Li Xue

implement Edesolvation energy in deeprank

2

Hi Alex, Currently deeprank implemented Eelec, Evdw, and BSA. But we did not implement desolvation energy in deeprank yet. Do you think we should implement it? Could you please point...

From @manonreau on graphprot: When you store loss values, do not forget to detach it from the computation graph (that is used for the back propagation) or you could run...

Deeprank uses xx.pth.tar as file extension (`NeuralNet.py`). It is not a tar file. Better change it to .pt.

tnr.png and tnr.png do not give much information as they do not reflect common cut-offs for deeprank scores. ROC curve is the combination of these two and is more informative.

ROC curves as Fig. S_XX

1

For the classification performance of HS vs. DR