risk-network 0.0.3b3__py3-none-any.whl → 0.0.4b0__py3-none-any.whl

risk/__init__.py

@@ -10,4 +10,4 @@ RISK: RISK Infers Spatial Kinship
 
 from risk.risk import RISK
 
-__version__ = "0.0.3-beta.3"
+__version__ = "0.0.4-beta.0"

risk/annotations/annotations.py

@@ -171,7 +171,9 @@ def get_description(words_column: pd.Series) -> str:
     stop_words = set(stopwords.words("english"))
     # Tokenize the concatenated string and filter out stopwords and non-alphabetic words
     words = [
-        word.lower()
+        (
+            word.lower() if word.istitle() else word
+        )  # Lowercase all words except proper nouns (e.g., RNA, mRNA)
         for word in word_tokenize(words_column.str.cat(sep=" "))
         if word.isalpha() and word.lower() not in stop_words
     ]

risk/network/io.py

@@ -29,9 +29,6 @@ class NetworkIO:
         self,
         compute_sphere: bool = True,
         surface_depth: float = 0.0,
-        distance_metric: str = "dijkstra",
-        edge_length_threshold: float = 0.5,
-        louvain_resolution: float = 0.1,
         min_edges_per_node: int = 0,
         include_edge_weight: bool = True,
         weight_label: str = "weight",
@@ -40,9 +37,6 @@ class NetworkIO:
         self.surface_depth = surface_depth
         self.include_edge_weight = include_edge_weight
         self.weight_label = weight_label
-        self.distance_metric = distance_metric
-        self.edge_length_threshold = edge_length_threshold
-        self.louvain_resolution = louvain_resolution
         self.min_edges_per_node = min_edges_per_node
 
     def load_gpickle_network(self, filepath: str) -> nx.Graph:
@@ -320,7 +314,6 @@ class NetworkIO:
         print(f"Projection: {'Sphere' if self.compute_sphere else 'Plane'}")
         if self.compute_sphere:
             print(f"Surface depth: {self.surface_depth}")
-        print(f"Edge length threshold: {self.edge_length_threshold}")
         print(f"Edge weight: {'Included' if self.include_edge_weight else 'Excluded'}")
         if self.include_edge_weight:
             print(f"Weight label: {self.weight_label}")

risk/network/plot.py

@@ -299,11 +299,11 @@ class NetworkPlotter:
         """
         # Log the plotting parameters
         params.log_plotter(
-            contour_levels=levels,
-            contour_bandwidth=bandwidth,
-            contour_grid_size=grid_size,
-            contour_alpha=alpha,
-            contour_color="custom" if isinstance(color, np.ndarray) else color,
+            subcontour_levels=levels,
+            subcontour_bandwidth=bandwidth,
+            subcontour_grid_size=grid_size,
+            subcontour_alpha=alpha,
+            subcontour_color="custom" if isinstance(color, np.ndarray) else color,
         )
         # Filter to get node IDs and their coordinates
         node_ids = [
@@ -402,7 +402,7 @@ class NetworkPlotter:
         fontcolor: Union[str, np.ndarray] = "black",
         arrow_linewidth: float = 1,
         arrow_color: Union[str, np.ndarray] = "black",
-        num_words: int = 10,
+        max_words: int = 10,
         min_words: int = 1,
     ) -> None:
         """Annotate the network graph with labels for different domains, positioned around the network for clarity.
@@ -415,7 +415,7 @@ class NetworkPlotter:
             fontcolor (str or np.ndarray, optional): Color of the label text. Can be a string or RGBA array. Defaults to "black".
             arrow_linewidth (float, optional): Line width of the arrows pointing to centroids. Defaults to 1.
             arrow_color (str or np.ndarray, optional): Color of the arrows. Can be a string or RGBA array. Defaults to "black".
-            num_words (int, optional): Maximum number of words in a label. Defaults to 10.
+            max_words (int, optional): Maximum number of words in a label. Defaults to 10.
             min_words (int, optional): Minimum number of words required to display a label. Defaults to 1.
         """
         # Log the plotting parameters
@@ -427,7 +427,7 @@ class NetworkPlotter:
             label_fontcolor="custom" if isinstance(fontcolor, np.ndarray) else fontcolor,
             label_arrow_linewidth=arrow_linewidth,
             label_arrow_color="custom" if isinstance(arrow_color, np.ndarray) else arrow_color,
-            label_num_words=num_words,
+            label_max_words=max_words,
             label_min_words=min_words,
         )
         # Convert color strings to RGBA arrays if necessary
@@ -442,24 +442,37 @@ class NetworkPlotter:
             if nodes:  # Skip if the domain has no nodes
                 domain_centroids[domain] = self._calculate_domain_centroid(nodes)
 
+        # Initialize empty lists to collect valid indices
+        valid_indices = []
+        filtered_domain_centroids = {}
+        # Loop through domain_centroids with index
+        for idx, (domain, centroid) in enumerate(domain_centroids.items()):
+            # Check if the domain passes the word count condition
+            if (
+                len(self.network_graph.trimmed_domain_to_term[domain].split(" ")[:max_words])
+                >= min_words
+            ):
+                # Add to filtered_domain_centroids
+                filtered_domain_centroids[domain] = centroid
+                # Keep track of the valid index
+                valid_indices.append(idx)
+
+        # Now filter fontcolor and arrow_color to keep only the valid indices
+        fontcolor = fontcolor[valid_indices]
+        arrow_color = arrow_color[valid_indices]
+
         # Calculate the bounding box around the network
         center, radius = _calculate_bounding_box(
             self.network_graph.node_coordinates, radius_margin=perimeter_scale
         )
-
-        # Filter out domains with insufficient words for labeling
-        filtered_domains = {
-            domain: centroid
-            for domain, centroid in domain_centroids.items()
-            if len(self.network_graph.trimmed_domain_to_term[domain].split(" ")[:num_words])
-            >= min_words
-        }
         # Calculate the best positions for labels around the perimeter
-        best_label_positions = _best_label_positions(filtered_domains, center, radius, offset)
+        best_label_positions = _best_label_positions(
+            filtered_domain_centroids, center, radius, offset
+        )
         # Annotate the network with labels
         for idx, (domain, pos) in enumerate(best_label_positions.items()):
-            centroid = filtered_domains[domain]
-            annotations = self.network_graph.trimmed_domain_to_term[domain].split(" ")[:num_words]
+            centroid = filtered_domain_centroids[domain]
+            annotations = self.network_graph.trimmed_domain_to_term[domain].split(" ")[:max_words]
             self.ax.annotate(
                 "\n".join(annotations),
                 xy=centroid,
@@ -473,6 +486,81 @@ class NetworkPlotter:
                 arrowprops=dict(arrowstyle="->", color=arrow_color[idx], linewidth=arrow_linewidth),
             )
 
+    def plot_sublabel(
+        self,
+        nodes: list,
+        label: str,
+        radial_position: float = 0.0,
+        perimeter_scale: float = 1.05,
+        offset: float = 0.10,
+        font: str = "Arial",
+        fontsize: int = 10,
+        fontcolor: str = "black",
+        arrow_linewidth: float = 1,
+        arrow_color: str = "black",
+    ) -> None:
+        """Annotate the network graph with a single label for the given nodes, positioned at a specified radial angle.
+
+        Args:
+            nodes (List[str]): List of node labels to be used for calculating the centroid.
+            label (str): The label to be annotated on the network.
+            radial_position (float, optional): Radial angle for positioning the label, in degrees (0-360). Defaults to 0.0.
+            perimeter_scale (float, optional): Scale factor for positioning the label around the perimeter. Defaults to 1.05.
+            offset (float, optional): Offset distance for the label from the perimeter. Defaults to 0.10.
+            font (str, optional): Font name for the label. Defaults to "Arial".
+            fontsize (int, optional): Font size for the label. Defaults to 10.
+            fontcolor (str, optional): Color of the label text. Defaults to "black".
+            arrow_linewidth (float, optional): Line width of the arrow pointing to the centroid. Defaults to 1.
+            arrow_color (str, optional): Color of the arrow. Defaults to "black".
+        """
+        # Log the plotting parameters
+        params.log_plotter(
+            sublabel_perimeter_scale=perimeter_scale,
+            sublabel_offset=offset,
+            sublabel_font=font,
+            sublabel_fontsize=fontsize,
+            sublabel_fontcolor="custom" if isinstance(fontcolor, np.ndarray) else fontcolor,
+            sublabel_arrow_linewidth=arrow_linewidth,
+            sublabel_arrow_color="custom" if isinstance(arrow_color, np.ndarray) else arrow_color,
+            sublabel_radial_position=radial_position,
+        )
+
+        # Map node labels to IDs
+        node_ids = [
+            self.network_graph.node_label_to_id_map.get(node)
+            for node in nodes
+            if node in self.network_graph.node_label_to_id_map
+        ]
+
+        # Calculate the centroid of the provided nodes
+        centroid = self._calculate_domain_centroid(node_ids)
+
+        # Calculate the bounding box around the network
+        center, radius = _calculate_bounding_box(
+            self.network_graph.node_coordinates, radius_margin=perimeter_scale
+        )
+
+        # Convert radial position to radians, adjusting for a 90-degree rotation
+        radial_radians = np.deg2rad(radial_position - 90)
+        label_position = (
+            center[0] + (radius + offset) * np.cos(radial_radians),
+            center[1] + (radius + offset) * np.sin(radial_radians),
+        )
+
+        # Annotate the network with the label
+        self.ax.annotate(
+            label,
+            xy=centroid,
+            xytext=label_position,
+            textcoords="data",
+            ha="center",
+            va="center",
+            fontsize=fontsize,
+            fontname=font,
+            color=fontcolor,
+            arrowprops=dict(arrowstyle="->", color=arrow_color, linewidth=arrow_linewidth),
+        )
+
     def _calculate_domain_centroid(self, nodes: list) -> tuple:
         """Calculate the most centrally located node in .
 
@@ -662,12 +750,12 @@ def _calculate_bounding_box(
 
 
 def _best_label_positions(
-    filtered_domains: Dict[str, Any], center: np.ndarray, radius: float, offset: float
+    filtered_domain_centroids: Dict[str, Any], center: np.ndarray, radius: float, offset: float
 ) -> Dict[str, Any]:
     """Calculate and optimize label positions for clarity.
 
     Args:
-        filtered_domains (dict): Centroids of the filtered domains.
+        filtered_domain_centroids (dict): Centroids of the filtered domains.
         center (np.ndarray): The center coordinates for label positioning.
         radius (float): The radius for positioning labels around the center.
         offset (float): The offset distance from the radius for positioning labels.
@@ -675,15 +763,16 @@ def _best_label_positions(
     Returns:
         dict: Optimized positions for labels.
     """
-    num_domains = len(filtered_domains)
+    num_domains = len(filtered_domain_centroids)
     # Calculate equidistant positions around the center for initial label placement
     equidistant_positions = _equidistant_angles_around_center(center, radius, offset, num_domains)
     # Create a mapping of domains to their initial label positions
     label_positions = {
-        domain: position for domain, position in zip(filtered_domains.keys(), equidistant_positions)
+        domain: position
+        for domain, position in zip(filtered_domain_centroids.keys(), equidistant_positions)
     }
     # Optimize the label positions to minimize distance to domain centroids
-    return _optimize_label_positions(label_positions, filtered_domains)
+    return _optimize_label_positions(label_positions, filtered_domain_centroids)
 
 
 def _equidistant_angles_around_center(

risk/risk.py

@@ -31,10 +31,7 @@ class RISK(NetworkIO, AnnotationsIO):
         self,
         compute_sphere: bool = True,
         surface_depth: float = 0.0,
-        distance_metric: str = "dijkstra",
-        louvain_resolution: float = 0.1,
         min_edges_per_node: int = 0,
-        edge_length_threshold: float = 0.5,
         include_edge_weight: bool = True,
         weight_label: str = "weight",
     ):
@@ -43,10 +40,7 @@ class RISK(NetworkIO, AnnotationsIO):
         Args:
             compute_sphere (bool, optional): Whether to map nodes to a sphere. Defaults to True.
             surface_depth (float, optional): Surface depth for the sphere. Defaults to 0.0.
-            distance_metric (str, optional): Distance metric to use in network analysis. Defaults to "dijkstra".
-            louvain_resolution (float, optional): Resolution parameter for Louvain clustering. Defaults to 0.1.
             min_edges_per_node (int, optional): Minimum number of edges per node. Defaults to 0.
-            edge_length_threshold (float, optional): Edge length threshold for analysis. Defaults to 0.5.
             include_edge_weight (bool, optional): Whether to include edge weights in calculations. Defaults to True.
             weight_label (str, optional): Label for edge weights. Defaults to "weight".
         """
@@ -55,10 +49,7 @@ class RISK(NetworkIO, AnnotationsIO):
         params.log_network(
             compute_sphere=compute_sphere,
             surface_depth=surface_depth,
-            distance_metric=distance_metric,
-            louvain_resolution=louvain_resolution,
             min_edges_per_node=min_edges_per_node,
-            edge_length_threshold=edge_length_threshold,
             include_edge_weight=include_edge_weight,
             weight_label=weight_label,
         )
@@ -67,10 +58,7 @@ class RISK(NetworkIO, AnnotationsIO):
             self,
             compute_sphere=compute_sphere,
             surface_depth=surface_depth,
-            distance_metric=distance_metric,
-            louvain_resolution=louvain_resolution,
             min_edges_per_node=min_edges_per_node,
-            edge_length_threshold=edge_length_threshold,
             include_edge_weight=include_edge_weight,
             weight_label=weight_label,
         )
@@ -79,10 +67,7 @@ class RISK(NetworkIO, AnnotationsIO):
         # Set class attributes
         self.compute_sphere = compute_sphere
         self.surface_depth = surface_depth
-        self.distance_metric = distance_metric
-        self.louvain_resolution = louvain_resolution
         self.min_edges_per_node = min_edges_per_node
-        self.edge_length_threshold = edge_length_threshold
         self.include_edge_weight = include_edge_weight
         self.weight_label = weight_label
 
@@ -95,6 +80,9 @@ class RISK(NetworkIO, AnnotationsIO):
         self,
         network: nx.Graph,
         annotations: Dict[str, Any],
+        distance_metric: str = "dijkstra",
+        louvain_resolution: float = 0.1,
+        edge_length_threshold: float = 0.5,
         score_metric: str = "sum",
         null_distribution: str = "network",
         num_permutations: int = 1000,
@@ -106,6 +94,9 @@ class RISK(NetworkIO, AnnotationsIO):
         Args:
             network (nx.Graph): The network graph.
             annotations (pd.DataFrame): The matrix of annotations associated with the network.
+            distance_metric (str, optional): Distance metric for neighborhood analysis. Defaults to "dijkstra".
+            louvain_resolution (float, optional): Resolution parameter for Louvain clustering. Defaults to 0.1.
+            edge_length_threshold (float, optional): Edge length threshold for neighborhood analysis. Defaults to 0.5.
             score_metric (str, optional): Scoring metric for neighborhood significance. Defaults to "sum".
             null_distribution (str, optional): Distribution used for permutation tests. Defaults to "network".
             num_permutations (int, optional): Number of permutations for significance testing. Defaults to 1000.
@@ -118,6 +109,9 @@ class RISK(NetworkIO, AnnotationsIO):
         print_header("Running permutation test")
         # Log neighborhood analysis parameters
         params.log_neighborhoods(
+            distance_metric=distance_metric,
+            louvain_resolution=louvain_resolution,
+            edge_length_threshold=edge_length_threshold,
             score_metric=score_metric,
             null_distribution=null_distribution,
             num_permutations=num_permutations,
@@ -126,17 +120,18 @@ class RISK(NetworkIO, AnnotationsIO):
         )
 
         # Display the chosen distance metric
-        if self.distance_metric == "louvain":
-            for_print_distance_metric = f"louvain (resolution={self.louvain_resolution})"
+        if distance_metric == "louvain":
+            for_print_distance_metric = f"louvain (resolution={louvain_resolution})"
         else:
-            for_print_distance_metric = self.distance_metric
+            for_print_distance_metric = distance_metric
         print(f"Distance metric: '{for_print_distance_metric}'")
+        print(f"Edge length threshold: {edge_length_threshold}")
         # Compute neighborhoods based on the network and distance metric
         neighborhoods = get_network_neighborhoods(
             network,
-            self.distance_metric,
-            self.edge_length_threshold,
-            louvain_resolution=self.louvain_resolution,
+            distance_metric,
+            edge_length_threshold,
+            louvain_resolution=louvain_resolution,
             random_seed=random_seed,
         )
 
@@ -144,6 +139,8 @@ class RISK(NetworkIO, AnnotationsIO):
         print(f"Null distribution: '{null_distribution}'")
         print(f"Neighborhood scoring metric: '{score_metric}'")
         print(f"Number of permutations: {num_permutations}")
+        print(f"Random seed: {random_seed}")
+        print(f"Maximum workers: {max_workers}")
         # Run the permutation test to compute neighborhood significance
         neighborhood_significance = compute_permutation(
             neighborhoods=neighborhoods,

risk/stats/stats.py

@@ -150,12 +150,14 @@ def _run_permutation_test(
             ]
 
             # Start the permutation process in parallel
-            results = pool.starmap_async(_permutation_process_subset, params_list)
+            results = pool.starmap_async(_permutation_process_subset, params_list, chunksize=1)
 
             # Update progress bar based on progress_counter
+            # NOTE: Waiting for results to be ready while updating progress bar gives a big improvement
+            # in performance, especially for large number of permutations and workers
             while not results.ready():
                 progress.update(progress_counter.value - progress.n)
-                results.wait(0.1)
+                results.wait(0.05)  # Wait for 50ms
 
             # Ensure progress bar reaches 100%
             progress.update(total_progress - progress.n)

{risk_network-0.0.3b3.dist-info → risk_network-0.0.4b0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: risk-network
-Version: 0.0.3b3
+Version: 0.0.4b0
 Summary: A Python package for biological network analysis
 Author: Ira Horecka
 Author-email: Ira Horecka <ira89@icloud.com>
@@ -736,7 +736,7 @@ RISK is a software tool for visualizing spatial relationships in networks. It ai
 
 *Saccharomyces cerevisiae* proteins oriented by physical interactions discovered through affinity enrichment and mass spectrometry (Michaelis et al., 2023).
 
-![Metabolic Network Demo](./docs/github/network.png)
+![PPI Network Demo](./docs/github/network.png)
 
 ## Installation
 

{risk_network-0.0.3b3.dist-info → risk_network-0.0.4b0.dist-info}/RECORD

@@ -1,8 +1,8 @@
-risk/__init__.py,sha256=RJu5X2UMuCRnZae_KH4Fc7_o_P4sSfTDEBowiVZ2Go4,122
+risk/__init__.py,sha256=_RCFU6OMr2y2rQgkEL8v7GNdoRzp66xcSTHGsIJYDuU,122
 risk/constants.py,sha256=AICk3x5qRQhls_ijTb4VdbdxU6mZ1aLGbAjLEdBwfJI,550
-risk/risk.py,sha256=cWpYogZ-vma4ZZjewVNRMzb2TqHv8YABuzP2brXpOqo,16399
+risk/risk.py,sha256=GSIhjtn__c6752O9fSLCHH21mY0m8XDKIiLLaDmPhoI,16228
 risk/annotations/__init__.py,sha256=vUpVvMRE5if01Ic8QY6M2Ae3EFGJHdugEe9PdEkAW4Y,138
-risk/annotations/annotations.py,sha256=gZ9gihK_eTWaX3eByh08xr97FX4-XKe6MBwCCjasEDU,10368
+risk/annotations/annotations.py,sha256=0-Yf2XPVdMzpttLLgLxtTTnH0Eed_Uv8VXMur6E6xKw,10481
 risk/annotations/io.py,sha256=ozi7aFn3_geB6G0kt7Ya1qVhNOqP6rB0YISjriSZyNw,7989
 risk/log/__init__.py,sha256=xuLImfxFlKpnVhzi_gDYlr2_c9cLkrw2c_3iEsXb1as,107
 risk/log/console.py,sha256=im9DRExwf6wHlcn9fewoDcKIpo3vPcorZIaNAl-0csY,355
@@ -14,13 +14,13 @@ risk/neighborhoods/neighborhoods.py,sha256=zGtxVIs0_Bg0wt1By6d77_lqW0PGXpOtQxeCE
 risk/network/__init__.py,sha256=iEPeJdZfqp0toxtbElryB8jbz9_t_k4QQ3iDvKE8C_0,126
 risk/network/geometry.py,sha256=euBMOVvxpj-0WZam40IbHdsT7E4WXpTwSxuGbmAGTDg,6757
 risk/network/graph.py,sha256=a7gM1d2jHqscFVwn1GZaJWb3oZOFraNsQ2RxC4osaV4,11528
-risk/network/io.py,sha256=KmdrsDZe-ZT4O59NYZM_nQd8Ew9qpbzQcqWS_PaE7eA,12559
-risk/network/plot.py,sha256=fy21X677xqJPFkn564Jegxy05C9x0pJXovd5fm3NZ4Q,34554
+risk/network/io.py,sha256=KR838qmbDjUX0ziXJ15pgT6LgdKRf3zJpxxAv0VtzbM,12202
+risk/network/plot.py,sha256=dbACRp73EnZZwdOAoIiMivhDn-b1MSDOxUcgSFRHOLI,38465
 risk/stats/__init__.py,sha256=4s9gdJo5B1G_cQc0iMoeIBt5OrQNXkdtNXkAMFQkLxc,103
 risk/stats/permutation.py,sha256=xgaZbaxo57t_FzPlpcb2nsq8oCzc_wj-zAm-xj3P2dA,3404
-risk/stats/stats.py,sha256=_3Fj5H8Nml4cExvLg7Mt_i1HCLAJJcJSDiiSzr3uFlo,15798
-risk_network-0.0.3b3.dist-info/LICENSE,sha256=jOtLnuWt7d5Hsx6XXB2QxzrSe2sWWh3NgMfFRetluQM,35147
-risk_network-0.0.3b3.dist-info/METADATA,sha256=4zGYMG1NL48Udn8jYkT8VCYDEEAuN5ycXBpvmxvdHtw,43256
-risk_network-0.0.3b3.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
-risk_network-0.0.3b3.dist-info/top_level.txt,sha256=NX7C2PFKTvC1JhVKv14DFlFAIFnKc6Lpsu1ZfxvQwVw,5
-risk_network-0.0.3b3.dist-info/RECORD,,
+risk/stats/stats.py,sha256=7Z-1sJ5zvS3XDjG2UfOV0Y3c3xliYeB-6fk_UHNqfiE,16019
+risk_network-0.0.4b0.dist-info/LICENSE,sha256=jOtLnuWt7d5Hsx6XXB2QxzrSe2sWWh3NgMfFRetluQM,35147
+risk_network-0.0.4b0.dist-info/METADATA,sha256=UgNIQbca_cOb1Ft3kBJ0qil5sF2Y392uzS1HDKfLqUU,43250
+risk_network-0.0.4b0.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
+risk_network-0.0.4b0.dist-info/top_level.txt,sha256=NX7C2PFKTvC1JhVKv14DFlFAIFnKc6Lpsu1ZfxvQwVw,5
+risk_network-0.0.4b0.dist-info/RECORD,,