A Comparison of Methods for Data-Driven Cancer Outlier Discovery, and An Application Scheme to Semisupervised Predictive Biomarker Discovery

@inproceedings{Karrila2011ACO,
  title={A Comparison of Methods for Data-Driven Cancer Outlier Discovery, and An Application Scheme to Semisupervised Predictive Biomarker Discovery},
  author={Seppo J. Karrila and Julian Hock Ean Lee and Greg Tucker-Kellogg},
  booktitle={Cancer informatics},
  year={2011}
}
A core component in translational cancer research is biomarker discovery using gene expression profiling for clinical tumors. This is often based on cell line experiments; one population is sampled for inference in another. We disclose a semisupervised workflow focusing on binary (switch-like, bimodal) informative genes that are likely cancer relevant, to mitigate this non-statistical problem. Outlier detection is a key enabling technology of the workflow, and aids in identifying the focus… CONTINUE READING