changed path creation

cami/AlgorithmWrapper.py

@@ -32,10 +32,10 @@ class AlgorithmWrapper(object):
         self.uid = uid
 
     def set_homepath(self, path):
-        self.home_path = path
+        self.home_path = os.path.abspath(path)
 
     def create_tmp_output_dir(self, tmp_dir):
-        out_dir = f'{tmp_dir}/{self.name}'
+        out_dir = os.path.join(tmp_dir, self.name)
         if not os.path.exists(out_dir):
             os.mkdir(out_dir)
             print(f"created temporary directory for {self.name} named {out_dir}...")

cami/DiamondWrapper.py

@@ -28,13 +28,14 @@ class DiamondWrapper(AlgorithmWrapper):
         # Run DIAMOnD.
 
         # path to diamond
-        diamond = f'cd {self.home_path}/tools/DIAMOnD/; python DIAMOnD.py'
+        diamond_path = os.path.join(self.home_path, 'tools/DIAMOnD/')
+        diamond = f'cd {diamond_path}; python DIAMOnD.py'
         ppi = inputparams[0] # path to ppi inputfile
         seeds = inputparams[1] # path to seed inputfile
         nof_predictions = inputparams[2] # how many active genes should be predicted
 
         out_filename = self.name_file('out') # name the outputfile
-        algo_output = f'{self.output_dir}/{out_filename}' # specify the output location
+        algo_output = os.join(self.output_dir, out_filename) # specify the output location
         #MC:
         #CONFIG alpha = 1
         command = f'{diamond} {ppi} {seeds} {nof_predictions} {self.alpha} {algo_output}'
@@ -50,9 +51,9 @@ class DiamondWrapper(AlgorithmWrapper):
         # prepare inputfiles
         # name ppi and seed file, specify path to files
         ppi_filename = self.name_file('ppi')
-        ppi_file = f'{self.output_dir}/{ppi_filename}'
+        ppi_file = os.path.join(self.output_dir, ppi_filename)
         seed_filename = self.name_file('seeds')
-        seed_file = f'{self.output_dir}/{seed_filename}'
+        seed_file = os.path.join(self.output_dir, seed_filename)
 
         # create ppi file
         with open(ppi_file, "w") as file:

cami/DominoWrapper.py

@@ -45,12 +45,11 @@ class DominoWrapper(AlgorithmWrapper):
         outputname = (os.path.basename(seeds)).rsplit(".")[0]
         #MC:
         #CONFIG output_name = 'modules.out'
-        algo_output = f'{self.output_dir}/{outputname}/{self.output_name}'
-
+        algo_output = os.path.join(self.output_dir, outputname, self.output_name)
         outputfilename = self.name_file('out', 'out')
-        command = f'mv {algo_output} {self.output_dir}/{outputfilename}'
+        command = f'mv {algo_output} {os.path.join(self.output_dir, outputfilename)}'
         subprocess.call(command, shell=True, stdout=subprocess.PIPE)
-        algo_output = f'{self.output_dir}/{outputfilename}'
+        algo_output = os.path.join(self.output_dir, outputfilename)
 
         assert os.path.exists(algo_output), f'Could not find output file {algo_output} for domino'
         print(f"{self.name} results saved in {algo_output}")
@@ -66,10 +65,10 @@ class DominoWrapper(AlgorithmWrapper):
         print(f'creating {self.name} input files in {self.output_dir}')
 
         ppi_filename = self.name_file('ppi', 'sif')
-        ppi_file = f'{self.output_dir}/{ppi_filename}'
+        ppi_file = os.path.join(self.output_dir, ppi_filename)
 
         seed_filename = self.name_file('seeds')
-        seed_file = f'{self.output_dir}/{seed_filename}'
+        seed_file = os.path.join(self.output_dir, seed_filename)
 
         # create the ppi_file which contains all edges in the ppi_network
         with open(ppi_file, "w") as file:
@@ -89,7 +88,7 @@ class DominoWrapper(AlgorithmWrapper):
         print(f'{self.name} seeds are saved in {seed_file}')
 
         slices_filename = self.name_file('slices')
-        slices_output = f'{self.output_dir}/{slices_filename}'
+        slices_output = os.path.join(self.output_dir, slices_filename)
 
         if not os.path.exists(slices_output):
             print('creating domino slices_file...')

cami/RobustWrapper.py

@@ -42,14 +42,14 @@ class RobustWrapper(AlgorithmWrapper):
         # [5] reduction factor
         # [6] number of steiner trees to be computed
         # [7] threshold
-
-        robust = f'cd {self.home_path}/tools/robust; python robust.py'
+        robust_path = os.join(self.home_path, 'tools/robust')
+        robust = f'cd {robust_path}; python robust.py'
 
         ppi = inputparams[0]
         seeds = inputparams[1]
 
         out_filename = self.name_file('out')
-        algo_output = f'{self.output_dir}/{out_filename}'
+        algo_output = os.path.join(self.output_dir, out_filename)
         # algo_output = f'./ms.graphml'
         #0.25 0.9 30 0.1
         #MC:
@@ -73,9 +73,9 @@ class RobustWrapper(AlgorithmWrapper):
 
         # prepare inputfiles
         ppi_filename = self.name_file('ppi')
-        ppi_file = f'{self.output_dir}/{ppi_filename}'
+        ppi_file = os.path.join(self.output_dir, ppi_filename)
         seed_filename = self.name_file('seeds')
-        seed_file = f'{self.output_dir}/{seed_filename}'
+        seed_file = os.path.join(self.output_dir, seed_filename)
 
         with open(ppi_file, "w") as file:
             file.write('node1\tnode2\n')

cami/TemplateWrapper.py

@@ -6,6 +6,11 @@ from configparser import ConfigParser
 class TemplateWrapper(AlgorithmWrapper):
     def __init__(self):
         """Each tool needs certain predefined instance variables:        
+        The only instance variables that need to be defined for each tool individually are:
+        - name (string): The name of the algorithm/tool
+        - code (int): A unique integer code for this tool. Choose any number (<21) that is not taken by other tools yet (currently taken are: 0,1,2,3)
+        - any constant numbers or variables that are defined in the config file for this tool
+        
         The following variables are inherited from the AlgorithmWrapper Super Class:
         - UID (string)
         - weight (int)
@@ -15,11 +20,6 @@ class TemplateWrapper(AlgorithmWrapper):
         - home_path (string)
         - config (string)
         There is no need to redefine these variables when introducing a new algorithm.
-        
-        The only instance variables that need to be defined for each tool individually are:
-        - name (string): The name of the algorithm/tool
-        - code (int): A unique integer code for this tool. Choose any number (<21) that is not taken by other tools yet (currently taken are: 0,1,2,3)
-        - any constant numbers or variables that are defined in the config file for this tool
         """
         super().__init__()
         self.name = '<tool_name>'
@@ -42,7 +42,6 @@ class TemplateWrapper(AlgorithmWrapper):
         Hint: Execute the algorithm and specify the outputfile name. From that outputfile 
         extract the predicted Active Module by using extract_output.
         
-
         Args:
             inputparams (list): A list of parameters for the algorithm that is defined via
                                 prepare_input()
@@ -109,7 +108,7 @@ class TemplateWrapper(AlgorithmWrapper):
            transforms them into a list of vertices in the PPI network.
            This list is handed back to the main CAMI suite for further
            processing.
-           FYI: CAMI uses the indices in the PPI network to reference 
+           Hint: CAMI uses the indices in the PPI network to reference 
            the input genes i.e. the genes in the list do not correspond
            to the genes in the input files.
 

cami/cami.py

 #!/usr/bin/env python3
+from cProfile import label
 import os
 import sys
 import shutil
-from unittest import result
+from turtle import color
 from DiamondWrapper import DiamondWrapper
 from DominoWrapper import DominoWrapper
 from RobustWrapper import RobustWrapper
@@ -48,16 +49,12 @@ def main(ppi_network, seeds, tools, tool_weights, consensus, evaluate,
         if choice == 'y':
             pass
         else:
-            print('Abort. Please try again.')
+            print('Aborted because of missing seeds. Please try again.')
             exit(1)
 
     seed_lst = checked_seed_lst.copy()
     print(f'Continuing with vertices at indices {[int(seed) for seed in seed_lst]} as input seeds')
 
-    # set weights for seed genes in ppi_graph
-    for seed in seed_lst:
-        ppi_graph.vertex_properties["cami_score"][seed] = seed_score #CONFIG seed_score = 10.0
-
     # change directory to ~/cami/cami (home of cami.py)
     cami_home = sys.argv[0].rsplit('/', 1)
     os.chdir(cami_home[0])
@@ -65,7 +62,7 @@ def main(ppi_network, seeds, tools, tool_weights, consensus, evaluate,
     home_path = os.path.dirname(os.getcwd())
     print(home_path)
     if identifier==None:
-        identifier = uuid.uuid4()
+        identifier = str(uuid.uuid4())
 
     if output_dir==None:
         output_dir = f'{home_path}/data/output/{identifier}'
@@ -106,7 +103,9 @@ def main(ppi_network, seeds, tools, tool_weights, consensus, evaluate,
     for idx, tool in enumerate(tool_wrappers):
         tool.set_weight(float(tool_weights[idx]))
 
-    cami = cami_suite.cami(ppi_graph, seed_lst, tool_wrappers, output_dir, identifier, tmp_dir, home_path, configuration)
+    original_ppi = ppi_graph.copy()
+    cami = cami_suite.cami(ppi_graph, seed_lst, tool_wrappers, output_dir, identifier, tmp_dir, home_path, configuration, seed_score)
+
         
     if ncbi:
         cami.ncbi = True
@@ -140,220 +139,227 @@ def main(ppi_network, seeds, tools, tool_weights, consensus, evaluate,
     
     elif (not consensus and not evaluate):
         cami.reset_ppi_graph()
+        
     # SEED VARIATION
     if seed_variation:
-        def make_consensus():
+        def make_consensus(vis=False):
             result_sets = cami.make_predictions()
             cami.create_consensus(result_sets)
-            if visualize:
+            if visualize and vis:
                 url = cami.visualize()
                 cami.download_diagram(url)
+        with open('/Users/Mia/cami_local/cami/data/output/explorativeness.tsv', 'a') as f:
+            make_consensus(vis=True)
+            seedname = seeds.rsplit('/',1)[0]
+            for tool in cami.result_gene_sets:
+                f.write(f'\n{seedname}\t{len(cami.seed_lst)}\t{tool}\t{len(cami.result_gene_sets[tool])}')
+        
+        with open(f'{output_dir}/00_node_degrees.tsv', 'w') as node_degrees:
+            node_degrees.write('vertex\tout_degree\tin_degree\n')
+            for vertex in cami.ppi_graph.vertices():
+                node_degrees.write(f'{cami.ppi_vertex2gene[vertex]}\t{vertex.out_degree()}\t{vertex.in_degree()}\n')   
+        
                 
         # initialize cami and seed_var
-        random.seed(20)
-        removal_frac = 0.5
-        nof_iterations = 3
         base_seeds = cami.origin_seed_lst
-        used_tools = [tool for tool in cami.result_gene_sets]
+        original_seeds = [cami.ppi_vertex2gene[seed] for seed in base_seeds]
+        print(f'Initializing CAMI and the seed variation by running CAMI with all given seeds:{original_seeds}')
+        #make_consensus(vis=True)
+        random.seed(50)
+        removal_frac = 0.2
+        nof_iterations = int(seed_variation)
+        used_tools = list(cami.result_gene_sets.keys())
         nof_seeds = len(base_seeds)
-        nof_removals = int(nof_seeds * removal_frac)
-        
-        make_consensus()
-
+        nof_removals = max([int(nof_seeds * removal_frac), 1])
         variation_results = []
-        with open(f'{output_dir}/seedvariation_results1.tsv', 'w') as res_table1:
-            with open(f'{output_dir}/seedvariation_results2.tsv', 'w') as res_table2:
+        result_file_1 = f'{output_dir}/00_seedvariation_results1.tsv'
+        result_file_2 = f'{output_dir}/00_seedvariation_results2.tsv'
+        result_file_3 = f'{output_dir}/00_seedvariation_results3.tsv'
+        result_file_4 = f'{output_dir}/00_seedvariation_results4.tsv'
+        with open(result_file_1, 'w') as res_table1:
+            with open(result_file_2, 'w') as res_table2:
+                with open(result_file_3, 'w') as res_table3:
+                    with open(result_file_4, 'w') as res_table4:
                         res_table1.write('id')
-                res_table2.write('id\tnof_removed_seeds\tremoved_seeds\t{used_seeds}')
-                res_table2.write('\ttool')
-                res_table2.write(f'\trediscovery_prevalence')
-                res_table2.write('\trediscovery_rate')
-                res_table2.write('\trediscovered_seeds')
+                        res_table2.write('id\tnof_removed_seeds\tremoved_seeds\t{used_seeds}\ttool\trediscovery_prevalence')
+                        res_table2.write('\trediscovery_rate\trediscovered_seeds')
                         for tool in used_tools:
                             res_table1.write(f'\t{tool}')                    
                         res_table1.write('\n')
                         res_table2.write('\n')
+                        res_table3.write('id\ttrue_positives\trediscoveries/module_size\n')
+                        tp_rate_dict = {k:list() for k in used_tools}
+                        module_size_dict = {k:list() for k in used_tools}
                         
                         for ident in range(nof_iterations):
                             res_table1.write(f'{ident}')
                             # update uid
                             new_identifier = identifier + f'_{ident}'
                             cami.reset_cami(new_uid=new_identifier)
+#                            cami.ppi_graph = original_ppi
                             
                             #remove seeds
+                            print(f'Removing {nof_removals} seeds from the original seed list...')
                             removed_seeds_idx = random.sample(list(range(nof_seeds)), nof_removals)
                             removed_seeds = cami.remove_seeds(removed_seeds_idx)
-                    
+                            rem_seeds = [cami.ppi_vertex2gene[seed] for seed in removed_seeds]
+                            print(f'Removed: {rem_seeds} from the seed list')
+                            print('Updating tools and repeat CAMI')
                             # reinitialize tools
                             cami.initialize_all_tools()
                             
                             # repeat consensus
+                            if ident%5==0:     
+                                make_consensus(vis=True)
+                            else:
                                 make_consensus()
                             
                             used_seeds = [cami.ppi_vertex2gene[seed] for seed in cami.seed_lst]
-                    rem_seeds = [cami.ppi_vertex2gene[seed] for seed in removed_seeds]
+                            
+                            
                             result_dict = cami.result_gene_sets
                             redisc_rate_dict = {}
                             redisc_seeds_dict = {}
-                    print(result_dict)
+                            
                             for tool in result_dict:
+                                nof_predictions = len(result_dict[tool]) + len(used_seeds)
                                 redisc_seeds = list(set(result_dict[tool]).intersection(set(rem_seeds)))
                                 redisc_prev = len(redisc_seeds)
                                 redisc_rate = redisc_prev / nof_removals
                                 redisc_rate_dict[tool] = redisc_rate #true positive rate: rate verhältnis von gefundenen und allgemein gefundenen
                                 redisc_seeds_dict[tool] = redisc_seeds
+                                tp_rate = redisc_prev / len(removed_seeds)
+                                tp_rate_dict[tool].append(tp_rate)
+                                module_size_frac = redisc_prev / nof_predictions
+                                assert module_size_frac <= 1
+                                module_size_dict[tool].append(module_size_frac)
+                                res_table3.write(f'{ident}\t{tool}\t{tp_rate}\t{module_size_frac}\n')
+                                res_table1.write('\t')
                                 for idx,seed in enumerate(redisc_seeds):
                                     if idx == 0:
-                                res_table1.write(f'\t{redisc_seeds[0]}')
+                                        res_table1.write(f'{redisc_seeds[0]}')
                                     else:
                                         res_table1.write(f',{seed}') 
-                        res_table2.write(f'{tool}')
                                 print(f'{tool} rediscovered {redisc_seeds} after removing {rem_seeds}.')
-                        res_table2.write(f'{ident}\t{nof_removals},\t{rem_seeds}\t{used_seeds}\t{tool}\t{redisc_prev}\t{redisc_rate}\t{redisc_seeds}\n')
+                                res_table2.write(f'{ident}\t{tool}\t{nof_removals},\t{rem_seeds}\t{used_seeds}\t{redisc_prev}\t{redisc_rate}\t{redisc_seeds}\n')
                             res_table1.write('\n')
                             variation_results.append((redisc_rate_dict, redisc_seeds_dict, used_seeds, rem_seeds))
                             
-        print(variation_results)
+        print(f'Result tables are saved in the following locations:')
+        print(f'Rediscovered seeds: {result_file_1}')
+        print(f'Rediscovery Rates: {result_file_2}')
+        print(f'Sensitivity: {result_file_3}')
+#        print(variation_results)
         rediscovery_rates_results = [results[0] for results in variation_results]
-        print(rediscovery_rates_results)
+#        print(rediscovery_rates_results)
         tools = [tool for tool in rediscovery_rates_results[0].keys()]
-        print(tools)
         redisc_rates = [[res[tool] for res in rediscovery_rates_results] for tool in tools]
         
 
         #PLOT
         
         # Create a figure instance
-        fig = plt.figure()
+        plt.figure(figsize=(16,6))
+        
+        # Extract Figure and Axes instance
+        ax1 = plt.subplot(1,2,1, label='ax1')
 
+        # Create a plot
+        violins1 = ax1.violinplot(redisc_rates, showmeans=True, showextrema=True)
+        
+        for violinpart in list(violins1.keys())[2:]:
+            violins1[violinpart].set_color('k')
+        for violin in violins1['bodies']:
+            violin.set_facecolor('red')
+        # Add title
+        ax1.set_title(f'Rediscovery rate after randomly removing {nof_removals} seeds\n{nof_iterations} times from {identifier} seeds.', wrap=True)
+
+        ax1.set_xticks(list(range(1,len(tools)+1)))
+        ax1.set_xticklabels(tools)
+
+        ax1.set_ylabel('Rediscovery rate (<rediscovered seeds>/<removed seeds>)', wrap=True)
+        
+        # ax4 = plt.subplot(1,3,2, label='ax4')
+        # violins2 = ax4.violinplot([tp_rate_dict[tool] for tool in tools], showmeans=True, showextrema=True)
+        # for violinpart in list(violins2.keys())[2:]:
+        #     violins2[violinpart].set_color('k')
+        # for violin in violins2['bodies']:
+        #     violin.set_facecolor('orange')
+        # # Add title
+        # ax4.set_title(f'True positive rates after randomly removing {nof_removals} seeds\n{nof_iterations} times from {identifier} seeds.', wrap=True)
+
+        # ax4.set_xticks(list(range(1,len(tools)+1)))
+        # ax4.set_xticklabels(tools)
+
+        # ax4.set_ylabel('Sensitivity (TP/TP + FN)', wrap=True)
+
+        ax5 = plt.subplot(1,2,2)
+        violins3 = ax5.violinplot([module_size_dict[tool] for tool in tools], showmeans=True, showextrema=True)
+        # Add title
+        for violinpart in list(violins3.keys())[2:]:
+            violins3[violinpart].set_color('k')
+            
+        for violin in violins3['bodies']:
+            violin.set_facecolor('blue')
+        ax5.set_title(f'Ratio of number of rediscovered seeds and predicted module size\nafter removing {nof_removals} seeds {nof_iterations} times from {identifier} seeds.', wrap=True)
+
+        ax5.set_xticks(list(range(1,len(tools)+1)))
+        ax5.set_xticklabels(tools)
+        
+        ax5.set_ylabel('(<rediscovered seeds>/<module size>)')
+        plt.tight_layout
+        plt.savefig(f'{output_dir}/00_{identifier}_seed_variation_result.png')
+        
+        print(f'Violin plot saved under: 00_{identifier}_seed_variation_result.png')
+        # plot TP Rate
         
         # Extract Figure and Axes instance
-        fig, ax = plt.subplots()
+        fig2, ax2 = plt.subplots()
 
+        colors = ['red', 'blue', 'black', 'purple']
+        legend = []
         # Create a plot
-        ax.violinplot(redisc_rates, showmeans=True, showextrema=True)
+        for idx,tool in enumerate(used_tools):
+            scatter = ax2.scatter(list(range(1,nof_iterations + 1)),tp_rate_dict[tool], color=colors[idx])
+            legend.append(scatter)
         
+        plt.legend(legend,
+                   used_tools)
         # Add title
-        ax.set_title(f'Rediscovery rate after randomly removing {nof_removals} seeds {nof_iterations} times from {identifier} seeds.')
-
-        ax.set_xticks(list(range(1,len(tools)+1)))
-        ax.set_xticklabels(tools)
-        
-        # Save the figure and show
-        plt.tight_layout()
-        plt.savefig(f'{output_dir}/{identifier}_seed_variation_rediscovery_rates.png')
-        
-        # variation_results:
-        # [tuple(<list of used seeds>, 
-        #        <list of removed_seeds>, 
-        #        <results dict: <tool>:<list of predicted genes>>), tuple(...), ...]
-        
-
-    
-    # # SEED VARIATION    
-    # if seed_variation:
-    #     random.seed(10)
-    #     removal_frac = 0.3
-    #     nof_iterations = 5
-        
-    #     result_sets = cami.make_predictions()
-    #     cami.create_consensus(result_sets)
-    #     if visualize:
-    #         url = cami.visualize()
-    #         cami.download_diagram(url)
-            
-    #     base_seeds = cami.seed_lst #lst
-    #     base_results = cami.result_gene_sets #dict
-    #     used_tools = [tool for tool in base_results]
-    #     nof_removals = int(len(base_seeds) * removal_frac)
-    #     nof_seeds = len(base_seeds)
-    #     variation_results = []
-    #     tool_dict = {'CAMI':0, 'DIAMOnD':1, 'DOMINO':2, 'ROBUST':3}
-    #     with open(f'{output_dir}/seedvariation_results.tsv', 'w') as res_table:   
-    #         res_table.write('id')
-    #         for tool in used_tools:
-    #             res_table.write(f'\t{tool}')
-    #         res_table.write('\n')
-    #         for ident in range(nof_iterations):
-    #             #reinitialize cami
-    #             #cami.ppi_graph = ppi_graph
-    #             cami.seed_lst = base_seeds
-    #             new_identifier = identifier + f'_{ident}'
-    #             #cami.result_gene_sets = {}
-    #             #cami.cami_vertices = []
-    #             res_table.write(f'{ident}')
-                
-    #             #remove seeds
-    #             removed_seeds_idx = random.sample(list(range(nof_seeds)), nof_removals)
-    #             removed_seeds = cami.remove_seeds(removed_seeds_idx).copy()
-    #             cami = cami_suite.cami(ppi_graph, cami.seed_lst, tool_wrappers, output_dir, new_identifier, tmp_dir, home_path, configuration)
-    #             cami.initialize_all_tools()
-    #             cami.initial_seed_lst = initial_seedlst
-    #             for seed in removed_seeds:
-    #                 cami.ppi_graph.vertex_properties["cami_score"][seed] = 0.0 #CONFIG seed_score = 10.0
-    #                 print(cami.ppi_graph.vertex_properties["predicted_by"][seed])
-    #             for seed in cami.seed_lst:
-    #                 cami.ppi_graph.vertex_properties["cami_score"][seed] = 10.0
-    #                 print(cami.ppi_graph.vertex_properties["predicted_by"][seed])
-                
-    #             result_sets = cami.make_predictions()
-    #             cami.create_consensus(result_sets)
-    #             if visualize:
-    #                 url = cami.visualize()
-    #                 cami.download_diagram(url)
-                
-    #             used_seeds = [cami.ppi_vertex2gene[seed] for seed in cami.seed_lst]
-    #             rem_seeds = [cami.ppi_vertex2gene[seed] for seed in removed_seeds]
-    #             result_dict = cami.result_gene_sets
-    #             redisc_rate_dict = {}
-    #             redisc_seeds_dict = {}
-    #             for tool in result_dict:
-    #                 redisc_seeds = list(set(result_dict[tool]).intersection(set(rem_seeds)))
-    #                 redisc_prev = len(redisc_seeds)
-    #                 redisc_rate = redisc_prev / nof_removals
-    #                 redisc_rate_dict[tool] = redisc_rate
-    #                 redisc_seeds_dict[tool] = redisc_seeds
-    #                 for idx,seed in enumerate(redisc_seeds):
-    #                     if idx == 0:
-    #                         res_table.write(f'\t{redisc_seeds[0]}')
-    #                     else:
-    #                         res_table.write(f',{seed}') 
-    #             res_table.write('\n')
-    #             variation_results.append((redisc_rate_dict, redisc_seeds_dict, used_seeds, rem_seeds))
+        ax2.set_title(f'Sensitivity (TP/TP + FN) in {nof_iterations} iterations.', wrap=True)
 
-    #     print(variation_results)
+        ax2.set_xticks(list(range(1,nof_iterations + 1)))
+        ax2.set_xticklabels([idx if idx%5==0 else '' for idx in range(1,nof_iterations+1)])
+        ax2.set_xlabel('Iterations')
+        ax2.set_ylabel('Sensitivity (TP/TP + FN)')
+        
+        # Save the figure
+        sensitivity_file = f'{output_dir}/00_{identifier}_seed_variation_tp_rates.png'
+        fig2.savefig(sensitivity_file)
+        print(f'Sensitivity plot saved under {sensitivity_file}')
+        
+        
+        # plot module size frac
+        fig3, ax3 = plt.subplots()
+        legend = []
+        for idx,tool in enumerate(used_tools):
+            scatter = ax3.scatter(list(range(1,nof_iterations + 1)), module_size_dict[tool], color=colors[idx])
+            legend.append(scatter)
+        
+        plt.legend(legend,
+                   used_tools)
+        # Add title
+        ax3.set_title(f'Ratio of number of rediscovered seeds and CAMI module size', wrap=True)
 
-    #     rediscovery_rates_results = [results[0] for results in variation_results]
-    #     mean_discovery_rates = {}
-    #     std_discovery_rates = {}
-    #     for tool in used_tools:
-    #         redisc_rates = [res[tool] for res in rediscovery_rates_results]
-    #         mean_discovery_rates[tool] = np.mean(redisc_rates)
-    #         std_discovery_rates[tool] = np.std(redisc_rates)
-        
-    #     # Create lists for the plot
-    #     x_pos = np.arange(len(used_tools))
-    #     redisc_rates = [mean_discovery_rates[tool] for tool in used_tools]
-    #     redisc_error = [std_discovery_rates[tool] for tool in used_tools]
-        
-    #     # Build the plot
-    #     fig, ax = plt.subplots()
-    #     ax.bar(x_pos, redisc_rates, yerr=redisc_error, align='center', alpha=0.5, ecolor='black', capsize=10)
-    #     ax.set_ylabel(f'Mean rediscovery rate after removing {removal_frac * 100}% of the original seeds.')
-    #     ax.set_xticks(x_pos)
-    #     ax.set_xticklabels(used_tools)
-    #     ax.set_title(f'Rediscovery rate of AMIMs after removing random seeds from the original seed set:{[cami.ppi_vertex2gene[seed] for seed in base_seeds]}')
-    #     ax.yaxis.grid(True)
-
-    #     # Save the figure and show
-    #     plt.tight_layout()
-    #     plt.savefig(f'{output_dir}/{identifier}_seed_variation_rediscovery_rates.png')
-        
-        # variation_results:
-        # [tuple(<list of used seeds>, 
-        #        <list of removed_seeds>, 
-        #        <results dict: <tool>:<list of predicted genes>>), tuple(...), ...]
+        ax3.set_xticks((list(range(1,nof_iterations + 1))))
+        ax3.set_xticklabels([idx if idx%5==0 else '' for idx in range(1,nof_iterations+1)])
+        ax3.set_xlabel('Iterations')
+        ax3.set_ylabel('Module size ratio (<rediscovered seeds>/<module size>)')
         
+        # Save the fig1ure
+        size_file = f'{output_dir}/00_{identifier}_redisc_modulesize_rate.png'
+        fig3.savefig(size_file)
+        print(f'Sensitivity plot saved under {size_file}')
         
     if save_temps:
         print(f'All temporary files were kept in {tmp_dir}')
@@ -386,7 +392,7 @@ if __name__ == "__main__":
     parser.add_argument('-w', '--tool_weights', nargs='+', action='store', default=None,
             help="List of weights for the tools. If you have [domino, diamond, robust] as list of tools and diamonds weight should be twice as high as the other tools type: 1 2 1")
     parser.add_argument('-c', '--consensus', action='store_true', help="run only the consensus prediction part of cami")
-    parser.add_argument('-var', '--seed_variation', action='store_true', help="vary the seeds of cami")
+    parser.add_argument('-var', '--seed_variation', action='store', help="repeat consensus selection multiple times (please provide the number of iterations) while removing 20 percent of the seeds.")
     parser.add_argument('-e', '--evaluate', action='store_true', help="run only the evaluation part of cami")
     parser.add_argument('-o', '--output_dir', action='store', help="path to output directory")
     parser.add_argument('-id', '--identifier', action='store', help="ID for the current excecution of cami. Defaults to a randomly generated ID")

cami/cami_suite.py

@@ -31,7 +31,7 @@ class cami():
     """ A module that is used for Active Module identifaction based on a
         consensus approach
     """
-    def __init__(self, ppi_graph, seed_lst, tool_wrappers, output_dir, uid, tmp_dir, home_path, config):
+    def __init__(self, ppi_graph, seed_lst, tool_wrappers, output_dir, uid, tmp_dir, home_path, config, seed_score):
         """Instance variables of CAMI
 
         :param ppi_graph: The PPI-Graph on which all predictions in CAMI are based of
@@ -59,7 +59,7 @@ class cami():
         self.tool_wrappers = tool_wrappers
         self.output_dir = output_dir
         self.tmp_dir = tmp_dir
-        self.uid = uid
+        self.uid = str(uid)
         self.nof_tools = len(tool_wrappers)
         self.result_gene_sets = {} #contains the genes predicted by the tools (not the indices)
         self.code2toolname = {tool.code:tool.name for tool in self.tool_wrappers}
@@ -68,16 +68,18 @@ class cami():
         self.cami_vertices = []
         self.ncbi = False
         self.config = config
+        self.seed_score = seed_score
+        # set weights for seed genes in ppi_graph
+        for seed in self.seed_lst:
+            self.ppi_graph.vertex_properties["cami_score"][seed] = self.seed_score
 
     def reset_cami(self, new_uid = ''):
+        self.uid = new_uid
         self.ppi_graph = self.origin_ppi_graph.copy()
         self.result_gene_sets = {}
         self.cami_vertices = []
         self.seed_lst = self.origin_seed_lst.copy()
 
-    def reset_ppi_graph(self):
-        self.ppi_graph = self.initial_ppi_graph.copy()
-
     def set_initial_seed_lst(self, seedlst):
         self.initial_seed_lst = seedlst
 
@@ -100,7 +102,6 @@ class cami():
         :return: A set of predicted vertices by the used tool
         :rtype: set()
         """
-        # TODO: Rethink placement of creation of the temporary directory?
         tool.create_tmp_output_dir(self.tmp_dir) # creates the temporary input directory
         print(f"preparing {tool.name} input...")
         inputparams = tool.prepare_input()
@@ -160,7 +161,7 @@ class cami():
         predicted_by = self.ppi_graph.vertex_properties["predicted_by"]
         cami_vertices = set()
         putative_vertices = set()
-        consens_threshold = min(self.nof_tools, 2)
+        consens_threshold = min(self.nof_tools, 2) # CONFIG: consensus_threshold = 2
 
         #parse every result set of each tool
         for tool in result_sets:
@@ -328,8 +329,8 @@ class cami():
         """
         removed_seeds = [self.seed_lst[idx] for idx in idx_lst]
         self.seed_lst = [seed for seed in self.seed_lst if seed not in removed_seeds]
-        
+        for seed in self.seed_lst:
+            self.ppi_graph.vertex_properties["cami_score"][seed] = self.seed_score
+        for seed in removed_seeds:
+            self.ppi_graph.vertex_properties["cami_score"][seed] = 0.0
         return removed_seeds
\ No newline at end of file
-
-    def vary_seeds(self, removal_frac, nof_iterations):
-        result_sets = self.make_predictions
\ No newline at end of file

cami/camiconf

@@ -13,7 +13,7 @@ output_name = 'modules.out'
 
 [diamond]
 alpha : 1
-pred_factor : 3
+pred_factor : 2
 max_preds : 100
 
 [robust]

cami/seed_variation.py

@@ -8,6 +8,6 @@ network = sys.argv[1]
 seedfiles = sys.argv[2:]
 config = 'seed_variationconf'
 for seeds in seedfiles:
-    identifier = basename(seeds).rsplit('.')[0] + '_seedvariation'
-    command = f'./cami.py -n {network} -s {seeds} -id {identifier} -conf {config} -var -f;'
+    identifier = basename(seeds).rsplit('.')[0]
+    command = f'./cami.py -n {network} -s {seeds} -id {identifier} -conf {config} -var 50 -f -v;'
     subprocess.call(command, shell=True)
\ No newline at end of file

cami/seed_variationconf

@@ -13,7 +13,7 @@ output_name = 'modules.out'
 
 [diamond]
 alpha : 1
-pred_factor : 3
+pred_factor : 2
 max_preds : 100
 
 [robust]

data/output/example_run/CAMI_module_example_run.txt

-26123
-80184
-79583
-79848
-95681
-27077
-56623
-200894
-5147
-4867
-54806
-57545
-79600
-23322
-153241
-91147
-10464
-8481
-403
-374654
-79867
-54903
-9851
-9731
-51684
-65062
-9662
-22832
-80776
-23271
-79632
-5108
-22981
-5048
-830
-10403
-43740578
-1639
-26586
-84445
-5347
-123811
-121441
-9113
-79649
-22919
-51199
-152185
-80254
-117178
-154796

data/output/example_run/CAMI_output_example_run.tsv

-gene	index_in_graph	cami_score	degree_in_graph	ncbi_url	ncbi_summary
-9662	6686	3.0	230	https://www.ncbi.nlm.nih.gov/gene/9662	This gene encodes a centrosomal protein, which acts as a scaffolding protein during early centriole biogenesis, and is also required for centriole-centriole cohesion during interphase. Mutations in this gene are associated with autosomal recessive primary microcephaly-8. [provided by RefSeq, Jun 2012]
-22832	21279	3.0	72	https://www.ncbi.nlm.nih.gov/gene/22832	Involved in cilium assembly. Located in axonemal microtubule; centriole; and centrosome. [provided by Alliance of Genome Resources, Nov 2021]
-80776	20662	3.0	14	https://www.ncbi.nlm.nih.gov/gene/80776	This gene encodes a B9 domain protein, which are exclusively found in ciliated organisms. The gene is upregulated during mucociliary differentiation, and the encoded protein localizes to basal bodies and cilia. Disrupting expression of this gene results in ciliogenesis defects. [provided by RefSeq, Oct 2009]
-23271	21328	3.0	10	https://www.ncbi.nlm.nih.gov/gene/23271	Enables microtubule minus-end binding activity. Involved in several processes, including axon development; regulation of dendrite development; and regulation of organelle organization. Located in cytosol and microtubule end. Colocalizes with Golgi apparatus; centrosome; and microtubule minus-end. [provided by Alliance of Genome Resources, Nov 2021]
-79632	25067	3.0	24	https://www.ncbi.nlm.nih.gov/gene/79632	Located in extracellular space. [provided by Alliance of Genome Resources, Nov 2021]
-5108	510	3.0	416	https://www.ncbi.nlm.nih.gov/gene/5108	The protein encoded by this gene is a component of centriolar satellites, which are electron dense granules scattered around centrosomes. Inhibition studies show that this protein is essential for the correct localization of several centrosomal proteins, and for anchoring microtubules to the centrosome. Chromosomal aberrations involving this gene are associated with papillary thyroid carcinomas and a variety of hematological malignancies, including atypical chronic myeloid leukemia and T-cell lymphoma. Multiple transcript variants encoding different isoforms have been found for this gene. [provided by RefSeq, Oct 2015]
-22981	4227	2.0	191	https://www.ncbi.nlm.nih.gov/gene/22981	Predicted to enable calcium ion binding activity. Predicted to be involved in microtubule anchoring at centrosome. Located in cytosol; intercellular bridge; and microtubule cytoskeleton. [provided by Alliance of Genome Resources, Nov 2021]
-5048	8200	2.0	118	https://www.ncbi.nlm.nih.gov/gene/5048	This locus was identified as encoding a gene that when mutated or lost caused the lissencephaly associated with Miller-Dieker lissencephaly syndrome. This gene encodes the non-catalytic alpha subunit of the intracellular Ib isoform of platelet-activating factor acteylhydrolase, a heterotrimeric enzyme that specifically catalyzes the removal of the acetyl group at the SN-2 position of platelet-activating factor (identified as 1-O-alkyl-2-acetyl-sn-glyceryl-3-phosphorylcholine). Two other isoforms of intracellular platelet-activating factor acetylhydrolase exist: one composed of multiple subunits, the other, a single subunit. In addition, a single-subunit isoform of this enzyme is found in serum. [provided by RefSeq, Apr 2009]
-830	6673	2.0	113	https://www.ncbi.nlm.nih.gov/gene/830	The protein encoded by this gene is a member of the F-actin capping protein alpha subunit family. It is the alpha subunit of the barbed-end actin binding protein Cap Z. By capping the barbed end of actin filaments, Cap Z regulates the growth of the actin filaments at the barbed end. [provided by RefSeq, Jul 2008]
-10403	4245	2.0	161	https://www.ncbi.nlm.nih.gov/gene/10403	This gene encodes a component of the NDC80 kinetochore complex. The encoded protein consists of an N-terminal microtubule binding domain and a C-terminal coiled-coiled domain that interacts with other components of the complex. This protein functions to organize and stabilize microtubule-kinetochore interactions and is required for proper chromosome segregation. [provided by RefSeq, Oct 2011]
-43740578	25258	2.0	2604	https://www.ncbi.nlm.nih.gov/gene/43740578	Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is an enveloped, positive-sense, single-stranded RNA virus that causes coronavirus disease 2019 (COVID-19). Virus particles include the RNA genetic material and structural proteins needed for invasion of host cells. Once inside the cell the infecting RNA is used to encode structural proteins that make up virus particles, nonstructural proteins that direct virus assembly, transcription, replication and host control and accessory proteins whose function has not been determined.~ ORF1ab, the largest gene, contains overlapping open reading frames that encode polyproteins PP1ab and PP1a. The polyproteins are cleaved to yield 16 nonstructural proteins, NSP1-16. Production of the longer (PP1ab) or shorter protein (PP1a) depends on a -1 ribosomal frameshifting event. The proteins, based on similarity to other coronaviruses, include the papain-like proteinase protein (NSP3), 3C-like proteinase (NSP5), RNA-dependent RNA polymerase (NSP12, RdRp), helicase (NSP13, HEL), endoRNAse (NSP15), 2'-O-Ribose-Methyltransferase (NSP16) and other nonstructural proteins. SARS-CoV-2 nonstructural proteins are responsible for viral transcription, replication, proteolytic processing, suppression of host immune responses and suppression of host gene expression. The RNA-dependent RNA polymerase is a target of antiviral therapies.
-1639	563	2.0	281	https://www.ncbi.nlm.nih.gov/gene/1639	This gene encodes the largest subunit of dynactin, a macromolecular complex consisting of 10 subunits ranging in size from 22 to 150 kD. Dynactin binds to both microtubules and cytoplasmic dynein. Dynactin is involved in a diverse array of cellular functions, including ER-to-Golgi transport, the centripetal movement of lysosomes and endosomes, spindle formation, chromosome movement, nuclear positioning, and axonogenesis. This subunit interacts with dynein intermediate chain by its domains directly binding to dynein and binds to microtubules via a highly conserved glycine-rich cytoskeleton-associated protein (CAP-Gly) domain in its N-terminus. Alternative splicing of this gene results in multiple transcript variants encoding distinct isoforms. Mutations in this gene cause distal hereditary motor neuronopathy type VIIB (HMN7B) which is also known as distal spinal and bulbar muscular atrophy (dSBMA). [provided by RefSeq, Oct 2008]
-26586	16438	2.0	15	https://www.ncbi.nlm.nih.gov/gene/26586	This gene encodes a cytoskeleton-associated protein that stabalizes microtubules and plays a role in the regulation of cell division. The encoded protein is itself regulated through phosphorylation at multiple serine and threonine residues. There is a pseudogene of this gene on chromosome 14. Alternative splicing results in multiple transcript variations. [provided by RefSeq, Nov 2013]
-84445	4153	2.0	112	https://www.ncbi.nlm.nih.gov/gene/84445	The protein encoded by this gene belongs to the leucine zipper tumor suppressor family of proteins, which function in transcription regulation and cell cycle control. This family member can repress beta-catenin-mediated transcriptional activation and is a negative regulator of the Wnt signaling pathway. It negatively regulates microtubule severing at centrosomes, and is necessary for central spindle formation and cytokinesis completion. It is implicated in cancer, where it may inhibit cell proliferation and decrease susceptibility to tumor development. Alternative splicing of this gene results in multiple transcript variants. [provided by RefSeq, Dec 2015]
-5347	6907	2.0	374	https://www.ncbi.nlm.nih.gov/gene/5347	The Ser/Thr protein kinase encoded by this gene belongs to the CDC5/Polo subfamily. It is highly expressed during mitosis and elevated levels are found in many different types of cancer. Depletion of this protein in cancer cells dramatically inhibited cell proliferation and induced apoptosis; hence, it is a target for cancer therapy. [provided by RefSeq, Sep 2015]
-123811	21319	2.0	9	https://www.ncbi.nlm.nih.gov/gene/123811	Enables identical protein binding activity. Involved in cilium assembly. Located in centriolar satellite and nucleoplasm. [provided by Alliance of Genome Resources, Nov 2021]
-121441	14665	2.0	91	https://www.ncbi.nlm.nih.gov/gene/121441	Predicted to be involved in protein localization to centrosome. Located in centrosome; nucleoplasm; and plasma membrane. [provided by Alliance of Genome Resources, Nov 2021]
-9113	9430	2.0	244	https://www.ncbi.nlm.nih.gov/gene/9113	The protein encoded by this gene is a putative serine/threonine kinase that localizes to the mitotic apparatus and complexes with cell cycle controller CDC2 kinase in early mitosis. The protein is phosphorylated in a cell-cycle dependent manner, with late prophase phosphorylation remaining through metaphase. The N-terminal region of the protein binds CDC2 to form a complex showing reduced H1 histone kinase activity, indicating a role as a negative regulator of CDC2/cyclin A. In addition, the C-terminal kinase domain binds to its own N-terminal region, suggesting potential negative regulation through interference with complex formation via intramolecular binding. Biochemical and genetic data suggest a role as a tumor suppressor. This is supported by studies in knockout mice showing development of soft-tissue sarcomas, ovarian stromal cell tumors and a high sensitivity to carcinogenic treatments. [provided by RefSeq, Apr 2017]
-79649	21211	2.0	13	https://www.ncbi.nlm.nih.gov/gene/79649	The protein encoded by this gene belongs to the MAP7 (microtubule-associated protein 7) family. Alternatively spliced transcript variants encoding different isoforms have been found. [provided by RefSeq, Mar 2010]
-22919	9823	2.0	234	https://www.ncbi.nlm.nih.gov/gene/22919	The protein encoded by this gene was first identified by its binding to the APC protein which is often mutated in familial and sporadic forms of colorectal cancer. This protein localizes to microtubules, especially the growing ends, in interphase cells. During mitosis, the protein is associated with the centrosomes and spindle microtubules. The protein also associates with components of the dynactin complex and the intermediate chain of cytoplasmic dynein. Because of these associations, it is thought that this protein is involved in the regulation of microtubule structures and chromosome stability. This gene is a member of the RP/EB family. [provided by RefSeq, Jul 2008]
-51199	8034	2.0	139	https://www.ncbi.nlm.nih.gov/gene/51199	This gene encodes one of the proteins important for centrosomal function. This protein is important for positioning and anchoring the microtubules minus-ends in epithelial cells. Localization of this protein to the centrosome requires three leucine zippers in the central coiled-coil domain. Multiple alternatively spliced transcript variants that encode different isoforms have been reported. [provided by RefSeq, Jul 2008]
-152185	14693	2.0	53	https://www.ncbi.nlm.nih.gov/gene/152185	Involved in metaphase plate congression; mitotic spindle assembly; and regulation of centriole replication. Located in centriole; centrosome; and spindle. [provided by Alliance of Genome Resources, Nov 2021]
-80254	4587	2.0	82	https://www.ncbi.nlm.nih.gov/gene/80254	This gene encodes a protein with six coiled-coil domains. The protein is localized to the centrosome, a non-membraneous organelle that functions as the major microtubule-organizing center in animal cells. Several alternatively spliced transcript variants have been found, but their biological validity has not been determined. [provided by RefSeq, Jul 2008]
-117178	9325	2.0	72	https://www.ncbi.nlm.nih.gov/gene/117178	This gene encodes a protein that binds the cancer-testis antigen Synovial Sarcoma X breakpoint 2 protein. The encoded protein may regulate the activity of Synovial Sarcoma X breakpoint 2 protein in malignant cells. Alternate splicing results in multiple transcript variants. A pseudogene of this gene is found on chromosome 3. [provided by RefSeq, Oct 2009]
-154796	12155	2.0	191	https://www.ncbi.nlm.nih.gov/gene/154796	This gene belongs to the motin family of angiostatin binding proteins characterized by conserved coiled-coil domains and C-terminal PDZ binding motifs. The encoded protein is expressed predominantly in endothelial cells of capillaries as well as larger vessels of the placenta where it may mediate the inhibitory effect of angiostatin on tube formation and the migration of endothelial cells toward growth factors during the formation of new blood vessels. Alternative splicing results in multiple transcript variants encoding different isoforms. [provided by RefSeq, Jul 2008]

data/output/example_run/DIAMOnD_output_example_run.tsv

-gene
-22981
-9924
-91978
-10982
-64770
-22924
-23085
-9631
-1540
-54785
-90417
-5116
-55860
-123811
-9857
-9662
-89891
-255758
-5347
-55112
-5108
-84318
-830
-219072
-115106
-84516
-5567
-79632
-26986
-3959
-149041
-53598
-7283
-55755
-10403
-51199
-7798
-117178
-165055
-79598
-8655
-10540
-54801
-51512
-4850
-116840
-26005
-3880
-23093
-55165
-79649
-10120
-23019
-29883
-99100
-225745
-7840
-29079
-29110
-22919
-9113
-10615
-85456
-49856
-200081
-10426
-653784
-11215
-54820
-114791
-25904
-55787
-10844
-4957
-5048
-80776
-1780
-159989
-121441
-57701
-6491
-7272
-11116
-1778
-23271
-1781
-10121
-103733
-5576
-84445
-84260
-192670
-43740578
-255967
-10526
-829
-27161
-7538
-69654
-43740572
-9495
-26058
-27229
-140735
-2804
-3796
-90410
-10807
-64793
-5575
-246176
-80097
-11190
-85459
-9738
-11004
-18536
-27185
-10024
-85379
-832
-54862
-54542
-54535
-5577
-80254
-28952
-8165
-192669
-51164
-9125
-29922
-57568
-85378
-4848
-13191
-55142
-7159
-22832
-9337
-6990
-55125
-1859
-57534
-57489
-22994
-51143
-10671
-145508
-54839
-26586
-324
-26523
-22995
-6993
-154796
-55559
-27327
-79441
-5573
-23112
-83658
-9859
-9659
-4849
-1783
-60313
-23354
-343099
-79596
-163786
-167838
-55571
-93323
-246175
-5566
-10198
-57536
-23299
-1639
-81565
-57472
-9212
-93594
-57690
-11258
-152185
-4591
-167691
-9465
-9928
-440145
-55835
-72083
-55722
-132320
-157922
-80817
-54930
-10142

data/output/example_run/DOMINO_output_example_run.tsv

-gene
-79796
-23277
-9364
-374407
-10806
-56350
-123811
-92595
-54622
-9662
-5108
-84747
-79632
-80776
-139324
-57333
-65988
-203259
-23271
-22832
-6102
-169792

data/output/example_run/ROBUST_output_example_run.tsv

-gene
-22981
-26586
-154796
-8239
-55379
-23224
-79649
-4893
-83737
-3845
-995
-9662
-5108
-5347
-22919
-9146
-6103
-9113
-830
-80254
-79632
-152185
-80776
-1639
-6440
-7157
-121441
-23271
-10403
-51199
-22832
-117178
-84445
-43740578
-43740574
-3309

data/output/example_run/all_predictions_example_run.tsv

-CAMI predictions with 26 of initially 34 seeds: ['26123', '80184', '79583', '79848', '95681', '27077', '56623', '200894', '5147', '4867', '54806', '57545', '79600', '23322', '153241', '91147', '10464', '8481', '403', '374654', '79867', '54903', '9851', '9731', '51684', '65062'],
-initially: ['26123', '80184', '51259', '79583', '79848', '95681', '23247', '27077', '56623', '200894', '5147', '4867', '9786', '80210', '54806', '57545', '79600', '317662', '23322', '153241', '91147', '10464', '8481', '65250', '403', '374654', '79867', '51524', '54903', '9851', '9731', '51684', '65062', '23116']
-gene	predicted_by	cami_score	index_in_graph	degree_in_graph
-5048	['CAMI', 'DIAMOnD']	2.0	8200	118
-28952	['DIAMOnD']	1.0	18440	98
-169792	['DOMINO']	1.0	4104	7
-23299	['DIAMOnD']	1.0	9739	61
-10121	['DIAMOnD']	1.0	9740	75
-22995	['DIAMOnD']	1.0	14861	48
-830	['CAMI', 'DIAMOnD', 'ROBUST']	2.0	6673	113
-8239	['ROBUST']	1.0	9751	208
-832	['DIAMOnD']	1.0	12316	55
-49856	['DIAMOnD']	1.0	6685	36
-9662	['CAMI', 'DIAMOnD', 'DOMINO', 'ROBUST']	3.0	6686	230
-55787	['DIAMOnD']	1.0	14881	29
-149041	['DIAMOnD']	1.0	17450	327
-10142	['DIAMOnD']	1.0	7723	70
-1639	['CAMI', 'DIAMOnD', 'ROBUST']	2.0	563	281
-26586	['CAMI', 'DIAMOnD', 'ROBUST']	2.0	16438	15
-84445	['CAMI', 'DIAMOnD', 'ROBUST']	2.0	4153	112
-200081	['DIAMOnD']	1.0	6717	83
-56350	['DOMINO']	1.0	9281	4
-9146	['ROBUST']	1.0	67	250
-10526	['DIAMOnD']	1.0	9286	43
-18536	['DIAMOnD']	1.0	21578	10
-89891	['DIAMOnD']	1.0	17483	29
-57536	['DIAMOnD']	1.0	12875	8
-79596	['DIAMOnD']	1.0	6731	41
-4850	['DIAMOnD']	1.0	10831	36
-27161	['DIAMOnD']	1.0	7760	191
-7538	['DIAMOnD']	1.0	7763	60
-1540	['DIAMOnD']	1.0	11350	321
-829	['DIAMOnD']	1.0	8286	49
-22919	['CAMI', 'DIAMOnD', 'ROBUST']	2.0	9823	234
-26058	['DIAMOnD']	1.0	610	44
-81565	['DIAMOnD']	1.0	4195	104
-29110	['DIAMOnD']	1.0	6755	365
-55755	['DIAMOnD']	1.0	16998	59
-27327	['DIAMOnD']	1.0	8810	135
-5576	['DIAMOnD']	1.0	8299	83
-9465	['DIAMOnD']	1.0	8300	25
-117178	['CAMI', 'DIAMOnD', 'ROBUST']	2.0	9325	72
-23354	['DIAMOnD']	1.0	15469	31
-11215	['DIAMOnD']	1.0	8303	31
-9495	['DIAMOnD']	1.0	8301	35
-11116	['DIAMOnD']	1.0	10353	75
-203259	['DOMINO']	1.0	8833	10
-22981	['CAMI', 'DIAMOnD', 'ROBUST']	2.0	4227	191
-60313	['DIAMOnD']	1.0	4230	20
-324	['DIAMOnD']	1.0	6797	175
-10403	['CAMI', 'DIAMOnD', 'ROBUST']	2.0	4245	161
-6440	['ROBUST']	1.0	14487	10
-995	['ROBUST']	1.0	9369	121
-9631	['DIAMOnD']	1.0	7835	66
-5116	['DIAMOnD']	1.0	9372	47
-6491	['DIAMOnD']	1.0	20125	49
-3309	['ROBUST']	1.0	8350	339
-145508	['DIAMOnD']	1.0	20642	29
-3796	['DIAMOnD']	1.0	20643	20
-55835	['DIAMOnD']	1.0	10918	72
-84516	['DIAMOnD']	1.0	4265	33
-43740578	['CAMI', 'DIAMOnD', 'ROBUST']	2.0	25258	2604
-2804	['DIAMOnD']	1.0	8873	18
-246175	['DIAMOnD']	1.0	18092	82
-57472	['DIAMOnD']	1.0	18093	38
-7159	['DIAMOnD']	1.0	175	127
-7283	['DIAMOnD']	1.0	6834	176
-43740572	['DIAMOnD']	1.0	25267	365
-139324	['DOMINO']	1.0	12980	2
-65988	['DOMINO']	1.0	12979	4
-80776	['CAMI', 'DIAMOnD', 'DOMINO', 'ROBUST']	3.0	20662	14
-11004	['DIAMOnD']	1.0	10935	23
-5566	['DIAMOnD']	1.0	6329	163
-85456	['DIAMOnD']	1.0	9404	32
-10807	['DIAMOnD']	1.0	8893	48
-55571	['DIAMOnD']	1.0	20678	43
-1778	['DIAMOnD']	1.0	7881	117
-54622	['DOMINO']	1.0	8906	4
-6993	['DIAMOnD']	1.0	9419	77
-29922	['DIAMOnD']	1.0	4302	42
-1859	['DIAMOnD']	1.0	7890	199
-4957	['DIAMOnD']	1.0	19668	18
-5567	['DIAMOnD']	1.0	213	80
-9113	['CAMI', 'DIAMOnD', 'ROBUST']	2.0	9430	244
-57534	['DIAMOnD']	1.0	12502	103
-7840	['DIAMOnD']	1.0	17626	16
-79649	['CAMI', 'DIAMOnD', 'ROBUST']	2.0	21211	13
-51512	['DIAMOnD']	1.0	21212	24
-255967	['DIAMOnD']	1.0	7899	26
-10198	['DIAMOnD']	1.0	21214	8
-9924	['DIAMOnD']	1.0	7898	25
-1780	['DIAMOnD']	1.0	4321	63
-9212	['DIAMOnD']	1.0	742	250
-4893	['ROBUST']	1.0	237	329
-57333	['DOMINO']	1.0	4334	3
-9364	['DOMINO']	1.0	23286	2
-54785	['DIAMOnD']	1.0	20729	111
-13191	['DIAMOnD']	1.0	14585	20
-5347	['CAMI', 'DIAMOnD', 'ROBUST']	2.0	6907	374
-103733	['DIAMOnD']	1.0	14587	18
-85378	['DIAMOnD']	1.0	14588	26
-99100	['DIAMOnD']	1.0	14590	8
-90417	['DIAMOnD']	1.0	14591	31
-54542	['DIAMOnD']	1.0	12544	147
-64793	['DIAMOnD']	1.0	18177	27
-219072	['DIAMOnD']	1.0	14593	16
-84747	['DOMINO']	1.0	23290	4
-10024	['DIAMOnD']	1.0	772	39
-10844	['DIAMOnD']	1.0	14599	58
-225745	['DIAMOnD']	1.0	14601	12
-93323	['DIAMOnD']	1.0	14602	29
-5573	['DIAMOnD']	1.0	266	81
-5575	['DIAMOnD']	1.0	267	29
-8165	['DIAMOnD']	1.0	268	143
-165055	['DIAMOnD']	1.0	20753	37
-54930	['DIAMOnD']	1.0	14611	23
-26986	['DIAMOnD']	1.0	787	308
-23019	['DIAMOnD']	1.0	6426	136
-69654	['DIAMOnD']	1.0	14619	16
-23224	['ROBUST']	1.0	16155	44
-22832	['CAMI', 'DIAMOnD', 'DOMINO', 'ROBUST']	3.0	21279	72
-55142	['DIAMOnD']	1.0	14623	37
-23277	['DOMINO']	1.0	20772	10
-53598	['DIAMOnD']	1.0	14629	16
-55860	['DIAMOnD']	1.0	14630	31
-54801	['DIAMOnD']	1.0	14633	49
-163786	['DIAMOnD']	1.0	14123	68
-9738	['DIAMOnD']	1.0	15148	77
-27185	['DIAMOnD']	1.0	812	119
-72083	['DIAMOnD']	1.0	14642	20
-114791	['DIAMOnD']	1.0	14643	48
-57489	['DIAMOnD']	1.0	20786	8
-80097	['DIAMOnD']	1.0	14645	34
-79441	['DIAMOnD']	1.0	14646	23
-11258	['DIAMOnD']	1.0	14647	27
-246176	['DIAMOnD']	1.0	25399	6
-374407	['DOMINO']	1.0	25394	2
-10120	['DIAMOnD']	1.0	14650	46
-167691	['DIAMOnD']	1.0	21311	31
-93594	['DIAMOnD']	1.0	21312	9
-84318	['DIAMOnD']	1.0	21313	10
-10615	['DIAMOnD']	1.0	14655	31
-91978	['DIAMOnD']	1.0	21314	8
-132320	['DIAMOnD']	1.0	21316	26
-55379	['ROBUST']	1.0	17216	170
-653784	['DIAMOnD']	1.0	14662	13
-123811	['CAMI', 'DIAMOnD', 'DOMINO']	2.0	21319	9
-10806	['DOMINO']	1.0	21320	2
-121441	['CAMI', 'DIAMOnD', 'ROBUST']	2.0	14665	91
-343099	['DIAMOnD']	1.0	21321	9
-54862	['DIAMOnD']	1.0	21323	12
-157922	['DIAMOnD']	1.0	21322	6
-57701	['DIAMOnD']	1.0	21325	12
-440145	['DIAMOnD']	1.0	14669	37
-26005	['DIAMOnD']	1.0	21327	6
-23271	['CAMI', 'DIAMOnD', 'DOMINO', 'ROBUST']	3.0	21328	10
-10982	['DIAMOnD']	1.0	3922	41
-54839	['DIAMOnD']	1.0	21331	10
-3845	['ROBUST']	1.0	340	999
-92595	['DOMINO']	1.0	4437	7
-23093	['DIAMOnD']	1.0	21335	6
-79796	['DOMINO']	1.0	21336	5
-83737	['ROBUST']	1.0	856	420
-7157	['ROBUST']	1.0	345	3271
-10671	['DIAMOnD']	1.0	14683	28
-9928	['DIAMOnD']	1.0	15197	61
-85459	['DIAMOnD']	1.0	21342	9
-116840	['DIAMOnD']	1.0	19293	16
-57690	['DIAMOnD']	1.0	16223	73
-51199	['CAMI', 'DIAMOnD', 'ROBUST']	2.0	8034	139
-57568	['DIAMOnD']	1.0	19300	16
-152185	['CAMI', 'DIAMOnD', 'ROBUST']	2.0	14693	53
-27229	['DIAMOnD']	1.0	14696	41
-85379	['DIAMOnD']	1.0	19305	12
-54820	['DIAMOnD']	1.0	14697	23
-5577	['DIAMOnD']	1.0	10090	72
-9125	['DIAMOnD']	1.0	17259	80
-7798	['DIAMOnD']	1.0	19311	21
-159989	['DIAMOnD']	1.0	4463	13
-84260	['DIAMOnD']	1.0	3954	40
-255758	['DIAMOnD']	1.0	21362	13
-55112	['DIAMOnD']	1.0	21363	10
-10540	['DIAMOnD']	1.0	3958	120
-115106	['DIAMOnD']	1.0	14711	57
-8655	['DIAMOnD']	1.0	6519	240
-154796	['CAMI', 'DIAMOnD', 'ROBUST']	2.0	12155	191
-54535	['DIAMOnD']	1.0	8062	90
-55165	['DIAMOnD']	1.0	4479	81
-26523	['DIAMOnD']	1.0	8066	82
-192669	['DIAMOnD']	1.0	8067	43
-83658	['DIAMOnD']	1.0	4484	20
-192670	['DIAMOnD']	1.0	8068	24
-23085	['DIAMOnD']	1.0	6536	33
-55559	['DIAMOnD']	1.0	11145	46
-1783	['DIAMOnD']	1.0	17295	39
-22994	['DIAMOnD']	1.0	15251	56
-23112	['DIAMOnD']	1.0	8595	106
-4591	['DIAMOnD']	1.0	3989	104
-7272	['DIAMOnD']	1.0	11672	25
-10426	['DIAMOnD']	1.0	12186	52
-3959	['DIAMOnD']	1.0	11166	95
-22924	['DIAMOnD']	1.0	4522	63
-25904	['DIAMOnD']	1.0	6571	35
-9337	['DIAMOnD']	1.0	4010	45
-51164	['DIAMOnD']	1.0	11182	62
-140735	['DIAMOnD']	1.0	4015	94
-6103	['ROBUST']	1.0	431	27
-55125	['DIAMOnD']	1.0	12213	50
-167838	['DIAMOnD']	1.0	7605	28
-64770	['DIAMOnD']	1.0	4538	80
-3880	['DIAMOnD']	1.0	4027	36
-9857	['DIAMOnD']	1.0	14271	50
-1781	['DIAMOnD']	1.0	4035	102
-6990	['DIAMOnD']	1.0	4036	18
-29079	['DIAMOnD']	1.0	7621	307
-4848	['DIAMOnD']	1.0	4037	92
-4849	['DIAMOnD']	1.0	4038	62
-43740574	['ROBUST']	1.0	25545	1364
-9859	['DIAMOnD']	1.0	14795	56
-51143	['DIAMOnD']	1.0	16852	55
-9659	['DIAMOnD']	1.0	473	54
-55722	['DIAMOnD']	1.0	4575	27
-11190	['DIAMOnD']	1.0	10729	24
-79632	['CAMI', 'DIAMOnD', 'DOMINO', 'ROBUST']	3.0	25067	24
-80254	['CAMI', 'DIAMOnD', 'ROBUST']	2.0	4587	82
-29883	['DIAMOnD']	1.0	8685	127
-6102	['DOMINO']	1.0	9715	14
-79598	['DIAMOnD']	1.0	12280	52
-90410	['DIAMOnD']	1.0	4091	68
-80817	['DIAMOnD']	1.0	4604	30
-5108	['CAMI', 'DIAMOnD', 'DOMINO', 'ROBUST']	3.0	510	416

data/output/example_run/venn_link_example_run.txt

-http://degradome.uniovi.es/cgi-bin/nVenn/nvenn.cgi?uid=11DAFB32
\ No newline at end of file