search

CSUBioGroup / GraphscoreDTA

A novel graph neural network strategy with the Vina distance optimization terms to predict protein-ligand binding affinity
GNU General Public License v3.0
24 stars 9 forks source link

Predicting ligands outside of the test set #2

Closed jnoske closed 6 months ago

jnoske commented 1 year ago

Dear GraphscoreDTA developers,

Thank you for the excellent work. However, I was wondering how the trained model can be used to predict protein-ligand binding affinities for a protein-ligand pair that is not in the test set?

Thank you for your input.

anotherras commented 1 year ago

I have encountered the same problem, how can I solve it? No code for processing data.

messcode commented 1 year ago

It would be very helpful if the authors can provide code for data processing.

heshiyue1999 commented 8 months ago

It would be very helpful if the authors can provide code for data processing.

Is the data preprocessing part implemented?

anxiangbiye1231 commented 8 months ago

It would be very helpful if the authors can provide code for data processing.

Is the data preprocessing part implemented?

  1. For the drug clustering method, the label id of the data set is not given, only the trained model is released; 2. The input feature script of the preprocessed data set is not released. It is difficult to achieve the original experiment, and can not be used as a benchmark for performance comparison
moranlin commented 7 months ago

Can the author give me a pre-processing process? I can't predict my own data even if you only give the processed data.

htumlc commented 6 months ago

这个数据是提取完特征的吗？