spacr 1.0.1__py3-none-any.whl → 1.0.3__py3-none-any.whl

spacr/__init__.py

@@ -1,4 +1,13 @@
-import logging, os
+import logging, os, builtins
+
+def silent_print(*args, **kwargs):
+    if "Welcome to CellposeSAM" in str(args[0]):
+        return  # skip the banner
+    return _original_print(*args, **kwargs)
+
+_original_print = builtins.print
+builtins.print = silent_print
+
 
 from . import core
 from . import io
@@ -22,7 +31,6 @@ from . import app_classify
 from . import app_sequencing
 from . import app_umap
 from . import submodules
-from . import openai
 from . import ml
 from . import toxo
 from . import spacr_cellpose

spacr/core.py

@@ -145,7 +145,7 @@ def preprocess_generate_masks(settings):
                         parasite_folder = os.path.join(mask_src, 'pathogen_mask_stack')
                         #organelle_folder = os.path.join(mask_src, 'organelle_mask_stack')
                         print(f'Adjusting cell masks with nuclei and pathogen masks')
-                        adjust_cell_masks(parasite_folder, cell_folder, nuclei_folder, overlap_threshold=5, perimeter_threshold=30)
+                        adjust_cell_masks(parasite_folder, cell_folder, nuclei_folder, overlap_threshold=5, perimeter_threshold=30, n_jobs=settings['n_jobs'])
                         stop = time.time()
                         adjust_time = (stop-start)/60
                         print(f'Cell mask adjustment: {adjust_time} min.')
@@ -243,6 +243,7 @@ def generate_cellpose_masks(src, settings, object_type):
         
     if object_type not in cellpose_channels:
         raise ValueError(f"Error: No channels were specified for object_type '{object_type}'. Check your settings.")
+    
     channels = cellpose_channels[object_type]
 
     #cellpose_batch_size = _get_cellpose_batch_size()

spacr/deep_spacr.py

@@ -940,7 +940,7 @@ def deep_spacr(settings={}):
             
 def model_knowledge_transfer(teacher_paths, student_save_path, data_loader, device='cpu', student_model_name='maxvit_t', pretrained=True, dropout_rate=None, use_checkpoint=False, alpha=0.5, temperature=2.0, lr=1e-4, epochs=10):
 
-    from spacr.utils import TorchModel  # Adapt if needed
+    from .utils import TorchModel
 
     # Adjust filename to reflect knowledge-distillation if desired
     if student_save_path.endswith('.pth'):
@@ -1044,7 +1044,7 @@ def model_knowledge_transfer(teacher_paths, student_save_path, data_loader, devi
             
 def model_fusion(model_paths,save_path,device='cpu',model_name='maxvit_t',pretrained=True,dropout_rate=None,use_checkpoint=False,aggregator='mean'):
 
-    from spacr.utils import TorchModel
+    from .utils import TorchModel
     
     if save_path.endswith('.pth'):
         save_path_part1, ext = os.path.splitext(save_path)

spacr/gui_core.py

@@ -549,16 +549,19 @@ def setup_settings_panel(vertical_container, settings_type='mask'):
     from .gui_elements import set_element_size
 
     size_dict = set_element_size()
+    
     settings_width = size_dict['settings_width']
-
+        
     # Create a PanedWindow for the settings panel
-    settings_paned_window = tk.PanedWindow(vertical_container, orient=tk.HORIZONTAL, width=size_dict['settings_width'])
+    settings_paned_window = tk.PanedWindow(vertical_container, orient=tk.HORIZONTAL, width=settings_width)
     vertical_container.add(settings_paned_window, stretch="always")
 
     settings_frame = tk.Frame(settings_paned_window, width=settings_width)
-    settings_frame.pack_propagate(False)  # Prevent the frame from resizing based on its children
+    settings_frame.pack_propagate(False)
 
     settings_paned_window.add(settings_frame)
+    #settings_paned_window.add(settings_frame, width=settings_width)
+    
 
     scrollable_frame = spacrFrame(settings_frame)
     scrollable_frame.grid(row=1, column=0, sticky="nsew")
@@ -1209,7 +1212,7 @@ def cleanup_previous_instance():
         canvas = None
 
     print("Previous instance cleaned up successfully.")
-
+    
 def initiate_root(parent, settings_type='mask'):
     """
     Initializes the root window and sets up the GUI components based on the specified settings type.
@@ -1223,6 +1226,7 @@ def initiate_root(parent, settings_type='mask'):
     """
     
     global q, fig_queue, thread_control, parent_frame, scrollable_frame, button_frame, vars_dict, canvas, canvas_widget, button_scrollable_frame, progress_bar, uppdate_frequency, figures, figure_index, index_control, usage_bars
+    from .gui_elements import set_element_size
     
     # Clean up any previous instance
     cleanup_previous_instance()
@@ -1235,8 +1239,6 @@ def initiate_root(parent, settings_type='mask'):
     uppdate_frequency = 500
     num_cores = os.cpu_count()
 
-    #chatbot = Chatbot(api_key="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")
-
     # Start tracemalloc and initialize global variables
     tracemalloc.start()
 

spacr/gui_elements.py

@@ -39,7 +39,7 @@ def restart_gui_app(root):
         root.destroy()
         
         # Import and launch a new instance of the application
-        from spacr.gui import gui_app
+        from .gui import gui_app
         new_root = tk.Tk()  # Create a fresh Tkinter root instance
         gui_app()
     except Exception as e:
@@ -81,7 +81,7 @@ def create_menu_bar(root):
     # Add a separator and an exit option
     app_menu.add_separator()
     #app_menu.add_command(label="Home",command=lambda: restart_gui_app(root))
-    app_menu.add_command(label="Help", command=lambda: webbrowser.open("https://spacr.readthedocs.io/en/latest/?badge=latest"))
+    app_menu.add_command(label="Help", command=lambda: webbrowser.open("https://einarolafsson.github.io/spacr/index.html"))
     app_menu.add_command(label="Exit", command=root.quit)
 
     # Configure the menu for the root window
@@ -2851,7 +2851,7 @@ class AnnotateApp:
         # Optionally, update your GUI status label
         self.update_gui_text("Merging data...")
 
-        from spacr.io import _read_and_merge_data  # Adapt to your actual import
+        from .io import _read_and_merge_data
 
         # (1) Merge data
         merged_df, obj_df_ls = _read_and_merge_data(

spacr/gui_utils.py

@@ -594,6 +594,12 @@ def setup_frame(parent_frame):
     tk.Label(settings_container, text="Settings Container", bg=style_out['bg_color']).pack(fill=tk.BOTH, expand=True)
 
     set_dark_style(style, parent_frame, [settings_container, vertical_container, horizontal_container, main_paned])
+    
+    # Set initial sash position for main_paned (left/right split)
+    parent_frame.update_idletasks()
+    screen_width = parent_frame.winfo_screenwidth()
+    target_width = int(screen_width / 4)
+    main_paned.sash_place(0, target_width, 0)
 
     return parent_frame, vertical_container, horizontal_container, settings_container
 

spacr/io.py

@@ -1,10 +1,9 @@
-import os, re, sqlite3, gc, torch, time, random, shutil, cv2, tarfile, cellpose, glob, queue, tifffile, czifile, atexit, datetime, traceback
+import os, re, sqlite3, gc, torch, time, random, shutil, cv2, tarfile, cellpose, glob, queue, tifffile, czifile, atexit, datetime
 import numpy as np
 import pandas as pd
 from PIL import Image, ImageOps
 from collections import defaultdict, Counter
 from pathlib import Path
-from functools import partial
 from matplotlib.animation import FuncAnimation
 from IPython.display import display
 from skimage.util import img_as_uint
@@ -298,26 +297,16 @@ def _load_normalized_images_and_labels(image_files, label_files, channels=None,
     return normalized_images, labels, image_names, label_names, orig_dims
 
 class CombineLoaders:
-
     """
     A class that combines multiple data loaders into a single iterator.
 
     Args:
         train_loaders (list): A list of data loaders.
 
-    Attributes:
-        train_loaders (list): A list of data loaders.
-        loader_iters (list): A list of iterator objects for each data loader.
-
-    Methods:
-        __iter__(): Returns the iterator object itself.
-        __next__(): Returns the next batch from one of the data loaders.
-
     Raises:
         StopIteration: If all data loaders have been exhausted.
-
     """
-
+    
     def __init__(self, train_loaders):
         self.train_loaders = train_loaders
         self.loader_iters = [iter(loader) for loader in train_loaders]
@@ -327,7 +316,7 @@ class CombineLoaders:
 
     def __next__(self):
         while self.loader_iters:
-            random.shuffle(self.loader_iters)  # Shuffle the loader_iters list
+            random.shuffle(self.loader_iters)
             for i, loader_iter in enumerate(self.loader_iters):
                 try:
                     batch = next(loader_iter)
@@ -377,14 +366,6 @@ class NoClassDataset(Dataset):
         transform (callable, optional): A function/transform to apply to the image data. Default is None.
         shuffle (bool, optional): Whether to shuffle the dataset. Default is True.
         load_to_memory (bool, optional): Whether to load all images into memory. Default is False.
-    
-    Attributes:
-        data_dir (str): The directory path where the image files are located.
-        transform (callable): A function/transform to apply to the image data.
-        shuffle (bool): Whether to shuffle the dataset.
-        load_to_memory (bool): Whether to load all images into memory.
-        filenames (list): A list of file paths for the image files.
-        images (list): A list of loaded images (if load_to_memory is True).
     """
     
     def __init__(self, data_dir, transform=None, shuffle=True, load_to_memory=False):
@@ -392,13 +373,16 @@ class NoClassDataset(Dataset):
         self.transform = transform
         self.shuffle = shuffle
         self.load_to_memory = load_to_memory
-        self.filenames = [os.path.join(data_dir, f) for f in os.listdir(data_dir) if os.path.isfile(os.path.join(data_dir, f))]
+        self.filenames = [
+            os.path.join(data_dir, f) 
+            for f in os.listdir(data_dir) 
+            if os.path.isfile(os.path.join(data_dir, f))
+        ]
         if self.shuffle:
             self.shuffle_dataset()
         if self.load_to_memory:
             self.images = [self.load_image(f) for f in self.filenames]
     
-    #@lru_cache(maxsize=None)
     def load_image(self, img_path):
         """
         Load an image from the given file path.
@@ -446,9 +430,9 @@ class NoClassDataset(Dataset):
             img = self.transform(img)
         else:
             img = ToTensor()(img)
-        # Return both the image and its filename
         return img, self.filenames[index]
 
+
 class spacrDataset(Dataset):
     def __init__(self, data_dir, loader_classes, transform=None, shuffle=True, pin_memory=False, specific_files=None, specific_labels=None):
         self.data_dir = data_dir
@@ -579,7 +563,7 @@ class spacrDataLoader(DataLoader):
     def __del__(self):
         self.cleanup()
 
-class NoClassDataset(Dataset):
+class NoClassDataset_v1(Dataset):
     def __init__(self, data_dir, transform=None, shuffle=True, load_to_memory=False):
         self.data_dir = data_dir
         self.transform = transform
@@ -614,7 +598,6 @@ class NoClassDataset(Dataset):
             img = ToTensor()(img)
         return img, self.filenames[index]
 
-    
 class TarImageDataset(Dataset):
     def __init__(self, tar_path, transform=None):
         self.tar_path = tar_path

spacr/ml.py

@@ -14,21 +14,18 @@ from IPython.display import display
 import scipy.stats as st
 import statsmodels.api as sm
 import statsmodels.formula.api as smf
-from statsmodels.tools import add_constant
 from statsmodels.regression.mixed_linear_model import MixedLM
-from statsmodels.tools.sm_exceptions import PerfectSeparationError
 from statsmodels.stats.outliers_influence import variance_inflation_factor
 from statsmodels.genmod.families import Binomial
 from statsmodels.genmod.families.links import logit
 from statsmodels.othermod.betareg import BetaModel
-from scipy.optimize import minimize
 from scipy.special import gammaln, psi, expit
 from sklearn.linear_model import Lasso, Ridge
 from sklearn.preprocessing import FunctionTransformer
 from patsy import dmatrices
 
-from sklearn.metrics import classification_report, accuracy_score
-from sklearn.model_selection import StratifiedKFold, cross_val_score
+from sklearn.metrics import classification_report
+from sklearn.model_selection import StratifiedKFold
 from sklearn.feature_selection import SelectKBest, f_classif
 from sklearn.model_selection import train_test_split
 from sklearn.ensemble import RandomForestClassifier, HistGradientBoostingClassifier
@@ -37,7 +34,7 @@ from sklearn.inspection import permutation_importance
 from sklearn.metrics import classification_report, precision_recall_curve
 from sklearn.preprocessing import StandardScaler
 from sklearn.preprocessing import MinMaxScaler
-from scipy.spatial.distance import cosine, euclidean, mahalanobis, cityblock, minkowski, chebyshev, hamming, jaccard, braycurtis
+from scipy.spatial.distance import cosine, euclidean, mahalanobis, cityblock, minkowski, chebyshev, braycurtis
 from xgboost import XGBClassifier
 
 import numpy as np
@@ -120,7 +117,7 @@ def scale_variables(X, y):
     
     return X_scaled, y_scaled
 
-def process_model_coefficients(model, regression_type, X, y, nc, pc, controls):
+def process_model_coefficients_v1(model, regression_type, X, y, nc, pc, controls):
     """Return DataFrame of model coefficients and p-values."""
     if regression_type in ['ols', 'gls', 'wls', 'rlm', 'glm', 'mixed', 'quantile', 'logit', 'probit', 'poisson']:
         coefs = model.params
@@ -159,7 +156,7 @@ def process_model_coefficients(model, regression_type, X, y, nc, pc, controls):
     coef_df['condition'] = coef_df.apply(lambda row: 'nc' if nc in row['feature'] else 'pc' if pc in row['feature'] else ('control' if row['grna'] in controls else 'other'),axis=1)
     return coef_df[~coef_df['feature'].str.contains('row|column')]
 
-def check_distribution(y):
+def check_distribution_v1(y):
     """Check the type of distribution to recommend a model."""
     if np.all((y == 0) | (y == 1)):
         print("Detected binary data.")
@@ -307,7 +304,7 @@ def check_and_clean_data(df, dependent_variable):
     print("Data is ready for model fitting.")
     return df_cleaned
 
-def check_normality(y, variable_name):
+def check_normality_v1(y, variable_name):
     """Check if the data is normally distributed using the Shapiro-Wilk test."""
     from scipy.stats import shapiro
 
@@ -326,7 +323,7 @@ def minimum_cell_simulation(settings, num_repeats=10, sample_size=100, tolerance
     Detect and mark the elbow point (inflection) with smoothing and tolerance control.
     """
 
-    from spacr.utils import correct_metadata_column_names
+    from .utils import correct_metadata_column_names
 
     # Load and process data
     if isinstance(settings['score_data'], str):

spacr/plot.py

@@ -1,4 +1,4 @@
-import os, random, cv2, glob, math, torch, skimage
+import os, random, cv2, glob, math, torch, itertools
 
 import numpy as np
 import pandas as pd
@@ -11,27 +11,19 @@ import scipy.stats as stats
 import statsmodels.api as sm
 import imageio.v2 as imageio
 from IPython.display import display
-from skimage.segmentation import find_boundaries
 from skimage import measure
 from skimage.measure import find_contours, label, regionprops
-from skimage.segmentation import mark_boundaries
 from skimage.transform import resize as sk_resize
 import scikit_posthocs as sp
 from scipy.stats import chi2_contingency
 import tifffile as tiff
 
-from scipy.stats import normaltest, ttest_ind, mannwhitneyu, f_oneway, kruskal
+from scipy.stats import normaltest, ttest_ind, mannwhitneyu, f_oneway, kruskal, levene, shapiro
 from statsmodels.stats.multicomp import pairwise_tukeyhsd
-from scipy.stats import ttest_ind, mannwhitneyu, levene, wilcoxon, kruskal, normaltest, shapiro
-import itertools
 import pingouin as pg
 
 from ipywidgets import IntSlider, interact
 from IPython.display import Image as ipyimage
-
-import matplotlib.patches as patches
-from collections import defaultdict
-from matplotlib.gridspec import GridSpec
 from matplotlib_venn import venn2
 
 def plot_image_mask_overlay(

spacr/sim.py

@@ -65,7 +65,7 @@ def gini_coefficient(x):
     diffsum = np.sum(np.abs(np.subtract.outer(x, x)))
     return diffsum / (2 * len(x) ** 2 * np.mean(x))
 
-def gini(x):
+def gini_V1(x):
     """
     Calculate the Gini coefficient for a given array of values.
 

spacr/sp_stats.py

@@ -1,7 +1,6 @@
 from scipy.stats import shapiro, normaltest, levene, ttest_ind, mannwhitneyu, kruskal, f_oneway
 from statsmodels.stats.multicomp import pairwise_tukeyhsd
 import scikit_posthocs as sp
-import numpy as np
 import pandas as pd
 from scipy.stats import chi2_contingency, fisher_exact
 import itertools

spacr/submodules.py

@@ -20,8 +20,7 @@ from IPython.display import display
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.inspection import permutation_importance
 from math import pi
-from scipy.stats import chi2_contingency, pearsonr
-from scipy.spatial.distance import cosine
+from scipy.stats import chi2_contingency
 
 from sklearn.metrics import mean_absolute_error
 from skimage.measure import regionprops, label as sklabel 
@@ -691,7 +690,8 @@ def analyze_plaques(settings):
     from .spacr_cellpose import identify_masks_finetune
     from .settings import get_analyze_plaque_settings
     from .utils import save_settings, download_models
-    from spacr import __file__ as spacr_path
+    #from spacr import __file__ as spacr_path
+    spacr_path = os.path.join(os.path.dirname(__file__), '__init__.py')
 
     download_models()
     package_dir = os.path.dirname(spacr_path)

spacr/timelapse.py

@@ -7,12 +7,18 @@ from IPython.display import display
 from IPython.display import Image as ipyimage
 import trackpy as tp
 from btrack import datasets as btrack_datasets
-from skimage.measure import regionprops, regionprops_table
+from skimage.measure import regionprops_table
 from scipy.signal import find_peaks
 from scipy.optimize import curve_fit, linear_sum_assignment
-from scipy.integrate import trapz
+
+try:
+    from numpy import trapz
+except ImportError:
+    from scipy.integrate import trapz
+    
 import matplotlib.pyplot as plt
 
+
 def _npz_to_movie(arrays, filenames, save_path, fps=10):
     """
     Convert a list of numpy arrays to a movie file.

spacr/toxo.py

@@ -5,23 +5,7 @@ import numpy as np
 from adjustText import adjust_text
 import pandas as pd
 from scipy.stats import fisher_exact
-from IPython.display import display
-from matplotlib.legend import Legend
-from matplotlib.transforms import Bbox
-from brokenaxes import brokenaxes
-
-import os
-import pandas as pd
-import seaborn as sns
-import matplotlib.pyplot as plt
-from scipy.spatial.distance import cosine
-from scipy.stats import pearsonr
-import pandas as pd
-import matplotlib.pyplot as plt
-import seaborn as sns
 from sklearn.metrics import mean_absolute_error
-
-
 from matplotlib.gridspec import GridSpec
 
 def custom_volcano_plot(data_path, metadata_path, metadata_column='tagm_location',point_size=50, figsize=20, threshold=0,save_path=None, x_lim=[-0.5, 0.5], y_lims=[[0, 6], [9, 20]]):

spacr/utils.py

@@ -1,8 +1,11 @@
+
 import os, re, sqlite3, torch, torchvision, random, string, shutil, cv2, tarfile, glob, psutil, platform, gzip, subprocess, time, requests, ast, traceback
+
 import numpy as np
 import pandas as pd
 from cellpose import models as cp_models
 from cellpose import denoise
+from functools import partial
 
 from skimage import morphology
 from skimage.measure import label, regionprops_table, regionprops
@@ -37,7 +40,6 @@ from torchvision import models
 from torchvision.models.resnet import ResNet18_Weights, ResNet34_Weights, ResNet50_Weights, ResNet101_Weights, ResNet152_Weights
 import torchvision.transforms as transforms
 from torchvision.models import resnet50
-from torchvision.utils import make_grid
 
 import seaborn as sns
 import matplotlib.pyplot as plt
@@ -65,10 +67,11 @@ from sklearn.decomposition import PCA
 from sklearn.ensemble import RandomForestClassifier
 
 from huggingface_hub import list_repo_files
-from spacr import __file__ as spacr_path
+
+#from spacr import __file__ as spacr_path
+spacr_path = os.path.join(os.path.dirname(__file__), '__init__.py')
 
 import umap.umap_ as umap
-#import umap
 
 def _generate_mask_random_cmap(mask):
     """
@@ -1283,7 +1286,7 @@ def _pivot_counts_table(db_path):
     pivoted_df.to_sql('pivoted_counts', conn, if_exists='replace', index=False)
     conn.close()
     
-def _get_cellpose_channels(src, nucleus_channel, pathogen_channel, cell_channel):
+def _get_cellpose_channels_v2(src, nucleus_channel, pathogen_channel, cell_channel):
     cell_mask_path = os.path.join(src, 'masks', 'cell_mask_stack')
     nucleus_mask_path = os.path.join(src, 'masks', 'nucleus_mask_stack')
     pathogen_mask_path = os.path.join(src, 'masks', 'pathogen_mask_stack')
@@ -1311,7 +1314,7 @@ def _get_cellpose_channels(src, nucleus_channel, pathogen_channel, cell_channel)
 
     return cellpose_channels
     
-def _get_cellpose_channels_v1(src, nucleus_channel, pathogen_channel, cell_channel):
+def _get_cellpose_channels(src, nucleus_channel, pathogen_channel, cell_channel):
 
     cell_mask_path = os.path.join(src, 'masks', 'cell_mask_stack')
     nucleus_mask_path = os.path.join(src, 'masks', 'nucleus_mask_stack')
@@ -1340,6 +1343,7 @@ def _get_cellpose_channels_v1(src, nucleus_channel, pathogen_channel, cell_chann
             cellpose_channels['cell'] = [0,1]
         else:
             cellpose_channels['cell'] = [0,0]
+            
     return cellpose_channels
 
 def annotate_conditions(df, cells=None, cell_loc=None, pathogens=None, pathogen_loc=None, treatments=None, treatment_loc=None):
@@ -1541,9 +1545,8 @@ class Cache:
     """
     A class representing a cache with a maximum size.
 
-    Attributes:
+    Args:
         max_size (int): The maximum size of the cache.
-        cache (OrderedDict): The cache data structure.
     """
 
     def __init__(self, max_size):
@@ -1562,23 +1565,15 @@ class Cache:
             self.cache.popitem(last=False)
         self.cache[key] = value
 
-class ScaledDotProductAttention(nn.Module):
+class ScaledDotProductAttention_v1(nn.Module):
     """
     Scaled Dot-Product Attention module.
 
     Args:
         d_k (int): The dimension of the key and query vectors.
-
-    Attributes:
-        d_k (int): The dimension of the key and query vectors.
-
-    Methods:
-        forward(Q, K, V): Performs the forward pass of the attention mechanism.
-
     """
-
     def __init__(self, d_k):
-        super(ScaledDotProductAttention, self).__init__()
+        super(ScaledDotProductAttention_v1, self).__init__()
         self.d_k = d_k
 
     def forward(self, Q, K, V):
@@ -1592,24 +1587,23 @@ class ScaledDotProductAttention(nn.Module):
 
         Returns:
             torch.Tensor: The output tensor of shape (batch_size, seq_len_q, d_k).
-
         """
         scores = torch.matmul(Q, K.transpose(-2, -1)) / torch.sqrt(torch.tensor(self.d_k, dtype=torch.float32))
         attention_probs = F.softmax(scores, dim=-1)
         output = torch.matmul(attention_probs, V)
         return output
 
-class SelfAttention(nn.Module):
+class SelfAttention_v1(nn.Module):
     """
     Self-Attention module that applies scaled dot-product attention mechanism.
-    
+
     Args:
         in_channels (int): Number of input channels.
         d_k (int): Dimensionality of the key and query vectors.
     """
 
     def __init__(self, in_channels, d_k):
-        super(SelfAttention, self).__init__()
+        super(SelfAttention_v1, self).__init__()
         self.W_q = nn.Linear(in_channels, d_k)
         self.W_k = nn.Linear(in_channels, d_k)
         self.W_v = nn.Linear(in_channels, d_k)
@@ -1618,10 +1612,10 @@ class SelfAttention(nn.Module):
     def forward(self, x):
         """
         Forward pass of the SelfAttention module.
-        
+
         Args:
             x (torch.Tensor): Input tensor of shape (batch_size, in_channels).
-        
+
         Returns:
             torch.Tensor: Output tensor of shape (batch_size, d_k).
         """
@@ -3298,7 +3292,7 @@ class SelectChannels:
             img[2, :, :] = 0  # Zero out the blue channel
         return img
     
-def preprocess_image(image_path, image_size=224, channels=[1,2,3], normalize=True):
+def preprocess_image_v1(image_path, image_size=224, channels=[1,2,3], normalize=True):
 
     if normalize:
         transform = transforms.Compose([
@@ -3739,7 +3733,7 @@ def merge_dataframes(df, image_paths_df, verbose):
         display(df)
     return df
 
-def remove_highly_correlated_columns(df, threshold):
+def remove_highly_correlated_columns_v1(df, threshold):
     corr_matrix = df.corr().abs()
     upper_tri = corr_matrix.where(np.triu(np.ones(corr_matrix.shape), k=1).astype(bool))
     to_drop = [column for column in upper_tri.columns if any(upper_tri[column] > threshold)]
@@ -4678,7 +4672,54 @@ def _merge_cells_without_nucleus(adj_cell_mask: np.ndarray, nuclei_mask: np.ndar
 
     return out.astype(np.uint16)
 
-def adjust_cell_masks(parasite_folder, cell_folder, nuclei_folder, overlap_threshold=5, perimeter_threshold=30):
+def process_mask_file_adjust_cell(file_name, parasite_folder, cell_folder, nuclei_folder, overlap_threshold, perimeter_threshold):
+    start = time.perf_counter()
+
+    parasite_path = os.path.join(parasite_folder, file_name)
+    cell_path = os.path.join(cell_folder, file_name)
+    nuclei_path = os.path.join(nuclei_folder, file_name)
+
+    if not (os.path.exists(cell_path) and os.path.exists(nuclei_path)):
+        raise ValueError(f"Corresponding cell or nuclei mask file for {file_name} not found.")
+
+    parasite_mask = np.load(parasite_path, allow_pickle=True)
+    cell_mask = np.load(cell_path, allow_pickle=True)
+    nuclei_mask = np.load(nuclei_path, allow_pickle=True)
+
+    merged_cell_mask = _merge_cells_based_on_parasite_overlap(parasite_mask, cell_mask, nuclei_mask, overlap_threshold, perimeter_threshold)
+    #merged_cell_mask = _merge_cells_without_nucleus(merged_cell_mask, nuclei_mask)
+
+    np.save(cell_path, merged_cell_mask)
+
+    end = time.perf_counter()
+    return end - start
+
+def adjust_cell_masks(parasite_folder, cell_folder, nuclei_folder, overlap_threshold=5, perimeter_threshold=30, n_jobs=None):
+    
+    parasite_files = sorted([f for f in os.listdir(parasite_folder) if f.endswith('.npy')])
+    cell_files = sorted([f for f in os.listdir(cell_folder) if f.endswith('.npy')])
+    nuclei_files = sorted([f for f in os.listdir(nuclei_folder) if f.endswith('.npy')])
+
+    if not (len(parasite_files) == len(cell_files) == len(nuclei_files)):
+        raise ValueError("The number of files in the folders do not match.")
+
+    n_jobs = n_jobs or max(1, cpu_count() - 2)
+
+    time_ls = []
+    files_to_process = len(parasite_files)
+    process_fn = partial(process_mask_file_adjust_cell,
+                         parasite_folder=parasite_folder,
+                         cell_folder=cell_folder,
+                         nuclei_folder=nuclei_folder,
+                         overlap_threshold=overlap_threshold,
+                         perimeter_threshold=perimeter_threshold)
+
+    with Pool(n_jobs) as pool:
+        for i, duration in enumerate(pool.imap_unordered(process_fn, parasite_files), 1):
+            time_ls.append(duration)
+            print_progress(i, files_to_process, n_jobs=n_jobs, time_ls=time_ls, batch_size=None, operation_type='adjust_cell_masks')
+
+def adjust_cell_masks_v1(parasite_folder, cell_folder, nuclei_folder, overlap_threshold=5, perimeter_threshold=30):
 
     """
     Process all npy files in the given folders. Merge and relabel cells in cell masks

{spacr-1.0.1.dist-info → spacr-1.0.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: spacr
-Version: 1.0.1
+Version: 1.0.3
 Summary: Spatial phenotype analysis of crisp screens (SpaCr)
 Home-page: https://github.com/EinarOlafsson/spacr
 Author: Einar Birnir Olafsson
@@ -75,7 +75,7 @@ Requires-Dist: ipywidgets <9.0,>=8.1.2
 Requires-Dist: brokenaxes <1.0,>=0.6.2
 Requires-Dist: huggingface-hub <0.25,>=0.24.0
 Provides-Extra: dev
-Requires-Dist: pytest <3.11,>=3.9 ; extra == 'dev'
+Requires-Dist: pytest <3.12,>=3.9 ; extra == 'dev'
 Provides-Extra: full
 Requires-Dist: opencv-python ; extra == 'full'
 Provides-Extra: headless
@@ -164,16 +164,6 @@ SpaCr GUI requires Tkinter.
 
    spacr
 
-Data Availability
------------------
-
-- **Raw sequencing data** are available from NCBI BioProject `PRJNA1261935 <https://www.ncbi.nlm.nih.gov/bioproject/PRJNA1261935>`_ and SRA accessions: `SRR33531217 <https://www.ncbi.nlm.nih.gov/sra/SRR33531217>`_, `SRR33531218 <https://www.ncbi.nlm.nih.gov/sra/SRR33531218>`_, `SRR33531219 <https://www.ncbi.nlm.nih.gov/sra/SRR33531219>`_, `SRR33531220 <https://www.ncbi.nlm.nih.gov/sra/SRR33531220>`_
-
-- **Image data** is deposited at EBI BioStudies under accession: 
-  `S-BIAD2076 <https://www.ebi.ac.uk/biostudies/studies/S-BIAD2076>`_  
-  *(If the link redirects to the main BioStudies portal, copy and paste it directly into your browser.)*
-
-
 Example Notebooks
 -----------------
 
@@ -204,6 +194,25 @@ Click below to explore the step-by-step GUI and Notebook tutorials for spaCR:
 
 |Tutorial|
 
+spaCRPower
+----------
+
+Power analasys of pooled perterbation spaCR screens.
+
+`spaCRPower <https://github.com/maomlab/spaCRPower>`_
+
+Data Availability
+-----------------
+
+- **Full microscopy image dataset:**  
+  `EMBL-EBI BioStudies S-BIAD2135 <https://doi.org/10.6019/S-BIAD2135>`_
+
+- **Testing dataset:**  
+  `Hugging Face toxo_mito <https://huggingface.co/datasets/einarolafsson/toxo_mito>`_
+
+- **Sequencing data:**  
+  `NCBI BioProject PRJNA1261935 <https://www.ncbi.nlm.nih.gov/bioproject/?term=PRJNA1261935>`_
+
 License
 -------
 spaCR is distributed under the terms of the MIT License.

{spacr-1.0.1.dist-info → spacr-1.0.3.dist-info}/RECORD

@@ -1,4 +1,4 @@
-spacr/__init__.py,sha256=EoGInYks0M4foZElYNhksrQK6aEO1au7cncWexWNhRw,1376
+spacr/__init__.py,sha256=dB3aFOfOe5m5x81CTENDDP3FToXQwZwdBPtLBTuT4Js,1601
 spacr/__main__.py,sha256=H4MjaMF9ohZL6xfl1kTxVn1Nt_vEhhZArENMMBv8f4E,77
 spacr/app_annotate.py,sha256=p0OyvgFycIug7RcLfejFmc4HWB7yQskCBxxy3Sdq_Y0,2905
 spacr/app_classify.py,sha256=urTP_wlZ58hSyM5a19slYlBxN0PdC-9-ga0hvq8CGWc,165
@@ -8,28 +8,28 @@ spacr/app_measure.py,sha256=_K7APYIeOKpV6e_LcqabBjvEi7mfq9Fch8175x1x0k8,162
 spacr/app_sequencing.py,sha256=DjG26jy4cpddnV8WOOAIiExtOe9MleVMY4MFa5uTo5w,157
 spacr/app_umap.py,sha256=ZWAmf_OsIKbYvolYuWPMYhdlVe-n2CADoJulAizMiEo,153
 spacr/chat_bot.py,sha256=n3Fhqg3qofVXHmh3H9sUcmfYy9MmgRnr48663MVdY9E,1244
-spacr/core.py,sha256=A1PCJHtlYjJBMdIY0QH1VcrmjsAZy-JYVHQcBXQ5za8,46640
-spacr/deep_spacr.py,sha256=055tIo3WP3elGFiIuSZaLURgu2XyUDxAdbw5ezASEqM,54526
+spacr/core.py,sha256=GZWrKVKH_3EghGGcvAtia9OFTQ6hkZtwQRw9dpv2MBM,46672
+spacr/deep_spacr.py,sha256=x3_102k-p9IN3gE3XYdsEnXGCOyGqQh_ny5A-SO9HkA,54497
 spacr/gui.py,sha256=NhMh96KoArrSAaJBV6PhDQpIC1cQpxgb6SclhRbYG8s,8122
-spacr/gui_core.py,sha256=kgOXpQiBp4QXp08KViWinDVB6pVM7Gfn26bKeees6tM,54561
-spacr/gui_elements.py,sha256=OTU7aeLrPiMUTnyCT-J7ygng3beI9tdA0MmypOavEkw,156123
-spacr/gui_utils.py,sha256=1mWns46yK-CQpbhtERSTPx7KXBYPUIQz2UnFFxNxOrU,40749
-spacr/io.py,sha256=g6vybQeGLdTXrAqEjM6X1aoB6lyZVUq6pTI0ASppX4g,159257
+spacr/gui_core.py,sha256=IWkTEHI8imt_Pk9s8IUKbK_zLXtQNrbvDVl36Ft-n5k,54429
+spacr/gui_elements.py,sha256=9hEcIJ5ROQmBfHIROukgFawF3go37w5B-3OEHedNk3A,156078
+spacr/gui_utils.py,sha256=OJT1LX3X1U95joUY30b5Vn9fBrC0V65K4VBvdCckeNI,40995
+spacr/io.py,sha256=RKvy8DjyWbGnjV6zcbx8YHm2AdrPiTQBpHKEVrpA6dc,158412
 spacr/logger.py,sha256=lJhTqt-_wfAunCPl93xE65Wr9Y1oIHJWaZMjunHUeIw,1538
 spacr/measure.py,sha256=nYvrfVfCIqD1AUk4QBE2jtpeSFtLdfUcnkhkqf9G4xQ,60877
 spacr/mediar.py,sha256=p0F515eFbm6_rePSnChsgqrgH-H5Sr_3zWrghtOnAUg,14863
-spacr/ml.py,sha256=XCRZeX7UkbMctQICIoskeWVx8CCmmCoHNauUOAkfFq0,91692
+spacr/ml.py,sha256=iE7vI9Q1rjN_gHukqe8IXiWFCRaFj1lj3poFjEZY6Kw,91499
 spacr/openai.py,sha256=5vBZ3Jl2llYcW3oaTEXgdyCB2aJujMUIO5K038z7w_A,1246
-spacr/plot.py,sha256=76E1CZpsmNeNtbnkXJtgcVOesq4voL7XkaUnD74RDMk,169418
+spacr/plot.py,sha256=OgMr1ur1RFcFoZC_K8f-Qra48i-YmwgyyE_JNi5mw28,169111
 spacr/sequencing.py,sha256=EY12RdW5QRKpHDRQCw1QoAlxCq8FK2v6WoVa5uuDBXQ,26745
 spacr/settings.py,sha256=38MClzEv-eP4Kfo_UJ_jlIzj0Vos3TY5-scPlBpolYI,88520
-spacr/sim.py,sha256=1xKhXimNU3ukzIw-3l9cF3Znc_brW8h20yv8fSTzvss,71173
-spacr/sp_stats.py,sha256=C93Xe5fphQOKthw4Tmj8pHx-Nb1houIL-YYVIfmnQPg,9535
+spacr/sim.py,sha256=EiCXNCarU6TAFwIKKSr7LOPKtNrxWK6_3XSBMaEpg20,71176
+spacr/sp_stats.py,sha256=KoQe5F0jfPBrZQ38MG_1b3AnF4XFNupR8a9crXiyi64,9516
 spacr/spacr_cellpose.py,sha256=AvnyD2qoj-lUqhICeTpfhyk9T2hCjZrpBXn2iKh1EYE,16785
-spacr/submodules.py,sha256=Z2i4kv_rWdxqoXsOKCF7BaSXtvaCZB69Ow8_FQBnZsY,83093
-spacr/timelapse.py,sha256=-5ZupTsCCpbenIQ2zsUmnwXh45B82fO-gPrSXOxu2s8,42980
-spacr/toxo.py,sha256=GoNfgyH-NJx3WOzNQPgzODir7Jp65fs7UM46XpzcrUo,26056
-spacr/utils.py,sha256=PulmDqENBFYKgN2fjcVSB39B_9CwwGDiBi9FOI55zQs,238470
+spacr/submodules.py,sha256=kyX_oX0llXBrU5YwLLq0DssCczG3J1BAa2QeKI9P7oE,83114
+spacr/timelapse.py,sha256=WKz21Qy4ZJAMHUeYZNHnuw8SATA-q2CfnKgEUETDGMM,43031
+spacr/toxo.py,sha256=7to5GHfHt0EPL9qaxAQnA-_Io1t2NQ1nBxXlfZc3_oI,25674
+spacr/utils.py,sha256=L1-F13dcBxRgBIX4toe_zYqL4FyIbtz3tYwtiQwyShY,240591
 spacr/version.py,sha256=axH5tnGwtgSnJHb5IDhiu4Zjk5GhLyAEDRe-rnaoFOA,409
 spacr/resources/data/lopit.csv,sha256=ERI5f9W8RdJGiSx_khoaylD374f8kmvLia1xjhD_mII,4421709
 spacr/resources/data/toxoplasma_metadata.csv,sha256=9TXx0VlClDHAxQmaLhoklE8NuETduXaGHZjhR_6lZfs,2969409
@@ -103,9 +103,9 @@ spacr/resources/icons/umap.png,sha256=dOLF3DeLYy9k0nkUybiZMe1wzHQwLJFRmgccppw-8b
 spacr/resources/images/plate1_E01_T0001F001L01A01Z01C02.tif,sha256=Tl0ZUfZ_AYAbu0up_nO0tPRtF1BxXhWQ3T3pURBCCRo,7958528
 spacr/resources/images/plate1_E01_T0001F001L01A02Z01C01.tif,sha256=m8N-V71rA1TT4dFlENNg8s0Q0YEXXs8slIn7yObmZJQ,7958528
 spacr/resources/images/plate1_E01_T0001F001L01A03Z01C03.tif,sha256=Pbhk7xn-KUP6RSIhJsxQcrHFImBm3GEpLkzx7WOc-5M,7958528
-spacr-1.0.1.dist-info/LICENSE,sha256=t0Pov6pnK8thLteoF4xZGmdCwe5mhNwl3OXxLYTGD9U,1081
-spacr-1.0.1.dist-info/METADATA,sha256=C_PPoW7NPT7RH3d3iJ2yfX3GR8cy-uQ8tx1RGmqq854,10963
-spacr-1.0.1.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
-spacr-1.0.1.dist-info/entry_points.txt,sha256=BMC0ql9aNNpv8lUZ8sgDLQMsqaVnX5L535gEhKUP5ho,296
-spacr-1.0.1.dist-info/top_level.txt,sha256=GJPU8FgwRXGzKeut6JopsSRY2R8T3i9lDgya42tLInY,6
-spacr-1.0.1.dist-info/RECORD,,
+spacr-1.0.3.dist-info/LICENSE,sha256=t0Pov6pnK8thLteoF4xZGmdCwe5mhNwl3OXxLYTGD9U,1081
+spacr-1.0.3.dist-info/METADATA,sha256=mHQ3iqlrD2kQfkGHtW4LURYbI1VOuMjzCpDLQJFW3NY,10792
+spacr-1.0.3.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
+spacr-1.0.3.dist-info/entry_points.txt,sha256=BMC0ql9aNNpv8lUZ8sgDLQMsqaVnX5L535gEhKUP5ho,296
+spacr-1.0.3.dist-info/top_level.txt,sha256=GJPU8FgwRXGzKeut6JopsSRY2R8T3i9lDgya42tLInY,6
+spacr-1.0.3.dist-info/RECORD,,