Colon cancer biomarkers

Abstract

Systems and methods for enhancing knowledge discovery from data using multiple learning machines in general and multiple support vector machines in particular. Training data for a learning machine is pre-processed in order to add meaning thereto. Multiple support vector machines, each comprising distinct kernels, are trained with the pre-processed training data and are tested with test data that is pre-processed in the same manner. The test outputs from multiple support vector machines are compared in order to determine which of the test outputs if any represents a optimal solution. Selection of one or more kernels may be adjusted and one or more support vector machines may be retrained and retested. Optimal solutions based on distinct input data sets may be combined to form a new input data set to be input into one or more additional support vector machine. The methods, systems and devices of the present invention comprise use of Support Vector Machines for the identification of patterns that are important for medical diagnosis, prognosis and treatment. Such patterns may be found in many different datasets. The present invention also comprises methods and compositions for the treatment and diagnosis of medical conditions.

1 - 17 . (canceled)  
     
     
         18 . A group of isolated genes indicative of colon cancer comprising: 
 the group of genes comprising H08393, M59040, T94579, H81558, R88740, T62947 and H64807;    where tissue composition affecting genes are excluded from the group and where each gene is modulated in colon cancer tissue.    
     
     
         19 . The group of genes according to  claim 18  wherein each member of the group of genes is a gene cluster center.  
     
     
         20 . The group of genes according to  claim 19  wherein the cluster around gene H08393 comprises isolated genes T48804 and T51529; the cluster around gene M59040 comprises isolated genes H04802, T65740, L39874 and R44740; the cluster around gene T94579 comprises isolated genes T63539, T54360, X17273, T57882, R89377, M19283, T83361, H66786, T51849 and T86444; the cluster around gene R88740 comprises isolated gene T54670; the cluster around gene T62947 comprises isolated genes T61609, T70062, U14971, T57619, U30825, L10284, D00763 and T58861.  
     
     
         21 . The group of genes according to  claim 19  wherein the group of genes is a biomarker for assessing colon cancer.  
     
     
         22 . A kit comprising a test for determining the presence of a gene from the group consisting essentially of H08393, M59040, T94579, H81558, R88740, T62947 and H64807 in a biological sample.  
     
     
         23 . The kit according to  claim 22  wherein the biological sample is a human tissue extract and the test uses a gene probe to determine the presence of the gene and thereby assesses the risk of colon cancer.  
     
     
         24 . A colon cancer biomarker comprising a group of non-tissue affecting genes which are modulated in colon cancer tissue, which group comprises isolated genes H08393, M59040, T94579, H81558, R88740, T62947 and H64807, the presence of which is useful in assessing colon cancer.  
     
     
         25 . The colon cancer biomarker according to  claim 24  wherein isolated genes H08393, M59040, T94579, H81558, R88740, T62947 and H64807 are each a gene cluster center.  
     
     
         26 . The colon cancer biomarker according to  claim 25  wherein the cluster around isolated gene H08393 comprises isolated genes T48804 and T51529; the cluster around isolated gene M59040 comprises isolated genes H04802, T65740, L39874 and R44740; the cluster around isolated gene T94579 comprises isolated genes T63539, T54360, X17273, T57882, R89377, M19283, T83361, H66786, T51849 and T86444; the cluster around isolated gene R88740 comprises isolated gene T54670; the cluster around isolated gene T62947 comprises isolated genes T61609, T70062, U14971, T57619, U30825, L10284, D00763 and T58861.  
     
     
         27 . A method for identifying a subject at risk for colon cancer development comprising: 
 (a) obtaining a test sample from the subject;    (b) determining a biomarker presence in said test sample; and    (c) assessing the risk for colon cancer development in the subject;    wherein the biomarker is a group of genes comprising H08393, M59040, T94579, H81558, R88740, T62947 and H64807 and where each gene codes a protein modulated in colon cancer tissue.    
     
     
         28 . The method according to  claim 27  wherein the isolated genes are gene cluster centers.  
     
     
         29 . The method according to  claim 28  wherein the cluster around center gene H08393 comprises genes T48804 and T51529; the cluster around center gene M59040 comprises genes H04802, T65740, L39874 and R44740; the cluster around center gene T94579 comprises genes T63539, T54360, X17273, T57882, R89377, M19283, T83361, H66786, T51849 and T86444; the cluster around center gene R88740 comprises gene T54670; the cluster around center gene T62947 comprises genes T61609, T70062, U14971, T57619, U30825, L10284, D00763 and T58861.  
     
     
         30 . A device for assessing a change in a biological system comprising: 
 a chip having specific binding protein, DNA, RNA, nucleic acids or combinations thereof which specifically bind a group of biomarker genes or a biomarker proteins encoded thereby, which binding indicates the change in the biological system; and    wherein the group of biomarker genes consists essentially of H08393, M59040, T94579, H81558, R88740, T62947 and H64807 and indicates colon cancer.    
     
     
         31 . The device according to  claim 30  wherein the change results in a treatable biological condition, according to medical treatment regimens selected from the group comprising: gene therapy, anti-tumor therapy, antisense therapy, chemotherapeutic therapy and combinations thereof.  
     
     
         32 . The device according to  claim 30  wherein the group of biomarker genes are cluster center genes wherein the cluster around center gene H08393 comprises isolated genes T48804 and T51529; the cluster around center gene M59040 comprises isolated genes H04802, T65740, L39874 and R44740; the cluster around center gene T94579 comprises isolated genes T63539, T54360, X17273, T57882, R89377, M19283, T83361, H66786, T51849 and T86444; the cluster around center gene R88740 comprises isolated gene T54670; the cluster around center gene T62947 comprises isolated genes T61609, T70062, U14971, T57619, U30825, L10284, D00763 and T58861.