Please login first
Alexander Gray  - - - 
Top co-authors See all
Facundo M. Fernández

114 shared publications

School of Chemistry and Biochemistry; Georgia Institute of Technology; Atlanta GA 30332 USA

John F. McDonald

64 shared publications

Integrated Cancer Research Center, School of Biological Sciences, and Parker H. Petit Institute of Bioengineering and Biosciences, Georgia Institute of Technology, 315 Ferst Dr, Atlanta, GA, 30332, USA.

Rajesh Narasimha

20 shared publications

Samsung Res. America, Richardson, TX, USA

Charles Lee Isbell

9 shared publications

Georgia Institute of Technology

Hua Ouyang

8 shared publications

Key Laboratory of Ecosystem Network Observation and Modelling, Institute of Geographical Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, People’s Republic of China

Publication Record
Distribution of Articles published per year 
(2009 - 2013)
Total number of journals
published in
Article 0 Reads 6 Citations Sparse high-dimensional fractional-norm support vector machine via DC programming Wei Guan, Alexander Gray Published: 01 November 2013
Computational Statistics & Data Analysis, doi: 10.1016/j.csda.2013.01.020
DOI See at publisher website
Article 0 Reads 3 Citations Fast kernel conditional density estimation: A dual-tree Monte Carlo approach Michael P. Holmes, Alexander G. Gray, Charles Lee Isbell Published: 01 July 2010
Computational Statistics & Data Analysis, doi: 10.1016/j.csda.2010.01.011
DOI See at publisher website
Article 0 Reads 7 Citations Automatic joint classification and segmentation of whole cell 3D images Rajesh Narasimha, Hua Ouyang, Alexander Gray, Steven W. McLa... Published: 01 June 2009
Pattern Recognition, doi: 10.1016/j.patcog.2008.08.009
DOI See at publisher website
Article 0 Reads 24 Citations Ovarian cancer detection from metabolomic liquid chromatography/mass spectrometry data by support vector machines Wei Guan, Manshui Zhou, Christina Y Hampton, Benedict B Beni... Published: 01 January 2009
BMC Bioinformatics, doi: 10.1186/1471-2105-10-259
DOI See at publisher website PubMed View at PubMed ABS Show/hide abstract
The majority of ovarian cancer biomarker discovery efforts focus on the identification of proteins that can improve the predictive power of presently available diagnostic tests. We here show that metabolomics, the study of metabolic changes in biological systems, can also provide characteristic small molecule fingerprints related to this disease. In this work, new approaches to automatic classification of metabolomic data produced from sera of ovarian cancer patients and benign controls are investigated. The performance of support vector machines (SVM) for the classification of liquid chromatography/time-of-flight mass spectrometry (LC/TOF MS) metabolomic data focusing on recognizing combinations or "panels" of potential metabolic diagnostic biomarkers was evaluated. Utilizing LC/TOF MS, sera from 37 ovarian cancer patients and 35 benign controls were studied. Optimum panels of spectral features observed in positive or/and negative ion mode electrospray (ESI) MS with the ability to distinguish between control and ovarian cancer samples were selected using state-of-the-art feature selection methods such as recursive feature elimination and L1-norm SVM. Three evaluation processes (leave-one-out-cross-validation, 12-fold-cross-validation, 52-20-split-validation) were used to examine the SVM models based on the selected panels in terms of their ability for differentiating control vs. disease serum samples. The statistical significance for these feature selection results were comprehensively investigated. Classification of the serum sample test set was over 90% accurate indicating promise that the above approach may lead to the development of an accurate and reliable metabolomic-based approach for detecting ovarian cancer.