Nonlinear Dimensionality Reduction by Minimum Curvilinearity for Unsupervised Discovery of Patterns in Multidimensional Proteomic Data

Massimo Alessio, Carlo V ittorio Cannistraci

Research output: Contribution to journalArticle

Abstract

Dimensionality reduction is largely and successfully employed for the visualization and discrimination of patterns, hidden in multidimensional proteomics datasets. Principal component analysis (PCA), which is the preferred approach for linear dimensionality reduction, may present serious limitations, in particular when samples are nonlinearly related, as often occurs in several two-dimensional electrophoresis (2-DE) datasets. An aggravating factor is that PCA robustness is impaired when the number of samples is small in comparison to the number of proteomic features, and this is the case in high-dimensional proteomic datasets, including 2-DE ones. Here, we describe the use of a nonlinear unsupervised learning machine for dimensionality reduction called minimum curvilinear embedding (MCE) that was successfully applied to different biological samples datasets. In particular, we provide an example where we directly compare MCE performance with that of PCA in disclosing neuropathic pain patterns, hidden in a multidimensional proteomic dataset.

Original languageEnglish
Pages (from-to)289-298
Number of pages10
JournalMethods in molecular biology (Clifton, N.J.)
Volume1384
DOIs
Publication statusPublished - 2016

Fingerprint

Proteomics
Principal Component Analysis
Neuralgia
Electrophoresis
Datasets

Keywords

  • High-dimensional data
  • Minimum curvilinear embedding
  • Minimum curvilinearity
  • Multivariate analysis
  • Nonlinear dimensionality reduction
  • Pattern recognition
  • Principal component analysis
  • Two-dimensional gel electrophoresis
  • Unsupervised machine learning
  • Visualization

ASJC Scopus subject areas

  • Medicine(all)
  • Molecular Biology
  • Genetics

Cite this

@article{5aadf06f65434202b98ea9785c99ad57,
title = "Nonlinear Dimensionality Reduction by Minimum Curvilinearity for Unsupervised Discovery of Patterns in Multidimensional Proteomic Data",
abstract = "Dimensionality reduction is largely and successfully employed for the visualization and discrimination of patterns, hidden in multidimensional proteomics datasets. Principal component analysis (PCA), which is the preferred approach for linear dimensionality reduction, may present serious limitations, in particular when samples are nonlinearly related, as often occurs in several two-dimensional electrophoresis (2-DE) datasets. An aggravating factor is that PCA robustness is impaired when the number of samples is small in comparison to the number of proteomic features, and this is the case in high-dimensional proteomic datasets, including 2-DE ones. Here, we describe the use of a nonlinear unsupervised learning machine for dimensionality reduction called minimum curvilinear embedding (MCE) that was successfully applied to different biological samples datasets. In particular, we provide an example where we directly compare MCE performance with that of PCA in disclosing neuropathic pain patterns, hidden in a multidimensional proteomic dataset.",
keywords = "High-dimensional data, Minimum curvilinear embedding, Minimum curvilinearity, Multivariate analysis, Nonlinear dimensionality reduction, Pattern recognition, Principal component analysis, Two-dimensional gel electrophoresis, Unsupervised machine learning, Visualization",
author = "Massimo Alessio and Cannistraci, {Carlo V ittorio}",
year = "2016",
doi = "10.1007/978-1-4939-3255-9_16",
language = "English",
volume = "1384",
pages = "289--298",
journal = "Methods in Molecular Biology",
issn = "1064-3745",
publisher = "Humana Press",

}

TY - JOUR

T1 - Nonlinear Dimensionality Reduction by Minimum Curvilinearity for Unsupervised Discovery of Patterns in Multidimensional Proteomic Data

AU - Alessio, Massimo

AU - Cannistraci, Carlo V ittorio

PY - 2016

Y1 - 2016

N2 - Dimensionality reduction is largely and successfully employed for the visualization and discrimination of patterns, hidden in multidimensional proteomics datasets. Principal component analysis (PCA), which is the preferred approach for linear dimensionality reduction, may present serious limitations, in particular when samples are nonlinearly related, as often occurs in several two-dimensional electrophoresis (2-DE) datasets. An aggravating factor is that PCA robustness is impaired when the number of samples is small in comparison to the number of proteomic features, and this is the case in high-dimensional proteomic datasets, including 2-DE ones. Here, we describe the use of a nonlinear unsupervised learning machine for dimensionality reduction called minimum curvilinear embedding (MCE) that was successfully applied to different biological samples datasets. In particular, we provide an example where we directly compare MCE performance with that of PCA in disclosing neuropathic pain patterns, hidden in a multidimensional proteomic dataset.

AB - Dimensionality reduction is largely and successfully employed for the visualization and discrimination of patterns, hidden in multidimensional proteomics datasets. Principal component analysis (PCA), which is the preferred approach for linear dimensionality reduction, may present serious limitations, in particular when samples are nonlinearly related, as often occurs in several two-dimensional electrophoresis (2-DE) datasets. An aggravating factor is that PCA robustness is impaired when the number of samples is small in comparison to the number of proteomic features, and this is the case in high-dimensional proteomic datasets, including 2-DE ones. Here, we describe the use of a nonlinear unsupervised learning machine for dimensionality reduction called minimum curvilinear embedding (MCE) that was successfully applied to different biological samples datasets. In particular, we provide an example where we directly compare MCE performance with that of PCA in disclosing neuropathic pain patterns, hidden in a multidimensional proteomic dataset.

KW - High-dimensional data

KW - Minimum curvilinear embedding

KW - Minimum curvilinearity

KW - Multivariate analysis

KW - Nonlinear dimensionality reduction

KW - Pattern recognition

KW - Principal component analysis

KW - Two-dimensional gel electrophoresis

KW - Unsupervised machine learning

KW - Visualization

UR - http://www.scopus.com/inward/record.url?scp=84984575683&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84984575683&partnerID=8YFLogxK

U2 - 10.1007/978-1-4939-3255-9_16

DO - 10.1007/978-1-4939-3255-9_16

M3 - Article

VL - 1384

SP - 289

EP - 298

JO - Methods in Molecular Biology

JF - Methods in Molecular Biology

SN - 1064-3745

ER -