Algorithms for disease diagnostics

Abstract

The present invention relates to compositions and methods for molecular profiling and diagnostics for genetic disorders and cancer, including but not limited to gene expression product markers associated with cancer or genetic disorders. In particular, the present invention provides algorithms and methods of classifying cancer, for example, thyroid cancer, methods of determining molecular profiles, and methods of analyzing results to provide a diagnosis.

What is claimed is: 
     
         1 . A method of diagnosing a genetic disorder or cancer comprising the steps of:
 (a) obtaining a biological sample comprising gene expression products;   (b) detecting the gene expression products of the biological sample;   (c) comparing to an amount in a control sample, an amount of one or more gene expression products in the biological sample to determine the differential gene expression product level between the biological sample and the control sample;   (d) classifying the biological sample by inputting the one or more differential gene expression product levels to a trained algorithm; wherein technical factor variables are removed from data based on differential gene expression product level and normalized prior to and during classification; and   (e) identifying the biological sample as positive for a genetic disorder or cancer if the trained algorithm classifies the sample as positive for the genetic disorder or cancer at a specified confidence level.   
     
     
         2 . The method of  claim 1 , wherein the gene expression product is mRNA. 
     
     
         3 . The method of  claim 2 , wherein the RNA has an RNA integrity number (RIN) of 2.0 or more. 
     
     
         4 . The method of  claim 2 , wherein the RNA with an RNA integrity number (RIN) of equal to or less than 5.0 is used for multi-gene microarray analysis. 
     
     
         5 . The method of  claim 1 , wherein the technical factor variable is any variable listed in Table 3 or a combination thereof. 
     
     
         6 . The method of  claim 1 , wherein multiple datasets based on differential gene expression product levels are joined. 
     
     
         7 . The method of  claim 1 , wherein a statistical method is used for training and testing a classifier, the statistical method is selected from the group consisting of support vector machines (SVM), linear discriminant analysis (LDA), K-nearest neighbor analysis (KNN), and random forest (RF). 
     
     
         8 . The method of  claim 1 , wherein the sample is obtained via one or more of the following: needle aspiration, fine needle aspiration, core needle biopsy, vacuum assisted biopsy, large core biopsy, incisional biopsy, excisional biopsy, punch biopsy, shave biopsy, or skin biopsy. 
     
     
         9 . The method of  claim 1 , wherein the sample is a pre-operative specimen. 
     
     
         10 . The method of  claim 1 , wherein the sample is a post-operative specimen. 
     
     
         11 . The method of  claim 1 , wherein the sample comprises thyroid tissue. 
     
     
         12 . The method of  claim 1 , wherein detecting the gene expression products of the biological test sample is performed by measuring mRNA. 
     
     
         13 . The method of  claim 13 , wherein mRNA is measured by one or more of the following: microarray, SAGE, blotting, RT-PCR, or quantitative PCR. 
     
     
         14 . The method of  claim 1 , wherein the normal sample is obtained from one or more of the following: the same individual as the test sample, a different individual from the test sample, a tissue or cell bank. 
     
     
         15 . The method of  claim 1 , wherein the normal control sample gene expression product amounts are from a database. 
     
     
         16 . The method of  claim 1 , wherein the method distinguishes thyroid carcinoma from benign thyroid diseases. 
     
     
         17 . The method of  claim 1  further comprising providing a suggested therapeutic intervention. 
     
     
         18 . The method of  claim 1 , wherein the results of the expression analysis provide a statistical confidence level above 90% that a given diagnosis is correct. 
     
     
         19 . The method of  claim 1  further comprising the step of performing a cytological analysis on a portion of the biological sample following step (a) to obtain a preliminary diagnosis. 
     
     
         20 . The method of  claim 1 , wherein the diagnosis of the genetic disorder or cancer has a specificity of at least 70%.