fangpingwan / neodti Goto Github PK

When I'm running the NeoDTI cv.py code,After running the code every time, before 2975 steps, it runs again from 0 steps, and keeps cycling, unable to print the final TXT result file. I would like to ask how to solve this problem, thank you for your help.The corresponding results are as follows:

step 2975 total and dtiloss 5052731.0 119.068855
valid auc aupr, 0.9600577877248452 0.8524570307967804 test auc aupr 0.9484424972853837 0.849887829154117
WARNING:tensorflow:From D:\miniconda3\envs\python_env_3.6\lib\site-packages\tensorflow\python\util\tf_should_use.py:170: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02.
Instructions for updating:
Use tf.global_variables_initializer instead.
step 0 total and dtiloss 235253940.0 1625.3303
valid auc aupr, 0.40999680272833844 0.085343755629563 test auc aupr 0.4201471685810438 0.07260654527827701
step 25 total and dtiloss 12311560.0 1506.531
valid auc aupr, 0.504126848792734 0.10535242762988771 test auc aupr 0.4953750481625483 0.08972111425033276

Hi, is the dataset for your Covid-19 KG paper: Knowledge-Graph-Based Drug Repositioning against COVID-19 by Graph Convolutional Network with Attention Mechanism?

Hi, thanks for releasing the source code. Could you please give the statistics of the knowledge graph? How many entities and edges are in the knowledge graph? Thank you.

您好！现在的代码只提供了正负样本1:10和全部负样本两个选项，请问该如何修改代码，使得它支持正负样本1:1呢？