Update README.md

README.md

@@ -6,14 +6,17 @@ This is the code repository for OctSurf: Efficient Hierarchical Voxel-based Mole
 
 ### Experiments
 
-#### PDBbind download  
+#### PDBbind Download  
+Download PDBbind general, refined, and core(CASF) from http://www.pdbbind.org.cn.   
+And fix some minor problems(replace several mol2 files by transforming sdf in general set, and remove the CONECT with index 0 pdb file). 
 ```angular2
 cd pdbbind
 bash data_download.sh
 cd ..
 ```
 
 #### Set-up enviroment
+Install packages and compile the required tools, e.g. the java tool for generating surface points, the C++ code for octree, and the operation (convolution etc.) API for tensorflow.
 ```angular2
 # compile java
 cd pdbbind/java
@@ -45,6 +48,11 @@ cd ../../
 ```
 
 #### Octree Generation Example
+Provide one example data 1A1E, also in refined-set.    
+
+Following steps can generate the points and build the OctSurf. (Default density for points is 6, and depth for OctSurf is 10.)    
+
+We also provide python tool to parse the generated OctSurf, and visualize it by generating vtk files that can visualize in Paraview.    
 ```angular2
 cd pdbbind/data_example/pdbbind
 cp ../../bash_scripts/octree_for_single.sh .
@@ -60,19 +68,27 @@ python octree_parse.py
 cd ../
 ```
 #### CNN modeling
-
 - prepare the data 
+First it will generate the points file for each complex in general, refined, core set. (The density of points can be specificed, low resolution OctSurf can use low density points to accelerate the process, here for depth=6 model, we use density 3).    
+
+Then the points and labels will be transformed into tfrecords file.   
 ```angular2
 bash data_prepare_model.sh
 cd ..
 ```
 - train model 
+Specify the config files (the network architecture, the input/log path, iterations etc.)  
+
+Train networks.
 ```angular2
 cd tensorflow/script
 python run_cls.py --config configs/train_resnet_depth6.yaml
 ```
 
-- test performance 
+- test performance  
+Specify the config files (the path for pretrained model/test dataset, network architecture, iterations etc)  
+
+Test the pre-trained model on test dataset, and report the performance.  
 ```angular2
 python test_reg_ave.py --config configs/test_resnet_depth6.yaml
 ```