Methods for analyzing high dimensional data for classifying, diagnosing, prognosticating, and/or predicting diseases and other biological states

A method of determining whether a subject has a cancer selected from the group consisting of neuroblastoma, rhabdomyosarcoma, non-Hodgkin's lymphoma, and Ewing's tumor comprising:

• (a) processing a biological sample from a subject whose cancer is unknown to obtain high dimensional experimental data selected from the group consisting of gene expression levels, protein expression levels, single nucleotide polymorphisms, or comparative genomic analysis;
• (b) detecting the presence of a first set of multiple data points in the high dimensional experimental data, wherein the first set of multiple data points is predictive for distinguishing the presence of neuroblastoma, rhabdomyosarcoma, non-Hodgkin's lymphoma, and Ewing's tumor from one another, as determined by
• training a supervised pattern recognition method using data obtained from a biological sample known to be either a neuroblastoma, rhabdomyosarcoma, non-Hodgkin's lymphoma, or Ewing's tumor to obtain a probability distribution relationship between the data obtained from each of the biological samples and the type of cancer;
• ranking individual data points from said first set of high dimensional data by determining the sensitivity of the data point to the classification of each type of cancer, wherein said ranking is dependent on an outcome of said supervised pattern recognition method;
• and choosing a first set of multiple data points from said high dimensional data as predictive for the type of cancer, wherein said choice is based on said relative ranking of said individual data points;
• and
• (c) determining whether the sample from the subject whose cancer is unknown can be classified as one of neuroblastoma, rhabdomyosarcoma, non-Hodgkin's lymphoma, or Ewing's tumor by detecting the presence of said first set of multiple data points in data obtained from the biological sample.