Update README.md

README.md

@@ -53,46 +53,34 @@ Before running Effector-GAN, users should make sure all the following packages a
     pip3 install sklearn
 
 
-##**Effector-GAN**
+## **Effector-GAN**
 
-    git clone git@github.com:Wangys-prog/prPred.git  
-
-**Add prPred into into environment variables**
-
-**(./prPred/dist/prPred)**
-
-   ` export PATH=$PATH:/xxxx/xxxx/xxxx/prPred/dist/prPred`  
+  `git clone git@github.com:Wangys-prog/prPred.git`  
 
 
 ## Input parameters
-prPred -h  
-    $ -i  inputfile in FASTA format  
-    $ -o  output folder 
+   Effector-GAN.py -h  
+     $ -i  inputfile in FASTA format  
+     $ -o  output folder 
  
 ### usage
-    `prPred -i /xxxx/xxxx/test/test.fasta -o result ` 
-**or**
-**Using absolute path to invoke prPred.py (/xxxx/xxxx/prPred/prPred.py)**
-
-   ` python xxxx/xxxx/prPred/prPred.py -i /xxxx/xxxx/test/test.fasta -o /xxxx/xxxxx/result  `
-      
-###**Output file**
-
-    > domain_result   
->     R_protein_possibility.fasta
 
+  `Effector-GAN.py -i test.fasta -o test_result.csv ` 
+     `
 
 ## WGAN.py
 
-   Synthetic protein feature samples based on generative adversarial networks
+     Synthetic protein feature samples based on generative adversarial networks
 
 ## CTST2.py
    
-   Effector-GAN uses the leave-one-out cross-validation (LOOCV) method based on K nearest neighbor algorithm (KNN; K=1) classifier to evaluate the optimal synthetic protein feature samples, which are used to augment the original positive training samples
+     Effector-GAN uses the leave-one-out cross-validation (LOOCV) method based on K nearest neighbor algorithm (KNN; K=1) classifier to evaluate the optimal synthetic protein feature samples, which are used to augment the original positive training samples
 
- 
+## figure_tsne.py
+  
+    t-SNE-transformed 2D visualization of real and synthetic protein feature samples obtained from different training iterations
 
 ## **If you use prPred, please cite:** 
-    (1) Wang Y, Wang P, Guo Y, et al. prPred: A Predictor to Identify Plant Resistance Proteins by Incorporating k-Spaced Amino Acid (Group) Pairs[J]. Frontiers in bioengineering and biotechnology, 2021, 8: 1593.
+    (1) Wang Y, .Effector-GAN: prediction of fungal effector proteins based on pre-trained deep representation learning methods and generative adversarial networks
     (2) Yansu Wang, Murong Zhou, Quan Zou, Lei Xu. Machine learning for phytopathology: from the molecular scale towards the network scale. Briefings in Bioinformatics. 2021, Doi: 10.1093/bib/bbab037
     (3) Yansu Wang, Lei Xu, Quan Zou, Chen Lin. prPred-DRLF: plant R protein predictor using deep representation learning features. Proteomics. 2021. DOI: 10.1002/pmic.202100161