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 .- 35 . (canceled) 
     
     
         36 . A method for processing or analyzing a sample of tissue of a subject, comprising:
 (a) processing said sample of tissue to yield a data set including data corresponding to levels of gene expression products in said sample of tissue, which sample is indeterminate when subjected to cytological analysis;   (b) inputting said data from (a) to a trained algorithm in a programmed computer to generate a classification of said sample of tissue as positive or negative for a disease at an accuracy of at least 90%, wherein said trained algorithm is trained with a plurality of training samples that is independent of said sample of tissue; and   (c) electronically outputting a report that identifies said classification of said sample of tissue as positive or negative for said disease.   
     
     
         37 . The method of  claim 36 , wherein said disease is cancer. 
     
     
         38 . The method of  claim 37 , wherein said cancer is thyroid cancer, lung cancer, adrenal cortical cancer, anal cancer, bile duct cancer, bladder cancer, bone cancer, breast cancer, cervical cancer, colorectal cancer, endometrial cancer, esophagus cancer, eye cancer, gallbladder cancer, gastrointestinal carcinoid tumors, gastrointestinal stromal tumors, kidney cancer, acute lymphocytic leukemia, acute myeloid leukemia, liver cancer, Non-Hodgkin's lymphoma, multiple myeloma, nasopharyngeal cancer, neuroblastoma, oropharyngeal cancer, osteosarcoma, ovarian cancer, pancreatic cancer, pituitary tumor, prostate cancer, retinoblastoma, melanoma stomach cancer, testicular cancer, thymus cancer, or uterine cancer. 
     
     
         39 . The method of  claim 37 , wherein said cancer is thyroid cancer. 
     
     
         40 . The method of  claim 37 , wherein said cancer is lung cancer. 
     
     
         41 . The method of  claim 37 , wherein said cancer is colorectal cancer. 
     
     
         42 . The method of  claim 37 , wherein said cancer is prostate cancer. 
     
     
         43 . The method of  claim 36 , wherein said disease a hyperproliferative disorder. 
     
     
         44 . The method of  claim 36 , wherein said sample of tissue comprises buccal tissue, skin tissue, heart tissue, lung tissue, kidney tissue, breast tissue, pancreas tissue, liver tissue, muscle tissue, smooth muscle tissue, bladder tissue, gall bladder tissue, colon tissue, intestine tissue, brain tissue, prostate tissue, or esophagus tissue. 
     
     
         45 . The method of  claim 36 , wherein said sample of tissue is obtained by swabbing. 
     
     
         46 . The method of  claim 36 , wherein said sample of tissue comprises two or more tissue types. 
     
     
         47 . The method of  claim 46 , wherein a first portion of said sample of tissue comprises a buccal tissue. 
     
     
         48 . The method of  claim 36 , wherein said sample of tissue comprises a blood sample. 
     
     
         49 . The method of  claim 36 , wherein said data comprises ribonucleic acid (RNA) data. 
     
     
         50 . The method of  claim 49 , wherein said RNA data comprises micro RNA data. 
     
     
         51 . The method of  claim 36 , wherein said data comprises deoxyribonucleic acid (DNA) data. 
     
     
         52 . The method of  claim 51 , wherein said processing comprises identifying a copy number variation or a variant in said DNA data. 
     
     
         53 . The method of  claim 36 , wherein said processing comprises assaying a portion of said sample of tissue by sequencing, array hybridization or nucleic acid amplification. 
     
     
         54 . The method of  claim 36 , wherein said plurality of training samples comprise a metastatic melanoma sample, a metastatic renal carcinoma sample, a metastatic breast carcinoma sample, a metastatic B cell lymphoma sample, or any combination thereof. 
     
     
         55 . The method of  claim 36 , wherein said plurality of training samples comprises a normal tissue sample and a plurality of samples having different tissue pathologies. 
     
     
         56 . The method of  claim 36 , wherein said trained algorithm generates said classification at a specificity of at least about 90%. 
     
     
         57 . The method of  claim 36 , wherein said trained algorithm generates said classification at a sensitivity of at least about 80%. 
     
     
         58 . The method of  claim 36 , wherein said sample of tissue has a benign condition, and wherein said trained algorithm does not classify said sample of tissue as positive for said disease. 
     
     
         59 . The method of  claim 36 , wherein said sample of tissue has a malignant condition, and wherein said trained algorithm classifies said sample of tissue as positive for said disease.