added matrix to notebook

module1_2/inputData/project-buxus/config.yaml

@@ -16,7 +16,7 @@ output_file:
   mwm_input_template: "/mwminputAnc"
   mwm_output_template: "/mwmoutputAnc"
   contig_template: "/contigAnc"
-  dcj_output_path: "/dcj_output.txt"
+  dcj_output_path: "/dcj_output"
   dcj_summary_path: "/dcj_summary.txt"
 
 # input path

module1_2/inputData/project-monocots/config.yaml

@@ -16,7 +16,7 @@ output_file:
   mwm_input_template: "/mwminputAnc"
   mwm_output_template: "/mwmoutputAnc"
   contig_template: "/contigAnc"
-  dcj_output_path: "/dcj_output.txt"
+  dcj_output_path: "/dcj_output"
   dcj_summary_path: "/dcj_summary.txt"
 
 # input path

module1_2/src/GeneFamily.py

@@ -93,11 +93,21 @@ class GeneFamily:
                 else:
                     # median_structure.append(line.rstrip().split("\t"))
                     newick_structure = line.rstrip()
-
-                    median_structure = self.convert_newick(newick_structure, all_leaves)
+                    conversion_input = newick_structure[:]
+                    
+                    # print(newick_structure)
+                    # print(type(conversion_input))
+                    
+                    # if newick structure is in the form "genomeName_genomeID" comment out for-loop if it's just genomeID
+                    for genome in all_leaves:
+                        genome_string = (str(genome[1]) + "_")
+                        conversion_input = conversion_input.replace(genome_string, "")
+
+                    # print(conversion_input)
+                    median_structure = self.convert_newick(conversion_input, all_leaves)
 
         all_leaves.sort()
-        print(median_structure)
+        # print(median_structure)
 
         return all_leaves, median_structure, newick_structure
 

module1_2/src/module1_main.py

@@ -71,23 +71,30 @@ def main():
 
     print("Start")
 
-    directory = parsed_config["output_path"] + parsed_config["project_name"] + "/"
+    directory = parsed_config["output_path"] + parsed_config["project_name"]
     os.makedirs(directory, exist_ok=True)
 
     # STEP 1: Reading in Genomes and Newick Tree Structure
+    print("STEP 1: Reading in Genomes and Newick Tree Structure")
     gene_family = GeneFamily(parsed_config)
     all_leaves, median_structure, newick_structure = gene_family.get_leaves_and_tree_info()
     # print(all_leaves)
     # print(median_structure)
+    print("Step 1 DONE")
 
     # STEP 2: Creating Gene Families
+    print("STEP 2: Creating Gene Families")
     gene_family.make_gene_family(all_leaves)
+    print("Step 2: DONE")
 
     # STEP 3: Representing Genomes by Gene Family Labels
+    print("STEP 3: Representing Genomes by Gene Family Labels")
     initialize_genome = Genome(gene_family.gene_list, all_leaves, parsed_config)
     genome = initialize_genome.get_genome_in_string()
+    print("Step 4: DONE")
 
-    # STEP 4-6: Generating Maximum Weight Matching Input, Performing MWMatching, Constructing Ancestral Contigs
+    # STEPS 4-6: Generating Maximum Weight Matching Input, Performing MWMatching, Constructing Ancestral Contigs
+    print("STEPS 4-6: Generating Maximum Weight Matching Input, Performing MWMatching, Constructing Ancestral Contigs")
 
     # Parameters for Generating Maximum Weight Matching Inputs
     window_size = parsed_config['ws']
@@ -98,56 +105,72 @@ def main():
     # tree_node = num_genomes - 2
     # print(num_genomes, tree_node, window_size, num_gene_families)
 
-    print("Start MWM Input")
     input_tree_node = MWMInputTreeNode(genome, all_leaves)
 
     anc = 1
-    dcj_files = ""
-    start_path = parsed_config['output_path'] + parsed_config['project_name']
+    dcj_files = []
 
     for structure in median_structure:
-        print(structure)
+        # print(structure)
 
         # output file paths for Maximum Weight Matching Input, Maximum Weight Matching Output and Ancestral Contigs
-        outfile_mwmin = start_path + parsed_config["output_file"]["mwm_input_template"] + str(anc) + ".txt"
-        outfile_mwmout = start_path + parsed_config["output_file"]["mwm_output_template"] + str(anc) + ".txt"
-        outfile_contig = start_path + parsed_config["output_file"]["contig_template"] + str(anc) + ".txt"
+        outfile_mwmin = directory + parsed_config["output_file"]["mwm_input_template"] + str(anc) + ".txt"
+        outfile_mwmout = directory + parsed_config["output_file"]["mwm_output_template"] + str(anc) + ".txt"
+        outfile_contig = directory + parsed_config["output_file"]["contig_template"] + str(anc) + ".txt"
 
         # Adding File Paths for later DCJ Computations
-        dcj_files += (outfile_contig + " ")
+        dcj_files.append(outfile_contig)
 
         # Generating Maximum Weight Matching Input
+        print("Starting MWM Input Generation")
         mwm_input = input_tree_node.get_mwm_input(structure, num_gene_families, window_size, min_adj_weight, outfile_mwmin)
+        # print("MWM Input Generation DONE")
 
         # Performing Maximum Weight Matching
-        # maxWeightMatching(mwm_input, outfile_mwmout)
-        print("MWM DONE")
+        print("Starting Maximum Weight Matching")
+        maxWeightMatching(mwm_input, outfile_mwmout)
+        # print("Maximum Weight Matching DONE")
 
         # Constructing Ancestral Contigs
+        print("Starting Construction of Ancestral Contig")
         contig = Contig(outfile_mwmout, num_gene_families)
         contig.get_edge()
         list_telomeres = contig.find_telomeres()
         contig_list = contig.get_contigs(list_telomeres, outfile_contig, anc)
+        # print("Contig Construction DONE")
 
         anc += 1
 
     # STEP 7: Calculating DCJ Distance Between Ancestral Contigs
+    print("STEP 7: Calculating DCJ Distance Between Ancestral Contigs")
     jar_path = parsed_config['input_file']['jar_path']
-    dcj_output_path = start_path + parsed_config['output_file']['dcj_output_path']
-    java_command = "java -jar " + jar_path + "/UniMoG-java11.jar " + dcj_files + "-m=1 -p > " + dcj_output_path
-    os.system(java_command)
-
-    with open(dcj_output_path, 'r') as f:
-        dcj_info = f.readlines()
-        dcj_summary = start_path + parsed_config['output_file']['dcj_summary_path']
-
-        with open(dcj_summary, 'w') as dcj_file:
-            for i in range(len(median_structure)):
-                dcj_file.write("median structure for Ancestor  "+str((i + 1))+":"+ "%s" % median_structure[i] + "\n")
-                
-            for line in dcj_info:
-                if line[0] == '>':
-                    dcj_file.write(line)
+    dcj_output = []
+
+    for i in range(1, anc):
+        for j in range(i + 1, anc):
+            dcj_output_path = directory + parsed_config['output_file']['dcj_output_path'] + str(i) + "_" + str(j) + ".txt"
+            command = "java -jar " + jar_path + "/UniMoG-java11.jar " + str(dcj_files[i - 1]) + " " + str(dcj_files[j - 1]) + " -m=1 -p >" + dcj_output_path
+            dcj_output.append(dcj_output_path)
+            os.system(command)
+
+    print("Step 7 DONE")
+
+    dcj_summary = directory + parsed_config['output_file']['dcj_summary_path']
+
+    print("Generating Summary of DCJ Calculations")
+    with open(dcj_summary, 'w') as dcj_summary_file:
+        for i in range(len(median_structure)):
+            dcj_summary_file.write("median structure for Ancestor  "+str((i + 1))+":"+ "%s" % median_structure[i] + "\n")
+
+        for file in dcj_output:
+            path = file
+
+            with open(path, 'r') as dcj_file:
+                dcj_info = dcj_file.readlines()
+
+            dcj_summary_file.write(dcj_info[0])
+
+    print("Summary Generated")
 
     # print(java_command)
     # print(dcj_files)