The present invention provides a method for preparing a
reference model for
cancer relapse prediction that provides higher resolution grading than Gleason
score alone. The method encompasses obtaining from different individuals a plurality of
prostate carcinoma tissue samples of known clinical outcome representing different
Gleason scores; selecting a set of signature genes having an
expression pattern that correlates positively or negatively in a statistically significant manner with the
Gleason scores; independently deriving a
prediction score that correlates
gene expression of each individual signature
gene with Gleason
score for each signature
gene in said plurality of
prostate carcinoma tissue samples; deriving a
prostate cancer gene expression (GEX)
score that correlates
gene expression of said set of signature genes with the Gleason score based on the combination of independently derived prediction scores in the plurality of
prostate cancer tissue samples; and correlating said GEX score with the clinical outcome for each
prostate carcinoma tissue sample. A set of signature genes is provided that encompasses all or a sub-combination of GI_2094528, KIP2, NRG1, NBL1, Prostein, CCNE2, CDC6, FBP1, HOXC6, MKI67, MYBL2, PTTG1, RAMP, UBE2C, Wnt5A, MEMD, AZGP1, CCK, MLCK, PPAP2B, and PROK1. Also provided a methods for predicting the probability of relapse of
cancer in an individual and methods for deriving a
prostate cancer gene expression (GEX) score for a
prostate carcinoma tissue sample obtained from an individual.