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.

1 .- 20 . (canceled) 
     
     
         21 . A method for processing or analyzing a tissue sample of a subject, comprising:
 (a) providing a nucleic acid sample derived from said tissue sample of said subject;   (b) sequencing nucleic acid molecules derived from said nucleic acid sample to generate a data set;   (c) using a programmed computer to process said data set to identify (i) a level of expression of one or more gene expression products in said nucleic acid sample, and (ii) one or more genetic mutations in said nucleic acid sample;   (d) using a trained algorithm to process said level of expression and said one or more genetic mutations identified in (c) to generate a classification of said tissue sample as positive or negative for a disease at an accuracy of at least 90%; and   (e) electronically outputting a report that identifies said classification of said tissue sample as positive or negative for said disease.   
     
     
         22 . The method of  claim 21 , wherein said one or more genetic mutations comprise a copy number variation, a deoxyribonucleic acid (DNA) polymorphism, or a combination thereof. 
     
     
         23 . The method of  claim 22 , wherein said one or more genetic mutations comprises said copy number variation. 
     
     
         24 . The method of  claim 22 , wherein said one or more genetic mutations comprises said DNA polymorphism. 
     
     
         25 . The method of  claim 21 , wherein said one or more genetic mutations comprise one or more members selected from the group consisting of a splice site variant, a single nucleotide polymorphism, a variable number repeat polymorphism, an insertion, a deletion, and a truncation. 
     
     
         26 . The method of  claim 21 , wherein said tissue sample comprises a blood sample or buccal tissue. 
     
     
         27 . The method of  claim 21 , wherein said tissue sample comprises a fine needle aspirate (FNA) sample. 
     
     
         28 . The method of  claim 21 , wherein said nucleic acid molecules comprise genomic deoxyribonucleic acid (DNA), messenger ribonucleic acid (RNA), microRNA, or any combination thereof. 
     
     
         29 . The method of  claim 21 , wherein said sequencing comprises high throughput sequencing. 
     
     
         30 . The method of  claim 21 , wherein said disease is cancer. 
     
     
         31 . The method of  claim 30 , wherein said cancer is thyroid cancer. 
     
     
         32 . The method of  claim 30 , wherein said cancer is lung cancer. 
     
     
         33 . The method of  claim 21 , wherein said trained algorithm is trained with a plurality of training samples that is independent of said tissue sample. 
     
     
         34 . The method of  claim 33 , wherein said plurality of training samples comprises normal tissue samples and samples having different tissue pathologies. 
     
     
         35 . The method of  claim 33 , wherein said plurality of training samples comprise tissue samples and fine needle aspirate samples. 
     
     
         36 . The method of  claim 21 , further comprising inputting information related to a medical history of said subject into said trained algorithm. 
     
     
         37 . The method of  claim 21 , wherein said level of expression of said one or more gene expression products and said one or more genetic mutations correspond to one or more genes in said nucleic acid sample. 
     
     
         38 . The method of  claim 21 , wherein said accuracy is at least 95%. 
     
     
         39 . The method of  claim 21 , wherein (c) comprises using said programmed computer to process said data set to identify levels of expression of a plurality of gene expression products corresponding to a plurality of genes in said nucleic acid sample. 
     
     
         40 . The method of  claim 21 , wherein (c) comprises using said programmed computer to process said data set to identify a plurality of genetic mutations in said nucleic acid sample.