Methods for predicting cancer outcome and gene signatures for use therein

Abstract

The present invention pertains to specific gene signatures for cancer that are used to predict survival and novel processes for identifying such gene signatures. In one embodiment, gene signatures for human colorectal cancer are identified and outcomes are linked to the specific gene signatures using significance analysis of microarrays (SAM) and support vector machines (SVM) to provide a prognosis / survival classifier.

Description

CROSS-REFERENCE TO A RELATED APPLICATION [0001] This application claims the benefit of U.S. Provisional Application Ser. No. 60 / 547,871, filed Feb. 25, 2004, which is hereby incorporated by reference in its entirety.BACKGROUND OF THE INVENTION [0002] In the last decade, scientists have labored to complete a high-quality, comprehensive sequence of the human genome. With its recent completion, a large number of genomic data sets have been made available in public databases. The available data, however, does not provide explanations regarding which aspects of human biology affect which genes. Researchers are just beginning to explore genomic function. [0003] Several technological advances have made it possible to accurately measure cellular constituents and therefore derive profiles. For example, new techniques provide the ability to monitor the expression level of a large number of transcripts at any one time (see, for example, Schena et al., “Quantitative monitoring of gene expressio...

AI Technical Summary

Benefits of technology

[0015] The present invention provides systems and methods for predicting outcomes in patients diagnosed with cancer. Specifically, the subject invention utilizes molecular staging with gene expression profiles to stage patients with cancer. In a specific embodiment, the present invention provides a gene expression profile based classifier that provides a means for accurately predicting colon cancer outcome.

Problems solved by technology

The available data, however, does not provide explanations regarding which aspects of human biology affect which genes.

Unfortunately, no research has yet been conducted on identifying specific genes associated with colorectal cancer and specific outcomes to provide an accurate prediction of prognosis.

The Dukes' staging system, however, has only been found useful in predicting the behaviour of a population of patients, rather than an individual.

Unfortunately, application of this staging system results in the potential over-treatment or under-treatment of a significant number of patients.

Further, Dukes' staging can only be applied after complete surgical resection rather than after a pre-surgical biopsy.

To date, however, little success has been achieved in developing a classifier that will predict colon cancer outcome equivalent to or better than that which is possible using the standard clinicopathologic staging systems (i.e., Dukes' stage system).

Images