Skip to content

evaluation: edge evaluation no selection #437

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ntalluri wants to merge 9 commits into
base: main
Choose a base branch
from
Open

evaluation: edge evaluation no selection #437

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
5d495da
added edge evaluation per dataset-edge-goldstandard pair
ntalluri Oct 30, 2025
206c453
Apply suggestions from code review
ntalluri Oct 30, 2025
5a6c4a8
in process of aggregate
ntalluri Oct 30, 2025
ebca036
Merge branch 'edge-evaluation-pca-chosen' of github.com:ntalluri/spra…
ntalluri Oct 30, 2025
bead0e7
added aggregate per algorithm
ntalluri Oct 30, 2025
94149b9
add a todo and remove the plan I made
ntalluri Oct 30, 2025
7277120
updated test cases and reworded comments
ntalluri Nov 7, 2025
26f3d54
attempt to fix the spacing
ntalluri Nov 7, 2025
319d292
add in code for pr per pathway
ntalluri Nov 7, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
118 changes: 94 additions & 24 deletions Snakefile
View file
Open in desktop

Large diffs are not rendered by default.

187 changes: 167 additions & 20 deletions spras/evaluation.py
View file
Open in desktop

Large diffs are not rendered by default.

4 changes: 4 additions & 0 deletions test/evaluate/expected/expected-pr-per-pathway-pca-chosen-edges.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
Pathway Precision Recall Gold_Standard_Type
test/evaluate/input/data-test-params-123/pathway.txt 0.0 0.0 directed
test/evaluate/input/data-test-params-123/pathway.txt 0.5 0.5 mixed
test/evaluate/input/data-test-params-123/pathway.txt 1.0 1.0 undirected
0 ...ed/expected-pr-per-pathway-pca-chosen.txt → ...ected-pr-per-pathway-pca-chosen-nodes.txt
View file
Open in desktop
File renamed without changes.
3 changes: 3 additions & 0 deletions test/evaluate/input/gs_directed_edge_table.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
A B D
B A D
B C D
2 changes: 2 additions & 0 deletions test/evaluate/input/gs_mixed_edge_table.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
A B U
B C D
2 changes: 2 additions & 0 deletions test/evaluate/input/gs_undirected_edge_table.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
A B U
B C U
76 changes: 59 additions & 17 deletions test/evaluate/test_evaluate.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,9 @@
OUT_DIR = 'test/evaluate/output/'
EXPECT_DIR = 'test/evaluate/expected/'
GS_NODE_TABLE = pd.read_csv(INPUT_DIR + 'gs_node_table.csv', header=0)
GS_MIXED_EDGE_TABLE = pd.read_csv(INPUT_DIR + 'gs_mixed_edge_table.csv', names=["Interactor1", "Interactor2", "Direction"], sep="\t")
GS_DIRECTED_EDGE_TABLE = pd.read_csv(INPUT_DIR + 'gs_directed_edge_table.csv', names=["Interactor1", "Interactor2", "Direction"], sep="\t")
GS_UNDIRECTED_EDGE_TABLE = pd.read_csv(INPUT_DIR + 'gs_undirected_edge_table.csv', names=["Interactor1", "Interactor2", "Direction"], sep="\t")
SUMMARY_FILE = INPUT_DIR + 'example_summary.txt'


Expand Down Expand Up @@ -81,26 +84,43 @@ def test_node_precision_recall_per_pathway_not_provided(self):
Evaluation.precision_and_recall_per_pathway(pr_df, output_file, output_png)

def test_node_precision_recall_pca_chosen_pathway_not_provided(self):
output_file = Path( OUT_DIR + 'pr-per-pathway-pca-chosen-not-provided.txt')
output_file.unlink(missing_ok=True)
output_png = Path(OUT_DIR + 'pr-per-pathway-pca-chosen-not-provided.png')
output_png.unlink(missing_ok=True)
node_output_file = Path( OUT_DIR + 'pr-per-pathway-pca-chosen-not-provided_nodes.txt')
node_output_file.unlink(missing_ok=True)
node_output_png = Path(OUT_DIR + 'pr-per-pathway-pca-chosen-not-provided_nodes.png')
node_output_png.unlink(missing_ok=True)

file_paths = []

pr_df = Evaluation.node_precision_and_recall(file_paths, GS_NODE_TABLE)
Evaluation.precision_and_recall_pca_chosen_pathway(pr_df, output_file, output_png)
Evaluation.precision_and_recall_pca_chosen_pathway(pr_df, node_output_file, node_output_png)

output = pd.read_csv(output_file, sep='\t', header=0).round(8)
node_output = pd.read_csv(node_output_file, sep='\t', header=0).round(8)
expected = pd.read_csv(EXPECT_DIR + 'expected-pr-pca-chosen-not-provided.txt', sep='\t', header=0).round(8)

assert output.equals(expected)
assert output_png.exists()
assert node_output.equals(expected)
assert node_output_png.exists()

def test_edge_precision_recall_pca_chosen_pathway_not_provided(self):
edge_output_file = Path( OUT_DIR + 'pr-per-pathway-pca-chosen-not-provided_edges.txt')
edge_output_file.unlink(missing_ok=True)
edge_output_png = Path(OUT_DIR + 'pr-per-pathway-pca-chosen-not-provided_edges.png')
edge_output_png.unlink(missing_ok=True)

file_paths = []

pr_df = Evaluation.edge_precision_and_recall(file_paths, GS_MIXED_EDGE_TABLE, GS_DIRECTED_EDGE_TABLE, GS_UNDIRECTED_EDGE_TABLE)
Evaluation.precision_and_recall_pca_chosen_pathway(pr_df, edge_output_file, edge_output_png)
edge_output = pd.read_csv(edge_output_file, sep='\t', header=0).round(8)
expected = pd.read_csv(EXPECT_DIR + 'expected-pr-pca-chosen-not-provided.txt', sep='\t', header=0).round(8)

assert edge_output.equals(expected)
assert edge_output_png.exists()

def test_node_precision_recall_pca_chosen_pathway(self):
output_file = Path(OUT_DIR + 'pr-per-pathway-pca-chosen.txt')
output_file.unlink(missing_ok=True)
output_png = Path(OUT_DIR + 'pr-per-pathway-pca-chosen.png')
output_png.unlink(missing_ok=True)
node_output_file = Path(OUT_DIR + 'pr-per-pathway-pca-chosen_nodes.txt')
node_output_file.unlink(missing_ok=True)
node_output_png = Path(OUT_DIR + 'pr-per-pathway-pca-chosen_nodes.png')
node_output_png.unlink(missing_ok=True)
output_coordinates = Path(OUT_DIR + 'pca-coordinates.tsv')
output_coordinates.unlink(missing_ok=True)

Expand All @@ -111,16 +131,38 @@ def test_node_precision_recall_pca_chosen_pathway(self):
ml.pca(dataframe, OUT_DIR + 'pca.png', OUT_DIR + 'pca-variance.txt', str(output_coordinates), kde=True, remove_empty_pathways=True)

pathway = Evaluation.pca_chosen_pathway([output_coordinates], SUMMARY_FILE, INPUT_DIR)

pr_df = Evaluation.node_precision_and_recall(pathway, GS_NODE_TABLE)
Evaluation.precision_and_recall_pca_chosen_pathway(pr_df, output_file, output_png, True)
Evaluation.precision_and_recall_pca_chosen_pathway(pr_df, node_output_file, node_output_png, True)

chosen = pd.read_csv(node_output_file, sep='\t', header=0).round(8)
expected = pd.read_csv(EXPECT_DIR + 'expected-pr-per-pathway-pca-chosen-nodes.txt', sep='\t', header=0).round(8)

chosen = pd.read_csv(output_file, sep='\t', header=0).round(8)
expected = pd.read_csv(EXPECT_DIR + 'expected-pr-per-pathway-pca-chosen.txt', sep='\t', header=0).round(8)
assert chosen.equals(expected)
assert node_output_png.exists()

def test_edge_precision_recall_pca_chosen_pathway(self):
edge_output_file = Path(OUT_DIR + 'pr-per-pathway-pca-chosen_edges.txt')
edge_output_file.unlink(missing_ok=True)
edge_output_png = Path(OUT_DIR + 'pr-per-pathway-pca-chosen_edges.png')
edge_output_png.unlink(missing_ok=True)
output_coordinates = Path(OUT_DIR + 'pca-coordinates.tsv')
output_coordinates.unlink(missing_ok=True)

file_paths = [INPUT_DIR + 'data-test-params-123/pathway.txt', INPUT_DIR + 'data-test-params-456/pathway.txt',
INPUT_DIR + 'data-test-params-789/pathway.txt', INPUT_DIR + 'data-test-params-empty/pathway.txt']

dataframe = ml.summarize_networks(file_paths)
ml.pca(dataframe, OUT_DIR + 'pca.png', OUT_DIR + 'pca-variance.txt', str(output_coordinates), kde=True, remove_empty_pathways=True)

pathway = Evaluation.pca_chosen_pathway([output_coordinates], SUMMARY_FILE, INPUT_DIR)
pr_df = Evaluation.edge_precision_and_recall(pathway, GS_MIXED_EDGE_TABLE, GS_DIRECTED_EDGE_TABLE, GS_UNDIRECTED_EDGE_TABLE)
Evaluation.precision_and_recall_pca_chosen_pathway(pr_df, edge_output_file, edge_output_png, True, True)

chosen = pd.read_csv(edge_output_file, sep='\t', header=0).round(8)
expected = pd.read_csv(EXPECT_DIR + 'expected-pr-per-pathway-pca-chosen-edges.txt', sep='\t', header=0).round(8)

assert chosen.equals(expected)
assert output_png.exists()
assert edge_output_png.exists()

def test_node_ensemble(self):
out_path_file = Path(OUT_DIR + 'node-ensemble.csv')
Expand Down
Loading