testing

Author: ctrlaltaf

classes/hypergeometric_distribution_class_V3.py

@@ -81,7 +81,6 @@ def predict(
             pos_n = len(positive_pro_pro_neighbor) #Number of protein neighbors the protein of interest has
             K = len(positive_go_neighbor) - 1 #Number of protein neighbors the GO term of interest has, same for pos & neg, does not include the protein of interest
             pos_k = positive_go_annotated_pro_pro_neighbor_count #The overlap between the GO term and the protein of interst's neighbor proteins
-            print("pos_N: ", pos_N, "pos_n: ", pos_n, "K: ", K, "pos_k: ", pos_k)
             #The hypergeometric function using variables above, math.comb(n,k) is an n choose k function
             positive_score = 1 - ((math.comb(K,pos_k)*math.comb(pos_N-K,pos_n-pos_k))/math.comb(pos_N,pos_n))
 

interactome_testing.py

@@ -0,0 +1,46 @@
+from pathlib import Path
+
+from tools.helper import create_ppi_network, read_specific_columns
+
+
+def main():
+    print("interactome testing")
+
+    fly_interactome_path = Path("./network/fly_propro.csv")
+    fly_go_association_path = Path("./network/fly_proGo.csv")
+    zfish_interactome_path = Path("./network/zfish_propro.csv")
+    zfish_go_association_path = Path("./network/zfish_proGo.csv")
+    bsub_interactome_path = Path("./network/bsub_propro.csv")
+    bsub_go_association_path = Path("./network/bsub_proGo.csv")
+
+    interactome_columns = [0, 1]
+    interactome = read_specific_columns(bsub_interactome_path, interactome_columns, ",")
+
+    go_inferred_columns = [0, 2]
+    go_protein_pairs = read_specific_columns(
+        bsub_go_association_path, go_inferred_columns, ","
+    )
+
+    # for pair in go_protein_pairs:
+    #     print(pair)
+
+    protein_list = []
+
+    # if there is no graph.pickle file in the output/dataset directory, uncomment the following lines
+    G, protein_list = create_ppi_network(interactome, go_protein_pairs)
+
+    self_edge_count = 0
+    for protein in protein_list:
+        print(protein["id"])
+        if G.has_edge(protein["id"], protein["id"]):
+            self_edge_count+=1
+            print("self edge")
+
+    print(self_edge_count)
+
+    # fly has no pro pro self edge
+    # zfish has 31 pro pro self edges
+    # bsub has 278 pro pro self edges
+
+if __name__ == "__main__":
+    main()

main.py

@@ -23,6 +23,7 @@
     read_specific_columns,
     print_progress,
     export_graph_to_pickle,
+    read_pro_go_data,
 )
 from tools.workflow import run_workflow, sample_data
 
@@ -55,13 +56,17 @@ def main():
     testing_output_image_path = Path("./output/images/")
     testing_input_directory_path = Path("./tests/testing-dataset/")
     testing_graph_file_path = Path(testing_input_directory_path, "graph.pickle")
-    
+
+    namespace = ["molecular_function", "biological_process", "cellular_component"]
+    # change the go_term_type variable to include which go term namespace you want
+    go_term_type = [namespace[2]]
+
     interactome_columns = [0, 1]
-    interactome = read_specific_columns(zfish_interactome_path, interactome_columns, ",")
+    interactome = read_specific_columns(fly_interactome_path, interactome_columns, ",")
 
-    go_inferred_columns = [0, 2]
-    go_protein_pairs = read_specific_columns(
-        zfish_go_association_path, go_inferred_columns, ","
+    go_inferred_columns = [0, 2, 3]
+    go_protein_pairs = read_pro_go_data(
+        fly_go_association_path, go_inferred_columns, go_term_type, ","
     )
 
     protein_list = []
@@ -77,13 +82,13 @@ def main():
 
     # Define algorithm classes and their names
     algorithm_classes = {
-        # "OverlappingNeighbors": OverlappingNeighbors,
-        # "OverlappingNeighborsV2": OverlappingNeighborsV2,
-        # "OverlappingNeighborsV3": OverlappingNeighborsV3,
-        # "ProteinDegree": ProteinDegree,
-        # "ProteinDegreeV2": ProteinDegreeV2,
-        # "ProteinDegreeV3": ProteinDegreeV3,
-        # "SampleAlgorithm": SampleAlgorithm,
+        "OverlappingNeighbors": OverlappingNeighbors,
+        "OverlappingNeighborsV2": OverlappingNeighborsV2,
+        "OverlappingNeighborsV3": OverlappingNeighborsV3,
+        "ProteinDegree": ProteinDegree,
+        "ProteinDegreeV2": ProteinDegreeV2,
+        "ProteinDegreeV3": ProteinDegreeV3,
+        "SampleAlgorithm": SampleAlgorithm,
         "HypergeometricDistribution": HypergeometricDistribution,
         "HypergeometricDistributionV2": HypergeometricDistributionV2,
         "HypergeometricDistributionV3": HypergeometricDistributionV3,

tools/helper.py

@@ -105,6 +105,27 @@ def read_specific_columns(file_path, columns, delimit):
         return None
 
 
+def read_pro_go_data(file_path, columns, namespace, delimit):
+    try:
+        with open(file_path, "r") as file:
+            next(file)
+            data = []
+            for line in file:
+                parts = line.strip().split(delimit)
+                selected_columns = []
+                for col in columns:
+                    selected_columns.append(parts[col].replace('"', ""))
+                if selected_columns[2] in namespace:
+                    data.append(selected_columns)
+            return data
+    except FileNotFoundError:
+        print(f"Error: File '{file_path}' not found.")
+        return None
+    except Exception as e:
+        print(f"An error occurred: {e}")
+        return None
+
+
 def generate_random_colors(num_colors):
     colors = []
     for _ in range(num_colors):
@@ -145,10 +166,10 @@ def add_print_statements(filename, statements):
 
 
 def export_graph_to_pickle(graph, filename):
-    with open(filename, 'wb') as f:
+    with open(filename, "wb") as f:
         pickle.dump(graph, f)
 
 
 def import_graph_from_pickle(filename):
-    with open(filename, 'rb') as f:
+    with open(filename, "rb") as f:
         return pickle.load(f)

tools/workflow.py

@@ -141,8 +141,15 @@ def generate_figures(algorithm_classes, results, output_image_path, output_data_
     colors = generate_random_colors(len(algorithm_classes))
 
     sorted_results = sort_results_by(results, "roc_auc", output_data_path)
-    i = 0
-    plt.figure()
+    # Initialize your parameters
+    fig_width = 10  # width in inches
+    fig_height = 7  # height in inches
+    fig_dpi = 100  # dots per inch for the figure
+    save_dpi = 200  # dots per inch for the saved image
+
+    plt.figure(figsize=(fig_width, fig_height), dpi=fig_dpi)
+
+    i = 0  # Initialize your index for colors
     for algorithm_name, metrics in sorted_results.items():
         plt.plot(
             metrics["fpr"],
@@ -164,7 +171,7 @@ def generate_figures(algorithm_classes, results, output_image_path, output_data_
 
     sorted_results = sort_results_by(results, "pr_auc", output_data_path)
     i = 0
-    plt.figure()
+    plt.figure(figsize=(fig_width, fig_height), dpi=fig_dpi)
     for algorithm_name, metrics in sorted_results.items():
         plt.plot(
             metrics["recall"],
@@ -177,7 +184,7 @@ def generate_figures(algorithm_classes, results, output_image_path, output_data_
     plt.xlabel("Recall")
     plt.ylabel("Precision")
     plt.title("Precision-Recall Curve")
-    plt.legend(loc="lower left")
+    plt.legend(loc="lower right")
     plt.savefig(Path(output_image_path, "multiple_pr_curves.png"))
     plt.show()