merge

.github/workflows/docker-image.yml

@@ -0,0 +1,30 @@
+name: Docker Image CI
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+
+jobs:
+
+  build:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Copy the compatible ParaAT version
+      run: cp -f /app/ParaAT.pl /app/ParaAT2.0/ParaAT.pl
+    - name: Build the Docker image
+      run: docker build . --file Dockerfile --tag dualhgt:$(date +%s)
+    - 
+      name: Login to Docker Hub
+      uses: docker/login-action@v3
+      with:
+        username: ${{ secrets.DOCKER_USERNAME }}
+        password: ${{ secrets.DOCKER_PASSWORD }}
+    - name: Push the Docker image
+      run: |
+        docker push dualhgt:$(date +%s)
+        docker push dualhgt:${{ github.sha }}

Dockerfile

@@ -75,14 +75,16 @@ RUN apt-get install -y locate libc6 muscle
 #USER appuser
 
 # Copy the source code into the container.
-COPY . .
+RUN git clone https://github.com/cl3mente/PlantPath2023.git
+
+RUN cp -f /app/PlantPath2023/ParaAT.pl /app/ParaAT2.0/ParaAT.pl
 
 ENV PATH=$PATH:/app/KaKs_Calculator3.0/src:/app/ParaAT2.0:/app/OrthoFinder
 
 RUN mkdir input
 
-RUN cp -f /app/ParaAT.pl /app/ParaAT2.0/ParaAT.pl
+
 
 VOLUME /app/input
 # CMD python HGT.py -i /data/bioinf2023/PlantPath2023/genomeANDgff -OFr /data/bioinf2023/PlantPath2023/genomeANDgff/results/prot/f7b812/Results_Feb23  -v -nt 50
-#ENTRYPOINT ["python","./HGT.py", "-i", "input"]
+#ENTRYPOINT ["python","./HGT.py", "-i", "input"]

dualHGT.py

@@ -771,7 +771,9 @@ def getHGT(matrix, gene_association):
     matrix2 = append_species(matrix, gene_association)
 
     # remove NAs
-    matrix2 = matrix2[matrix2['dist'] != "NA"]
+    #matrix2 = matrix2[matrix2['dist'] != "NA"]
+    matrix2[matrix2['dist'] == "NA"] = 0
+
     matrix2['dist'] = pd.to_numeric(matrix2['dist'], downcast='float')
 
     # initialize an empty column for the HGT score
@@ -924,7 +926,7 @@ def prepare_input(arg):
     except FileExistsError:
         print(f"Folder '{output_folder}' already exists. Wait a second??")
 
-    logfile = os.path.join(output_folder, 'log.txt')
+    logfile = os.path.join(output_folder, f'log_{current_date}.txt')
     logfile = open(logfile, 'w')
 
     def write_and_log(msg):

dualHGT/dualHGT/dualHGT.py

@@ -535,7 +535,7 @@ def kaksparallel(file: str) -> list:
     if not os.path.exists(output) or not os.path.getsize(output) > 0:
         runkaks = KAKS % (file,  #the .axt file passed as input
                           output,  # the output file
-                          "NG")  # NG is the model used for the calculation
+                          "MA")  # Model Averaging is used for the calculation
         run = subprocess.Popen(runkaks, shell=True, stderr=subprocess.PIPE, stdout=subprocess.PIPE)
 
         out, err = run.communicate()
@@ -771,7 +771,8 @@ def getHGT(matrix, gene_association):
     matrix2 = append_species(matrix, gene_association)
 
     # remove NAs
-    matrix2 = matrix2[matrix2['dist'] != "NA"]
+    # matrix2 = matrix2[matrix2['dist'] != "NA"]
+    matrix2[matrix2['dist'] == "NA"] = 0
     matrix2['dist'] = pd.to_numeric(matrix2['dist'], downcast='float')
 
     # initialize an empty column for the HGT score