nettracer3d 0.4.3__tar.gz → 0.4.5__tar.gz

{nettracer3d-0.4.3/src/nettracer3d.egg-info → nettracer3d-0.4.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: nettracer3d
-Version: 0.4.3
+Version: 0.4.5
 Summary: Scripts for intializing and analyzing networks from segmentations of three dimensional images.
 Author-email: Liam McLaughlin <boom2449@gmail.com>
 Project-URL: User_Manual, https://drive.google.com/drive/folders/1fTkz3n4LN9_VxKRKC8lVQSlrz_wq0bVn?usp=drive_link
@@ -11,7 +11,7 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: numpy
+Requires-Dist: numpy==1.26.4
 Requires-Dist: scipy
 Requires-Dist: scikit-image
 Requires-Dist: Pillow
@@ -25,14 +25,28 @@ Requires-Dist: python-louvain
 Requires-Dist: tifffile
 Requires-Dist: qtrangeslider
 Requires-Dist: PyQt6
+Requires-Dist: scikit-learn
 Provides-Extra: cuda11
 Requires-Dist: cupy-cuda11x; extra == "cuda11"
+Requires-Dist: torch==2.2.0+cu118; extra == "cuda11"
+Requires-Dist: torchvision==0.17.0+cu118; extra == "cuda11"
+Requires-Dist: torchaudio==2.2.0+cu118; extra == "cuda11"
 Provides-Extra: cuda12
 Requires-Dist: cupy-cuda12x; extra == "cuda12"
+Requires-Dist: torch==2.2.0+cu121; extra == "cuda12"
+Requires-Dist: torchvision==0.17.0+cu121; extra == "cuda12"
+Requires-Dist: torchaudio==2.2.0+cu121; extra == "cuda12"
 Provides-Extra: cupy
 Requires-Dist: cupy; extra == "cupy"
+Requires-Dist: torch; extra == "cupy"
+Requires-Dist: torchvision; extra == "cupy"
+Requires-Dist: torchaudio; extra == "cupy"
+Provides-Extra: gpu
+Requires-Dist: cupy-cuda11x; (platform_system == "Linux" and platform_machine == "x86_64") and extra == "gpu"
+Requires-Dist: cupy-cuda12x; platform_system == "Windows" and extra == "gpu"
+Requires-Dist: cupy; platform_system == "Darwin" and extra == "gpu"
 
-NetTracer3D is a python package developed for both 2D and 3D analysis of microscopic images in the .tif file format. It supports generation of 3D networks showing the relationships between objects (or nodes) in three dimensional space, either based on their own proximity or connectivity via connecting objects such as nerves or blood vessels. In addition to these functionalities are several advanced 3D data processing algorithms, such as labeling of branched structures or abstraction of branched structures into networks. Note that nettracer3d uses segmented data, which can be segmented from other softwares such as ImageJ and imported into NetTracer3D, although it does offer its own segmentation via intensity or volumetric thresholding. NetTracer3D currently has a fully functional GUI. To use the GUI, after installing the nettracer3d package via pip, enter the command 'nettracer3d' in your command prompt:
+NetTracer3D is a python package developed for both 2D and 3D analysis of microscopic images in the .tif file format. It supports generation of 3D networks showing the relationships between objects (or nodes) in three dimensional space, either based on their own proximity or connectivity via connecting objects such as nerves or blood vessels. In addition to these functionalities are several advanced 3D data processing algorithms, such as labeling of branched structures or abstraction of branched structures into networks. Note that nettracer3d uses segmented data, which can be segmented from other softwares such as ImageJ and imported into NetTracer3D, although it does offer its own segmentation via intensity and volumetric thresholding, or random forest machine learning segmentation. NetTracer3D currently has a fully functional GUI. To use the GUI, after installing the nettracer3d package via pip, enter the command 'nettracer3d' in your command prompt:
 
 
 This gui is built from the PyQt6 package and therefore may not function on dockers or virtual envs that are unable to support PyQt6 displays. More advanced documentation (especially for the GUI) is coming down the line, but for now please see: https://drive.google.com/drive/folders/1fTkz3n4LN9_VxKRKC8lVQSlrz_wq0bVn?usp=drive_link

{nettracer3d-0.4.3 → nettracer3d-0.4.5}/README.md

@@ -1,4 +1,4 @@
-NetTracer3D is a python package developed for both 2D and 3D analysis of microscopic images in the .tif file format. It supports generation of 3D networks showing the relationships between objects (or nodes) in three dimensional space, either based on their own proximity or connectivity via connecting objects such as nerves or blood vessels. In addition to these functionalities are several advanced 3D data processing algorithms, such as labeling of branched structures or abstraction of branched structures into networks. Note that nettracer3d uses segmented data, which can be segmented from other softwares such as ImageJ and imported into NetTracer3D, although it does offer its own segmentation via intensity or volumetric thresholding. NetTracer3D currently has a fully functional GUI. To use the GUI, after installing the nettracer3d package via pip, enter the command 'nettracer3d' in your command prompt:
+NetTracer3D is a python package developed for both 2D and 3D analysis of microscopic images in the .tif file format. It supports generation of 3D networks showing the relationships between objects (or nodes) in three dimensional space, either based on their own proximity or connectivity via connecting objects such as nerves or blood vessels. In addition to these functionalities are several advanced 3D data processing algorithms, such as labeling of branched structures or abstraction of branched structures into networks. Note that nettracer3d uses segmented data, which can be segmented from other softwares such as ImageJ and imported into NetTracer3D, although it does offer its own segmentation via intensity and volumetric thresholding, or random forest machine learning segmentation. NetTracer3D currently has a fully functional GUI. To use the GUI, after installing the nettracer3d package via pip, enter the command 'nettracer3d' in your command prompt:
 
 
 This gui is built from the PyQt6 package and therefore may not function on dockers or virtual envs that are unable to support PyQt6 displays. More advanced documentation (especially for the GUI) is coming down the line, but for now please see: https://drive.google.com/drive/folders/1fTkz3n4LN9_VxKRKC8lVQSlrz_wq0bVn?usp=drive_link

{nettracer3d-0.4.3 → nettracer3d-0.4.5}/pyproject.toml

@@ -1,12 +1,12 @@
 [project]
 name = "nettracer3d"
-version = "0.4.3"
+version = "0.4.5"
 authors = [
   { name="Liam McLaughlin", email="boom2449@gmail.com" },
 ]
 description = "Scripts for intializing and analyzing networks from segmentations of three dimensional images."
 dependencies = [
-    "numpy",
+    "numpy == 1.26.4",
     "scipy",
     "scikit-image",
     "Pillow",
@@ -19,8 +19,10 @@ dependencies = [
     "python-louvain",
     "tifffile",
     "qtrangeslider",
-    "PyQt6"
+    "PyQt6",
+    "scikit-learn"
 ]
+
 readme = "README.md"
 requires-python = ">=3.8"
 classifiers = [
@@ -30,9 +32,29 @@ classifiers = [
 ]
 
 [project.optional-dependencies]
-CUDA11 = ["cupy-cuda11x"]
-CUDA12 = ["cupy-cuda12x"]
-cupy = ["cupy"]
+CUDA11 = [
+"cupy-cuda11x",
+"torch==2.2.0+cu118",
+"torchvision==0.17.0+cu118",
+"torchaudio==2.2.0+cu118"
+]
+CUDA12 = [
+"cupy-cuda12x",
+"torch==2.2.0+cu121",
+"torchvision==0.17.0+cu121",
+"torchaudio==2.2.0+cu121"
+]
+cupy = [
+"cupy",
+"torch",  # Will get CPU version by default
+"torchvision",
+"torchaudio"
+]
+GPU = [  # Meta-dependency that user can choose based on their CUDA version
+"cupy-cuda11x ; platform_system=='Linux' and platform_machine=='x86_64'",
+"cupy-cuda12x ; platform_system=='Windows'",
+"cupy ; platform_system=='Darwin'"
+]
 
 [project.scripts]
 nettracer3d = "nettracer3d.run:main"

{nettracer3d-0.4.3 → nettracer3d-0.4.5}/src/nettracer3d/nettracer.py

@@ -858,10 +858,26 @@ def hash_inners(search_region, inner_edges, GPU = True):
 
     return inner_edges
 
+
+def dilate_2D(array, search, scaling = 1):
+
+    inv = array < 1
+
+    inv = smart_dilate.compute_distance_transform_distance(inv)
+
+    inv = inv * scaling
+
+    inv = inv <= search
+
+    return inv
+
+
 def dilate_3D(tiff_array, dilated_x, dilated_y, dilated_z):
     """Internal method to dilate an array in 3D. Dilation this way is much faster than using a distance transform although the latter is theoretically more accurate.
     Arguments are an array,  and the desired pixel dilation amounts in X, Y, Z."""
 
+    if tiff_array.shape[0] == 1:
+        return dilate_2D(tiff_array, ((dilated_x - 1) / 2))
 
     if dilated_x == 3 and dilated_y == 3  and dilated_z == 3:
 
@@ -996,6 +1012,8 @@ def dilate_3D_recursive(tiff_array, dilated_x, dilated_y, dilated_z, step_size=N
     
     Each dilation parameter represents (n-1)/2 steps outward from the object.
     """
+    if tiff_array.shape[0] == 1:
+        return dilate_2D(tiff_array, ((dilated_x - 1) / 2))
     # Calculate the smallest dimension of the array
     min_dim = min(tiff_array.shape)
     
@@ -1836,6 +1854,7 @@ def watershed(image, directory = None, proportion = 0.1, GPU = True, smallest_ra
                     gotoexcept = 1/0
 
             except (cp.cuda.memory.OutOfMemoryError, ZeroDivisionError) as e:
+                
                 if predownsample is None:
                     down_factor = smart_dilate.catch_memory(e) #Obtain downsample amount based on memory missing
                 else:
@@ -1866,8 +1885,12 @@ def watershed(image, directory = None, proportion = 0.1, GPU = True, smallest_ra
 
     labels, _ = label_objects(distance)
 
+    if len(labels.shape) ==2:
+        labels = np.expand_dims(labels, axis = 0)
+
     del distance
 
+
     if labels.shape[1] < original_shape[1]: #If downsample was used, upsample output
         labels = upsample_with_padding(labels, downsample_needed, original_shape)
         labels = labels * old_mask
@@ -1876,8 +1899,7 @@ def watershed(image, directory = None, proportion = 0.1, GPU = True, smallest_ra
         labels = smart_dilate.smart_label(image, labels, GPU = GPU, predownsample = predownsample2)
 
     if directory is None:
-        tifffile.imwrite("Watershed_output.tif", labels)
-        print("Watershed saved to 'Watershed_output.tif'")
+        pass
     else:
         tifffile.imwrite(f"{directory}/Watershed_output.tif", labels)
         print(f"Watershed saved to {directory}/'Watershed_output.tif'")
@@ -2410,6 +2432,7 @@ class Network_3D:
         Can be called on a Network_3D object to save the node centroids properties to hard mem as a .xlsx file. It will save to the active directory if none is specified.
         :param directory: (Optional - Val = None; String). The path to an indended directory to save the centroids to.
         """
+
         if self._node_centroids is not None:
             if directory is None:
                 network_analysis._save_centroid_dictionary(self._node_centroids, 'node_centroids.xlsx')
@@ -2420,7 +2443,14 @@ class Network_3D:
                 print(f"Centroids saved to {directory}/node_centroids.xlsx")
 
         if self._node_centroids is None:
-            print("Node centroids attribute is empty, did not save...")
+            if directory is None:
+                network_analysis._save_centroid_dictionary({}, 'node_centroids.xlsx')
+                print("Centroids saved to node_centroids.xlsx")
+
+            if directory is not None:
+                network_analysis._save_centroid_dictionary({}, f'{directory}/node_centroids.xlsx')
+                print(f"Centroids saved to {directory}/node_centroids.xlsx")
+
 
     def save_edge_centroids(self, directory = None):
         """
@@ -2438,6 +2468,13 @@ class Network_3D:
 
         if self._edge_centroids is None:
             print("Edge centroids attribute is empty, did not save...")
+            if directory is None:
+                network_analysis._save_centroid_dictionary({}, 'edge_centroids.xlsx', index = 'Edge ID')
+                print("Centroids saved to edge_centroids.xlsx")
+
+            if directory is not None:
+                network_analysis._save_centroid_dictionary({}, f'{directory}/edge_centroids.xlsx', index = 'Edge ID')
+                print(f"Centroids saved to {directory}/edge_centroids.xlsx")
 
     def save_search_region(self, directory = None):
         """
@@ -2490,7 +2527,13 @@ class Network_3D:
                 print(f"Node identities saved to {directory}/node_identities.xlsx")
 
         if self._node_identities is None:
-            print("Node identities attribute is empty...")
+            if directory is None:
+                network_analysis.save_singval_dict({}, 'NodeID', 'Identity', 'node_identities.xlsx')
+                print("Node identities saved to node_identities.xlsx")
+
+            if directory is not None:
+                network_analysis.save_singval_dict({}, 'NodeID', 'Identity', f'{directory}/node_identities.xlsx')
+                print(f"Node identities saved to {directory}/node_identities.xlsx")
 
     def save_communities(self, directory = None):
         """
@@ -2507,8 +2550,13 @@ class Network_3D:
                 print(f"Communities saved to {directory}/node_communities.xlsx")
 
         if self._communities is None:
-            print("Communities attribute is empty...")
+            if directory is None:
+                network_analysis.save_singval_dict({}, 'NodeID', 'Community', 'node_communities.xlsx')
+                print("Communities saved to node_communities.xlsx")
 
+            if directory is not None:
+                network_analysis.save_singval_dict({}, 'NodeID', 'Community', f'{directory}/node_communities.xlsx')
+                print(f"Communities saved to {directory}/node_communities.xlsx")
 
     def save_network_overlay(self, directory = None, filename = None):