risk-network 0.0.8b22__py3-none-any.whl → 0.0.8b24__py3-none-any.whl

risk/__init__.py

@@ -7,4 +7,4 @@ RISK: RISK Infers Spatial Kinships
 
 from risk.risk import RISK
 
-__version__ = "0.0.8-beta.22"
+__version__ = "0.0.8-beta.24"

risk/annotations/annotations.py

@@ -3,6 +3,7 @@ risk/annotations/annotations
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 """
 
+import re
 from collections import Counter
 from itertools import compress
 from typing import Any, Dict, List, Set
@@ -205,19 +206,26 @@ def get_weighted_description(words_column: pd.Series, scores_column: pd.Series)
             weight = max(1, int((0 if pd.isna(score) else score) * 10))
             weighted_words.extend([word] * weight)
 
-    # Tokenize the weighted words
+    # Tokenize the weighted words, but preserve number-word patterns like '4-alpha'
     tokens = word_tokenize(" ".join(weighted_words))
-    # Separate numeric tokens
-    numeric_tokens = [token for token in tokens if token.replace(".", "", 1).isdigit()]
-    unique_numeric_values = set(numeric_tokens)
-    if len(unique_numeric_values) == 1:
-        return f"{list(unique_numeric_values)[0]}"
-
-    # Filter alphabetic and numeric tokens
-    words = [word for word in tokens if word.isalpha() or word.replace(".", "", 1).isdigit()]
-    # Apply word similarity filtering to remove redundant terms
-    simplified_words = _simplify_word_list(words)
-    # Generate a coherent description from the processed words
+    # Ensure we treat "4-alpha" or other "number-word" patterns as single tokens
+    combined_tokens = []
+    for token in tokens:
+        # Match patterns like '4-alpha' or '5-hydroxy' and keep them together
+        if re.match(r"^\d+-\w+", token):
+            combined_tokens.append(token)
+        elif token.replace(".", "", 1).isdigit():  # Handle pure numeric tokens
+            # Ignore pure numbers as descriptions unless necessary
+            continue
+        else:
+            combined_tokens.append(token)
+
+    # Prevent descriptions like just '4' from being selected
+    if len(combined_tokens) == 1 and combined_tokens[0].isdigit():
+        return "N/A"  # Return "N/A" for cases where it's just a number
+
+    # Simplify the word list and generate the description
+    simplified_words = _simplify_word_list(combined_tokens)
     description = _generate_coherent_description(simplified_words)
 
     return description

risk/network/plot/labels.py

@@ -614,9 +614,11 @@ class Labels:
         Returns:
             str: Processed terms separated by TERM_DELIMITER, with words combined if necessary to fit within constraints.
         """
-        # Handle ids_to_replace logic
+        # Return custom labels if domain is in ids_to_replace
         if ids_to_replace and domain in ids_to_replace:
             terms = ids_to_replace[domain].split(" ")
+            return terms
+
         else:
             terms = self.graph.domain_id_to_domain_terms_map[domain].split(" ")
 

risk/network/plot/utils/layout.py

@@ -30,6 +30,44 @@ def calculate_bounding_box(
     return center, radius
 
 
+def refine_center_iteratively(
+    node_coordinates: np.ndarray,
+    radius_margin: float = 1.05,
+    max_iterations: int = 10,
+    tolerance: float = 1e-2,
+) -> Tuple[np.ndarray, float]:
+    """Refine the center of the graph iteratively to minimize skew in node distribution.
+
+    Args:
+        node_coordinates (np.ndarray): Array of node coordinates (x, y).
+        radius_margin (float, optional): Margin factor to apply to the bounding box radius. Defaults to 1.05.
+        max_iterations (int, optional): Maximum number of iterations for refining the center. Defaults to 10.
+        tolerance (float, optional): Stopping tolerance for center adjustment. Defaults to 1e-2.
+
+    Returns:
+        tuple: Refined center and the final radius.
+    """
+    # Initial center and radius based on the bounding box
+    center, radius = calculate_bounding_box(node_coordinates, radius_margin)
+    for _ in range(max_iterations):
+        # Shift the coordinates based on the current center
+        shifted_coordinates = node_coordinates - center
+        # Calculate skew (difference in distance from the center)
+        skew = np.mean(shifted_coordinates, axis=0)
+        # If skew is below tolerance, stop
+        if np.linalg.norm(skew) < tolerance:
+            break
+
+        # Adjust the center by moving it in the direction opposite to the skew
+        center += skew
+
+    # After refinement, recalculate the bounding radius
+    shifted_coordinates = node_coordinates - center
+    new_radius = np.max(np.linalg.norm(shifted_coordinates, axis=1)) * radius_margin
+
+    return center, new_radius
+
+
 def calculate_centroids(network, domain_id_to_node_ids_map):
     """Calculate the centroid for each domain based on node x and y coordinates in the network.
 

risk/risk.py

@@ -93,6 +93,9 @@ class RISK(NetworkIO, AnnotationsIO):
             random_seed=random_seed,
         )
 
+        # Make a copy of the network to avoid modifying the original
+        network = network.copy()
+
         # Load neighborhoods based on the network and distance metric
         neighborhoods = self._load_neighborhoods(
             network,
@@ -150,6 +153,9 @@ class RISK(NetworkIO, AnnotationsIO):
             random_seed=random_seed,
         )
 
+        # Make a copy of the network to avoid modifying the original
+        network = network.copy()
+
         # Load neighborhoods based on the network and distance metric
         neighborhoods = self._load_neighborhoods(
             network,
@@ -216,6 +222,9 @@ class RISK(NetworkIO, AnnotationsIO):
             max_workers=max_workers,
         )
 
+        # Make a copy of the network to avoid modifying the original
+        network = network.copy()
+
         # Load neighborhoods based on the network and distance metric
         neighborhoods = self._load_neighborhoods(
             network,
@@ -295,6 +304,9 @@ class RISK(NetworkIO, AnnotationsIO):
             max_cluster_size=max_cluster_size,
         )
 
+        # Make a copy of the network to avoid modifying the original
+        network = network.copy()
+
         logger.debug(f"p-value cutoff: {pval_cutoff}")
         logger.debug(f"FDR BH cutoff: {fdr_cutoff}")
         logger.debug(

{risk_network-0.0.8b22.dist-info → risk_network-0.0.8b24.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: risk-network
-Version: 0.0.8b22
+Version: 0.0.8b24
 Summary: A Python package for biological network analysis
 Author: Ira Horecka
 Author-email: Ira Horecka <ira89@icloud.com>

{risk_network-0.0.8b22.dist-info → risk_network-0.0.8b24.dist-info}/RECORD

@@ -1,8 +1,8 @@
-risk/__init__.py,sha256=fz5ZBsLUlWdBQ5uJS0qBge1qwPNox0OYhi4OXkjQxwI,113
+risk/__init__.py,sha256=cH9ocvJT5oWRV0qbQAG2O5ZSdpVcuvxbHoe8hT6DeJM,113
 risk/constants.py,sha256=XInRaH78Slnw_sWgAsBFbUHkyA0h0jL0DKGuQNbOvjM,550
-risk/risk.py,sha256=rjV0hllegCX978QaUo175FworKxNXlhQEQaQAPjHqos,23397
+risk/risk.py,sha256=7JERU-ZkDuESY3LJDyqEJGVs-YdYQwCt2SO3nHGYk0E,23809
 risk/annotations/__init__.py,sha256=kXgadEXaCh0z8OyhOhTj7c3qXGmWgOhaSZ4gSzSb59U,147
-risk/annotations/annotations.py,sha256=giLJht0tPtf4UdtH_d0kbCZQU5H5fZoupGDFKaNbC_Q,12700
+risk/annotations/annotations.py,sha256=dHO6kQOQjMA57nYA-yTAU1uB-ieiZ5sknAKvX6vF0Os,13024
 risk/annotations/io.py,sha256=powWzeimVdE0WCwlBCXyu5otMyZZHQujC0DS3m5DC0c,9505
 risk/log/__init__.py,sha256=aDUz5LMFQsz0UlsQI2EdXtiBKRLfml1UMeZKC7QQIGU,134
 risk/log/config.py,sha256=m8pzj-hN4vI_2JdJUfyOoSvzT8_lhoIfBt27sKbnOes,4535
@@ -18,11 +18,11 @@ risk/network/io.py,sha256=u0PPcKjp6Xze--7eDOlvalYkjQ9S2sjiC-ac2476PUI,22942
 risk/network/plot/__init__.py,sha256=MfmaXJgAZJgXZ2wrhK8pXwzETlcMaLChhWXKAozniAo,98
 risk/network/plot/canvas.py,sha256=ZO6bHw1chIsUqtE7IkPKdgX4tFLA-T5OwN5SojqGSNU,10672
 risk/network/plot/contour.py,sha256=CwX4i3uE5HL0W4kfx34U7YyoTTqMxyb7xaXKRVoNLzY,15265
-risk/network/plot/labels.py,sha256=ozkqwhBOTHKJLaAz4dJopXuykAvssSZUer2W5V0x2jM,45103
+risk/network/plot/labels.py,sha256=2XTL8jwqiGnkJYQizQDgUrjU8CPyjpwV3AapsG_Uqw4,45153
 risk/network/plot/network.py,sha256=6RURL1OdBFyQ34qNcwM_uH3LSQGYZZ8tZT51dggH1a0,13685
 risk/network/plot/plotter.py,sha256=iTPMiTnTTatM_-q1Ox_bjt5Pvv-Lo8gceiYB6TVzDcw,5770
 risk/network/plot/utils/color.py,sha256=WSs1ge2oZ8yXwyVk2QqBF-avRd0aYT-sYZr9cxxAn7M,19626
-risk/network/plot/utils/layout.py,sha256=5DpRLvabgnPWwVJ-J3W6oFBBvbjCrudvvW4HDOzzoTo,1960
+risk/network/plot/utils/layout.py,sha256=RnJq0yODpoheZnDl7KKFPQeXrnrsS3FLIdxupoYVZq4,3553
 risk/stats/__init__.py,sha256=WcgoETQ-hS0LQqKRsAMIPtP15xZ-4eul6VUBuUx4Wzc,220
 risk/stats/hypergeom.py,sha256=oc39f02ViB1vQ-uaDrxG_tzAT6dxQBRjc88EK2EGn78,2282
 risk/stats/poisson.py,sha256=polLgwS08MTCNzupYdmMUoEUYrJOjAbcYtYwjlfeE5Y,1803
@@ -30,8 +30,8 @@ risk/stats/stats.py,sha256=6iGi0-oN05mTmupg6X_VEBxEQvi2rujNhfPk4aLjwNI,7186
 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-0.0.8b22.dist-info/LICENSE,sha256=jOtLnuWt7d5Hsx6XXB2QxzrSe2sWWh3NgMfFRetluQM,35147
-risk_network-0.0.8b22.dist-info/METADATA,sha256=9trSkrh2Od_B2qltA2n_uVcvX1kUlMy-QmLO4WThrds,47498
-risk_network-0.0.8b22.dist-info/WHEEL,sha256=OVMc5UfuAQiSplgO0_WdW7vXVGAt9Hdd6qtN4HotdyA,91
-risk_network-0.0.8b22.dist-info/top_level.txt,sha256=NX7C2PFKTvC1JhVKv14DFlFAIFnKc6Lpsu1ZfxvQwVw,5
-risk_network-0.0.8b22.dist-info/RECORD,,
+risk_network-0.0.8b24.dist-info/LICENSE,sha256=jOtLnuWt7d5Hsx6XXB2QxzrSe2sWWh3NgMfFRetluQM,35147
+risk_network-0.0.8b24.dist-info/METADATA,sha256=YlQYQ6UuQrShoKaJtiryZKTj1_bPrqJQxYN7PAAlHj4,47498
+risk_network-0.0.8b24.dist-info/WHEEL,sha256=OVMc5UfuAQiSplgO0_WdW7vXVGAt9Hdd6qtN4HotdyA,91
+risk_network-0.0.8b24.dist-info/top_level.txt,sha256=NX7C2PFKTvC1JhVKv14DFlFAIFnKc6Lpsu1ZfxvQwVw,5
+risk_network-0.0.8b24.dist-info/RECORD,,