Abstract: A computer system for performing data analysis services using a support vector machine for analyzing data received from a remote source on a distributed network includes a server in communication with the distributed network for receiving a data set and a financial account identifier associated with the remote source. The server communicates over the distributed network with a financial institution to receive funds from a financial account identified by the financial account identifier. A processor receives one or more data sets from the remote source and pre-processes the data to enhance meaning within the data set. The pre-processed data is used to train and test a support vector machine for recognizing patterns within the data. Live data is processed using the trained and tested support vector machine to generate an output which is transmitted to the remote source after the server confirms that payment for the data processing service has been received.

Abstract: Gene expression data are analyzed using learning machines such as support vector machines (SVM) and ridge regression classifiers to rank genes according to their ability to distinguish between BPH (benign prostatic hyperplasia) and all other conditions. Results are provided showing the correlation of results obtained using data from two independent studies that took place at different times using different microarrays. Genes are ranked according to area-under-the-curve, false discovery rate and fold change.

Abstract: Identification of a determinative subset of features from within a large set of features is performed by training a support vector machine to rank the features according to classifier weights, where features are removed to determine how their removal affects the value of the classifier weights. The features having the smallest weight values are removed and a new support vector machine is trained with the remaining weights. The process is repeated until a relatively small subset of features remain that is capable of accurately separating the data into different patterns or classes. The method is applied for selecting the smallest number of genes that are capable of accurately distinguishing between medical conditions such as cancer and non-cancer.

Abstract: Gene expression data are analyzed using learning machines such as support vector machines (SVM) and ridge regression classifiers to rank genes according to their ability to separate prostate cancer from BPH (benign prostatic hyperplasia) and to distinguish cancer volume. Other tests identify biomarker candidates for distinguishing between tumor (Grade 3 and Grade 4 (G3/4)) and normal tissue.

Abstract: The present invention provides methods for diagnosing cancers, such as prostate cancer. Also, methods for evaluating the prostate cancer state of a patient are described herein. These methods involve the detection, analysis, and classification of biological patterns in biological samples. The biological patterns are obtained using, for example, mass spectrometry systems, antibody based techniques, or nucleic acid based techniques. The present invention also includes therapeutic and prophylactic agents that target the biomarkers described herein. Also, the present invention provides methods for the treatment of prostate cancer using the markers described herein or agents that mimic the properties of these markers.