A Diagnostics & Imaging Week

Health Discovery (HDC; Savannah, Georgia) reported that the U.S. Patent and Trademark Office has issued two new patents to further expand HDC's intellectual property holdings covering applications of support vector machines (SVMs) for a range of technologies.

The first patent, No. 7,353,215, claims a method for analysis of any type of data that has a structure. One of the most familiar types of structured data is documents, making the patent claims highly relevant to commercial data mining applications, including Internet browsers and search engines.

Other applications include molecular biology, in which DNA sequence matching is a critical operation, HDC said.

Since DNA databases contain huge volumes of data sequences, methods for efficient processing of DNA sequence matching are widely needed. In the area of proteomics, the method for protein characterization involves comparison of tandem mass spectrometry data with libraries of identified spectra in an approach called "spectral matching."

The second patent, No. 7,318,051, covers additional feature selection techniques for identifying important pieces of information needed to solve complex pattern-recognition problems.

HDC said that, with the new patents, it holds exclusive rights to 30 issued U.S. and international patents covering uses of SVM and fractal genomics modeling technology for discovery of knowledge from large data sets.

HDC describes itself as a biology-oriented biomarker discovery company focused on molecular diagnostic development.