Characteristics and Validation Techniques for PCA-Based Gene-Expression Signatures

摘要

Background. Many gene-expression signatures exist for describing the biological state of profiled tumors. Principal ComponentAnalysis (PCA) can be used to summarize a gene signature into a single score. Our hypothesis is that gene signatures can bevalidated when applied to new datasets, using inherent properties of PCA. Results. This validation is based on four key concepts.Coherence: elements of a gene signature should be correlated beyond chance. Uniqueness: the general direction of the data beingexamined can drive most of the observed signal. Robustness: if a gene signature is designed to measure a single biological effect,thenthissignalshouldbesufficientlystronganddistinctcomparedtoothersignalswithinthesignature.Transferability:thederivedPCA gene signature score should describe the same biology in the target dataset as it does in the training dataset. Conclusions. Theproposed validation procedure ensures that PCA-based gene signatures perform as expected when applied to datasets other thanthose that the signatures were trained upon. Complex signatures, describing multiple independent biological components, are alsoeasily identified.