added jaccard index figure.

Author: ctrlaltaf

Snakefile

@@ -380,13 +380,15 @@ rule evaluation:
     output: 
         eval_file = SEP.join([out_dir, "{dataset_gold_standard_pairs}-evaluation.txt"]),
         pr_edge_file = SEP.join([out_dir, '{dataset_gold_standard_pairs}-eval', "precision-recall-per-pathway_edge.txt"]),
-        pr_edge_png = SEP.join([out_dir, '{dataset_gold_standard_pairs}-eval', 'precision-recall-per-pathway_edge.png'])
+        pr_edge_png = SEP.join([out_dir, '{dataset_gold_standard_pairs}-eval', 'precision-recall-per-pathway_edge.png']),
+        heatmap_edge_png = SEP.join([out_dir, '{dataset_gold_standard_pairs}-eval', 'jaccard-heatmap.png'])
+
     run:
         node_table = Evaluation.from_file(input.gold_standard_file).node_table
         edge_table = Evaluation.from_file(input.gold_standard_file).edge_table
         Evaluation.precision(input.pathways, node_table, output.eval_file)
         Evaluation.precision_and_recall_edge(input.pathways, edge_table, algorithms, output.pr_edge_file, output.pr_edge_png)
-
+        Evaluation.jaccard_edge_heatmap(input.pathways, edge_table, output.heatmap_edge_png)
 # Remove the output directory
 rule clean:
     shell: f'rm -rf {out_dir}'

spras/evaluation.py

@@ -2,7 +2,8 @@
 import pickle as pkl
 from pathlib import Path
 from typing import Dict, Iterable
-
+import numpy as np
+import seaborn as sns
 from matplotlib import pyplot as plt
 import pandas as pd
 from sklearn.metrics import precision_score, recall_score
@@ -169,3 +170,48 @@ def precision_and_recall_edge(file_paths: Iterable[Path], edge_table: pd.DataFra
                 plt.plot([], [])
                 plt.title("Empty Pathway Files")
                 plt.savefig(output_png)
+
+
+    @staticmethod
+    def jaccard_edge_heatmap(file_paths: Iterable[Path], edge_table: pd.DataFrame, output_png:str=None):
+        """
+        Takes in file paths for a specific dataset and an associated gold standard edge table.
+        Generates a jaccard index heatmap image that compares all the edge similarity between each dataset and the gold standard
+        Returns output back to output_png
+        @param file_paths: file paths of pathway reconstruction algorithm outputs
+        @param edge_table: the gold standard edges
+        @param output_png (optional): the filename to plot the heatmap (not a PRC)
+        """
+        gs_edges = set()
+        for row in edge_table.itertuples():
+            gs_edges.add((row[1], row[2]))
+        
+        # calculate all the jaccard edge index for each method against the gold standard
+        jaccard_edge_indices_list = []
+        algorithms = []
+        for file in file_paths:
+            df = pd.read_table(file, sep="\t", header=0, usecols=["Node1", "Node2"])
+            method_edges = set()
+            for row in df.itertuples():
+                method_edges.add((row[1], row[2]))
+            edge_union = gs_edges | method_edges
+            edge_intersection = gs_edges & method_edges
+            jaccard_edge_index = len(edge_intersection) / len(edge_union)
+            jaccard_edge_indices_list.append(float(jaccard_edge_index))
+            algorithms.append(file.split("/")[1].split("-")[1])
+
+        jaccard_edge_indices = np.asanyarray([jaccard_edge_indices_list])
+
+        plt.figure(figsize=(10, 8))
+        sns.heatmap(
+            jaccard_edge_indices,
+            annot=True,
+            cmap="viridis",
+            xticklabels=algorithms,
+            yticklabels=[""],
+        )
+        plt.xlabel("Algorithms")
+        plt.ylabel("Pathways")
+        plt.title("Jaccard Index Edge Heatmap")
+        plt.tick_params(axis='x', which='major', labelsize=7.5)
+        plt.savefig(output_png, format="png", dpi=300)