Skip to main content
. 2020 May 2;34(10):1013–1026. doi: 10.1007/s10822-020-00314-0

Fig. 5.

Fig. 5

SHAP-based interpretation of MT-DNN predictions. Each output neuron facilitates activity prediction of a different target (Tx). A SHAP-based explanation model is generated for each node/target. For a given test compound, each output prediction is rationalized