Open suzannejin opened 3 years ago
Hi, You are welcome. The training and test data generation is very flexible, which depends on what you want the model to learn. 1) In the original paper, we removed all cyclic gene pairs. 2) I think you can try it, and just keep in mind that the training and test should follow the same standard.
Hi!
In the paper, you mentioned:
What I am not clear is if you removed all the cyclic gene pairs (A->B, and B->A), or just kept one direction. So for example, if you have A->B and B->A, you kept A->B but not B->A, or you removed both of them directly (?)
Also, if instead of predicting regulatory pairs, I only want to predict the pairs in the same pathway no matter their causality, then can I keep other KEGG edge types that are not activation or inhibition?
Thanks in advance!!