risk-network 0.0.13b3__tar.gz → 0.0.13b4__tar.gz

{risk_network-0.0.13b3/src/risk_network.egg-info → risk_network-0.0.13b4}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: risk-network
-Version: 0.0.13b3
-Summary: A Python package for biological network analysis.
+Version: 0.0.13b4
+Summary: A Python package for scalable network analysis and high-quality visualization.
 Author-email: Ira Horecka <ira89@icloud.com>
 License: GPL-3.0-or-later
 Project-URL: Homepage, https://github.com/riskportal/network

{risk_network-0.0.13b3 → risk_network-0.0.13b4}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
 [project]
 name = "risk-network"
 dynamic = ["version"]
-description = "A Python package for biological network analysis."
+description = "A Python package for scalable network analysis and high-quality visualization."
 authors = [
     { name = "Ira Horecka", email = "ira89@icloud.com" },
 ]

{risk_network-0.0.13b3 → risk_network-0.0.13b4}/src/risk/__init__.py

@@ -7,4 +7,4 @@ RISK: Regional Inference of Significant Kinships
 
 from risk.risk import RISK
 
-__version__ = "0.0.13-beta.3"
+__version__ = "0.0.13-beta.4"

{risk_network-0.0.13b3 → risk_network-0.0.13b4}/src/risk/annotation/annotation.py

@@ -36,7 +36,10 @@ initialize_nltk()
 
 
 def load_annotation(
-    network: nx.Graph, annotation_input: Dict[str, Any], min_nodes_per_term: int = 2
+    network: nx.Graph,
+    annotation_input: Dict[str, Any],
+    min_nodes_per_term: int = 1,
+    max_nodes_per_term: int = 10_000,
 ) -> Dict[str, Any]:
     """Convert annotation input to a sparse matrix and reindex based on the network's node labels.
 
@@ -44,7 +47,9 @@ def load_annotation(
         network (nx.Graph): The network graph.
         annotation_input (Dict[str, Any]): An annotation dictionary.
         min_nodes_per_term (int, optional): The minimum number of network nodes required for each annotation
-            term to be included. Defaults to 2.
+            term to be included. Defaults to 1.
+        max_nodes_per_term (int, optional): The maximum number of network nodes allowed for each annotation
+            term. Defaults to 10_000.
 
     Returns:
         Dict[str, Any]: A dictionary containing ordered nodes, ordered annotations, and the sparse binary annotations
@@ -52,7 +57,6 @@ def load_annotation(
 
     Raises:
         ValueError: If no annotation is found for the nodes in the network.
-        ValueError: If no annotation has at least min_nodes_per_term nodes in the network.
     """
     # Step 1: Map nodes and annotations to indices
     node_label_order = [attr["label"] for _, attr in network.nodes(data=True) if "label" in attr]
@@ -72,9 +76,18 @@ def load_annotation(
     # Create a sparse binary matrix
     num_nodes = len(node_to_idx)
     num_annotation = len(annotation_to_idx)
-    annotation_pivot = coo_matrix((data, (row, col)), shape=(num_nodes, num_annotation)).tocsr()
-    # Step 3: Filter out annotations with fewer than min_nodes_per_term occurrences
-    valid_annotation = annotation_pivot.sum(axis=0).A1 >= min_nodes_per_term
+    # Convert to a sparse matrix and set the data type to uint8 for binary representation
+    annotation_pivot = (
+        coo_matrix((data, (row, col)), shape=(num_nodes, num_annotation)).tocsr().astype(np.uint8)
+    )
+    # Step 3: Filter out annotations with too few or too many nodes
+    valid_annotation = np.array(
+        [
+            annotation_pivot[:, i].sum() >= min_nodes_per_term
+            and annotation_pivot[:, i].sum() <= max_nodes_per_term
+            for i in range(num_annotation)
+        ]
+    )
     annotation_pivot = annotation_pivot[:, valid_annotation]
     # Step 4: Raise errors for empty matrices
     if annotation_pivot.nnz == 0:
@@ -83,7 +96,7 @@ def load_annotation(
     num_remaining_annotation = annotation_pivot.shape[1]
     if num_remaining_annotation == 0:
         raise ValueError(
-            f"No annotation terms found with at least {min_nodes_per_term} nodes in the network."
+            f"No annotation terms found with at least {min_nodes_per_term} nodes and at most {max_nodes_per_term} nodes."
         )
 
     # Step 5: Extract ordered nodes and annotations
@@ -94,6 +107,7 @@ def load_annotation(
 
     # Log the filtering details
     logger.info(f"Minimum number of nodes per annotation term: {min_nodes_per_term}")
+    logger.info(f"Maximum number of nodes per annotation term: {max_nodes_per_term}")
     logger.info(f"Number of input annotation terms: {num_annotation}")
     logger.info(f"Number of remaining annotation terms: {num_remaining_annotation}")
 
@@ -122,7 +136,7 @@ def define_top_annotation(
         significant_significance_matrix (np.ndarray): Enrichment matrix below alpha threshold.
         significant_binary_significance_matrix (np.ndarray): Binary significance matrix below alpha threshold.
         min_cluster_size (int, optional): Minimum cluster size. Defaults to 5.
-        max_cluster_size (int, optional): Maximum cluster size. Defaults to 1000.
+        max_cluster_size (int, optional): Maximum cluster size. Defaults to 10_000.
 
     Returns:
         pd.DataFrame: DataFrame with top annotations and their properties.

{risk_network-0.0.13b3 → risk_network-0.0.13b4}/src/risk/annotation/io.py

@@ -21,7 +21,11 @@ class AnnotationIO:
     """
 
     def load_annotation_json(
-        self, network: nx.Graph, filepath: str, min_nodes_per_term: int = 2
+        self,
+        network: nx.Graph,
+        filepath: str,
+        min_nodes_per_term: int = 1,
+        max_nodes_per_term: int = 10_000,
     ) -> Dict[str, Any]:
         """Load annotation from a JSON file and convert them to a DataFrame.
 
@@ -29,7 +33,9 @@ class AnnotationIO:
             network (NetworkX graph): The network to which the annotation is related.
             filepath (str): Path to the JSON annotation file.
             min_nodes_per_term (int, optional): The minimum number of network nodes required for each annotation
-                term to be included. Defaults to 2.
+                term to be included. Defaults to 1.
+            max_nodes_per_term (int, optional): The maximum number of network nodes allowed for each annotation
+                term to be included. Defaults to 10_000.
 
         Returns:
             Dict[str, Any]: A dictionary containing ordered nodes, ordered annotations, and the annotation matrix.
@@ -37,7 +43,10 @@ class AnnotationIO:
         filetype = "JSON"
         # Log the loading of the JSON file
         params.log_annotation(
-            filetype=filetype, filepath=filepath, min_nodes_per_term=min_nodes_per_term
+            filetype=filetype,
+            filepath=filepath,
+            min_nodes_per_term=min_nodes_per_term,
+            max_nodes_per_term=max_nodes_per_term,
         )
         self._log_loading_annotation(filetype, filepath=filepath)
 
@@ -45,7 +54,7 @@ class AnnotationIO:
         with open(filepath, "r", encoding="utf-8") as file:
             annotation_input = json.load(file)
 
-        return load_annotation(network, annotation_input, min_nodes_per_term)
+        return load_annotation(network, annotation_input, min_nodes_per_term, max_nodes_per_term)
 
     def load_annotation_excel(
         self,
@@ -55,7 +64,8 @@ class AnnotationIO:
         nodes_colname: str = "nodes",
         sheet_name: str = "Sheet1",
         nodes_delimiter: str = ";",
-        min_nodes_per_term: int = 2,
+        min_nodes_per_term: int = 1,
+        max_nodes_per_term: int = 10_000,
     ) -> Dict[str, Any]:
         """Load annotation from an Excel file and associate them with the network.
 
@@ -67,7 +77,9 @@ class AnnotationIO:
             sheet_name (str, optional): The name of the Excel sheet to load (default is 'Sheet1').
             nodes_delimiter (str, optional): Delimiter used to separate multiple nodes within the nodes column (default is ';').
             min_nodes_per_term (int, optional): The minimum number of network nodes required for each annotation
-                term to be included. Defaults to 2.
+                term to be included. Defaults to 1.
+            max_nodes_per_term (int, optional): The maximum number of network nodes allowed for each annotation
+                term to be included. Defaults to 10_000.
 
         Returns:
             Dict[str, Any]: A dictionary where each label is paired with its respective list of nodes,
@@ -76,7 +88,10 @@ class AnnotationIO:
         filetype = "Excel"
         # Log the loading of the Excel file
         params.log_annotation(
-            filetype=filetype, filepath=filepath, min_nodes_per_term=min_nodes_per_term
+            filetype=filetype,
+            filepath=filepath,
+            min_nodes_per_term=min_nodes_per_term,
+            max_nodes_per_term=max_nodes_per_term,
         )
         self._log_loading_annotation(filetype, filepath=filepath)
 
@@ -89,7 +104,7 @@ class AnnotationIO:
         # Convert the DataFrame to a dictionary pairing labels with their corresponding nodes
         annotation_input = annotation.set_index(label_colname)[nodes_colname].to_dict()
 
-        return load_annotation(network, annotation_input, min_nodes_per_term)
+        return load_annotation(network, annotation_input, min_nodes_per_term, max_nodes_per_term)
 
     def load_annotation_csv(
         self,
@@ -98,7 +113,8 @@ class AnnotationIO:
         label_colname: str = "label",
         nodes_colname: str = "nodes",
         nodes_delimiter: str = ";",
-        min_nodes_per_term: int = 2,
+        min_nodes_per_term: int = 1,
+        max_nodes_per_term: int = 10_000,
     ) -> Dict[str, Any]:
         """Load annotation from a CSV file and associate them with the network.
 
@@ -109,7 +125,9 @@ class AnnotationIO:
             nodes_colname (str): Name of the column containing the nodes associated with each label.
             nodes_delimiter (str, optional): Delimiter used to separate multiple nodes within the nodes column (default is ';').
             min_nodes_per_term (int, optional): The minimum number of network nodes required for each annotation
-                term to be included. Defaults to 2.
+                term to be included. Defaults to 1.
+            max_nodes_per_term (int, optional): The maximum number of network nodes allowed for each annotation
+                term to be included. Defaults to 10_000.
 
         Returns:
             Dict[str, Any]: A dictionary where each label is paired with its respective list of nodes,
@@ -118,7 +136,10 @@ class AnnotationIO:
         filetype = "CSV"
         # Log the loading of the CSV file
         params.log_annotation(
-            filetype=filetype, filepath=filepath, min_nodes_per_term=min_nodes_per_term
+            filetype=filetype,
+            filepath=filepath,
+            min_nodes_per_term=min_nodes_per_term,
+            max_nodes_per_term=max_nodes_per_term,
         )
         self._log_loading_annotation(filetype, filepath=filepath)
 
@@ -127,7 +148,7 @@ class AnnotationIO:
             filepath, label_colname, nodes_colname, delimiter=",", nodes_delimiter=nodes_delimiter
         )
 
-        return load_annotation(network, annotation_input, min_nodes_per_term)
+        return load_annotation(network, annotation_input, min_nodes_per_term, max_nodes_per_term)
 
     def load_annotation_tsv(
         self,
@@ -136,7 +157,8 @@ class AnnotationIO:
         label_colname: str = "label",
         nodes_colname: str = "nodes",
         nodes_delimiter: str = ";",
-        min_nodes_per_term: int = 2,
+        min_nodes_per_term: int = 1,
+        max_nodes_per_term: int = 10_000,
     ) -> Dict[str, Any]:
         """Load annotation from a TSV file and associate them with the network.
 
@@ -147,7 +169,9 @@ class AnnotationIO:
             nodes_colname (str): Name of the column containing the nodes associated with each label.
             nodes_delimiter (str, optional): Delimiter used to separate multiple nodes within the nodes column (default is ';').
             min_nodes_per_term (int, optional): The minimum number of network nodes required for each annotation
-                term to be included. Defaults to 2.
+                term to be included. Defaults to 1.
+            max_nodes_per_term (int, optional): The maximum number of network nodes allowed for each annotation
+                term to be included. Defaults to 10_000.
 
         Returns:
             Dict[str, Any]: A dictionary where each label is paired with its respective list of nodes,
@@ -156,7 +180,10 @@ class AnnotationIO:
         filetype = "TSV"
         # Log the loading of the TSV file
         params.log_annotation(
-            filetype=filetype, filepath=filepath, min_nodes_per_term=min_nodes_per_term
+            filetype=filetype,
+            filepath=filepath,
+            min_nodes_per_term=min_nodes_per_term,
+            max_nodes_per_term=max_nodes_per_term,
         )
         self._log_loading_annotation(filetype, filepath=filepath)
 
@@ -165,10 +192,14 @@ class AnnotationIO:
             filepath, label_colname, nodes_colname, delimiter="\t", nodes_delimiter=nodes_delimiter
         )
 
-        return load_annotation(network, annotation_input, min_nodes_per_term)
+        return load_annotation(network, annotation_input, min_nodes_per_term, max_nodes_per_term)
 
     def load_annotation_dict(
-        self, network: nx.Graph, content: Dict[str, Any], min_nodes_per_term: int = 2
+        self,
+        network: nx.Graph,
+        content: Dict[str, Any],
+        min_nodes_per_term: int = 1,
+        max_nodes_per_term: int = 10_000,
     ) -> Dict[str, Any]:
         """Load annotation from a provided dictionary and convert them to a dictionary annotation.
 
@@ -176,7 +207,9 @@ class AnnotationIO:
             network (NetworkX graph): The network to which the annotation is related.
             content (Dict[str, Any]): The annotation dictionary to load.
             min_nodes_per_term (int, optional): The minimum number of network nodes required for each annotation
-                term to be included. Defaults to 2.
+                term to be included. Defaults to 1.
+            max_nodes_per_term (int, optional): The maximum number of network nodes allowed for each annotation
+                term to be included. Defaults to 10_000.
 
         Returns:
             Dict[str, Any]: A dictionary containing ordered nodes, ordered annotations, and the annotation matrix.
@@ -192,11 +225,16 @@ class AnnotationIO:
 
         filetype = "Dictionary"
         # Log the loading of the annotation from the dictionary
-        params.log_annotation(filepath="In-memory dictionary", filetype=filetype)
+        params.log_annotation(
+            filepath="In-memory dictionary",
+            filetype=filetype,
+            min_nodes_per_term=min_nodes_per_term,
+            max_nodes_per_term=max_nodes_per_term,
+        )
         self._log_loading_annotation(filetype, "In-memory dictionary")
 
         # Load the annotation as a dictionary from the provided dictionary
-        return load_annotation(network, content, min_nodes_per_term)
+        return load_annotation(network, content, min_nodes_per_term, max_nodes_per_term)
 
     def _load_matrix_file(
         self,

{risk_network-0.0.13b3 → risk_network-0.0.13b4/src/risk_network.egg-info}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: risk-network
-Version: 0.0.13b3
-Summary: A Python package for biological network analysis.
+Version: 0.0.13b4
+Summary: A Python package for scalable network analysis and high-quality visualization.
 Author-email: Ira Horecka <ira89@icloud.com>
 License: GPL-3.0-or-later
 Project-URL: Homepage, https://github.com/riskportal/network

{risk_network-0.0.13b3 → risk_network-0.0.13b4}/tests/test_load_annotation.py

@@ -3,11 +3,11 @@ tests/test_load_annotation
 ~~~~~~~~~~~~~~~~~~~~~~~~~~
 """
 
+import json
+
 import pytest
 from scipy.sparse import csr_matrix, vstack
 
-# Ensure dummy fixtures are imported by referencing them in test signatures below.
-
 
 def test_missing_annotation_file(risk_obj, dummy_network):
     """Test loading an annotation file that does not exist.
@@ -22,6 +22,7 @@ def test_missing_annotation_file(risk_obj, dummy_network):
             filepath=annotation_file,
             network=dummy_network,
             min_nodes_per_term=1,
+            max_nodes_per_term=1000,
         )
 
 
@@ -38,6 +39,7 @@ def test_load_annotation_csv(risk_obj, cytoscape_network, data_path):
         filepath=str(annotation_file),
         network=cytoscape_network,
         min_nodes_per_term=1,
+        max_nodes_per_term=1000,
     )
 
     assert annotation is not None
@@ -57,6 +59,7 @@ def test_csv_annotation_structure(risk_obj, cytoscape_network, data_path):
         filepath=str(annotation_file),
         network=cytoscape_network,
         min_nodes_per_term=1,
+        max_nodes_per_term=1000,
     )
 
     assert isinstance(annotation, dict), "Annotation should be a dictionary"
@@ -82,6 +85,7 @@ def test_load_annotation_dict(risk_obj, dummy_network, dummy_annotation_dict):
         content=dummy_annotation_dict,
         network=dummy_network,
         min_nodes_per_term=1,
+        max_nodes_per_term=1000,
     )
 
     assert annotation is not None
@@ -100,6 +104,7 @@ def test_dict_annotation_structure(risk_obj, dummy_network, dummy_annotation_dic
         content=dummy_annotation_dict,
         network=dummy_network,
         min_nodes_per_term=1,
+        max_nodes_per_term=1000,
     )
 
     assert isinstance(annotation, dict), "Annotation should be a dictionary"
@@ -126,6 +131,7 @@ def test_load_annotation_json(risk_obj, cytoscape_network, data_path):
         filepath=str(annotation_file),
         network=cytoscape_network,
         min_nodes_per_term=1,
+        max_nodes_per_term=1000,
     )
 
     assert annotation is not None
@@ -145,6 +151,7 @@ def test_json_annotation_structure(risk_obj, cytoscape_network, data_path):
         filepath=str(annotation_file),
         network=cytoscape_network,
         min_nodes_per_term=1,
+        max_nodes_per_term=1000,
     )
 
     assert isinstance(annotation, dict), "Annotation should be a dictionary"
@@ -171,6 +178,7 @@ def test_load_annotation_tsv(risk_obj, cytoscape_network, data_path):
         filepath=str(annotation_file),
         network=cytoscape_network,
         min_nodes_per_term=1,
+        max_nodes_per_term=1000,
     )
 
     assert annotation is not None
@@ -190,6 +198,7 @@ def test_tsv_annotation_structure(risk_obj, cytoscape_network, data_path):
         filepath=str(annotation_file),
         network=cytoscape_network,
         min_nodes_per_term=1,
+        max_nodes_per_term=1000,
     )
 
     assert isinstance(annotation, dict), "Annotation should be a dictionary"
@@ -216,6 +225,7 @@ def test_load_annotation_excel(risk_obj, cytoscape_network, data_path):
         filepath=str(annotation_file),
         network=cytoscape_network,
         min_nodes_per_term=1,
+        max_nodes_per_term=1000,
     )
 
     assert annotation is not None
@@ -235,6 +245,7 @@ def test_excel_annotation_structure(risk_obj, cytoscape_network, data_path):
         filepath=str(annotation_file),
         network=cytoscape_network,
         min_nodes_per_term=1,
+        max_nodes_per_term=1000,
     )
 
     assert isinstance(annotation, dict), "Annotation should be a dictionary"
@@ -262,11 +273,13 @@ def test_combined_annotation(risk_obj, cytoscape_network, data_path):
         filepath=str(csv_file),
         network=cytoscape_network,
         min_nodes_per_term=1,
+        max_nodes_per_term=1000,
     )
     json_annotation = risk_obj.load_annotation_json(
         filepath=str(json_file),
         network=cytoscape_network,
         min_nodes_per_term=1,
+        max_nodes_per_term=1000,
     )
     # Combine the components of the annotations
     combined_annotation = {
@@ -289,3 +302,32 @@ def test_combined_annotation(risk_obj, cytoscape_network, data_path):
     assert len(combined_annotation["ordered_nodes"]) == len(csv_annotation["ordered_nodes"]) + len(
         json_annotation["ordered_nodes"]
     )
+
+
+def test_min_max_nodes_per_term(risk_obj, cytoscape_network, data_path):
+    """Test that loaded annotation respects min and max node limits per term.
+
+    Args:
+        risk_obj: The RISK object instance used for loading annotation.
+        cytoscape_network: The network object to which annotation will be applied.
+        data_path: The base path to the directory containing the annotation files.
+    """
+    annotation_file = data_path / "json" / "annotation" / "go_biological_process.json"
+    min_nodes = 2
+    max_nodes = 100
+    # Load annotation with filtering
+    annotation = risk_obj.load_annotation_json(
+        filepath=str(annotation_file),
+        network=cytoscape_network,
+        min_nodes_per_term=min_nodes,
+        max_nodes_per_term=max_nodes,
+    )
+    # Extract the mapping of term to genes from the raw JSON input
+    with open(annotation_file, "r") as f:
+        raw_dict = json.load(f)
+
+    filtered_terms = annotation["ordered_annotation"]
+    for term in filtered_terms:
+        gene_count = len(raw_dict[term])
+        assert gene_count >= min_nodes, f"Term {term} has too few genes: {gene_count}"
+        assert gene_count <= max_nodes, f"Term {term} has too many genes: {gene_count}"

{risk_network-0.0.13b3 → risk_network-0.0.13b4}/tests/test_log.py

@@ -66,7 +66,9 @@ def test_params_log_annotation(log_capture):
         filetype="CSV",
         filepath="mock/path/to/file.csv",
         min_nodes_per_term=3,
+        max_nodes_per_term=5,
     )
     assert params.annotation["filetype"] == "CSV"
     assert params.annotation["filepath"] == "mock/path/to/file.csv"
     assert params.annotation["min_nodes_per_term"] == 3
+    assert params.annotation["max_nodes_per_term"] == 5