Proteomic patterns for classification of ovarian cancer and CTCL serum samples utilizing peak pairs indicative of post-translational modifications

Chenwei Liu, Nancy Shea, Sally Rucker, Linda Harvey, Paul Russo, Richard Saul, Mary F. Lopez, Alvydas Mikulskis, Scott Kuzdzal, Eva Golenko, David Fishman, Eric Vonderheid, Susan Booher, Edward W. Cowen, Sam T. Hwang, Gordon R. Whiteley

Research output: Contribution to journalArticle

Abstract

Proteomic patterns as a potential diagnostic technology has been well established for several cancer conditions and other diseases. The use of machine learning techniques such as decision trees, neural networks, genetic algorithms, and other methods has been the basis for pattern determination. Cancer is known to involve signaling pathways that are regulated through PTM of proteins. These modifications are also detectable with high confidence using high-resolution MS. We generated data using a prOTOF™ mass spectrometer on two sets of patient samples: ovarian cancer and cutaneous t-cell lymphoma (CTCL) with matched normal samples for each disease. Using the knowledge of mass shifts caused by common modifications, we built models using peak pairs and compared this to a conventional technique using individual peaks. The results for each disease showed that a small number of peak pairs gave classification equal to or better than the conventional technique that used multiple individual peaks. This simple peak picking technique could be used to guide identification of important peak pairs involved in the disease process.

Original languageEnglish (US)
Pages (from-to)4045-4052
Number of pages8
JournalProteomics
Volume7
Issue number22
DOIs
StatePublished - Nov 2007

Fingerprint

Skin Neoplasms
Post Translational Protein Processing
Proteomics
Ovarian Neoplasms
Lymphoma
Serum
Pulse time modulation
Decision Trees
Mass spectrometers
Decision trees
Learning systems
Neoplasms
Genetic algorithms
Technology
Neural networks
Proteins

Keywords

  • Bioinformatics
  • Post-translational modifications
  • Proteomic patterns

ASJC Scopus subject areas

  • Molecular Biology
  • Genetics

Cite this

Proteomic patterns for classification of ovarian cancer and CTCL serum samples utilizing peak pairs indicative of post-translational modifications. / Liu, Chenwei; Shea, Nancy; Rucker, Sally; Harvey, Linda; Russo, Paul; Saul, Richard; Lopez, Mary F.; Mikulskis, Alvydas; Kuzdzal, Scott; Golenko, Eva; Fishman, David; Vonderheid, Eric; Booher, Susan; Cowen, Edward W.; Hwang, Sam T.; Whiteley, Gordon R.

In: Proteomics, Vol. 7, No. 22, 11.2007, p. 4045-4052.

Research output: Contribution to journalArticle

Liu, C, Shea, N, Rucker, S, Harvey, L, Russo, P, Saul, R, Lopez, MF, Mikulskis, A, Kuzdzal, S, Golenko, E, Fishman, D, Vonderheid, E, Booher, S, Cowen, EW, Hwang, ST & Whiteley, GR 2007, 'Proteomic patterns for classification of ovarian cancer and CTCL serum samples utilizing peak pairs indicative of post-translational modifications', Proteomics, vol. 7, no. 22, pp. 4045-4052. https://doi.org/10.1002/pmic.200601044
Liu, Chenwei ; Shea, Nancy ; Rucker, Sally ; Harvey, Linda ; Russo, Paul ; Saul, Richard ; Lopez, Mary F. ; Mikulskis, Alvydas ; Kuzdzal, Scott ; Golenko, Eva ; Fishman, David ; Vonderheid, Eric ; Booher, Susan ; Cowen, Edward W. ; Hwang, Sam T. ; Whiteley, Gordon R. / Proteomic patterns for classification of ovarian cancer and CTCL serum samples utilizing peak pairs indicative of post-translational modifications. In: Proteomics. 2007 ; Vol. 7, No. 22. pp. 4045-4052.
@article{4b5e7ad993b84f34862a9ce36e90f692,
title = "Proteomic patterns for classification of ovarian cancer and CTCL serum samples utilizing peak pairs indicative of post-translational modifications",
abstract = "Proteomic patterns as a potential diagnostic technology has been well established for several cancer conditions and other diseases. The use of machine learning techniques such as decision trees, neural networks, genetic algorithms, and other methods has been the basis for pattern determination. Cancer is known to involve signaling pathways that are regulated through PTM of proteins. These modifications are also detectable with high confidence using high-resolution MS. We generated data using a prOTOF™ mass spectrometer on two sets of patient samples: ovarian cancer and cutaneous t-cell lymphoma (CTCL) with matched normal samples for each disease. Using the knowledge of mass shifts caused by common modifications, we built models using peak pairs and compared this to a conventional technique using individual peaks. The results for each disease showed that a small number of peak pairs gave classification equal to or better than the conventional technique that used multiple individual peaks. This simple peak picking technique could be used to guide identification of important peak pairs involved in the disease process.",
keywords = "Bioinformatics, Post-translational modifications, Proteomic patterns",
author = "Chenwei Liu and Nancy Shea and Sally Rucker and Linda Harvey and Paul Russo and Richard Saul and Lopez, {Mary F.} and Alvydas Mikulskis and Scott Kuzdzal and Eva Golenko and David Fishman and Eric Vonderheid and Susan Booher and Cowen, {Edward W.} and Hwang, {Sam T.} and Whiteley, {Gordon R.}",
year = "2007",
month = "11",
doi = "10.1002/pmic.200601044",
language = "English (US)",
volume = "7",
pages = "4045--4052",
journal = "Proteomics",
issn = "1615-9853",
publisher = "Wiley-VCH Verlag",
number = "22",

}

TY - JOUR

T1 - Proteomic patterns for classification of ovarian cancer and CTCL serum samples utilizing peak pairs indicative of post-translational modifications

AU - Liu, Chenwei

AU - Shea, Nancy

AU - Rucker, Sally

AU - Harvey, Linda

AU - Russo, Paul

AU - Saul, Richard

AU - Lopez, Mary F.

AU - Mikulskis, Alvydas

AU - Kuzdzal, Scott

AU - Golenko, Eva

AU - Fishman, David

AU - Vonderheid, Eric

AU - Booher, Susan

AU - Cowen, Edward W.

AU - Hwang, Sam T.

AU - Whiteley, Gordon R.

PY - 2007/11

Y1 - 2007/11

N2 - Proteomic patterns as a potential diagnostic technology has been well established for several cancer conditions and other diseases. The use of machine learning techniques such as decision trees, neural networks, genetic algorithms, and other methods has been the basis for pattern determination. Cancer is known to involve signaling pathways that are regulated through PTM of proteins. These modifications are also detectable with high confidence using high-resolution MS. We generated data using a prOTOF™ mass spectrometer on two sets of patient samples: ovarian cancer and cutaneous t-cell lymphoma (CTCL) with matched normal samples for each disease. Using the knowledge of mass shifts caused by common modifications, we built models using peak pairs and compared this to a conventional technique using individual peaks. The results for each disease showed that a small number of peak pairs gave classification equal to or better than the conventional technique that used multiple individual peaks. This simple peak picking technique could be used to guide identification of important peak pairs involved in the disease process.

AB - Proteomic patterns as a potential diagnostic technology has been well established for several cancer conditions and other diseases. The use of machine learning techniques such as decision trees, neural networks, genetic algorithms, and other methods has been the basis for pattern determination. Cancer is known to involve signaling pathways that are regulated through PTM of proteins. These modifications are also detectable with high confidence using high-resolution MS. We generated data using a prOTOF™ mass spectrometer on two sets of patient samples: ovarian cancer and cutaneous t-cell lymphoma (CTCL) with matched normal samples for each disease. Using the knowledge of mass shifts caused by common modifications, we built models using peak pairs and compared this to a conventional technique using individual peaks. The results for each disease showed that a small number of peak pairs gave classification equal to or better than the conventional technique that used multiple individual peaks. This simple peak picking technique could be used to guide identification of important peak pairs involved in the disease process.

KW - Bioinformatics

KW - Post-translational modifications

KW - Proteomic patterns

UR - http://www.scopus.com/inward/record.url?scp=36549020565&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36549020565&partnerID=8YFLogxK

U2 - 10.1002/pmic.200601044

DO - 10.1002/pmic.200601044

M3 - Article

VL - 7

SP - 4045

EP - 4052

JO - Proteomics

JF - Proteomics

SN - 1615-9853

IS - 22

ER -