feat: add new summary statistics

spras/analysis/summary.py

@@ -1,4 +1,5 @@
 from pathlib import Path
+from statistics import median
 from typing import Iterable
 
 import networkx as nx
@@ -50,8 +51,40 @@ def summarize_networks(file_paths: Iterable[Path], node_table: pd.DataFrame, alg
         number_edges = nw.number_of_edges()
         ncc = nx.number_connected_components(nw)
 
+        # Save the max/median degree, average clustering coefficient, and density
+        if number_nodes == 0:
+            max_degree = 0
+            median_degree = 0.0
+            density = 0.0
+        else:
+            degrees = [deg for _, deg in nw.degree()]
+            max_degree = max(degrees)
+            median_degree = median(degrees)
+            density = nx.density(nw)
+
+        cc = list(nx.connected_components(nw))
+        # Save the max diameter
+        # Use diameter only for components with ≥2 nodes (singleton components have diameter 0)
+        diameters = [
+            nx.diameter(nw.subgraph(c).copy()) if len(c) > 1 else 0
+            for c in cc
+        ]
+        max_diameter = max(diameters, default=0)
+
+        # Save the average path lengths
+        # Compute average shortest path length only for components with ≥2 nodes (undefined for singletons, set to 0.0)
+        avg_path_lengths = [
+            nx.average_shortest_path_length(nw.subgraph(c).copy()) if len(c) > 1 else 0.0
+            for c in cc
+        ]
+
+        if len(avg_path_lengths) != 0:
+            avg_path_len = sum(avg_path_lengths) / len(avg_path_lengths)
+        else:
+            avg_path_len = 0.0
+
         # Initialize list to store current network information
-        cur_nw_info = [nw_name, number_nodes, number_edges, ncc]
+        cur_nw_info = [nw_name, number_nodes, number_edges, ncc, density, max_degree, median_degree, max_diameter, avg_path_len]
 
         # Iterate through each node property and save the intersection with the current network
         for node_list in nodes_by_col:
@@ -71,7 +104,7 @@ def summarize_networks(file_paths: Iterable[Path], node_table: pd.DataFrame, alg
         nw_info.append(cur_nw_info)
 
     # Prepare column names
-    col_names = ['Name', 'Number of nodes', 'Number of edges', 'Number of connected components']
+    col_names = ['Name', 'Number of nodes', 'Number of edges', 'Number of connected components', 'Density', 'Max degree', 'Median degree', 'Max diameter', 'Average path length']
     col_names.extend(nodes_by_col_labs)
     col_names.append('Parameter combination')
 

test/analysis/expected_output/expected_egfr_summary.txt

@@ -0,0 +1,10 @@
+Name	Number of nodes	Number of edges	Number of connected components	Density	Max degree	Median degree	Max diameter	Average path length	Nodes in prize	Nodes in sources	Nodes in targets	Nodes in active	Nodes in dummy	Parameter combination
+test/analysis/input/egfr/tps-egfr-domino-params-V3X4RW7_pathway.txt	48	45	3	0.0398936170212766	5	2.0	16	3.882808476926124	27	0	27	27	0	{'slice_threshold': 0.3, 'module_threshold': 0.05}
+test/analysis/input/egfr/tps-egfr-meo-params-GKEDDFZ_pathway.txt	1877	12845	1	0.007295700506524384	469	6.0	6	2.7973618474338107	621	1	620	621	1	{'local_search': 'Yes', 'max_path_length': 3, 'rand_restarts': 10}
+test/analysis/input/egfr/tps-egfr-omicsintegrator1-params-3THRXWW_pathway.txt	28	20	8	0.05291005291005291	4	1.0	5	1.306439393939394	28	1	27	28	1	{'b': 2, 'd': 10, 'g': '1e-3', 'r': 0.01, 'w': 0.1, 'mu': 0.008, 'dummy_mode': 'file'}
+test/analysis/input/egfr/tps-egfr-omicsintegrator1-params-5QH767V_pathway.txt	39	31	8	0.04183535762483131	6	1.0	5	1.5084498834498834	39	1	38	39	1	{'b': 10, 'd': 10, 'g': '1e-3', 'r': 0.01, 'w': 0.1, 'mu': 0.008, 'dummy_mode': 'file'}
+test/analysis/input/egfr/tps-egfr-omicsintegrator1-params-ITO5EQS_pathway.txt	14	9	5	0.0989010989010989	4	1.0	2	1.1866666666666668	14	0	14	14	0	{'b': 0.55, 'd': 10, 'g': '1e-3', 'r': 0.01, 'w': 0.1, 'mu': 0.008, 'dummy_mode': 'file'}
+test/analysis/input/egfr/tps-egfr-omicsintegrator2-params-EHHWPMD_pathway.txt	593	591	2	0.0033669841848593955	32	1.0	30	6.72248989073389	531	1	530	531	1	{'b': 2, 'g': 3}
+test/analysis/input/egfr/tps-egfr-omicsintegrator2-params-IV3IPCJ_pathway.txt	704	702	2	0.002836867968446916	35	1.0	24	6.038766691954387	616	1	615	616	1	{'b': 4, 'g': 0}
+test/analysis/input/egfr/tps-egfr-pathlinker-params-7S4SLU6_pathway.txt	14	17	1	0.18681318681318682	6	2.0	7	2.857142857142857	6	1	5	6	1	{'k': 10}
+test/analysis/input/egfr/tps-egfr-pathlinker-params-TCEMRS7_pathway.txt	25	32	1	0.10666666666666667	8	2.0	7	3.486666666666667	11	1	10	11	1	{'k': 20}

test/analysis/expected_output/expected_example_summary.txt

@@ -0,0 +1,13 @@
+Name	Number of nodes	Number of edges	Number of connected components	Density	Max degree	Median degree	Max diameter	Average path length	Nodes in prize	Nodes in active	Nodes in dummy	Nodes in sources	Nodes in targets	Parameter combination
+test/analysis/input/example/data0-allpairs-params-BEH6YB2_pathway.txt	3	2	1	0.6666666666666666	2	1.0	2	1.3333333333333333	2	2	1	1	1	{'spras_placeholder': 'no parameters'}
+test/analysis/input/example/data0-domino-params-V3X4RW7_pathway.txt	0	0	0	0.0	0	0.0	0	0.0	0	0	0	0	0	{'slice_threshold': 0.3, 'module_threshold': 0.05}
+test/analysis/input/example/data0-meo-params-GKEDDFZ_pathway.txt	3	2	1	0.6666666666666666	2	1.0	2	1.3333333333333333	2	2	1	1	1	{'max_path_length': 3, 'local_search': 'Yes', 'rand_restarts': 10}
+test/analysis/input/example/data0-mincostflow-params-SZPZVU6_pathway.txt	3	2	1	0.6666666666666666	2	1.0	2	1.3333333333333333	2	2	1	1	1	{'flow': 1, 'capacity': 1}
+test/analysis/input/example/data0-omicsintegrator1-params-E3LSEZQ_pathway.txt	3	2	1	0.6666666666666666	2	1.0	2	1.3333333333333333	2	2	1	1	1	{'b': 6, 'w': 5.0, 'd': 10, 'dummy_mode': 'file'}
+test/analysis/input/example/data0-omicsintegrator1-params-NFIPHUX_pathway.txt	0	0	0	0.0	0	0.0	0	0.0	0	0	0	0	0	{'b': 6, 'w': 0.0, 'd': 10, 'dummy_mode': 'file'}
+test/analysis/input/example/data0-omicsintegrator1-params-SU2S63Y_pathway.txt	3	2	1	0.6666666666666666	2	1.0	2	1.3333333333333333	2	2	1	1	1	{'b': 5, 'w': 0.0, 'd': 10, 'dummy_mode': 'file'}
+test/analysis/input/example/data0-omicsintegrator1-params-V26JBGX_pathway.txt	0	0	0	0.0	0	0.0	0	0.0	0	0	0	0	0	{'b': 5, 'w': 5.0, 'd': 10, 'dummy_mode': 'file'}
+test/analysis/input/example/data0-omicsintegrator2-params-EHHWPMD_pathway.txt	0	0	0	0.0	0	0.0	0	0.0	0	0	0	0	0	{'b': 2, 'g': 3}
+test/analysis/input/example/data0-omicsintegrator2-params-IV3IPCJ_pathway.txt	3	2	1	0.6666666666666666	2	1.0	2	1.3333333333333333	2	2	1	1	1	{'b': 4, 'g': 0}
+test/analysis/input/example/data0-pathlinker-params-6SWY7JS_pathway.txt	3	2	1	0.6666666666666666	2	1.0	2	1.3333333333333333	2	2	1	1	1	{'k': 200}
+test/analysis/input/example/data0-pathlinker-params-VQL7BDZ_pathway.txt	3	2	1	0.6666666666666666	2	1.0	2	1.3333333333333333	2	2	1	1	1	{'k': 100}

test/analysis/test_summary.py

@@ -51,7 +51,7 @@ def test_example_networks(self):
 
         # Comparing the dataframes directly with equals does not match because of how the parameter
         # combinations column is loaded from disk. Therefore, write both to disk and compare the files.
-        assert filecmp.cmp(out_path, EXPECT_DIR + "test_example_summary.txt", shallow=False)
+        assert filecmp.cmp(out_path, EXPECT_DIR + "expected_example_summary.txt", shallow=False)
 
     def test_egfr_networks(self):
         """Test data from EGFR workflow"""
@@ -80,7 +80,7 @@ def test_egfr_networks(self):
 
         # Comparing the dataframes directly with equals does not match because of how the parameter
         # combinations column is loaded from disk. Therefore, write both to disk and compare the files.
-        assert filecmp.cmp(out_path, EXPECT_DIR + "test_egfr_summary.txt", shallow=False)
+        assert filecmp.cmp(out_path, EXPECT_DIR + "expected_egfr_summary.txt", shallow=False)
 
     def test_load_dataset_dict(self):
         """Test loading files from dataset_dict"""