Questions about predicting specific DDI types on Dataset2

[bbjy]

Hi, thank you for your work.

I don't understand what it means to predict specific DDI type. How do you conduct this experiments and what's the meaning of the results? The multi-type prediction is a multi-label classification problem, why the ROC-AUC metric could be used? Do the results represent the average of the prediction result of each type?

I am looking forward to your reply! Thank you!

[matenure]

It has been quite long since we finished this work, so I do not quite remember all the details. As to this question, I think we did not predict the specific DDI types, but just predicted whether there is a DDI between two drugs. The label vector for a node is actually a binary vector which indicates the connection with other nodes (each dimension is a drug).

Of course the codes may be possibly adapted to a multi-type DDI prediction, but it needs some extra effort.