YLoc--an interpretable web server for predicting subcellular localization

Abstract

Predicting subcellular localization has become a valuable alternative to time-consuming experimental methods. Major drawbacks of many of these predictors is their lack of interpretability and the fact that they do not provide an estimate of the confidence of an individual prediction. We present YLoc, an interpretable web server for predicting subcellular localization. YLoc uses natural language to explain why a prediction was made and which biological property of the protein was mainly responsible for it. In addition, YLoc estimates the reliability of its own predictions. YLoc can, thus, assist in understanding protein localization and in location engineering of proteins. The YLoc web server is available online at www.multiloc.org/YLoc.

Figure 1.

The attribute table of the YLoc web service lists all attributes in order of their influence on the prediction outcome. All attributes are expressed in biological terms. The +(+) or −(−) indicates whether that attribute value is (very) typical or (very) untypical for a location.

Figure 2.

The detailed attribute page of the feature ‘secretory pathway sorting signal’ in YLoc-LowRes (animal version). The distribution of proteins from the cy, mi, nu and SP over the different attribute intervals is shown.