Skip to content

evaluation: Edge evaluation pca-chosen #432

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 11 commits into
base: main
Choose a base branch
from
Open

evaluation: Edge evaluation pca-chosen #432

Show file tree
Hide file tree
Changes from 8 commits
Commits
Show all changes
11 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
f31d598
made changes based on review
ntalluri Nov 7, 2025
f192723
Update spras/evaluation.py
ntalluri Nov 7, 2025
e3c69d7
style: fmt
tristan-f-r Dec 5, 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
74 changes: 55 additions & 19 deletions Snakefile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -106,23 +106,31 @@ def make_final_input(wildcards):
final_input.extend(expand('{out_dir}{sep}{dataset}-ml{sep}{algorithm}-jaccard-heatmap.png',out_dir=out_dir,sep=SEP,dataset=dataset_labels,algorithm=algorithms))

if _config.config.analysis_include_evaluation:
# node evaluation
final_input.extend(expand('{out_dir}{sep}{dataset_gold_standard_pair}-eval{sep}pr-per-pathway-nodes.txt',out_dir=out_dir,sep=SEP,dataset_gold_standard_pair=dataset_gold_standard_node_pairs,algorithm_params=algorithms_with_params))
final_input.extend(expand('{out_dir}{sep}{dataset_gold_standard_pair}-eval{sep}pr-per-pathway-nodes.png',out_dir=out_dir,sep=SEP,dataset_gold_standard_pair=dataset_gold_standard_node_pairs))
final_input.extend(expand('{out_dir}{sep}{dataset_gold_standard_pair}-eval{sep}pr-pca-chosen-pathway-nodes.txt',out_dir=out_dir,sep=SEP,dataset_gold_standard_pair=dataset_gold_standard_node_pairs))
final_input.extend(expand('{out_dir}{sep}{dataset_gold_standard_pair}-eval{sep}pr-pca-chosen-pathway-nodes.png',out_dir=out_dir,sep=SEP,dataset_gold_standard_pair=dataset_gold_standard_node_pairs))
final_input.extend(expand('{out_dir}{sep}{dataset_gold_standard_pair}-eval{sep}pr-curve-ensemble-nodes.png',out_dir=out_dir,sep=SEP,dataset_gold_standard_pair=dataset_gold_standard_node_pairs))
final_input.extend(expand('{out_dir}{sep}{dataset_gold_standard_pair}-eval{sep}pr-curve-ensemble-nodes.txt',out_dir=out_dir,sep=SEP,dataset_gold_standard_pair=dataset_gold_standard_node_pairs))
# dummy file
final_input.extend(expand('{out_dir}{sep}{dataset_gold_standard_pair}-eval{sep}dummy-edge.txt',out_dir=out_dir,sep=SEP,dataset_gold_standard_pair=dataset_gold_standard_edge_pairs))


# edge evaluation
final_input.extend(expand('{out_dir}{sep}{dataset_gold_standard_pair}-eval{sep}pr-pca-chosen-pathway-edges.txt',out_dir=out_dir,sep=SEP,dataset_gold_standard_pair=dataset_gold_standard_edge_pairs))
final_input.extend(expand('{out_dir}{sep}{dataset_gold_standard_pair}-eval{sep}pr-pca-chosen-pathway-edges.png',out_dir=out_dir,sep=SEP,dataset_gold_standard_pair=dataset_gold_standard_edge_pairs))

if _config.config.analysis_include_evaluation_aggregate_algo:
# node evaluation
final_input.extend(expand('{out_dir}{sep}{dataset_gold_standard_pair}-eval{sep}pr-per-pathway-for-{algorithm}-nodes.txt',out_dir=out_dir,sep=SEP,dataset_gold_standard_pair=dataset_gold_standard_node_pairs,algorithm=algorithms))
final_input.extend(expand('{out_dir}{sep}{dataset_gold_standard_pair}-eval{sep}pr-per-pathway-for-{algorithm}-nodes.png',out_dir=out_dir,sep=SEP,dataset_gold_standard_pair=dataset_gold_standard_node_pairs,algorithm=algorithms))
final_input.extend(expand('{out_dir}{sep}{dataset_gold_standard_pair}-eval{sep}pr-pca-chosen-pathway-per-algorithm-nodes.txt',out_dir=out_dir,sep=SEP,dataset_gold_standard_pair=dataset_gold_standard_node_pairs))
final_input.extend(expand('{out_dir}{sep}{dataset_gold_standard_pair}-eval{sep}pr-pca-chosen-pathway-per-algorithm-nodes.png',out_dir=out_dir,sep=SEP,dataset_gold_standard_pair=dataset_gold_standard_node_pairs))
final_input.extend(expand('{out_dir}{sep}{dataset_gold_standard_pair}-eval{sep}pr-curve-ensemble-nodes-per-algorithm-nodes.png',out_dir=out_dir,sep=SEP,dataset_gold_standard_pair=dataset_gold_standard_node_pairs))
final_input.extend(expand('{out_dir}{sep}{dataset_gold_standard_pair}-eval{sep}pr-curve-ensemble-nodes-per-algorithm-nodes.txt',out_dir=out_dir,sep=SEP,dataset_gold_standard_pair=dataset_gold_standard_node_pairs))

# edge evaluation
final_input.extend(expand('{out_dir}{sep}{dataset_gold_standard_pair}-eval{sep}pr-pca-chosen-pathway-per-algorithm-edges.txt',out_dir=out_dir,sep=SEP,dataset_gold_standard_pair=dataset_gold_standard_edge_pairs))
final_input.extend(expand('{out_dir}{sep}{dataset_gold_standard_pair}-eval{sep}pr-pca-chosen-pathway-per-algorithm-edges.png',out_dir=out_dir,sep=SEP,dataset_gold_standard_pair=dataset_gold_standard_edge_pairs))

# Since (formatted) pathway files are interesting to the user, we preserve them.
final_input.extend(expand('{out_dir}{sep}{dataset}-{algorithm_params}{sep}pathway.txt', out_dir=out_dir, sep=SEP, dataset=dataset_labels, algorithm_params=algorithms_with_params))

Expand Down Expand Up @@ -427,7 +435,6 @@ def get_dataset_label(wildcards):
dataset = parts[0]
return dataset


# Returns all pathways for a specific dataset
def collect_pathways_per_dataset(wildcards):
dataset_label = get_dataset_label(wildcards)
Expand Down Expand Up @@ -478,7 +485,7 @@ def collect_pca_coordinates_per_dataset(wildcards):

# Run PCA chosen to select the representative from all pathway outputs for a given dataset,
# then evaluate with precision and recall against the corresponding gold standard
rule evaluation_pca_chosen:
rule evaluation_pca_chosen_nodes:
input:
node_gold_standard_file = get_gold_standard_pickle_file,
pca_coordinates_file = collect_pca_coordinates_per_dataset,
Expand All @@ -492,27 +499,67 @@ rule evaluation_pca_chosen:
pr_df = Evaluation.node_precision_and_recall(pca_chosen_pathway, node_table)
Evaluation.precision_and_recall_pca_chosen_pathway(pr_df, output.node_pca_chosen_pr_file, output.node_pca_chosen_pr_png)

rule evaluation_pca_chosen_edges:
input:
edge_gold_standard_file = get_gold_standard_pickle_file,
pca_coordinates_file = collect_pca_coordinates_per_dataset,
pathway_summary_file = collect_summary_statistics_per_dataset
output:
edge_pca_chosen_pr_file = SEP.join([out_dir, '{dataset_gold_standard_pair}-eval', 'pr-pca-chosen-pathway-edges.txt']),
edge_pca_chosen_pr_png = SEP.join([out_dir, '{dataset_gold_standard_pair}-eval', 'pr-pca-chosen-pathway-edges.png']),
run:
mixed_edge_table = Evaluation.from_file(input.edge_gold_standard_file).mixed_edge_table
undirected_edge_table = Evaluation.from_file(input.edge_gold_standard_file).undirected_edge_table
directed_edge_table = Evaluation.from_file(input.edge_gold_standard_file).directed_edge_table
pca_chosen_pathway = Evaluation.pca_chosen_pathway(input.pca_coordinates_file, input.pathway_summary_file, out_dir)
pr_df = Evaluation.edge_precision_and_recall(pca_chosen_pathway, mixed_edge_table, directed_edge_table, undirected_edge_table)
Evaluation.precision_and_recall_pca_chosen_pathway(pr_df, output.edge_pca_chosen_pr_file, output.edge_pca_chosen_pr_png, edge_evaluation=True)

# Returns pca coordinates for a specific algorithm and dataset
def collect_pca_coordinates_per_algo_per_dataset(wildcards):
dataset_label = get_dataset_label(wildcards)
return expand('{out_dir}{sep}{dataset}-ml{sep}{algorithm}-pca-coordinates.txt', out_dir=out_dir, sep=SEP, dataset=dataset_label, algorithm=algorithms_mult_param_combos) #TODO we are using algos with mult param combos, what to do when empty?

# Run PCA chosen to select the representative pathway per algorithm pathway outputs for a given dataset,
# then evaluate with precision and recall against the corresponding gold standard
rule evaluation_per_algo_pca_chosen:
rule evaluation_per_algo_pca_chosen_nodes:
input:
node_gold_standard_file = get_gold_standard_pickle_file,
pca_coordinates_file = collect_pca_coordinates_per_algo_per_dataset,
pca_coordinates_files = collect_pca_coordinates_per_algo_per_dataset,
pathway_summary_file = collect_summary_statistics_per_dataset
output:
node_pca_chosen_pr_file = SEP.join([out_dir, '{dataset_gold_standard_pair}-eval', 'pr-pca-chosen-pathway-per-algorithm-nodes.txt']),
node_pca_chosen_pr_png = SEP.join([out_dir, '{dataset_gold_standard_pair}-eval', 'pr-pca-chosen-pathway-per-algorithm-nodes.png']),
run:
node_table = Evaluation.from_file(input.node_gold_standard_file).node_table
pca_chosen_pathways = Evaluation.pca_chosen_pathway(input.pca_coordinates_file, input.pathway_summary_file, out_dir)
pca_chosen_pathways = Evaluation.pca_chosen_pathway(input.pca_coordinates_files, input.pathway_summary_file, out_dir)
pr_df = Evaluation.node_precision_and_recall(pca_chosen_pathways, node_table)
Evaluation.precision_and_recall_pca_chosen_pathway(pr_df, output.node_pca_chosen_pr_file, output.node_pca_chosen_pr_png, include_aggregate_algo_eval)

rule evaluation_per_algo_pca_chosen_edges:
input:
edge_gold_standard_file = get_gold_standard_pickle_file,
pca_coordinates_files = collect_pca_coordinates_per_algo_per_dataset,
pathway_summary_file = collect_summary_statistics_per_dataset
output:
edge_pca_chosen_pr_file = SEP.join([out_dir, '{dataset_gold_standard_pair}-eval', 'pr-pca-chosen-pathway-per-algorithm-edges.txt']),
edge_pca_chosen_pr_png = SEP.join([out_dir, '{dataset_gold_standard_pair}-eval', 'pr-pca-chosen-pathway-per-algorithm-edges.png']),
run:
mixed_edge_table = Evaluation.from_file(input.edge_gold_standard_file).mixed_edge_table
undirected_edge_table = Evaluation.from_file(input.edge_gold_standard_file).undirected_edge_table
directed_edge_table = Evaluation.from_file(input.edge_gold_standard_file).directed_edge_table

pca_chosen_pathways = Evaluation.pca_chosen_pathway(input.pca_coordinates_files, input.pathway_summary_file, out_dir)
pr_df = Evaluation.edge_precision_and_recall(pca_chosen_pathways, mixed_edge_table, directed_edge_table, undirected_edge_table)

Evaluation.precision_and_recall_pca_chosen_pathway(pr_df, output.edge_pca_chosen_pr_file, output.edge_pca_chosen_pr_png, include_aggregate_algo_eval, edge_evaluation=True)

# Returns pca coordinates for a specific algorithm and dataset
def collect_pca_coordinates_per_algo_per_dataset(wildcards):
dataset_label = get_dataset_label(wildcards)
return expand('{out_dir}{sep}{dataset}-ml{sep}{algorithm}-pca-coordinates.txt', out_dir=out_dir, sep=SEP, dataset=dataset_label, algorithm=algorithms_mult_param_combos) #TODO we are using algos with mult param combos, what to do when empty?


# Return the dataset pickle file for a specific dataset
def get_dataset_pickle_file(wildcards):
dataset_label = get_dataset_label(wildcards)
Expand Down Expand Up @@ -556,17 +603,6 @@ rule evaluation_per_algo_ensemble_pr_curve:
node_ensembles_dict = Evaluation.edge_frequency_node_ensemble(node_table, input.ensemble_files, input.dataset_file)
Evaluation.precision_recall_curve_node_ensemble(node_ensembles_dict, node_table, output.node_pr_curve_png, output.node_pr_curve_file, include_aggregate_algo_eval)

rule evaluation_edge_dummy:
input:
edge_gold_standard_file = get_gold_standard_pickle_file,
output:
dummy_file = SEP.join([out_dir, '{dataset_gold_standard_pair}-eval', 'dummy-edge.txt']),
run:
mixed_edge_table = Evaluation.from_file(input.edge_gold_standard_file).mixed_edge_table
undirected_edge_table = Evaluation.from_file(input.edge_gold_standard_file).undirected_edge_table
directed_edge_table = Evaluation.from_file(input.edge_gold_standard_file).directed_edge_table
Evaluation.edge_dummy_function(mixed_edge_table, undirected_edge_table, directed_edge_table, output.dummy_file)

# Remove the output directory
rule clean:
shell: f'rm -rf {out_dir}'
Loading
Loading