Semi-supervised classification using sparse representation for cancer recurrence prediction

Yan Cui, Xiaodong Cai, Zhong Jin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Gene expression profiles have been used to predict cancer recurrence or other clinical outcomes of cancer patients. However, clinical information of cancer patients is often incomplete, which yields many unlabeled samples that cannot be used in supervised learning. In this is paper, we develop a novel semi-supervised leaning (SSL) method that uses both labeled and unlabeled patient samples to predict cancer recurrence. Our new SSL algorithm employs a sparse representation approach where a labeled sample is represented as a combination of a small number of properly chosen unlabeled samples. Experiments with a set of gene expression data from patients with colorectal cancer(CRC) demonstrate that our SSL algorithm can improve prediction accuracy compared to other two SSL methods including TSVM and T3VM, and the traditional support vector machine.

Original languageEnglish
Title of host publicationProceedings - IEEE International Workshop on Genomic Signal Processing and Statistics
Pages102-105
Number of pages4
DOIs
StatePublished - Dec 1 2013
Event2013 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2013 - Houston, TX, United States
Duration: Nov 17 2013Nov 19 2013

Other

Other2013 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2013
CountryUnited States
CityHouston, TX
Period11/17/1311/19/13

Fingerprint

Gene expression
Recurrence
Supervised learning
Support vector machines
Neoplasms
Transcriptome
Colorectal Neoplasms
Experiments
Learning
Gene Expression

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology (miscellaneous)
  • Computational Theory and Mathematics
  • Signal Processing
  • Biomedical Engineering

Cite this

Cui, Y., Cai, X., & Jin, Z. (2013). Semi-supervised classification using sparse representation for cancer recurrence prediction. In Proceedings - IEEE International Workshop on Genomic Signal Processing and Statistics (pp. 102-105). [6735949] https://doi.org/10.1109/GENSIPS.2013.6735949

Semi-supervised classification using sparse representation for cancer recurrence prediction. / Cui, Yan; Cai, Xiaodong; Jin, Zhong.

Proceedings - IEEE International Workshop on Genomic Signal Processing and Statistics. 2013. p. 102-105 6735949.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Cui, Y, Cai, X & Jin, Z 2013, Semi-supervised classification using sparse representation for cancer recurrence prediction. in Proceedings - IEEE International Workshop on Genomic Signal Processing and Statistics., 6735949, pp. 102-105, 2013 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2013, Houston, TX, United States, 11/17/13. https://doi.org/10.1109/GENSIPS.2013.6735949
Cui Y, Cai X, Jin Z. Semi-supervised classification using sparse representation for cancer recurrence prediction. In Proceedings - IEEE International Workshop on Genomic Signal Processing and Statistics. 2013. p. 102-105. 6735949 https://doi.org/10.1109/GENSIPS.2013.6735949
Cui, Yan ; Cai, Xiaodong ; Jin, Zhong. / Semi-supervised classification using sparse representation for cancer recurrence prediction. Proceedings - IEEE International Workshop on Genomic Signal Processing and Statistics. 2013. pp. 102-105
@inproceedings{73eaed9919bf471292a0d6ad992ff9d1,
title = "Semi-supervised classification using sparse representation for cancer recurrence prediction",
abstract = "Gene expression profiles have been used to predict cancer recurrence or other clinical outcomes of cancer patients. However, clinical information of cancer patients is often incomplete, which yields many unlabeled samples that cannot be used in supervised learning. In this is paper, we develop a novel semi-supervised leaning (SSL) method that uses both labeled and unlabeled patient samples to predict cancer recurrence. Our new SSL algorithm employs a sparse representation approach where a labeled sample is represented as a combination of a small number of properly chosen unlabeled samples. Experiments with a set of gene expression data from patients with colorectal cancer(CRC) demonstrate that our SSL algorithm can improve prediction accuracy compared to other two SSL methods including TSVM and T3VM, and the traditional support vector machine.",
author = "Yan Cui and Xiaodong Cai and Zhong Jin",
year = "2013",
month = "12",
day = "1",
doi = "10.1109/GENSIPS.2013.6735949",
language = "English",
isbn = "9781479934621",
pages = "102--105",
booktitle = "Proceedings - IEEE International Workshop on Genomic Signal Processing and Statistics",

}

TY - GEN

T1 - Semi-supervised classification using sparse representation for cancer recurrence prediction

AU - Cui, Yan

AU - Cai, Xiaodong

AU - Jin, Zhong

PY - 2013/12/1

Y1 - 2013/12/1

N2 - Gene expression profiles have been used to predict cancer recurrence or other clinical outcomes of cancer patients. However, clinical information of cancer patients is often incomplete, which yields many unlabeled samples that cannot be used in supervised learning. In this is paper, we develop a novel semi-supervised leaning (SSL) method that uses both labeled and unlabeled patient samples to predict cancer recurrence. Our new SSL algorithm employs a sparse representation approach where a labeled sample is represented as a combination of a small number of properly chosen unlabeled samples. Experiments with a set of gene expression data from patients with colorectal cancer(CRC) demonstrate that our SSL algorithm can improve prediction accuracy compared to other two SSL methods including TSVM and T3VM, and the traditional support vector machine.

AB - Gene expression profiles have been used to predict cancer recurrence or other clinical outcomes of cancer patients. However, clinical information of cancer patients is often incomplete, which yields many unlabeled samples that cannot be used in supervised learning. In this is paper, we develop a novel semi-supervised leaning (SSL) method that uses both labeled and unlabeled patient samples to predict cancer recurrence. Our new SSL algorithm employs a sparse representation approach where a labeled sample is represented as a combination of a small number of properly chosen unlabeled samples. Experiments with a set of gene expression data from patients with colorectal cancer(CRC) demonstrate that our SSL algorithm can improve prediction accuracy compared to other two SSL methods including TSVM and T3VM, and the traditional support vector machine.

UR - http://www.scopus.com/inward/record.url?scp=84897724990&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897724990&partnerID=8YFLogxK

U2 - 10.1109/GENSIPS.2013.6735949

DO - 10.1109/GENSIPS.2013.6735949

M3 - Conference contribution

SN - 9781479934621

SP - 102

EP - 105

BT - Proceedings - IEEE International Workshop on Genomic Signal Processing and Statistics

ER -