Home > Research > Publications & Outputs > Measuring similarity and improving stability in...
View graph of relations

Measuring similarity and improving stability in biomarker identification methods applied to Fourier-transform infrared (FTIR) spectroscopy

Research output: Contribution to journalJournal articlepeer-review

Published

Standard

Measuring similarity and improving stability in biomarker identification methods applied to Fourier-transform infrared (FTIR) spectroscopy. / Trevisan, Julio; Park, Juhyun; Angelov, Plamen; Ahmadzai, Abdullah; Gajjar, Ketan; Scott, Andrew D.; Carmichael, Paul L.; Martin, Frank.

In: Journal of Biophotonics, Vol. 7, No. 3-4, 04.2014, p. 254-265.

Research output: Contribution to journalJournal articlepeer-review

Harvard

APA

Vancouver

Author

Trevisan, Julio ; Park, Juhyun ; Angelov, Plamen ; Ahmadzai, Abdullah ; Gajjar, Ketan ; Scott, Andrew D. ; Carmichael, Paul L. ; Martin, Frank. / Measuring similarity and improving stability in biomarker identification methods applied to Fourier-transform infrared (FTIR) spectroscopy. In: Journal of Biophotonics. 2014 ; Vol. 7, No. 3-4. pp. 254-265.

Bibtex

@article{a41806cfdfa34799992d4a6211ad4e5d,
title = "Measuring similarity and improving stability in biomarker identification methods applied to Fourier-transform infrared (FTIR) spectroscopy",
abstract = "FTIR spectroscopy is a powerful diagnostic tool that can also derive biochemical signatures of a wide range of cellular materials, such as cytology, histology, live cells, and biofluids. However, while classification is a well-established subject, biomarker identification lacks standards and validation of its methods. Validation of biomarker identification methods is difficult because, unlike classification, there is usually no reference biomarker against which to test the biomarkers extracted by a method. Inthis paper, we propose a framework to assess and improve the stability of biomarkers derived by a method, and to compare biomarkers derived by different method set-ups and between different methods by means of a proposed “biomarkers similarity index”.",
keywords = "biomarkers, classification , data mining , Fourier-transform infrared spectroscopy , statistical data analysis , validation studies , biospectroscopy , computational framework",
author = "Julio Trevisan and Juhyun Park and Plamen Angelov and Abdullah Ahmadzai and Ketan Gajjar and Scott, {Andrew D.} and Carmichael, {Paul L.} and Frank Martin",
year = "2014",
month = apr,
doi = "10.1002/jbio.201300190",
language = "English",
volume = "7",
pages = "254--265",
journal = "Journal of Biophotonics",
issn = "1864-063X",
publisher = "Wiley-VCH Verlag",
number = "3-4",

}

RIS

TY - JOUR

T1 - Measuring similarity and improving stability in biomarker identification methods applied to Fourier-transform infrared (FTIR) spectroscopy

AU - Trevisan, Julio

AU - Park, Juhyun

AU - Angelov, Plamen

AU - Ahmadzai, Abdullah

AU - Gajjar, Ketan

AU - Scott, Andrew D.

AU - Carmichael, Paul L.

AU - Martin, Frank

PY - 2014/4

Y1 - 2014/4

N2 - FTIR spectroscopy is a powerful diagnostic tool that can also derive biochemical signatures of a wide range of cellular materials, such as cytology, histology, live cells, and biofluids. However, while classification is a well-established subject, biomarker identification lacks standards and validation of its methods. Validation of biomarker identification methods is difficult because, unlike classification, there is usually no reference biomarker against which to test the biomarkers extracted by a method. Inthis paper, we propose a framework to assess and improve the stability of biomarkers derived by a method, and to compare biomarkers derived by different method set-ups and between different methods by means of a proposed “biomarkers similarity index”.

AB - FTIR spectroscopy is a powerful diagnostic tool that can also derive biochemical signatures of a wide range of cellular materials, such as cytology, histology, live cells, and biofluids. However, while classification is a well-established subject, biomarker identification lacks standards and validation of its methods. Validation of biomarker identification methods is difficult because, unlike classification, there is usually no reference biomarker against which to test the biomarkers extracted by a method. Inthis paper, we propose a framework to assess and improve the stability of biomarkers derived by a method, and to compare biomarkers derived by different method set-ups and between different methods by means of a proposed “biomarkers similarity index”.

KW - biomarkers

KW - classification

KW - data mining

KW - Fourier-transform infrared spectroscopy

KW - statistical data analysis

KW - validation studies

KW - biospectroscopy

KW - computational framework

U2 - 10.1002/jbio.201300190

DO - 10.1002/jbio.201300190

M3 - Journal article

VL - 7

SP - 254

EP - 265

JO - Journal of Biophotonics

JF - Journal of Biophotonics

SN - 1864-063X

IS - 3-4

ER -