mrzqaq/mcanet

Source code of paper: "MCANet: Shared-weight-based MultiheadCrossAttention network for drug-target interaction prediction"

mcanet's Issues

Question about how to preprocess about DeepConv-DTI

Dear authors:

I want to know how the author trained the baseline about DeepConv-DTI mainly about how to preprocess the origin data, When I trained the code ar DeepConv-DTI, the memory was quiet high.

Thank you very much for your kind consideration and I am looking forward to your reply.

Baseline model implementation

Hello, I was reading your paper about MACNet recently.
According to MCANet you compared MCANet with MolTrans, TransformerCPI etc.

These baseline models are implemented by yourself or their official repositories?Because I have also reproduced these two benchmark methods recently, but found that the AUPR result in your paper is higher than the result written by the original author's paper.And I use the same evaluation metrics as yours in Davis and KIBA, but the result is much worse than yours.

If convenient, could you provide baseline model implementation about Davis and KIBA dataset?