risk-network 0.0.6b9__py3-none-any.whl → 0.0.7__py3-none-any.whl

risk/stats/permutation/permutation.py

@@ -4,6 +4,7 @@ risk/stats/permutation/permutation
 """
 
 from multiprocessing import get_context, Manager
+from multiprocessing.managers import ValueProxy
 from tqdm import tqdm
 from typing import Any, Callable, Dict
 
@@ -28,7 +29,7 @@ def compute_permutation_test(
         neighborhoods (np.ndarray): Binary matrix representing neighborhoods.
         annotations (np.ndarray): Binary matrix representing annotations.
         score_metric (str, optional): Metric to use for scoring ('sum', 'mean', etc.). Defaults to "sum".
-        null_distribution (str, optional): Type of null distribution ('network' or other). Defaults to "network".
+        null_distribution (str, optional): Type of null distribution ('network' or 'annotations'). Defaults to "network".
         num_permutations (int, optional): Number of permutations to run. Defaults to 1000.
         random_seed (int, optional): Seed for random number generation. Defaults to 888.
         max_workers (int, optional): Number of workers for multiprocessing. Defaults to 1.
@@ -78,7 +79,7 @@ def _run_permutation_test(
         neighborhoods (np.ndarray): The neighborhood matrix.
         annotations (np.ndarray): The annotation matrix.
         neighborhood_score_func (Callable): Function to calculate neighborhood scores.
-        null_distribution (str, optional): Type of null distribution. Defaults to "network".
+        null_distribution (str, optional): Type of null distribution ('network' or 'annotations'). Defaults to "network".
         num_permutations (int, optional): Number of permutations. Defaults to 1000.
         random_seed (int, optional): Seed for random number generation. Defaults to 888.
         max_workers (int, optional): Number of workers for multiprocessing. Defaults to 4.
@@ -91,8 +92,12 @@ def _run_permutation_test(
     # Determine the indices to use based on the null distribution type
     if null_distribution == "network":
         idxs = range(annotations.shape[0])
-    else:
+    elif null_distribution == "annotations":
         idxs = np.nonzero(np.sum(~np.isnan(annotations), axis=1))[0]
+    else:
+        raise ValueError(
+            "Invalid null_distribution value. Choose either 'network' or 'annotations'."
+        )
 
     # Replace NaNs with zeros in the annotations matrix
     annotations[np.isnan(annotations)] = 0
@@ -107,7 +112,6 @@ def _run_permutation_test(
     # Initialize count matrices for depletion and enrichment
     counts_depletion = np.zeros(observed_neighborhood_scores.shape)
     counts_enrichment = np.zeros(observed_neighborhood_scores.shape)
-
     # Determine the number of permutations to run in each worker process
     subset_size = num_permutations // max_workers
     remainder = num_permutations % max_workers
@@ -117,7 +121,6 @@ def _run_permutation_test(
     manager = Manager()
     progress_counter = manager.Value("i", 0)
     total_progress = num_permutations
-
     # Execute the permutation test using multiprocessing
     with ctx.Pool(max_workers) as pool:
         with tqdm(total=total_progress, desc="Total progress", position=0) as progress:
@@ -131,7 +134,8 @@ def _run_permutation_test(
                     neighborhood_score_func,
                     subset_size + (1 if i < remainder else 0),
                     progress_counter,
-                    rng,  # Pass the RNG to each process
+                    max_workers,
+                    rng,  # Pass the random number generator to each worker
                 )
                 for i in range(max_workers)
             ]
@@ -148,10 +152,10 @@ def _run_permutation_test(
             # Ensure progress bar reaches 100%
             progress.update(total_progress - progress.n)
 
-            # Accumulate results from each worker
-            for local_counts_depletion, local_counts_enrichment in results.get():
-                counts_depletion = np.add(counts_depletion, local_counts_depletion)
-                counts_enrichment = np.add(counts_enrichment, local_counts_enrichment)
+    # Accumulate results from each worker
+    for local_counts_depletion, local_counts_enrichment in results.get():
+        counts_depletion = np.add(counts_depletion, local_counts_depletion)
+        counts_enrichment = np.add(counts_enrichment, local_counts_enrichment)
 
     return counts_depletion, counts_enrichment
 
@@ -163,7 +167,8 @@ def _permutation_process_subset(
     observed_neighborhood_scores: np.ndarray,
     neighborhood_score_func: Callable,
     subset_size: int,
-    progress_counter,
+    progress_counter: ValueProxy,
+    max_workers: int,
     rng: np.random.Generator,
 ) -> tuple:
     """Process a subset of permutations for the permutation test.
@@ -175,7 +180,8 @@ def _permutation_process_subset(
         observed_neighborhood_scores (np.ndarray): Observed neighborhood scores.
         neighborhood_score_func (Callable): Function to calculate neighborhood scores.
         subset_size (int): Number of permutations to run in this subset.
-        progress_counter: Shared counter for tracking progress.
+        progress_counter (multiprocessing.managers.ValueProxy): Shared counter for tracking progress.
+        max_workers (int): Number of workers for multiprocessing.
         rng (np.random.Generator): Random number generator object.
 
     Returns:
@@ -184,10 +190,11 @@ def _permutation_process_subset(
     # Initialize local count matrices for this worker
     local_counts_depletion = np.zeros(observed_neighborhood_scores.shape)
     local_counts_enrichment = np.zeros(observed_neighborhood_scores.shape)
-    # NOTE: Limit the number of threads used by NumPy's BLAS implementation to 1.
-    # This can help prevent oversubscription of CPU resources during multiprocessing,
-    # ensuring that each process doesn't use more than one CPU core.
-    with threadpool_limits(limits=1, user_api="blas"):
+    # NOTE: Limit the number of threads used by NumPy's BLAS implementation to 1 when more than one worker is used.
+    # This can help prevent oversubscription of CPU resources during multiprocessing, ensuring that each process
+    # doesn't use more than one CPU core.
+    limits = None if max_workers == 1 else 1
+    with threadpool_limits(limits=limits, user_api="blas"):
         for _ in range(subset_size):
             # Permute the annotation matrix using the RNG
             annotation_matrix_permut = annotation_matrix[rng.permutation(idxs)]
@@ -205,7 +212,6 @@ def _permutation_process_subset(
                 local_counts_enrichment,
                 permuted_neighborhood_scores >= observed_neighborhood_scores,
             )
-
             # Update the shared progress counter
             progress_counter.value += 1
 

risk/stats/permutation/test_functions.py

@@ -1,6 +1,6 @@
 """
-risk/stats/permutation/test_function
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+risk/stats/permutation/test_functions
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 """
 
 import numpy as np

risk/stats/poisson.py

@@ -0,0 +1,44 @@
+"""
+risk/stats/poisson
+~~~~~~~~~~~~~~~~~~
+"""
+
+from typing import Dict, Any
+
+import numpy as np
+from scipy.stats import poisson
+
+
+def compute_poisson_test(
+    neighborhoods: np.ndarray, annotations: np.ndarray, null_distribution: str = "network"
+) -> Dict[str, Any]:
+    """Compute Poisson test for enrichment and depletion in neighborhoods with selectable null distribution.
+
+    Args:
+        neighborhoods (np.ndarray): Binary matrix representing neighborhoods.
+        annotations (np.ndarray): Binary matrix representing annotations.
+        null_distribution (str, optional): Type of null distribution ('network' or 'annotations'). Defaults to "network".
+
+    Returns:
+        dict: Dictionary containing depletion and enrichment p-values.
+    """
+    # Matrix multiplication to get the number of annotated nodes in each neighborhood
+    annotated_in_neighborhood = neighborhoods @ annotations
+
+    # Compute lambda_expected based on the chosen null distribution
+    if null_distribution == "network":
+        # Use the mean across neighborhoods (axis=1)
+        lambda_expected = np.mean(annotated_in_neighborhood, axis=1, keepdims=True)
+    elif null_distribution == "annotations":
+        # Use the mean across annotations (axis=0)
+        lambda_expected = np.mean(annotated_in_neighborhood, axis=0, keepdims=True)
+    else:
+        raise ValueError(
+            "Invalid null_distribution value. Choose either 'network' or 'annotations'."
+        )
+
+    # Compute p-values for enrichment and depletion using Poisson distribution
+    enrichment_pvals = 1 - poisson.cdf(annotated_in_neighborhood - 1, lambda_expected)
+    depletion_pvals = poisson.cdf(annotated_in_neighborhood, lambda_expected)
+
+    return {"enrichment_pvals": enrichment_pvals, "depletion_pvals": depletion_pvals}

{risk_network-0.0.6b9.dist-info → risk_network-0.0.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: risk-network
-Version: 0.0.6b9
+Version: 0.0.7
 Summary: A Python package for biological network analysis
 Author: Ira Horecka
 Author-email: Ira Horecka <ira89@icloud.com>

risk_network-0.0.7.dist-info/RECORD

@@ -0,0 +1,30 @@
+risk/__init__.py,sha256=gan-IiMjd-I7uHhZ63SkH_N40btvcNbrREH27gHjIZA,105
+risk/constants.py,sha256=XInRaH78Slnw_sWgAsBFbUHkyA0h0jL0DKGuQNbOvjM,550
+risk/risk.py,sha256=FaQhDCBZxZSAXJsScH0rSbjjCTNZA5vgf9rJj1GHW44,20924
+risk/annotations/__init__.py,sha256=vUpVvMRE5if01Ic8QY6M2Ae3EFGJHdugEe9PdEkAW4Y,138
+risk/annotations/annotations.py,sha256=ySc_N3nXnKx5RnOpFaEkM6zvTbswbrRcfFLzM0KdOck,11391
+risk/annotations/io.py,sha256=TTXVJQgUGAlKpnGBcx7Dow146IGyozA03nSbl3S7M5M,9475
+risk/log/__init__.py,sha256=aDUz5LMFQsz0UlsQI2EdXtiBKRLfml1UMeZKC7QQIGU,134
+risk/log/config.py,sha256=m8pzj-hN4vI_2JdJUfyOoSvzT8_lhoIfBt27sKbnOes,4535
+risk/log/params.py,sha256=DUmsqPo9hi3rQHFgLTunP14I-vVoyQSFZbx5aSYmVts,6363
+risk/neighborhoods/__init__.py,sha256=tKKEg4lsbqFukpgYlUGxU_v_9FOqK7V0uvM9T2QzoL0,206
+risk/neighborhoods/community.py,sha256=stYYBXeZlGLMV-k8ckQeIqThT6v9y-S3hETobAo9590,6817
+risk/neighborhoods/domains.py,sha256=Ov52EEr-tWqy96y8_0tJ9f1K8FI-8tZQxHR7a59A1k8,10738
+risk/neighborhoods/neighborhoods.py,sha256=M-wL4xB_BUTlSZg90swygO5NdrZ6hFUFqs6jsiZaqHk,18260
+risk/network/__init__.py,sha256=iEPeJdZfqp0toxtbElryB8jbz9_t_k4QQ3iDvKE8C_0,126
+risk/network/geometry.py,sha256=H1yGVVqgbfpzBzJwEheDLfvGLSA284jGQQTn612L4Vc,6759
+risk/network/graph.py,sha256=_LEoom4EEowGALuJKSXcev9RAAHu2FqIeq3u7mkifW0,16479
+risk/network/io.py,sha256=ASoKG4vkCC_aHwxlF4502W_SyaaCrRnHsTmRwL00spI,21266
+risk/network/plot.py,sha256=9GcLKkH3CMEtraYnfdLXNJCi04rBQCjw4T6Q8k5yNOI,67091
+risk/stats/__init__.py,sha256=WcgoETQ-hS0LQqKRsAMIPtP15xZ-4eul6VUBuUx4Wzc,220
+risk/stats/hypergeom.py,sha256=o6Qnj31gCAKxr2uQirXrbv7XvdDJGEq69MFW-ubx_hA,2272
+risk/stats/poisson.py,sha256=8x9hB4DCukq4gNIlIKO-c_jYG1-BTwTX53oLauFyfj8,1793
+risk/stats/stats.py,sha256=kvShov-94W6ffgDUTb522vB9hDJQSyTsYif_UIaFfSM,7059
+risk/stats/permutation/__init__.py,sha256=neJp7FENC-zg_CGOXqv-iIvz1r5XUKI9Ruxhmq7kDOI,105
+risk/stats/permutation/permutation.py,sha256=kmSZ7bQ-AD0TFiQDgIwfxTeqHa4pjp7fIcOzAqyhUNY,9714
+risk/stats/permutation/test_functions.py,sha256=lftOude6hee0pyR80HlBD32522JkDoN5hrKQ9VEbuoY,2345
+risk_network-0.0.7.dist-info/LICENSE,sha256=jOtLnuWt7d5Hsx6XXB2QxzrSe2sWWh3NgMfFRetluQM,35147
+risk_network-0.0.7.dist-info/METADATA,sha256=xxBE9FEu5YSnh41_SJZeJskSX-VFY0HnRarXFapvEag,43140
+risk_network-0.0.7.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
+risk_network-0.0.7.dist-info/top_level.txt,sha256=NX7C2PFKTvC1JhVKv14DFlFAIFnKc6Lpsu1ZfxvQwVw,5
+risk_network-0.0.7.dist-info/RECORD,,

{risk_network-0.0.6b9.dist-info → risk_network-0.0.7.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.0.0)
+Generator: setuptools (75.1.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

risk/log/console.py

@@ -1,16 +0,0 @@
-"""
-risk/log/console
-~~~~~~~~~~~~~~~~
-"""
-
-
-def print_header(input_string: str) -> None:
-    """Print the input string as a header with a line of dashes above and below it.
-
-    Args:
-        input_string (str): The string to be printed as a header.
-    """
-    border = "-" * len(input_string)
-    print(border)
-    print(input_string)
-    print(border)

risk/stats/fisher_exact.py

@@ -1,132 +0,0 @@
-"""
-risk/stats/fisher_exact
-~~~~~~~~~~~~~~~~~~~~~~~
-"""
-
-from multiprocessing import get_context, Manager
-from tqdm import tqdm
-from typing import Any, Dict
-
-import numpy as np
-from scipy.stats import fisher_exact
-
-
-def compute_fisher_exact_test(
-    neighborhoods: np.ndarray,
-    annotations: np.ndarray,
-    max_workers: int = 4,
-) -> Dict[str, Any]:
-    """Compute Fisher's exact test for enrichment and depletion in neighborhoods.
-
-    Args:
-        neighborhoods (np.ndarray): Binary matrix representing neighborhoods.
-        annotations (np.ndarray): Binary matrix representing annotations.
-        max_workers (int, optional): Number of workers for multiprocessing. Defaults to 4.
-
-    Returns:
-        dict: Dictionary containing depletion and enrichment p-values.
-    """
-    # Ensure that the matrices are binary (boolean) and free of NaN values
-    neighborhoods = neighborhoods.astype(bool)  # Convert to boolean
-    annotations = annotations.astype(bool)  # Convert to boolean
-
-    # Initialize the process of calculating p-values using multiprocessing
-    ctx = get_context("spawn")
-    manager = Manager()
-    progress_counter = manager.Value("i", 0)
-    total_tasks = neighborhoods.shape[1] * annotations.shape[1]
-
-    # Calculate the workload per worker
-    chunk_size = total_tasks // max_workers
-    remainder = total_tasks % max_workers
-
-    # Execute the Fisher's exact test using multiprocessing
-    with ctx.Pool(max_workers) as pool:
-        with tqdm(total=total_tasks, desc="Total progress", position=0) as progress:
-            params_list = []
-            start_idx = 0
-            for i in range(max_workers):
-                end_idx = start_idx + chunk_size + (1 if i < remainder else 0)
-                params_list.append(
-                    (neighborhoods, annotations, start_idx, end_idx, progress_counter)
-                )
-                start_idx = end_idx
-
-            # Start the Fisher's exact test process in parallel
-            results = pool.starmap_async(_fisher_exact_process_subset, params_list, chunksize=1)
-
-            # Update progress bar based on progress_counter
-            while not results.ready():
-                progress.update(progress_counter.value - progress.n)
-                results.wait(0.05)  # Wait for 50ms
-            # Ensure progress bar reaches 100%
-            progress.update(total_tasks - progress.n)
-
-            # Accumulate results from each worker
-            depletion_pvals, enrichment_pvals = [], []
-            for dp, ep in results.get():
-                depletion_pvals.extend(dp)
-                enrichment_pvals.extend(ep)
-
-    # Reshape the results back into arrays with the appropriate dimensions
-    depletion_pvals = np.array(depletion_pvals).reshape(
-        neighborhoods.shape[1], annotations.shape[1]
-    )
-    enrichment_pvals = np.array(enrichment_pvals).reshape(
-        neighborhoods.shape[1], annotations.shape[1]
-    )
-
-    return {
-        "depletion_pvals": depletion_pvals,
-        "enrichment_pvals": enrichment_pvals,
-    }
-
-
-def _fisher_exact_process_subset(
-    neighborhoods: np.ndarray,
-    annotations: np.ndarray,
-    start_idx: int,
-    end_idx: int,
-    progress_counter,
-) -> tuple:
-    """Process a subset of neighborhoods using Fisher's exact test.
-
-    Args:
-        neighborhoods (np.ndarray): The full neighborhood matrix.
-        annotations (np.ndarray): The annotation matrix.
-        start_idx (int): Starting index of the neighborhood-annotation pairs to process.
-        end_idx (int): Ending index of the neighborhood-annotation pairs to process.
-        progress_counter: Shared counter for tracking progress.
-
-    Returns:
-        tuple: Local p-values for depletion and enrichment.
-    """
-    # Initialize lists to store p-values for depletion and enrichment
-    depletion_pvals = []
-    enrichment_pvals = []
-    # Process the subset of tasks assigned to this worker
-    for idx in range(start_idx, end_idx):
-        i = idx // annotations.shape[1]  # Neighborhood index
-        j = idx % annotations.shape[1]  # Annotation index
-
-        neighborhood = neighborhoods[:, i]
-        annotation = annotations[:, j]
-
-        # Calculate the contingency table values
-        TP = np.sum(neighborhood & annotation)
-        FP = np.sum(neighborhood & ~annotation)
-        FN = np.sum(~neighborhood & annotation)
-        TN = np.sum(~neighborhood & ~annotation)
-        table = np.array([[TP, FP], [FN, TN]])
-
-        # Perform Fisher's exact test for depletion (alternative='less')
-        _, p_value_depletion = fisher_exact(table, alternative="less")
-        depletion_pvals.append(p_value_depletion)
-        # Perform Fisher's exact test for enrichment (alternative='greater')
-        _, p_value_enrichment = fisher_exact(table, alternative="greater")
-        enrichment_pvals.append(p_value_enrichment)
-
-        # Update the shared progress counter
-        progress_counter.value += 1
-
-    return depletion_pvals, enrichment_pvals

risk_network-0.0.6b9.dist-info/RECORD

@@ -1,30 +0,0 @@
-risk/__init__.py,sha256=6tlj1gnLhGwFbzT3xQqzWEWhatgBFXGguhpqJMhE5EA,112
-risk/constants.py,sha256=XInRaH78Slnw_sWgAsBFbUHkyA0h0jL0DKGuQNbOvjM,550
-risk/risk.py,sha256=-QVVWCBNmu3ho0QDiB5lRqpNsBR5fkpXpWJan3K3YGg,20702
-risk/annotations/__init__.py,sha256=vUpVvMRE5if01Ic8QY6M2Ae3EFGJHdugEe9PdEkAW4Y,138
-risk/annotations/annotations.py,sha256=DRUTdGzMdqo62NWSapBUksbvPr9CrzD76qtOcxeNKmo,10554
-risk/annotations/io.py,sha256=lo7NKqOVkeeBp58JBxWJHtA0xjL5Yoxqe9Ox0daKlZk,9457
-risk/log/__init__.py,sha256=xuLImfxFlKpnVhzi_gDYlr2_c9cLkrw2c_3iEsXb1as,107
-risk/log/console.py,sha256=im9DRExwf6wHlcn9fewoDcKIpo3vPcorZIaNAl-0csY,355
-risk/log/params.py,sha256=Tbb-sovFTptGBqPDKafUA8KOpby4zFObutAT_Iti1hE,6302
-risk/neighborhoods/__init__.py,sha256=tKKEg4lsbqFukpgYlUGxU_v_9FOqK7V0uvM9T2QzoL0,206
-risk/neighborhoods/community.py,sha256=7ebo1Q5KokSQISnxZIh2SQxsKXdXm8aVkp-h_DiQ3K0,6818
-risk/neighborhoods/domains.py,sha256=5V--Nj-TrSdubhD_2PI57ffcn_PMSEgpX_iY5OjT6R8,10626
-risk/neighborhoods/neighborhoods.py,sha256=sHmjFFl2U5qV9YbQCRbpbI36j7dS7IFfFwwRb1_-AuM,13945
-risk/network/__init__.py,sha256=iEPeJdZfqp0toxtbElryB8jbz9_t_k4QQ3iDvKE8C_0,126
-risk/network/geometry.py,sha256=H1yGVVqgbfpzBzJwEheDLfvGLSA284jGQQTn612L4Vc,6759
-risk/network/graph.py,sha256=7haHu4M3fleqbrIzs6HC9jnKizSERzmmAYSmUwdoSXA,13953
-risk/network/io.py,sha256=gG50kOknO-D3HkW1HsbHMkTMvjUtn3l4W4Jwd-rXNr8,21202
-risk/network/plot.py,sha256=_g5xHolMTAfZCBvYYEX1CYME4s4zA2hTHtN-utaMPik,61978
-risk/stats/__init__.py,sha256=e-BE_Dr_jgiK6hKM-T-tlG4yvHnId8e5qjnM0pdwNVc,230
-risk/stats/fisher_exact.py,sha256=-bPwzu76-ob0HzrTV20mXUTot7v-MLuqFaAoab-QxPg,4966
-risk/stats/hypergeom.py,sha256=lrIFdhCWRjvM4apYw1MlOKqT_IY5OjtCwrjdtJdt6Tg,4954
-risk/stats/stats.py,sha256=kvShov-94W6ffgDUTb522vB9hDJQSyTsYif_UIaFfSM,7059
-risk/stats/permutation/__init__.py,sha256=neJp7FENC-zg_CGOXqv-iIvz1r5XUKI9Ruxhmq7kDOI,105
-risk/stats/permutation/permutation.py,sha256=qLWdwxEY6nmkYPxpM8HLDcd2mbqYv9Qr7CKtJvhLqIM,9220
-risk/stats/permutation/test_functions.py,sha256=HuDIM-V1jkkfE1rlaIqrWWBSKZt3dQ1f-YEDjWpnLSE,2343
-risk_network-0.0.6b9.dist-info/LICENSE,sha256=jOtLnuWt7d5Hsx6XXB2QxzrSe2sWWh3NgMfFRetluQM,35147
-risk_network-0.0.6b9.dist-info/METADATA,sha256=xhmfOR_CeYgPfZQ6n5OGN4zkiOJMYZ6j3SXVqt3dWzo,43142
-risk_network-0.0.6b9.dist-info/WHEEL,sha256=5Mi1sN9lKoFv_gxcPtisEVrJZihrm_beibeg5R6xb4I,91
-risk_network-0.0.6b9.dist-info/top_level.txt,sha256=NX7C2PFKTvC1JhVKv14DFlFAIFnKc6Lpsu1ZfxvQwVw,5
-risk_network-0.0.6b9.dist-info/RECORD,,