Predicting hepatitis B virus-positive metastatic hepatocellular carcinomas using gene expression profiling and supervised machine learning

Qing Hai Ye, Lun Xiu Qin, Marshonna Forgues, Ping He, Jin Woo Kim, Amy C. Peng, Richard Simon, Yan Li, Ana I. Robles, Yidong Chen, Zeng Chen Ma, Zhi Quan Wu, Sheng Long Ye, Yin Kun Liu, Zhao You Tang, Xin Wei Wang

Research output: Contribution to journalArticle

643 Citations (Scopus)

Abstract

Hepatocellular carcinoma (HCC) is one of the most common and aggressive human malignancies. Its high mortality rate is mainly a result of intra-hepatic metastases. We analyzed the expression profiles of HCC samples without or with intra-hepatic metastases. Using a supervised machine-learning algorithm, we generated for the first time a molecular signature that can classify metastatic HCC patients and identified genes that were relevant to metastasis and patient survival. We found that the gene expression signature of primary HCCs with accompanying metastasis was very similar to that of their corresponding metastases, implying that genes favoring metastasis progression were initiated in the primary tumors. Osteopontin, which was identified as a lead gene in the signature, was over-expressed in metastatic HCC; an osteopontin-specific antibody effectively blocked HCC cell invasion in vitro and inhibited pulmonary metastasis of HCC cells in nude mice. Thus, osteopontin acts as both a diagnostic marker and a potential therapeutic target for metastatic HCC.

Original languageEnglish (US)
Pages (from-to)416-423
Number of pages8
JournalNature Medicine
Volume9
Issue number4
DOIs
StatePublished - Apr 1 2003
Externally publishedYes

Fingerprint

Osteopontin
Gene Expression Profiling
Viruses
Hepatitis B virus
Gene expression
Learning systems
Hepatocellular Carcinoma
Genes
Neoplasm Metastasis
Learning algorithms
Tumors
Antibodies
Liver
Supervised Machine Learning
Transcriptome
Nude Mice
Neoplasms
Lung
Survival
Mortality

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Medicine(all)

Cite this

Predicting hepatitis B virus-positive metastatic hepatocellular carcinomas using gene expression profiling and supervised machine learning. / Ye, Qing Hai; Qin, Lun Xiu; Forgues, Marshonna; He, Ping; Kim, Jin Woo; Peng, Amy C.; Simon, Richard; Li, Yan; Robles, Ana I.; Chen, Yidong; Ma, Zeng Chen; Wu, Zhi Quan; Ye, Sheng Long; Liu, Yin Kun; Tang, Zhao You; Wang, Xin Wei.

In: Nature Medicine, Vol. 9, No. 4, 01.04.2003, p. 416-423.

Research output: Contribution to journalArticle

Ye, QH, Qin, LX, Forgues, M, He, P, Kim, JW, Peng, AC, Simon, R, Li, Y, Robles, AI, Chen, Y, Ma, ZC, Wu, ZQ, Ye, SL, Liu, YK, Tang, ZY & Wang, XW 2003, 'Predicting hepatitis B virus-positive metastatic hepatocellular carcinomas using gene expression profiling and supervised machine learning', Nature Medicine, vol. 9, no. 4, pp. 416-423. https://doi.org/10.1038/nm843
Ye, Qing Hai ; Qin, Lun Xiu ; Forgues, Marshonna ; He, Ping ; Kim, Jin Woo ; Peng, Amy C. ; Simon, Richard ; Li, Yan ; Robles, Ana I. ; Chen, Yidong ; Ma, Zeng Chen ; Wu, Zhi Quan ; Ye, Sheng Long ; Liu, Yin Kun ; Tang, Zhao You ; Wang, Xin Wei. / Predicting hepatitis B virus-positive metastatic hepatocellular carcinomas using gene expression profiling and supervised machine learning. In: Nature Medicine. 2003 ; Vol. 9, No. 4. pp. 416-423.
@article{527f70833be14baaa1d5dfdb9c859405,
title = "Predicting hepatitis B virus-positive metastatic hepatocellular carcinomas using gene expression profiling and supervised machine learning",
abstract = "Hepatocellular carcinoma (HCC) is one of the most common and aggressive human malignancies. Its high mortality rate is mainly a result of intra-hepatic metastases. We analyzed the expression profiles of HCC samples without or with intra-hepatic metastases. Using a supervised machine-learning algorithm, we generated for the first time a molecular signature that can classify metastatic HCC patients and identified genes that were relevant to metastasis and patient survival. We found that the gene expression signature of primary HCCs with accompanying metastasis was very similar to that of their corresponding metastases, implying that genes favoring metastasis progression were initiated in the primary tumors. Osteopontin, which was identified as a lead gene in the signature, was over-expressed in metastatic HCC; an osteopontin-specific antibody effectively blocked HCC cell invasion in vitro and inhibited pulmonary metastasis of HCC cells in nude mice. Thus, osteopontin acts as both a diagnostic marker and a potential therapeutic target for metastatic HCC.",
author = "Ye, {Qing Hai} and Qin, {Lun Xiu} and Marshonna Forgues and Ping He and Kim, {Jin Woo} and Peng, {Amy C.} and Richard Simon and Yan Li and Robles, {Ana I.} and Yidong Chen and Ma, {Zeng Chen} and Wu, {Zhi Quan} and Ye, {Sheng Long} and Liu, {Yin Kun} and Tang, {Zhao You} and Wang, {Xin Wei}",
year = "2003",
month = "4",
day = "1",
doi = "10.1038/nm843",
language = "English (US)",
volume = "9",
pages = "416--423",
journal = "Nature Medicine",
issn = "1078-8956",
publisher = "Nature Publishing Group",
number = "4",

}

TY - JOUR

T1 - Predicting hepatitis B virus-positive metastatic hepatocellular carcinomas using gene expression profiling and supervised machine learning

AU - Ye, Qing Hai

AU - Qin, Lun Xiu

AU - Forgues, Marshonna

AU - He, Ping

AU - Kim, Jin Woo

AU - Peng, Amy C.

AU - Simon, Richard

AU - Li, Yan

AU - Robles, Ana I.

AU - Chen, Yidong

AU - Ma, Zeng Chen

AU - Wu, Zhi Quan

AU - Ye, Sheng Long

AU - Liu, Yin Kun

AU - Tang, Zhao You

AU - Wang, Xin Wei

PY - 2003/4/1

Y1 - 2003/4/1

N2 - Hepatocellular carcinoma (HCC) is one of the most common and aggressive human malignancies. Its high mortality rate is mainly a result of intra-hepatic metastases. We analyzed the expression profiles of HCC samples without or with intra-hepatic metastases. Using a supervised machine-learning algorithm, we generated for the first time a molecular signature that can classify metastatic HCC patients and identified genes that were relevant to metastasis and patient survival. We found that the gene expression signature of primary HCCs with accompanying metastasis was very similar to that of their corresponding metastases, implying that genes favoring metastasis progression were initiated in the primary tumors. Osteopontin, which was identified as a lead gene in the signature, was over-expressed in metastatic HCC; an osteopontin-specific antibody effectively blocked HCC cell invasion in vitro and inhibited pulmonary metastasis of HCC cells in nude mice. Thus, osteopontin acts as both a diagnostic marker and a potential therapeutic target for metastatic HCC.

AB - Hepatocellular carcinoma (HCC) is one of the most common and aggressive human malignancies. Its high mortality rate is mainly a result of intra-hepatic metastases. We analyzed the expression profiles of HCC samples without or with intra-hepatic metastases. Using a supervised machine-learning algorithm, we generated for the first time a molecular signature that can classify metastatic HCC patients and identified genes that were relevant to metastasis and patient survival. We found that the gene expression signature of primary HCCs with accompanying metastasis was very similar to that of their corresponding metastases, implying that genes favoring metastasis progression were initiated in the primary tumors. Osteopontin, which was identified as a lead gene in the signature, was over-expressed in metastatic HCC; an osteopontin-specific antibody effectively blocked HCC cell invasion in vitro and inhibited pulmonary metastasis of HCC cells in nude mice. Thus, osteopontin acts as both a diagnostic marker and a potential therapeutic target for metastatic HCC.

UR - http://www.scopus.com/inward/record.url?scp=0037391756&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037391756&partnerID=8YFLogxK

U2 - 10.1038/nm843

DO - 10.1038/nm843

M3 - Article

C2 - 12640447

AN - SCOPUS:0037391756

VL - 9

SP - 416

EP - 423

JO - Nature Medicine

JF - Nature Medicine

SN - 1078-8956

IS - 4

ER -