Analysis of mass spectral serum profiles for biomarker selection

Habtom W. Ressom; Rency S. Varghese; Mohamed Abdel-Hamid; Sohair Abdel Latif Eissa; Daniel Saha; Lenka Goldman; Emanuel F. Petricoin; Thomas P. Conrads; Timothy D. Veenstra; Christopher A. Loffredo; Radoslav Goldman

doi:10.1093/bioinformatics/bti670

Analysis of mass spectral serum profiles for biomarker selection

Habtom W. Ressom^*, Rency S. Varghese, Mohamed Abdel-Hamid, Sohair Abdel Latif Eissa, Daniel Saha, Lenka Goldman, Emanuel F. Petricoin, Thomas P. Conrads, Timothy D. Veenstra, Christopher A. Loffredo, Radoslav Goldman

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

73 Scopus citations

Abstract

Motivation: Mass spectrometric profiles of peptides and proteins obtained by current technologies are characterized by complex spectra, high dimensionality and substantial noise. These characteristics generate challenges in the discovery of proteins and protein-profiles that distinguish disease states, e.g. cancer patients from healthy individuals. We present low-level methods for the processing of mass spectral data and a machine learning method that combines support vector machines, with particle swarm optimization for biomarker selection. Results: The proposed method identified mass points that achieved high prediction accuracy in distinguishing liver cancer patients from healthy individuals in SELDI-QqTOF profiles of serum.

Original language	English
Pages (from-to)	4039-4045
Number of pages	7
Journal	Bioinformatics
Volume	21
Issue number	21
DOIs	https://doi.org/10.1093/bioinformatics/bti670
State	Published - Nov 2005
Externally published	Yes

Access to Document

10.1093/bioinformatics/bti670

Cite this

@article{e4bd07619d924f019ef21ec59f27970a,

title = "Analysis of mass spectral serum profiles for biomarker selection",

abstract = "Motivation: Mass spectrometric profiles of peptides and proteins obtained by current technologies are characterized by complex spectra, high dimensionality and substantial noise. These characteristics generate challenges in the discovery of proteins and protein-profiles that distinguish disease states, e.g. cancer patients from healthy individuals. We present low-level methods for the processing of mass spectral data and a machine learning method that combines support vector machines, with particle swarm optimization for biomarker selection. Results: The proposed method identified mass points that achieved high prediction accuracy in distinguishing liver cancer patients from healthy individuals in SELDI-QqTOF profiles of serum.",

author = "Ressom, {Habtom W.} and Varghese, {Rency S.} and Mohamed Abdel-Hamid and Eissa, {Sohair Abdel Latif} and Daniel Saha and Lenka Goldman and Petricoin, {Emanuel F.} and Conrads, {Thomas P.} and Veenstra, {Timothy D.} and Loffredo, {Christopher A.} and Radoslav Goldman",

note = "Funding Information: suggestions and discussions. This work was supported in part by US Army Medical Research and Material Command, the Prostate Cancer Research Program grant DAMD17-02-1-0057 and the American Cancer Society grant CRTG-02-245-01-CCE awarded to R.G.",

year = "2005",

month = nov,

doi = "10.1093/bioinformatics/bti670",

language = "English",

volume = "21",

pages = "4039--4045",

journal = "Bioinformatics",

issn = "1367-4803",

number = "21",

}

TY - JOUR

T1 - Analysis of mass spectral serum profiles for biomarker selection

AU - Ressom, Habtom W.

AU - Varghese, Rency S.

AU - Abdel-Hamid, Mohamed

AU - Eissa, Sohair Abdel Latif

AU - Saha, Daniel

AU - Goldman, Lenka

AU - Petricoin, Emanuel F.

AU - Conrads, Thomas P.

AU - Veenstra, Timothy D.

AU - Loffredo, Christopher A.

AU - Goldman, Radoslav

N1 - Funding Information: suggestions and discussions. This work was supported in part by US Army Medical Research and Material Command, the Prostate Cancer Research Program grant DAMD17-02-1-0057 and the American Cancer Society grant CRTG-02-245-01-CCE awarded to R.G.

PY - 2005/11

Y1 - 2005/11

N2 - Motivation: Mass spectrometric profiles of peptides and proteins obtained by current technologies are characterized by complex spectra, high dimensionality and substantial noise. These characteristics generate challenges in the discovery of proteins and protein-profiles that distinguish disease states, e.g. cancer patients from healthy individuals. We present low-level methods for the processing of mass spectral data and a machine learning method that combines support vector machines, with particle swarm optimization for biomarker selection. Results: The proposed method identified mass points that achieved high prediction accuracy in distinguishing liver cancer patients from healthy individuals in SELDI-QqTOF profiles of serum.

AB - Motivation: Mass spectrometric profiles of peptides and proteins obtained by current technologies are characterized by complex spectra, high dimensionality and substantial noise. These characteristics generate challenges in the discovery of proteins and protein-profiles that distinguish disease states, e.g. cancer patients from healthy individuals. We present low-level methods for the processing of mass spectral data and a machine learning method that combines support vector machines, with particle swarm optimization for biomarker selection. Results: The proposed method identified mass points that achieved high prediction accuracy in distinguishing liver cancer patients from healthy individuals in SELDI-QqTOF profiles of serum.

UR - http://www.scopus.com/inward/record.url?scp=27744595524&partnerID=8YFLogxK

U2 - 10.1093/bioinformatics/bti670

DO - 10.1093/bioinformatics/bti670

M3 - Article

C2 - 16159919

AN - SCOPUS:27744595524

SN - 1367-4803

VL - 21

SP - 4039

EP - 4045

JO - Bioinformatics

JF - Bioinformatics

IS - 21

ER -

Analysis of mass spectral serum profiles for biomarker selection

Abstract

Access to Document

Fingerprint

Cite this