Created by Health Discovery Corporation's scientific mathematicians, RFE-SVM is used to find discriminate relationships within clinical datasets and within gene expression datasets created from micro-arrays of tumor versus normal tissues. Using RFE-SVM, the scientists at HDC have been able to access specific genetic information that the previously most advanced bioinformatics techniques missed. For example, RFE-SVMs are able to filter irrelevant, tissue-specific genes from those related to malignancy. RFE-SVM also identifies gene expression patterns related to severity of the disease. The data analysis technique provides the physician with patient-specific information and is an enhanced decision-making tool for pharmacogenic and toxicological profiling of the patient. HDC scientists note that RFE-SVM's analytic methods are effective for finding genes implicated in several cancers.
Additionally, RFE-SVM technology is able to rank order the analyzed genetic information to determine the most important gene in the molecular diagnostic test. The ability to rank order the genes also allows HDC scientists to identify IP free genes available for patent protection by the company.
The success of RFE-SVM is documented in numerous published academic papers worldwide.
Because RFE-SVM technology was discovered by our scientists, HDC holds the only issued patents in the world for this technology.
Details of this RFE demonstration can be read in the paper "Gene Selection for Cancer Classification using Support Vector Machines" by Isabelle Guyon, Jason Weston, Stephen Barnhill, M.D. and Vladimir Vapnik.