Localized data fusion for kernel k-means clustering with application to cancer biology

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

40 Citations (Scopus)

Abstract

In many modern applications from, for example, bioinformatics and computer vision, samples have multiple feature representations coming from different data sources. Multiview learning algorithms try to exploit all these available information to obtain a better learner in such scenarios. In this paper, we propose a novel multiple kernel learning algorithm that extends kernel k-means clustering to the multiview setting, which combines kernels calculated on the views in a localized way to better capture sample-specific characteristics of the data. We demonstrate the better performance of our localized data fusion approach on a human colon and rectal cancer data set by clustering patients. Our method finds more relevant prognostic patient groups than global data fusion methods when we evaluate the results with respect to three commonly used clinical biomarkers.

Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems
PublisherNeural information processing systems foundation
Pages1305-1313
Number of pages9
Volume2
EditionJanuary
StatePublished - 2014
Event28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014 - Montreal, Canada
Duration: Dec 8 2014Dec 13 2014

Other

Other28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014
CountryCanada
CityMontreal
Period12/8/1412/13/14

Fingerprint

Data fusion
Learning algorithms
Biomarkers
Bioinformatics
Computer vision

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Gonen, M., & Margolin, A. (2014). Localized data fusion for kernel k-means clustering with application to cancer biology. In Advances in Neural Information Processing Systems (January ed., Vol. 2, pp. 1305-1313). Neural information processing systems foundation.

Localized data fusion for kernel k-means clustering with application to cancer biology. / Gonen, Mehmet; Margolin, Adam.

Advances in Neural Information Processing Systems. Vol. 2 January. ed. Neural information processing systems foundation, 2014. p. 1305-1313.

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

Gonen, M & Margolin, A 2014, Localized data fusion for kernel k-means clustering with application to cancer biology. in Advances in Neural Information Processing Systems. January edn, vol. 2, Neural information processing systems foundation, pp. 1305-1313, 28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014, Montreal, Canada, 12/8/14.
Gonen M, Margolin A. Localized data fusion for kernel k-means clustering with application to cancer biology. In Advances in Neural Information Processing Systems. January ed. Vol. 2. Neural information processing systems foundation. 2014. p. 1305-1313
Gonen, Mehmet ; Margolin, Adam. / Localized data fusion for kernel k-means clustering with application to cancer biology. Advances in Neural Information Processing Systems. Vol. 2 January. ed. Neural information processing systems foundation, 2014. pp. 1305-1313
@inproceedings{193aad004f904cae92d6f2b2b938f39f,
title = "Localized data fusion for kernel k-means clustering with application to cancer biology",
abstract = "In many modern applications from, for example, bioinformatics and computer vision, samples have multiple feature representations coming from different data sources. Multiview learning algorithms try to exploit all these available information to obtain a better learner in such scenarios. In this paper, we propose a novel multiple kernel learning algorithm that extends kernel k-means clustering to the multiview setting, which combines kernels calculated on the views in a localized way to better capture sample-specific characteristics of the data. We demonstrate the better performance of our localized data fusion approach on a human colon and rectal cancer data set by clustering patients. Our method finds more relevant prognostic patient groups than global data fusion methods when we evaluate the results with respect to three commonly used clinical biomarkers.",
author = "Mehmet Gonen and Adam Margolin",
year = "2014",
language = "English (US)",
volume = "2",
pages = "1305--1313",
booktitle = "Advances in Neural Information Processing Systems",
publisher = "Neural information processing systems foundation",
edition = "January",

}

TY - GEN

T1 - Localized data fusion for kernel k-means clustering with application to cancer biology

AU - Gonen, Mehmet

AU - Margolin, Adam

PY - 2014

Y1 - 2014

N2 - In many modern applications from, for example, bioinformatics and computer vision, samples have multiple feature representations coming from different data sources. Multiview learning algorithms try to exploit all these available information to obtain a better learner in such scenarios. In this paper, we propose a novel multiple kernel learning algorithm that extends kernel k-means clustering to the multiview setting, which combines kernels calculated on the views in a localized way to better capture sample-specific characteristics of the data. We demonstrate the better performance of our localized data fusion approach on a human colon and rectal cancer data set by clustering patients. Our method finds more relevant prognostic patient groups than global data fusion methods when we evaluate the results with respect to three commonly used clinical biomarkers.

AB - In many modern applications from, for example, bioinformatics and computer vision, samples have multiple feature representations coming from different data sources. Multiview learning algorithms try to exploit all these available information to obtain a better learner in such scenarios. In this paper, we propose a novel multiple kernel learning algorithm that extends kernel k-means clustering to the multiview setting, which combines kernels calculated on the views in a localized way to better capture sample-specific characteristics of the data. We demonstrate the better performance of our localized data fusion approach on a human colon and rectal cancer data set by clustering patients. Our method finds more relevant prognostic patient groups than global data fusion methods when we evaluate the results with respect to three commonly used clinical biomarkers.

UR - http://www.scopus.com/inward/record.url?scp=84937844255&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84937844255&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2

SP - 1305

EP - 1313

BT - Advances in Neural Information Processing Systems

PB - Neural information processing systems foundation

ER -