risk-network 0.0.9b5__py3-none-any.whl → 0.0.9b6__py3-none-any.whl

risk/__init__.py

@@ -7,4 +7,4 @@ RISK: RISK Infers Spatial Kinships
 
 from risk.risk import RISK
 
-__version__ = "0.0.9-beta.5"
+__version__ = "0.0.9-beta.6"

risk/annotations/annotations.py

@@ -15,6 +15,8 @@ import pandas as pd
 from nltk.tokenize import word_tokenize
 from nltk.corpus import stopwords
 
+from risk.log import logger
+
 
 def _setup_nltk():
     """Ensure necessary NLTK data is downloaded."""
@@ -35,15 +37,23 @@ _setup_nltk()
 stop_words = set(stopwords.words("english"))
 
 
-def load_annotations(network: nx.Graph, annotations_input: Dict[str, Any]) -> Dict[str, Any]:
+def load_annotations(
+    network: nx.Graph, annotations_input: Dict[str, Any], min_nodes_per_term: int = 2
+) -> Dict[str, Any]:
     """Convert annotations input to a DataFrame and reindex based on the network's node labels.
 
     Args:
         network (nx.Graph): The network graph.
         annotations_input (Dict[str, Any]): A dictionary with annotations.
+        min_nodes_per_term (int, optional): The minimum number of network nodes required for each annotation
+            term to be included. Defaults to 2.
 
     Returns:
         Dict[str, Any]: A dictionary containing ordered nodes, ordered annotations, and the binary annotations matrix.
+
+    Raises:
+        ValueError: If no annotations are found for the nodes in the network.
+        ValueError: If no annotations have at least min_nodes_per_term nodes in the network.
     """
     # Flatten the dictionary to a list of tuples for easier DataFrame creation
     flattened_annotations = [
@@ -61,13 +71,24 @@ def load_annotations(network: nx.Graph, annotations_input: Dict[str, Any]) -> Di
     annotations_pivot = annotations_pivot.reindex(index=node_label_order)
     # Raise an error if no valid annotations are found for the nodes in the network
     if annotations_pivot.notnull().sum().sum() == 0:
+        raise ValueError("No terms found in the annotation file for the nodes in the network.")
+
+    # Filter out annotations with fewer than min_nodes_per_term occurrences
+    # This assists in reducing noise and focusing on more relevant annotations for statistical analysis
+    num_terms_before_filtering = annotations_pivot.shape[1]
+    annotations_pivot = annotations_pivot.loc[
+        :, (annotations_pivot.sum(axis=0) >= min_nodes_per_term)
+    ]
+    num_terms_after_filtering = annotations_pivot.shape[1]
+    # Log the number of annotations before and after filtering
+    logger.info(f"Minimum number of nodes per annotation term: {min_nodes_per_term}")
+    logger.info(f"Number of input annotation terms: {num_terms_before_filtering}")
+    logger.info(f"Number of remaining annotation terms: {num_terms_after_filtering}")
+    if num_terms_after_filtering == 0:
         raise ValueError(
-            "No annotations found in the annotations file for the nodes in the network."
+            f"No annotation terms found with at least {min_nodes_per_term} nodes in the network."
         )
 
-    # Remove columns with all zeros and those with only a single '1' to improve statistical performance
-    # (i.e., it's unreliable to compute the significance of an annotation in a node cluster based on a single occurrence).
-    annotations_pivot = annotations_pivot.loc[:, (annotations_pivot.sum(axis=0) > 1)]
     # Extract ordered nodes and annotations
     ordered_nodes = tuple(annotations_pivot.index)
     ordered_annotations = tuple(annotations_pivot.columns)

risk/annotations/io.py

@@ -25,12 +25,16 @@ class AnnotationsIO:
     def __init__(self):
         pass
 
-    def load_json_annotation(self, network: nx.Graph, filepath: str) -> Dict[str, Any]:
+    def load_json_annotation(
+        self, network: nx.Graph, filepath: str, min_nodes_per_term: int = 2
+    ) -> Dict[str, Any]:
         """Load annotations from a JSON file and convert them to a DataFrame.
 
         Args:
             network (NetworkX graph): The network to which the annotations are related.
             filepath (str): Path to the JSON annotations file.
+            min_nodes_per_term (int, optional): The minimum number of network nodes required for each annotation
+                term to be included. Defaults to 2.
 
         Returns:
             Dict[str, Any]: A dictionary containing ordered nodes, ordered annotations, and the annotations matrix.
@@ -40,12 +44,11 @@ class AnnotationsIO:
         params.log_annotations(filepath=filepath, filetype=filetype)
         _log_loading(filetype, filepath=filepath)
 
-        # Open and read the JSON file
+        # Load the JSON file into a dictionary
         with open(filepath, "r") as file:
             annotations_input = json.load(file)
 
-        # Load the annotations into the provided network
-        return load_annotations(network, annotations_input)
+        return load_annotations(network, annotations_input, min_nodes_per_term)
 
     def load_excel_annotation(
         self,
@@ -55,6 +58,7 @@ class AnnotationsIO:
         nodes_colname: str = "nodes",
         sheet_name: str = "Sheet1",
         nodes_delimiter: str = ";",
+        min_nodes_per_term: int = 2,
     ) -> Dict[str, Any]:
         """Load annotations from an Excel file and associate them with the network.
 
@@ -65,6 +69,8 @@ class AnnotationsIO:
             nodes_colname (str): Name of the column containing the nodes associated with each label.
             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.
 
         Returns:
             Dict[str, Any]: A dictionary where each label is paired with its respective list of nodes,
@@ -82,10 +88,9 @@ class AnnotationsIO:
             lambda x: x.split(nodes_delimiter)
         )
         # Convert the DataFrame to a dictionary pairing labels with their corresponding nodes
-        label_node_dict = annotation.set_index(label_colname)[nodes_colname].to_dict()
+        annotations_input = annotation.set_index(label_colname)[nodes_colname].to_dict()
 
-        # Load the annotations into the provided network
-        return load_annotations(network, label_node_dict)
+        return load_annotations(network, annotations_input, min_nodes_per_term)
 
     def load_csv_annotation(
         self,
@@ -94,6 +99,7 @@ class AnnotationsIO:
         label_colname: str = "label",
         nodes_colname: str = "nodes",
         nodes_delimiter: str = ";",
+        min_nodes_per_term: int = 2,
     ) -> Dict[str, Any]:
         """Load annotations from a CSV file and associate them with the network.
 
@@ -103,6 +109,8 @@ class AnnotationsIO:
             label_colname (str): Name of the column containing the labels (e.g., GO terms).
             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.
 
         Returns:
             Dict[str, Any]: A dictionary where each label is paired with its respective list of nodes,
@@ -118,8 +126,7 @@ class AnnotationsIO:
             filepath, label_colname, nodes_colname, delimiter=",", nodes_delimiter=nodes_delimiter
         )
 
-        # Load the annotations into the provided network
-        return load_annotations(network, annotations_input)
+        return load_annotations(network, annotations_input, min_nodes_per_term)
 
     def load_tsv_annotation(
         self,
@@ -128,6 +135,7 @@ class AnnotationsIO:
         label_colname: str = "label",
         nodes_colname: str = "nodes",
         nodes_delimiter: str = ";",
+        min_nodes_per_term: int = 2,
     ) -> Dict[str, Any]:
         """Load annotations from a TSV file and associate them with the network.
 
@@ -137,6 +145,8 @@ class AnnotationsIO:
             label_colname (str): Name of the column containing the labels (e.g., GO terms).
             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.
 
         Returns:
             Dict[str, Any]: A dictionary where each label is paired with its respective list of nodes,
@@ -152,15 +162,18 @@ class AnnotationsIO:
             filepath, label_colname, nodes_colname, delimiter="\t", nodes_delimiter=nodes_delimiter
         )
 
-        # Load the annotations into the provided network
-        return load_annotations(network, annotations_input)
+        return load_annotations(network, annotations_input, min_nodes_per_term)
 
-    def load_dict_annotation(self, network: nx.Graph, content: Dict[str, Any]) -> Dict[str, Any]:
+    def load_dict_annotation(
+        self, network: nx.Graph, content: Dict[str, Any], min_nodes_per_term: int = 2
+    ) -> Dict[str, Any]:
         """Load annotations from a provided dictionary and convert them to a dictionary annotation.
 
         Args:
             network (NetworkX graph): The network to which the annotations are related.
             content (Dict[str, Any]): The annotations 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.
 
         Returns:
             Dict[str, Any]: A dictionary containing ordered nodes, ordered annotations, and the annotations matrix.
@@ -176,13 +189,8 @@ class AnnotationsIO:
         params.log_annotations(filepath="In-memory dictionary", filetype=filetype)
         _log_loading(filetype, "In-memory dictionary")
 
-        # Load the annotations into the provided network
-        annotations_dict = load_annotations(network, content)
-        # Ensure the output is a dictionary
-        if not isinstance(annotations_dict, dict):
-            raise ValueError("Expected output to be a dictionary")
-
-        return annotations_dict
+        # Load the annotations as a dictionary from the provided dictionary
+        return load_annotations(network, content, min_nodes_per_term)
 
 
 def _load_matrix_file(

{risk_network-0.0.9b5.dist-info → risk_network-0.0.9b6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: risk-network
-Version: 0.0.9b5
+Version: 0.0.9b6
 Summary: A Python package for biological network analysis
 Author: Ira Horecka
 Author-email: Ira Horecka <ira89@icloud.com>

{risk_network-0.0.9b5.dist-info → risk_network-0.0.9b6.dist-info}/RECORD

@@ -1,9 +1,9 @@
-risk/__init__.py,sha256=xpU4eFf8OBGeA2fxuMCAFmBEQO6YlnDSVL09OvyHThs,112
+risk/__init__.py,sha256=fpCtulKZFHI4Je7dm4qBJHyP9InK9uDRYmYYgog9BGQ,112
 risk/constants.py,sha256=XInRaH78Slnw_sWgAsBFbUHkyA0h0jL0DKGuQNbOvjM,550
 risk/risk.py,sha256=De1vn8Xc-TKz6aTL0bvJI-SVrIqU3k0IWAbKc7dde1c,23618
 risk/annotations/__init__.py,sha256=kXgadEXaCh0z8OyhOhTj7c3qXGmWgOhaSZ4gSzSb59U,147
-risk/annotations/annotations.py,sha256=aC30M-wdd72ZjOfn8RZKAsGM7Yti0Wl_4CHTvayoPvY,13312
-risk/annotations/io.py,sha256=eOkPD9G6KzkhGRc_ZW2McxQ8665o-H3uDG8bmKlzQ80,9591
+risk/annotations/annotations.py,sha256=WVT9wzTm8lTpMw_3SnbyljWR77yExo0rb1zVgJza8nw,14284
+risk/annotations/io.py,sha256=Nj_RPmn-WM1zMsssm9bVGR94SHytkEBK-wcBJ3WhqkU,10310
 risk/log/__init__.py,sha256=gy7C5L6D222AYUChq5lkc0LsCJ_QMQPaFiBJKbecdac,201
 risk/log/console.py,sha256=C52s3FgQ2e9kQWcXL8m7rs_pnKXt5Yy8PBHmQkOTiNo,4537
 risk/log/parameters.py,sha256=o4StqYCa0kt7_Ht4mKa1DwwvhGUwkC_dGBaiUIc0GB0,5683
@@ -32,8 +32,8 @@ risk/stats/stats.py,sha256=z8NrhiVj4BzJ250bVLfytpmfC7RzYu7mBuIZD_l0aCA,7222
 risk/stats/permutation/__init__.py,sha256=neJp7FENC-zg_CGOXqv-iIvz1r5XUKI9Ruxhmq7kDOI,105
 risk/stats/permutation/permutation.py,sha256=meBNSrbRa9P8WJ54n485l0H7VQJlMSfHqdN4aCKYCtQ,10105
 risk/stats/permutation/test_functions.py,sha256=lftOude6hee0pyR80HlBD32522JkDoN5hrKQ9VEbuoY,2345
-risk_network-0.0.9b5.dist-info/LICENSE,sha256=jOtLnuWt7d5Hsx6XXB2QxzrSe2sWWh3NgMfFRetluQM,35147
-risk_network-0.0.9b5.dist-info/METADATA,sha256=Oc_07HiBSedyTbbiP-2a-xeLgEH-3zzNdXYzV6FSdQY,47497
-risk_network-0.0.9b5.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
-risk_network-0.0.9b5.dist-info/top_level.txt,sha256=NX7C2PFKTvC1JhVKv14DFlFAIFnKc6Lpsu1ZfxvQwVw,5
-risk_network-0.0.9b5.dist-info/RECORD,,
+risk_network-0.0.9b6.dist-info/LICENSE,sha256=jOtLnuWt7d5Hsx6XXB2QxzrSe2sWWh3NgMfFRetluQM,35147
+risk_network-0.0.9b6.dist-info/METADATA,sha256=0YZ5Rd4bqOid3nSHpa-S6fBBtBhYPoAQ1SlACtmDVaw,47497
+risk_network-0.0.9b6.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
+risk_network-0.0.9b6.dist-info/top_level.txt,sha256=NX7C2PFKTvC1JhVKv14DFlFAIFnKc6Lpsu1ZfxvQwVw,5
+risk_network-0.0.9b6.dist-info/RECORD,,