressed sequence tags were used to evaluate the accuracy of a multiclass classifier based on a support vector machine algorithm. Overall classification accuracy was 78%, far exceeding the accuracy of random classification (9%). Poorly differentiated cancers resulted in low-confidence predictions and could not be accurately classified according to their tissue of origin, indicating that they are molecularly distinct entities with dramatically different gene expression patterns compared with their well differentiated counterparts. Taken together, these results demonstrate the feasibility of accurate, multiclass molecular cancer classification and suggest a strategy for future clinical implementation of molecular cancer diagnostics.

AB - The optimal treatment of patients with cancer depends on establishing accurate diagnoses by using a complex combination of clinical and histopathological data. In some instances, this task is difficult or impossible because of atypical clinical presentation or histopathology. To determine whether the diagnosis of multiple common adult malignancies could be achieved purely by molecular classification, we subjected 218 tumor samples, spanning 14 common tumor types, and 90 normal tissue samples to oligonucleotide microarray gene expression analysis. The expression levels of 16,063 genes and expressed sequence tags were used to evaluate the accuracy of a multiclass classifier based on a support vector machine algorithm. Overall classification accuracy was 78%, far exceeding the accuracy of random classification (9%). Poorly differentiated cancers resulted in low-confidence predictions and could not be accurately classified according to their tissue of origin, indicating that they are molecularly distinct entities with dramatically different gene expression patterns compared with their well differentiated counterparts. Taken together, these results demonstrate the feasibility of accurate, multiclass molecular cancer classification and suggest a strategy for future clinical implementation of molecular cancer diagnostics.

UR - http://www.scopus.com/inward/record.url?scp=0347201147&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0347201147&partnerID=8YFLogxK

U2 - 10.1073/pnas.211566398

DO - 10.1073/pnas.211566398

M3 - Article

VL - 98

SP - 15149

EP - 15154

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 - 26

ER -