Update README.md

 # Deep GONet
 # Deep GONet
 
 
-From the article entitled **Deep GONet: Self-explainable deep neural network based on Gene Ontology for phenotype prediction from gene expression data** (submitted to APBC 2021) by Victoria Bourgeais, Farida Zehraoui, Mohamed Ben Hamdoune, and Blaise Hanczar.
+Original code from the article entitled **Deep GONet: Self-explainable deep neural network based on Gene Ontology for phenotype prediction from gene expression data** (accepted both in APBC 2021 and BMC Bioinformatics) by Victoria Bourgeais, Farida Zehraoui, Mohamed Ben Hamdoune, and Blaise Hanczar.
 
 
 ---
 ---
 
 
@@ -14,7 +14,7 @@ The code is implemented in Python using the [Tensorflow](https://www.tensorflow.
 
 
 ### Dataset
 ### Dataset
 
 
-The full dataset can be downloaded on ArrayExpress database under the id [E-MTAB-3732](https://www.ebi.ac.uk/arrayexpress/experiments/E-MTAB-3732/). Here, you can find the pre-processed training and test sets:
+The full microarray dataset can be downloaded on ArrayExpress database under the id [E-MTAB-3732](https://www.ebi.ac.uk/arrayexpress/experiments/E-MTAB-3732/). Here, you can find the pre-processed training and test sets:
 
 
 [training set](https://entrepot.ibisc.univ-evry.fr/f/5b57ab5a69de4f6ab26b/?dl=1)
 [training set](https://entrepot.ibisc.univ-evry.fr/f/5b57ab5a69de4f6ab26b/?dl=1)
 
 
@@ -22,9 +22,12 @@ The full dataset can be downloaded on ArrayExpress database under the id [E-MTAB
 
 
 Additional files for NN architecture: [filesforNNarch](https://entrepot.ibisc.univ-evry.fr/f/6f1c513798df41999b5d/?dl=1) 
 Additional files for NN architecture: [filesforNNarch](https://entrepot.ibisc.univ-evry.fr/f/6f1c513798df41999b5d/?dl=1) 
 
 
+TCGA dataset can be downloaded from [GDC portal](https://portal.gdc.cancer.gov/). 
+
 ### Usage
 ### Usage
 
 
-Deep GONet was achieved with the $L_{GO}$ regularization and the hyperparameter $\alpha=1e^{-2}$.  
+The following show how to train and evaluate the neural network.
+Deep GONet was achieved with the $L_{GO}$ regularization and the hyperparameter $\alpha=1e^{-2}$ on the microarray dataset.
 To replicate it, the command line flag *type_training* needs to be set to LGO (default value) and the command line flag *alpha* to $1e^{-2}$ (default value).  
 To replicate it, the command line flag *type_training* needs to be set to LGO (default value) and the command line flag *alpha* to $1e^{-2}$ (default value).  
 
 
 There exists 3 functions (flag *processing*): one is dedicated to the training of the model (*train*), another one to the evaluation of the model on the test set (*evaluate*), and the last one to the prediction of the outcomes of the samples from the test set (*predict*).
 There exists 3 functions (flag *processing*): one is dedicated to the training of the model (*train*), another one to the evaluation of the model on the test set (*evaluate*), and the last one to the prediction of the outcomes of the samples from the test set (*predict*).
@@ -86,4 +89,9 @@ python DeepGONet.py --alpha=0 --EPOCHS=100 --is_training=True --display_step=5 -
 
 
 ###  Interpretation tool
 ###  Interpretation tool
 
 
-Please see the notebook entitled *Interpretation_tool.ipynb* to perform the biological interpretation of the results.
\ No newline at end of file
+Please see the notebook entitled *Interpretation_tool.ipynb* to perform the biological interpretation of the results.
+
+## How to cite this work?
+
+Bourgeais, V., Zehraoui, F., Ben Hamdoune, M., & Hanczar, B. (2021). Deep GONet: Self-explainable deep neural network based on Gene Ontology for phenotype prediction from gene expression data. BMC Bioinformatics, 22(10), 455. https://doi.org/10.1186/s12859-021-04370-7
+