A molecular blueprint for targeting cancer?

Wouldn't it be fabulous if inspection of a tumour would immediately suggest the most effective therapy for total eradication of the disease? The ability to rapidly translate the defects of a tumour cell into a molecular blueprint for therapeutic targeting is an important step in the realization of this dream. To this end, researchers have charted every conceivable quality of tumour cells—including biochemical peculiarities and genetic abnormalities—with the hope of identifying signature changes that indicate the critical defects of a given tumour's physiology. Armed with this accumulated knowledge, we may soon be able to customize therapy. For this approach to be effective, we need techniques that can rapidly scan the total genome for mutations, and an understanding of the functional significance of the mutational spectra. On page 99 of this issue, Laleh Shayesteh and colleagues provide a nascent example of the latter; they present data suggesting that PIK3CA, encoding PI3–kinase, is an oncogene important in ovarian cancer by virtue of its frequent amplification in these tumours.

For defined phenotypes such as drug resistance, identification of the amplified gene is straightforward because manipulation of the candidate gene may verify or refute its effect. Furthermore, the selection pressure—in this case, growth in the presence of drug—is defined. For more complex phenotypes, such as tumorigenic potential, the complexity of the variables involved in generating the phenotype renders analysis immensely more difficult. For this reason, most genes that respond to selection pressure and drive the plethora of amplifications and deletions identified by chromosomal analysis of tumour samples are currently unknown.