Classifying Cancer Types Based on Microarray Gene Expressions using Conformal Prediction

The key aspect in cancer treatment is to predict the subclass of the cancer accurately. To this aim, making use of the microarray gen data collected from cancerous tissues has been increasingly popular recently. In the present study, to predict the subclass of various cancer types, we employ the Conformal Prediction method, which outputs a set of classes guaranteeing to some extent that the true subclass is in the set of the predicted classes, different from the conventional machine learning classification algorithms. We tested the performance of the conformal prediction on five different microarray cancer data, ranging from leukemia to prostate cancer. The results showed that the true subclass of the cancer is in the predicted set in almost all settings; and the predicted sets includes as less as possible classes, hence are compacts.