Abstract
Since the turn of the century, researchers have sought to diagnose cancer based on gene expression signatures measured from the blood or biopsy as biomarkers. This task, known as classification, is typically solved using a suite of algorithms that learn a mathematical rule capable of discriminating one group (e.g., cases) from another (e.g., controls). However, discriminatory methods can only identify cancerous samples that resemble those that the algorithm already saw during training. As such, we argue that discriminatory methods are fundamentally ill-suited for the classification of cancer: because the possibility space of cancer is definitively large, the existence of a one-of-a-kind gene expression signature becomes very likely. Instead, we propose using an established surveillance method that detects anomalous samples based on their deviation from a learned normal steady-state structure. By transferring this method to transcriptomic data, we can create an anomaly detector for tissue transcriptomes, a “tissue detector”, that is capable of identifying cancer without ever seeing a single cancer example. Using models trained on normal GTEx samples, we show that our “tissue detector” can accurately classify TCGA samples as normal or cancerous and that its performance is further improved by including more normal samples in the training set. We conclude this report by emphasizing the conceptual advantages of anomaly detection and by highlighting future directions for this field of study.