	US 7,617,163 B2
	Kernels and kernel methods for spectral data
Asa Ben-Hur, Seattle, Wash. (US); André Elisseeff, Thalwil (Switzerland); Olivier Chapelle, Tuebingen (Germany); and Jason Aaron Edward Weston, New York, N.Y. (US)
Assigned to Health Discovery Corporation, Savannah, Ga. (US)
Filed on Oct. 09, 2002, as Appl. No. 10/267,977.
Application 10/267977 is a continuation in part of application No. 10/477078, granted, now 7,353,215, previously published as PCT/US02/14311, filed on May 07, 2002.
Application 10/267977 is a continuation in part of application No. 10/267977.
Application 10/267977 is a continuation in part of application No. 10/057849, filed on Jan. 24, 2002, granted, now 7,117,188.
Application 10/057849 is a continuation in part of application No. 09/633410, filed on Aug. 07, 2000, granted, now 6,882,990.
Claims priority of provisional application 60/289163, filed on May 07, 2001.
Claims priority of provisional application 60/329874, filed on Oct. 17, 2001.
Claims priority of provisional application 60/328309, filed on Oct. 09, 2001.
Prior Publication US 2005/0228591 A1, Oct. 13, 2005
Int. Cl. G06F 15/18 (2006.01)

U.S. Cl. 706—12 [706/45; 706/20; 706/25]

25 Claims

1. A method for analysis of data contained in a plurality of spectra generated from mass spectrographic measurement of protein samples corresponding to different biological conditions, wherein the different biological conditions have associated different levels of protein expression, the method comprising:

downloading the plurality of spectra into a computer system comprising a processor and a storage device, wherein the processor is programmed to execute at least one support vector machine and performs the steps of:

aligning the plurality of spectra, comprising:

selecting a first example spectrum as a baseline example;

sliding each spectral peak of a second example spectrum one at a time along a plurality of peaks within the baseline example;

applying a scoring function to obtain a similarity score between each spectral peak of the second example spectrum and the peaks within the baseline example, the similarity score being determined according to the relationship

where x_iand x₀are feature vectors corresponding to peaks of an i^thexample spectrum and the baseline spectrum, respectively, and ∥x_i∥ is the l₁norm,

offsetting the second example spectrum relative to the baseline example according to the similarity score achieved for the second example spectrum;

repeating the step of aligning the spectra for at least one additional example spectrum to create a set of aligned spectra;

applying a feature selection algorithm to the set of aligned spectra to select a subset of spectral peaks that discriminate between the different biological conditions;

training and testing the at least one support vector machine using the set of aligned spectra to provide a trained at least one support vector machine for processing of live data;

inputting live spectral data from live protein samples to be analyzed, selecting the subset of spectral peaks from the live spectral data, aligning the live spectral data and processing the live spectral data using the trained at least one support vector machine; and

displaying a listing comprising two or more subsets of live protein samples wherein each subset is identified as belonging to a group possessing one of the different biological conditions.