Evaluating network-based missing protein prediction using p-values, Bayes Factors, and probabilities.

Abstract

Some prediction methods use probability to rank their predictions, while some other prediction methods do not rank their predictions and instead use [Formula: see text]-values to support their predictions. This disparity renders direct cross-comparison of these two kinds of methods difficult. In particular, approaches such as the Bayes Factor upper Bound (BFB) for [Formula: see text]-value conversion may not make correct assumptions for this kind of cross-comparisons. Here, using a well-established case study on renal cancer proteomics and in the context of missing protein prediction, we demonstrate how to compare these two kinds of prediction methods using two different strategies. The first strategy is based on false discovery rate (FDR) estimation, which does not make the same naïve assumptions as BFB conversions. The second strategy is a powerful approach which we colloquially call "home ground testing". Both strategies perform better than BFB conversions. Thus, we recommend comparing prediction methods by standardization to a common performance benchmark such as a global FDR. And where this is not possible, we recommend reciprocal "home ground testing".