Projection to latent structures as a strategy for peptides microarray data analysis

D. S. Anisimov, S. V. Podlesnykh, E. A. Kolosova, D. N. Shcherbakov, V. D. Petrova, Stephen Johnston, A. F. Lazarev, N. N. Oskorbin, Andrei Chapoval, M. A. Ryazanov

Research output: Contribution to journalArticle

Abstract

Currently various microarrays platforms containing nucleotides, proteins, peptides, glycans and other molecules are used in biomedical research. Number and density of immobilized molecules on microarrays are constantly increasing. Microarray data handling requires optimization of methods for their analysis. Peptide microarrays data analysis has certain characteristics that require non-conventional statistical methods. In this paper we present the results of antibody repertoire analysis in breast cancer patients sera utilizing microchips containing 330,000 peptides. We investigated methods for space dimension reduction such as projective methods and methods for selection of informative features. We have shown that method of projection to latent structures can detect an effective data dimension, reduce overfitting of the model and increase the quality of object recognition. Accuracy of the experimental results was assessed with the ROC-curve; the best quality was achieved with three latent structures without normalization and reduction of total numbers of peptides.

Original languageEnglish (US)
Pages (from-to)435-445
Number of pages11
JournalMathematical Biology and Bioinformatics
Volume12
Issue number2
DOIs
StatePublished - Jan 1 2017

Fingerprint

Microarray Data Analysis
Microarrays
Peptides
Projection
Microarray
Molecules
Data handling
Object recognition
Nucleotides
Data Handling
Antibodies
Overfitting
Receiver Operating Characteristic Curve
Object Recognition
Dimension Reduction
Statistical methods
Microarray Data
Breast Cancer
Antibody
Statistical method

Keywords

  • Clustering
  • Latent variables
  • Method of projection to latent structures
  • Microarrays
  • Normalization
  • Peptides
  • ROC

ASJC Scopus subject areas

  • Biomedical Engineering
  • Applied Mathematics

Cite this

Anisimov, D. S., Podlesnykh, S. V., Kolosova, E. A., Shcherbakov, D. N., Petrova, V. D., Johnston, S., ... Ryazanov, M. A. (2017). Projection to latent structures as a strategy for peptides microarray data analysis. Mathematical Biology and Bioinformatics, 12(2), 435-445. https://doi.org/10.17537/2017.12.435

Projection to latent structures as a strategy for peptides microarray data analysis. / Anisimov, D. S.; Podlesnykh, S. V.; Kolosova, E. A.; Shcherbakov, D. N.; Petrova, V. D.; Johnston, Stephen; Lazarev, A. F.; Oskorbin, N. N.; Chapoval, Andrei; Ryazanov, M. A.

In: Mathematical Biology and Bioinformatics, Vol. 12, No. 2, 01.01.2017, p. 435-445.

Research output: Contribution to journalArticle

Anisimov, DS, Podlesnykh, SV, Kolosova, EA, Shcherbakov, DN, Petrova, VD, Johnston, S, Lazarev, AF, Oskorbin, NN, Chapoval, A & Ryazanov, MA 2017, 'Projection to latent structures as a strategy for peptides microarray data analysis', Mathematical Biology and Bioinformatics, vol. 12, no. 2, pp. 435-445. https://doi.org/10.17537/2017.12.435
Anisimov, D. S. ; Podlesnykh, S. V. ; Kolosova, E. A. ; Shcherbakov, D. N. ; Petrova, V. D. ; Johnston, Stephen ; Lazarev, A. F. ; Oskorbin, N. N. ; Chapoval, Andrei ; Ryazanov, M. A. / Projection to latent structures as a strategy for peptides microarray data analysis. In: Mathematical Biology and Bioinformatics. 2017 ; Vol. 12, No. 2. pp. 435-445.
@article{ed6f79bb5eaf4ae9a3b6a3f35521eec8,
title = "Projection to latent structures as a strategy for peptides microarray data analysis",
abstract = "Currently various microarrays platforms containing nucleotides, proteins, peptides, glycans and other molecules are used in biomedical research. Number and density of immobilized molecules on microarrays are constantly increasing. Microarray data handling requires optimization of methods for their analysis. Peptide microarrays data analysis has certain characteristics that require non-conventional statistical methods. In this paper we present the results of antibody repertoire analysis in breast cancer patients sera utilizing microchips containing 330,000 peptides. We investigated methods for space dimension reduction such as projective methods and methods for selection of informative features. We have shown that method of projection to latent structures can detect an effective data dimension, reduce overfitting of the model and increase the quality of object recognition. Accuracy of the experimental results was assessed with the ROC-curve; the best quality was achieved with three latent structures without normalization and reduction of total numbers of peptides.",
keywords = "Clustering, Latent variables, Method of projection to latent structures, Microarrays, Normalization, Peptides, ROC",
author = "Anisimov, {D. S.} and Podlesnykh, {S. V.} and Kolosova, {E. A.} and Shcherbakov, {D. N.} and Petrova, {V. D.} and Stephen Johnston and Lazarev, {A. F.} and Oskorbin, {N. N.} and Andrei Chapoval and Ryazanov, {M. A.}",
year = "2017",
month = "1",
day = "1",
doi = "10.17537/2017.12.435",
language = "English (US)",
volume = "12",
pages = "435--445",
journal = "Mathematical Biology and Bioinformatics",
issn = "1994-6538",
publisher = "Institute of Mathematical Problems of Biology",
number = "2",

}

TY - JOUR

T1 - Projection to latent structures as a strategy for peptides microarray data analysis

AU - Anisimov, D. S.

AU - Podlesnykh, S. V.

AU - Kolosova, E. A.

AU - Shcherbakov, D. N.

AU - Petrova, V. D.

AU - Johnston, Stephen

AU - Lazarev, A. F.

AU - Oskorbin, N. N.

AU - Chapoval, Andrei

AU - Ryazanov, M. A.

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Currently various microarrays platforms containing nucleotides, proteins, peptides, glycans and other molecules are used in biomedical research. Number and density of immobilized molecules on microarrays are constantly increasing. Microarray data handling requires optimization of methods for their analysis. Peptide microarrays data analysis has certain characteristics that require non-conventional statistical methods. In this paper we present the results of antibody repertoire analysis in breast cancer patients sera utilizing microchips containing 330,000 peptides. We investigated methods for space dimension reduction such as projective methods and methods for selection of informative features. We have shown that method of projection to latent structures can detect an effective data dimension, reduce overfitting of the model and increase the quality of object recognition. Accuracy of the experimental results was assessed with the ROC-curve; the best quality was achieved with three latent structures without normalization and reduction of total numbers of peptides.

AB - Currently various microarrays platforms containing nucleotides, proteins, peptides, glycans and other molecules are used in biomedical research. Number and density of immobilized molecules on microarrays are constantly increasing. Microarray data handling requires optimization of methods for their analysis. Peptide microarrays data analysis has certain characteristics that require non-conventional statistical methods. In this paper we present the results of antibody repertoire analysis in breast cancer patients sera utilizing microchips containing 330,000 peptides. We investigated methods for space dimension reduction such as projective methods and methods for selection of informative features. We have shown that method of projection to latent structures can detect an effective data dimension, reduce overfitting of the model and increase the quality of object recognition. Accuracy of the experimental results was assessed with the ROC-curve; the best quality was achieved with three latent structures without normalization and reduction of total numbers of peptides.

KW - Clustering

KW - Latent variables

KW - Method of projection to latent structures

KW - Microarrays

KW - Normalization

KW - Peptides

KW - ROC

UR - http://www.scopus.com/inward/record.url?scp=85050873050&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050873050&partnerID=8YFLogxK

U2 - 10.17537/2017.12.435

DO - 10.17537/2017.12.435

M3 - Article

AN - SCOPUS:85050873050

VL - 12

SP - 435

EP - 445

JO - Mathematical Biology and Bioinformatics

JF - Mathematical Biology and Bioinformatics

SN - 1994-6538

IS - 2

ER -