spacr 0.9.1__py3-none-any.whl → 0.9.21__py3-none-any.whl

spacr/measure.py

@@ -2,12 +2,11 @@ import os, cv2, time, sqlite3, traceback, shutil
 import numpy as np
 import pandas as pd
 from collections import defaultdict
-from scipy.stats import pearsonr
+from scipy.stats import pearsonr, skew, kurtosis, mode
 import multiprocessing as mp
-from scipy.ndimage import distance_transform_edt, generate_binary_structure
+from scipy.ndimage import distance_transform_edt, generate_binary_structure, binary_dilation, gaussian_filter, center_of_mass
 from skimage.measure import regionprops, regionprops_table, shannon_entropy
 from skimage.exposure import rescale_intensity
-from scipy.ndimage import binary_dilation
 from skimage.segmentation import find_boundaries
 from skimage.feature import graycomatrix, graycoprops
 from mahotas.features import zernike_moments
@@ -16,7 +15,6 @@ from skimage.util import img_as_bool
 import matplotlib.pyplot as plt
 from math import ceil, sqrt
 
-
 def get_components(cell_mask, nucleus_mask, pathogen_mask):
     """
     Get the components (nucleus and pathogens) for each cell in the given masks.
@@ -250,6 +248,148 @@ def _create_dataframe(radial_distributions, object_type):
         return df
 
 def _extended_regionprops_table(labels, image, intensity_props):
+    """
+    Calculate extended region properties table, adding a suite of advanced quantitative features.
+    """
+    
+    def _gini(array):
+        # Compute Gini coefficient (nan safe)
+        array = np.abs(array[~np.isnan(array)])
+        n = array.size
+        if n == 0:
+            return np.nan
+        array = np.sort(array)
+        index = np.arange(1, n + 1)
+        return (np.sum((2 * index - n - 1) * array)) / (n * np.sum(array)) if np.sum(array) else np.nan
+    
+    props = regionprops_table(labels, image, properties=intensity_props)
+    df = pd.DataFrame(props)
+
+    regions = regionprops(labels, intensity_image=image)
+    integrated_intensity = []
+    std_intensity = []
+    median_intensity = []
+    skew_intensity = []
+    kurtosis_intensity = []
+    mode_intensity = []
+    range_intensity = []
+    iqr_intensity = []
+    cv_intensity = []
+    gini_intensity = []
+    frac_high90 = []
+    frac_low10 = []
+    entropy_intensity = []
+
+    for region in regions:
+        intens = region.intensity_image[region.image]
+        intens = intens[~np.isnan(intens)]
+        if intens.size == 0:
+            integrated_intensity.append(np.nan)
+            std_intensity.append(np.nan)
+            median_intensity.append(np.nan)
+            skew_intensity.append(np.nan)
+            kurtosis_intensity.append(np.nan)
+            mode_intensity.append(np.nan)
+            range_intensity.append(np.nan)
+            iqr_intensity.append(np.nan)
+            cv_intensity.append(np.nan)
+            gini_intensity.append(np.nan)
+            frac_high90.append(np.nan)
+            frac_low10.append(np.nan)
+            entropy_intensity.append(np.nan)
+        else:
+            integrated_intensity.append(np.sum(intens))
+            std_intensity.append(np.std(intens))
+            median_intensity.append(np.median(intens))
+            skew_intensity.append(skew(intens) if intens.size > 2 else np.nan)
+            kurtosis_intensity.append(kurtosis(intens) if intens.size > 3 else np.nan)
+            # Mode (use first mode value if multimodal)
+            try:
+                mode_val = mode(intens, nan_policy='omit').mode
+                mode_intensity.append(mode_val[0] if len(mode_val) > 0 else np.nan)
+            except Exception:
+                mode_intensity.append(np.nan)
+            range_intensity.append(np.ptp(intens))
+            iqr_intensity.append(np.percentile(intens, 75) - np.percentile(intens, 25))
+            cv_intensity.append(np.std(intens) / np.mean(intens) if np.mean(intens) != 0 else np.nan)
+            gini_intensity.append(_gini(intens))
+            frac_high90.append(np.mean(intens > np.percentile(intens, 90)))
+            frac_low10.append(np.mean(intens < np.percentile(intens, 10)))
+            entropy_intensity.append(shannon_entropy(intens) if intens.size > 1 else 0.0)
+
+    df['integrated_intensity'] = integrated_intensity
+    df['std_intensity'] = std_intensity
+    df['median_intensity'] = median_intensity
+    df['skew_intensity'] = skew_intensity
+    df['kurtosis_intensity'] = kurtosis_intensity
+    df['mode_intensity'] = mode_intensity
+    df['range_intensity'] = range_intensity
+    df['iqr_intensity'] = iqr_intensity
+    df['cv_intensity'] = cv_intensity
+    df['gini_intensity'] = gini_intensity
+    df['frac_high90'] = frac_high90
+    df['frac_low10'] = frac_low10
+    df['entropy_intensity'] = entropy_intensity
+
+    percentiles = [5, 10, 25, 50, 75, 85, 95]
+    for p in percentiles:
+        df[f'percentile_{p}'] = [
+            np.percentile(region.intensity_image[region.image], p)
+            for region in regions
+        ]
+    return df
+
+def _extended_regionprops_table_v2(labels, image, intensity_props):
+    """
+    Calculate extended region properties table, adding integrated intensity,
+    skewness, kurtosis, std, and median intensity per region.
+    """
+    # regionprops_table gives you vectorized props, but not everything you want
+    props = regionprops_table(labels, image, properties=intensity_props)
+    df = pd.DataFrame(props)
+
+    # Compute extra features region-by-region
+    regions = regionprops(labels, intensity_image=image)
+    integrated_intensity = []
+    std_intensity = []
+    median_intensity = []
+    skew_intensity = []
+    kurtosis_intensity = []
+    for region in regions:
+        intens = region.intensity_image[region.image]
+        # Handle empty region edge-case (shouldn't happen)
+        if intens.size == 0:
+            integrated_intensity.append(np.nan)
+            std_intensity.append(np.nan)
+            median_intensity.append(np.nan)
+            skew_intensity.append(np.nan)
+            kurtosis_intensity.append(np.nan)
+        else:
+            integrated_intensity.append(np.sum(intens))
+            std_intensity.append(np.std(intens))
+            median_intensity.append(np.median(intens))
+            # Only valid for >2 pixels
+            skew_intensity.append(skew(intens) if intens.size > 2 else np.nan)
+            kurtosis_intensity.append(kurtosis(intens) if intens.size > 3 else np.nan)
+
+    df['integrated_intensity'] = integrated_intensity
+    df['std_intensity'] = std_intensity
+    df['median_intensity'] = median_intensity
+    df['skew_intensity'] = skew_intensity
+    df['kurtosis_intensity'] = kurtosis_intensity
+
+    # You can add other features here if desired
+
+    # Percentiles (your existing code—optional if you want to keep)
+    percentiles = [5, 10, 25, 50, 75, 85, 95]
+    for p in percentiles:
+        df[f'percentile_{p}'] = [
+            np.percentile(region.intensity_image[region.image], p)
+            for region in regions
+        ]
+    return df
+
+def _extended_regionprops_table_v1(labels, image, intensity_props):
     """
     Calculate extended region properties table.
 
@@ -495,8 +635,75 @@ def _estimate_blur(image):
     # Compute and return the variance of the Laplacian
     return lap.var()
 
+def _measure_intensity_distance(cell_mask, nucleus_mask, pathogen_mask, channel_arrays, settings):
+    """
+    Compute Gaussian-smoothed intensity-weighted centroid distances for each cell object.
+    """
+
+    sigma = settings.get('distance_gaussian_sigma', 1.0)
+    cell_labels = np.unique(cell_mask)
+    cell_labels = cell_labels[cell_labels > 0]
+
+    dfs = []
+    nucleus_dt = distance_transform_edt(nucleus_mask == 0)
+    pathogen_dt = distance_transform_edt(pathogen_mask == 0)
+
+    for ch in range(channel_arrays.shape[-1]):
+        channel_img = channel_arrays[:, :, ch]
+        blurred_img = gaussian_filter(channel_img, sigma=sigma)
+
+        data = []
+        for label in cell_labels:
+            cell_coords = np.argwhere(cell_mask == label)
+            if cell_coords.size == 0:
+                data.append([label, np.nan, np.nan])
+                continue
+
+            minr, minc = np.min(cell_coords, axis=0)
+            maxr, maxc = np.max(cell_coords, axis=0) + 1
+
+            cell_submask = (cell_mask[minr:maxr, minc:maxc] == label)
+            blurred_subimg = blurred_img[minr:maxr, minc:maxc]
+
+            if np.sum(cell_submask) == 0:
+                data.append([label, np.nan, np.nan])
+                continue
+
+            masked_intensity = blurred_subimg * cell_submask
+            com_local = center_of_mass(masked_intensity)
+            if np.isnan(com_local[0]):
+                data.append([label, np.nan, np.nan])
+                continue
+
+            com_global = (com_local[0] + minr, com_local[1] + minc)
+            com_global_int = tuple(np.round(com_global).astype(int))
+
+            x, y = com_global_int
+            if not (0 <= x < cell_mask.shape[0] and 0 <= y < cell_mask.shape[1]):
+                data.append([label, np.nan, np.nan])
+                continue
+
+            nucleus_dist = nucleus_dt[x, y]
+            pathogen_dist = pathogen_dt[x, y]
+
+            data.append([label, nucleus_dist, pathogen_dist])
+
+        df = pd.DataFrame(data, columns=['label',
+                                         f'cell_channel_{ch}_distance_to_nucleus',
+                                         f'cell_channel_{ch}_distance_to_pathogen'])
+        dfs.append(df)
+
+    # Merge all channel dataframes on label
+    merged_df = dfs[0]
+    for df in dfs[1:]:
+        merged_df = merged_df.merge(df, on='label', how='outer')
+
+    return merged_df
+
+
 #@log_function_call
 def _intensity_measurements(cell_mask, nucleus_mask, pathogen_mask, cytoplasm_mask, channel_arrays, settings, sizes=[3, 6, 12, 24], periphery=True, outside=True):
+    
     """
     Calculate various intensity measurements for different regions in the image.
 
@@ -536,8 +743,8 @@ def _intensity_measurements(cell_mask, nucleus_mask, pathogen_mask, cytoplasm_ma
                 df.append(empty_df)
                 continue
                 
-            mask_intensity_df = _extended_regionprops_table(label, channel, intensity_props) 
-            mask_intensity_df['shannon_entropy'] = shannon_entropy(channel, base=2)
+            mask_intensity_df = _extended_regionprops_table(label, channel, intensity_props)
+            #mask_intensity_df['shannon_entropy'] = shannon_entropy(channel, base=2)
 
             if homogeneity:
                 homogeneity_df = _calculate_homogeneity(label, channel, distances)
@@ -558,6 +765,10 @@ def _intensity_measurements(cell_mask, nucleus_mask, pathogen_mask, cytoplasm_ma
 
             mask_intensity_df.columns = [f'{ls[j]}_channel_{i}_{col}' if col != 'label' else col for col in mask_intensity_df.columns]
             df.append(mask_intensity_df)
+            
+    if isinstance(settings['distance_gaussian_sigma'], int):
+        intensity_distance_df = _measure_intensity_distance(cell_mask, nucleus_mask, pathogen_mask, channel_arrays, settings)
+        cell_dfs.append(intensity_distance_df)
     
     if radial_dist:
         if np.max(nucleus_mask) != 0:
@@ -565,7 +776,7 @@ def _intensity_measurements(cell_mask, nucleus_mask, pathogen_mask, cytoplasm_ma
             nucleus_df = _create_dataframe(nucleus_radial_distributions, 'nucleus')
             dfs[1].append(nucleus_df)
             
-        if np.max(nucleus_mask) != 0:
+        if np.max(pathogen_mask) != 0:
             pathogen_radial_distributions = _calculate_radial_distribution(cell_mask, pathogen_mask, channel_arrays, num_bins=6)
             pathogen_df = _create_dataframe(pathogen_radial_distributions, 'pathogen')
             dfs[2].append(pathogen_df)
@@ -785,6 +996,7 @@ def _measure_crop_core(index, time_ls, file, settings):
                 #merge skeleton_df with cell_df here
 
             cell_intensity_df, nucleus_intensity_df, pathogen_intensity_df, cytoplasm_intensity_df = _intensity_measurements(cell_mask, nucleus_mask, pathogen_mask, cytoplasm_mask, channel_arrays, settings, sizes=[1, 2, 3, 4, 5], periphery=True, outside=True)
+                        
             if settings['cell_mask_dim'] is not None:
                 cell_merged_df = _merge_and_save_to_database(cell_df, cell_intensity_df, 'cell', source_folder, file_name, settings['experiment'], settings['timelapse'])
             if settings['nucleus_mask_dim'] is not None:

spacr/settings.py

@@ -313,7 +313,9 @@ def get_measure_crop_settings(settings={}):
     settings.setdefault('pathogen_min_size',0)
     settings.setdefault('cytoplasm_min_size',0)
     settings.setdefault('merge_edge_pathogen_cells', True)
-
+    
+    settings.setdefault('distance_gaussian_sigma', 1)
+    
     if settings['test_mode']:
         settings['verbose'] = True
         settings['plot'] = True
@@ -1000,7 +1002,8 @@ expected_types = {
     "cell_diamiter":int,
     "nucleus_diamiter":int,
     "pathogen_diamiter":int,
-    "consolidate":bool
+    "consolidate":bool,
+    "distance_gaussian_sigma":int
 }
 
 categories = {"Paths":[ "src", "grna", "barcodes", "custom_model_path", "dataset","model_path","grna_csv","row_csv","column_csv", "metadata_files", "score_data","count_data"],
@@ -1022,7 +1025,7 @@ categories = {"Paths":[ "src", "grna", "barcodes", "custom_model_path", "dataset
              "Plot": ["split_axis_lims", "x_lim","log_x","log_y", "plot_control", "plot_nr", "examples_to_plot", "normalize_plots", "cmap", "figuresize", "plot_cluster_grids", "img_zoom", "row_limit", "color_by", "plot_images", "smooth_lines", "plot_points", "plot_outlines", "black_background", "plot_by_cluster", "heatmap_feature","grouping","min_max","cmap","save_figure"],
              "Timelapse": ["timelapse", "fps", "timelapse_displacement", "timelapse_memory", "timelapse_frame_limits", "timelapse_remove_transient", "timelapse_mode", "timelapse_objects", "compartments"],
              "Advanced": ["merge_edge_pathogen_cells", "test_images", "random_test", "test_nr", "test", "test_split", "normalize", "target_unique_count","threshold_multiplier", "threshold_method", "min_n","shuffle", "target_intensity_min", "cells_per_well", "nuclei_limit", "pathogen_limit", "background", "backgrounds", "schedule", "test_size","exclude","n_repeats","top_features", "model_type_ml", "model_type","minimum_cell_count","n_estimators","preprocess", "remove_background", "normalize", "lower_percentile", "merge_pathogens", "batch_size", "filter", "save", "masks", "verbose", "randomize", "n_jobs"],
-             "Beta": ["all_to_mip", "upscale", "upscale_factor", "consolidate"]
+             "Beta": ["all_to_mip", "upscale", "upscale_factor", "consolidate", "distance_gaussian_sigma"]
              }
 
 

spacr/utils.py

@@ -4602,7 +4602,10 @@ def adjust_cell_masks(parasite_folder, cell_folder, nuclei_folder, overlap_thres
         raise ValueError("The number of files in the folders do not match.")
     
     # Match files by name
-    for file_name in parasite_files:
+    time_ls = []
+    files_to_process = len(parasite_files)
+    for files_processed, file_name in enumerate(parasite_files):
+        start = time.time()
         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)
@@ -4621,6 +4624,12 @@ def adjust_cell_masks(parasite_folder, cell_folder, nuclei_folder, overlap_thres
     
         # Overwrite the original cell mask file with the merged result
         np.save(cell_path, merged_cell_mask)
+        
+        stop = time.time()
+        duration = (stop - start)
+        time_ls.append(duration)
+        files_processed += 1
+        print_progress(files_processed, files_to_process, n_jobs=1, time_ls=time_ls, batch_size=None, operation_type=f'adjust_cell_masks')
 
 def process_masks(mask_folder, image_folder, channel, batch_size=50, n_clusters=2, plot=False):
     

spacr-0.9.21.dist-info/METADATA

@@ -0,0 +1,194 @@
+Metadata-Version: 2.1
+Name: spacr
+Version: 0.9.21
+Summary: Spatial phenotype analysis of crisp screens (SpaCr)
+Home-page: https://github.com/EinarOlafsson/spacr
+Author: Einar Birnir Olafsson
+Author-email: olafsson@med.umich.com
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Description-Content-Type: text/x-rst
+License-File: LICENSE
+Requires-Dist: numpy <2.0,>=1.26.4
+Requires-Dist: pandas <3.0,>=2.2.1
+Requires-Dist: scipy <2.0,>=1.12.0
+Requires-Dist: cellpose <4.0,>=3.0.6
+Requires-Dist: scikit-image <1.0,>=0.22.0
+Requires-Dist: scikit-learn <2.0,>=1.4.1
+Requires-Dist: scikit-posthocs <0.20,>=0.10.0
+Requires-Dist: mahotas <2.0,>=1.4.13
+Requires-Dist: btrack <1.0,>=0.6.5
+Requires-Dist: trackpy <1.0,>=0.6.2
+Requires-Dist: statsmodels <1.0,>=0.14.1
+Requires-Dist: shap <1.0,>=0.45.0
+Requires-Dist: torch <3.0,>=2.0
+Requires-Dist: torchvision <1.0,>=0.1
+Requires-Dist: torch-geometric <3.0,>=2.5
+Requires-Dist: torchcam <1.0,>=0.4.0
+Requires-Dist: transformers <5.0,>=4.45.2
+Requires-Dist: segmentation-models-pytorch >=0.3.3
+Requires-Dist: monai >=1.3.0
+Requires-Dist: captum <1.0,>=0.7.0
+Requires-Dist: seaborn <1.0,>=0.13.2
+Requires-Dist: matplotlib <4.0,>=3.8.3
+Requires-Dist: matplotlib-venn <2.0,>=1.1
+Requires-Dist: adjustText <2.0,>=1.2.0
+Requires-Dist: bottleneck <2.0,>=1.3.6
+Requires-Dist: numexpr <3.0,>=2.8.4
+Requires-Dist: opencv-python-headless <5.0,>=4.9.0.80
+Requires-Dist: pillow <11.0,>=10.2.0
+Requires-Dist: tifffile >=2023.4.12
+Requires-Dist: nd2reader <4.0,>=3.3.0
+Requires-Dist: czifile
+Requires-Dist: pylibCZIrw <6.0,>=5.0.0
+Requires-Dist: aicspylibczi
+Requires-Dist: readlif
+Requires-Dist: imageio <3.0,>=2.34.0
+Requires-Dist: pingouin <1.0,>=0.5.5
+Requires-Dist: umap-learn <1.0,>=0.5.6
+Requires-Dist: ttkthemes <4.0,>=3.2.2
+Requires-Dist: xgboost <3.0,>=2.0.3
+Requires-Dist: PyWavelets <2.0,>=1.6.0
+Requires-Dist: ttf-opensans >=2020.10.30
+Requires-Dist: customtkinter <6.0,>=5.2.2
+Requires-Dist: biopython <2.0,>=1.80
+Requires-Dist: lxml <6.0,>=5.1.0
+Requires-Dist: psutil <6.0,>=5.9.8
+Requires-Dist: gputil <2.0,>=1.4.0
+Requires-Dist: gpustat <2.0,>=1.1.1
+Requires-Dist: pyautogui <1.0,>=0.9.54
+Requires-Dist: tables <4.0,>=3.8.0
+Requires-Dist: rapidfuzz <4.0,>=3.9
+Requires-Dist: keyring <16.0,>=15.1
+Requires-Dist: screeninfo <1.0,>=0.8.1
+Requires-Dist: fastremap >=1.14.1
+Requires-Dist: pytz >=2023.3.post1
+Requires-Dist: tqdm >=4.65.0
+Requires-Dist: wandb >=0.16.2
+Requires-Dist: openai <2.0,>=1.50.2
+Requires-Dist: gdown
+Requires-Dist: IPython <9.0,>=8.18.1
+Requires-Dist: ipykernel
+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'
+Provides-Extra: full
+Requires-Dist: opencv-python ; extra == 'full'
+Provides-Extra: headless
+Requires-Dist: opencv-python-headless ; extra == 'headless'
+
+.. |Docs| image:: https://github.com/EinarOlafsson/spacr/actions/workflows/pages/pages-build-deployment/badge.svg
+   :target: https://einarolafsson.github.io/spacr/index.html
+.. |PyPI version| image:: https://badge.fury.io/py/spacr.svg
+   :target: https://badge.fury.io/py/spacr
+.. |Python version| image:: https://img.shields.io/pypi/pyversions/spacr
+   :target: https://pypistats.org/packages/spacr
+.. |Licence: GPL v3| image:: https://img.shields.io/github/license/EinarOlafsson/spacr
+   :target: https://github.com/EinarOlafsson/spacr/blob/master/LICENSE
+.. |repo size| image:: https://img.shields.io/github/repo-size/EinarOlafsson/spacr
+   :target: https://github.com/EinarOlafsson/spacr/
+
+.. _docs: https://einarolafsson.github.io/spacr/index.html
+
+Badges
+------
+|Docs| |PyPI version| |Python version| |Licence: GPL v3| |repo size|
+
+SpaCr
+=====
+
+**Spatial phenotype analysis of CRISPR-Cas9 screens (SpaCr).**
+
+The spatial organization of organelles and proteins within cells constitutes a key level of functional regulation. In the context of infectious disease, the spatial relationships between host cell structures and intracellular pathogens are critical to understanding host clearance mechanisms and how pathogens evade them. SpaCr is a Python-based software package for generating single-cell image data for deep-learning sub-cellular/cellular phenotypic classification from pooled genetic CRISPR-Cas9 screens. SpaCr provides a flexible toolset to extract single-cell images and measurements from high-content cell painting experiments, train deep-learning models to classify cellular/subcellular phenotypes, simulate, and analyze pooled CRISPR-Cas9 imaging screens.
+
+Features
+--------
+
+-  **Generate Masks:** Generate cellpose masks of cell, nuclei, and pathogen objects.
+-  **Object Measurements:** Measurements for each object including scikit-image regionprops, intensity percentiles, shannon-entropy, Pearson’s and Manders’ correlations, homogeneity, and radial distribution. Measurements are saved to a SQL database in object-level tables.
+-  **Crop Images:** Save objects (cells, nuclei, pathogen, cytoplasm) as images. Object image paths are saved in a SQL database.
+-  **Train CNNs or Transformers:** Train Torch models to classify single object images.
+-  **Manual Annotation:** Supports manual annotation of single-cell images and segmentation to refine training datasets for training CNNs/Transformers or cellpose, respectively.
+-  **Finetune Cellpose Models:** Adjust pre-existing Cellpose models to your specific dataset for improved performance.
+-  **Timelapse Data Support:** Track objects in timelapse image data.
+-  **Simulations:** Simulate spatial phenotype screens.
+-  **Sequencing:** Map FASTQ reads to barcode and gRNA barcode metadata.
+-  **Misc:** Analyze Ca oscillation, recruitment, infection rate, plaque size/count.
+
+.. image:: https://github.com/EinarOlafsson/spacr/raw/main/spacr/resources/icons/flow_chart_v2.png
+   :alt: SpaCr workflow
+   :align: center
+
+
+**Overview and data organization of spaCR.**
+
+**a.** Schematic workflow of the spaCR pipeline for pooled image-based CRISPR screens. Microscopy images (TIFF, LIF, CZI, NDI) and sequencing reads (FASTQ) are used as inputs (black). The main modules (teal) are: (1) Mask: generates object masks for cells, nuclei, pathogens, and cytoplasm; (2) Measure: extracts object-level features and crops object images, storing quantitative data in an SQL database; (3) Classify—applies machine learning (ML, e.g., XGBoost) or deep learning (DL, e.g., PyTorch) models to classify objects, summarizing results as well-level classification scores; (4) Map Barcodes: extracts and maps row, column, and gRNA barcodes from sequencing data to corresponding wells; (5) Regression: estimates gRNA effect sizes and gene scores via multiple linear regression using well-level summary statistics.
+**b.** Downstream submodules available for extended analyses at each stage.
+**c.** Output folder structure for each module, including locations for raw and processed images, masks, object-level measurements, datasets, and results.
+**d.** List of all spaCR package modules.
+
+Installation
+------------
+
+**Linux recommended.**  
+If using Windows, switch to Linux—it's free, open-source, and better.
+
+**macOS prerequisites (before install):**
+
+::
+
+   brew install libomp
+   brew install hdf5
+
+**Linux GUI requirement:**  
+SpaCr GUI requires Tkinter.  
+
+::
+
+   sudo apt-get install python3-tk
+
+**Installation:**
+
+::
+
+   pip install spacr
+
+**Run SpaCr GUI:**
+
+::
+
+   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>`_
+
+Example Notebooks
+-----------------
+
+The following example Jupyter notebooks illustrate common workflows using spaCR.
+
+- `Generate masks <https://github.com/EinarOlafsson/spacr/blob/main/Notebooks/1_spacr_generate_masks.ipynb>`_  
+  *Generate cell, nuclei, and pathogen segmentation masks from microscopy images using Cellpose.*
+
+- `Capture single cell images and measurements <https://github.com/EinarOlafsson/spacr/blob/main/Notebooks/2_spacr_generate_mesurments_crop_images.ipynb>`_  
+  *Extract object-level measurements and crop single-cell images for downstream analysis.*
+
+- `Machine learning based object classification <https://github.com/EinarOlafsson/spacr/blob/main/Notebooks/3a_spacr_machine_learning.ipynb>`_  
+  *Train traditional machine learning models (e.g., XGBoost) to classify cell phenotypes based on extracted features.*
+
+- `Computer vision based object classification <https://github.com/EinarOlafsson/spacr/blob/main/Notebooks/3b_spacr_computer_vision.ipynb>`_  
+  *Train and evaluate deep learning models (PyTorch CNNs/Transformers) on cropped object images.*
+
+- `Map sequencing barcodes <https://github.com/EinarOlafsson/spacr/blob/main/Notebooks/4_spacr_map_barecodes.ipynb>`_  
+  *Map sequencing reads to row, column, and gRNA barcodes for CRISPR screen genotype-phenotype mapping.*
+
+- `Finetune cellpose models <https://github.com/EinarOlafsson/spacr/blob/main/Notebooks/5_spacr_train_cellpose.ipynb>`_  
+  *Finetune Cellpose models using your own annotated training data for improved segmentation accuracy.*
+  

{spacr-0.9.1.dist-info → spacr-0.9.21.dist-info}/RECORD

@@ -16,20 +16,20 @@ spacr/gui_elements.py,sha256=5a3BOpctBPklsT1NungqS72h1Bg1FArUndE0OfvWD8Y,152646
 spacr/gui_utils.py,sha256=vv_uBOA0n-04KCCicYHhNt3sRbm0IPLM5r8QX5EkJ1Q,40867
 spacr/io.py,sha256=SYLhupKnOJJscNSGE4N67E32-ywhwrjRccIfZrL38Uk,157966
 spacr/logger.py,sha256=lJhTqt-_wfAunCPl93xE65Wr9Y1oIHJWaZMjunHUeIw,1538
-spacr/measure.py,sha256=Z3u4BU5RzcY82IZuboQ0OsxuXaPVwOlH65Rw6FrL5z4,55045
+spacr/measure.py,sha256=XmOCKriS-kuRy-EPhQ_z7CRNg6DukyTpwQCiuSPNd_c,63414
 spacr/mediar.py,sha256=p0F515eFbm6_rePSnChsgqrgH-H5Sr_3zWrghtOnAUg,14863
 spacr/ml.py,sha256=XCRZeX7UkbMctQICIoskeWVx8CCmmCoHNauUOAkfFq0,91692
 spacr/openai.py,sha256=5vBZ3Jl2llYcW3oaTEXgdyCB2aJujMUIO5K038z7w_A,1246
 spacr/plot.py,sha256=M2w9ytR8iMFtsVPhmQ5tzIWTQDmbtCzs1-7hALUIQtg,167339
 spacr/sequencing.py,sha256=EY12RdW5QRKpHDRQCw1QoAlxCq8FK2v6WoVa5uuDBXQ,26745
-spacr/settings.py,sha256=Fd5RbNxjBmWG6bCCDprVvy8dTjBzSK7L71k_-mJXBsk,87380
+spacr/settings.py,sha256=tEFKYqMYQoObrNuKL3XdinRebQxJcuA3Gn9wK44vqhs,87505
 spacr/sim.py,sha256=1xKhXimNU3ukzIw-3l9cF3Znc_brW8h20yv8fSTzvss,71173
 spacr/sp_stats.py,sha256=mbhwsyIqt5upsSD346qGjdCw7CFBa0tIS7zHU9e0jNI,9536
 spacr/spacr_cellpose.py,sha256=RBHMs2vwXcfkj0xqAULpALyzJYXddSRycgZSzmwI7v0,14755
 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=RA4V1EDXsU_Gs6QgplvOA4lVIRFQJVJ1JAzQsaunHiU,234010
+spacr/utils.py,sha256=cw5zM6zpFWWUZQKwtYvXc_rNfBMW2ldbnlw8s6f6bFQ,234397
 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
@@ -82,6 +82,7 @@ spacr/resources/icons/convert.png,sha256=vLyTkQeUZ9q-pirhtZeXDq3-DzfjoPMjLlgKl5W
 spacr/resources/icons/default.png,sha256=KoNhaSHukO4wDyivyYEgSbb5mGj-sAxmhKikLLtNpWs,20341
 spacr/resources/icons/dna_matrix.mp4,sha256=NegOQkn4q4kHhFgqcIX2dd58wVytBtnkmbgg0ZegL8U,23462876
 spacr/resources/icons/download.png,sha256=1nUoWRaTc4vIsK6gompdeqk0cIv2GdH-gCNHaEBX6Mc,20467
+spacr/resources/icons/flow_chart_v2.png,sha256=4U4uzJlyQ8L-exWIXIhyqtkoO-KIiubO23kA7eLZYYE,640609
 spacr/resources/icons/logo.pdf,sha256=VB4cS41V3VV_QxD7l6CwdQKQiYLErugLBxWoCoxjQU0,377925
 spacr/resources/icons/logo_spacr.png,sha256=qG3e3bdrAefhl1281rfo0R2XP0qA-c-oaBCXjxMGXkw,42587
 spacr/resources/icons/logo_spacr_1.png,sha256=g9y2ZmnV3hab8r1idDfytm8AaHbBiQdu_93Jd7YKzwA,610892
@@ -101,9 +102,9 @@ 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-0.9.1.dist-info/LICENSE,sha256=SR-2MeGc6SCM1UORJYyarSWY_A-JaOMFDj7ReSs9tRM,1083
-spacr-0.9.1.dist-info/METADATA,sha256=Lh02YCW7LiHlegDZDIIascNP_XrFD421ewydkNNjjSY,6208
-spacr-0.9.1.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
-spacr-0.9.1.dist-info/entry_points.txt,sha256=BMC0ql9aNNpv8lUZ8sgDLQMsqaVnX5L535gEhKUP5ho,296
-spacr-0.9.1.dist-info/top_level.txt,sha256=GJPU8FgwRXGzKeut6JopsSRY2R8T3i9lDgya42tLInY,6
-spacr-0.9.1.dist-info/RECORD,,
+spacr-0.9.21.dist-info/LICENSE,sha256=SR-2MeGc6SCM1UORJYyarSWY_A-JaOMFDj7ReSs9tRM,1083
+spacr-0.9.21.dist-info/METADATA,sha256=YqQuqZf-_FromxA3MZdQVVujyS2xRwOoZ_AHqCcvv_I,9636
+spacr-0.9.21.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
+spacr-0.9.21.dist-info/entry_points.txt,sha256=BMC0ql9aNNpv8lUZ8sgDLQMsqaVnX5L535gEhKUP5ho,296
+spacr-0.9.21.dist-info/top_level.txt,sha256=GJPU8FgwRXGzKeut6JopsSRY2R8T3i9lDgya42tLInY,6
+spacr-0.9.21.dist-info/RECORD,,

spacr-0.9.1.dist-info/METADATA

@@ -1,144 +0,0 @@
-Metadata-Version: 2.1
-Name: spacr
-Version: 0.9.1
-Summary: Spatial phenotype analysis of crisp screens (SpaCr)
-Home-page: https://github.com/EinarOlafsson/spacr
-Author: Einar Birnir Olafsson
-Author-email: olafsson@med.umich.com
-Classifier: Programming Language :: Python :: 3
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Description-Content-Type: text/x-rst
-License-File: LICENSE
-Requires-Dist: numpy <2.0,>=1.26.4
-Requires-Dist: pandas <3.0,>=2.2.1
-Requires-Dist: scipy <2.0,>=1.12.0
-Requires-Dist: cellpose <4.0,>=3.0.6
-Requires-Dist: scikit-image <1.0,>=0.22.0
-Requires-Dist: scikit-learn <2.0,>=1.4.1
-Requires-Dist: scikit-posthocs <0.20,>=0.10.0
-Requires-Dist: mahotas <2.0,>=1.4.13
-Requires-Dist: btrack <1.0,>=0.6.5
-Requires-Dist: trackpy <1.0,>=0.6.2
-Requires-Dist: statsmodels <1.0,>=0.14.1
-Requires-Dist: shap <1.0,>=0.45.0
-Requires-Dist: torch <3.0,>=2.0
-Requires-Dist: torchvision <1.0,>=0.1
-Requires-Dist: torch-geometric <3.0,>=2.5
-Requires-Dist: torchcam <1.0,>=0.4.0
-Requires-Dist: transformers <5.0,>=4.45.2
-Requires-Dist: segmentation-models-pytorch >=0.3.3
-Requires-Dist: monai >=1.3.0
-Requires-Dist: captum <1.0,>=0.7.0
-Requires-Dist: seaborn <1.0,>=0.13.2
-Requires-Dist: matplotlib <4.0,>=3.8.3
-Requires-Dist: matplotlib-venn <2.0,>=1.1
-Requires-Dist: adjustText <2.0,>=1.2.0
-Requires-Dist: bottleneck <2.0,>=1.3.6
-Requires-Dist: numexpr <3.0,>=2.8.4
-Requires-Dist: opencv-python-headless <5.0,>=4.9.0.80
-Requires-Dist: pillow <11.0,>=10.2.0
-Requires-Dist: tifffile >=2023.4.12
-Requires-Dist: nd2reader <4.0,>=3.3.0
-Requires-Dist: czifile
-Requires-Dist: pylibCZIrw <6.0,>=5.0.0
-Requires-Dist: aicspylibczi
-Requires-Dist: readlif
-Requires-Dist: imageio <3.0,>=2.34.0
-Requires-Dist: pingouin <1.0,>=0.5.5
-Requires-Dist: umap-learn <1.0,>=0.5.6
-Requires-Dist: ttkthemes <4.0,>=3.2.2
-Requires-Dist: xgboost <3.0,>=2.0.3
-Requires-Dist: PyWavelets <2.0,>=1.6.0
-Requires-Dist: ttf-opensans >=2020.10.30
-Requires-Dist: customtkinter <6.0,>=5.2.2
-Requires-Dist: biopython <2.0,>=1.80
-Requires-Dist: lxml <6.0,>=5.1.0
-Requires-Dist: psutil <6.0,>=5.9.8
-Requires-Dist: gputil <2.0,>=1.4.0
-Requires-Dist: gpustat <2.0,>=1.1.1
-Requires-Dist: pyautogui <1.0,>=0.9.54
-Requires-Dist: tables <4.0,>=3.8.0
-Requires-Dist: rapidfuzz <4.0,>=3.9
-Requires-Dist: keyring <16.0,>=15.1
-Requires-Dist: screeninfo <1.0,>=0.8.1
-Requires-Dist: fastremap >=1.14.1
-Requires-Dist: pytz >=2023.3.post1
-Requires-Dist: tqdm >=4.65.0
-Requires-Dist: wandb >=0.16.2
-Requires-Dist: openai <2.0,>=1.50.2
-Requires-Dist: gdown
-Requires-Dist: IPython <9.0,>=8.18.1
-Requires-Dist: ipykernel
-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'
-Provides-Extra: full
-Requires-Dist: opencv-python ; extra == 'full'
-Provides-Extra: headless
-Requires-Dist: opencv-python-headless ; extra == 'headless'
-
-.. |Documentation Status| image:: https://readthedocs.org/projects/spacr/badge/?version=latest
-   :target: https://einarolafsson.github.io/spacr
-.. |PyPI version| image:: https://badge.fury.io/py/spacr.svg
-   :target: https://badge.fury.io/py/spacr
-.. |Python version| image:: https://img.shields.io/pypi/pyversions/spacr
-   :target: https://pypistats.org/packages/spacr
-.. |Licence: GPL v3| image:: https://img.shields.io/github/license/EinarOlafsson/spacr
-   :target: https://github.com/EinarOlafsson/spacr/blob/master/LICENSE
-.. |repo size| image:: https://img.shields.io/github/repo-size/EinarOlafsson/spacr
-   :target: https://github.com/EinarOlafsson/spacr/
-
-|Documentation Status| |PyPI version| |Python version| |Licence: GPL v3| |repo size|
-
-SpaCr
-=====
-
-Spatial phenotype analysis of CRISPR-Cas9 screens (SpaCr). The spatial organization of organelles and proteins within cells constitutes a key level of functional regulation. In the context of infectious disease, the spatial relationships between host cell structures and intracellular pathogens are critical to understanding host clearance mechanisms and how pathogens evade them. SpaCr is a Python-based software package for generating single-cell image data for deep-learning sub-cellular/cellular phenotypic classification from pooled genetic CRISPR-Cas9 screens. SpaCr provides a flexible toolset to extract single-cell images and measurements from high-content cell painting experiments, train deep-learning models to classify cellular/subcellular phenotypes, simulate, and analyze pooled CRISPR-Cas9 imaging screens.
-
-Features
---------
-
--  **Generate Masks:** Generate cellpose masks of cell, nuclei, and pathogen objects.
-
--  **Object Measurements:** Measurements for each object including scikit-image-regionprops, intensity percentiles, shannon-entropy, pearsons and manders correlations, homogeneity, and radial distribution. Measurements are saved to a SQL database in object-level tables.
-
--  **Crop Images:** Save objects (cells, nuclei, pathogen, cytoplasm) as images. Object image paths are saved in a SQL database.
-
--  **Train CNNs or Transformers:** Train Torch models to classify single object images.
-
--  **Manual Annotation:** Supports manual annotation of single-cell images and segmentation to refine training datasets for training CNNs/Transformers or cellpose, respectively.
-
--  **Finetune Cellpose Models:** Adjust pre-existing Cellpose models to your specific dataset for improved performance.
-
--  **Timelapse Data Support:** Track objects in timelapse image data.
-
--  **Simulations:** Simulate spatial phenotype screens.
-
--  **Sequencing:** Map FASTQ reads to barcode and gRNA barcode metadata.
-
--  **Misc:** Analyze Ca oscillation, recruitment, infection rate, plaque size/count.
-
-Installation
-------------
-
-If using Windows, switch to Linux—it's free, open-source, and better.
-
-Before installing SpaCr on OSX ensure OpenMP is installed::
-
-   brew install libomp
-   brew install hdf5
-
-SpaCr GUI requires Tkinter. On Linux, ensure Tkinter is installed. (Tkinter is included with the standard Python installation on macOS and Windows)::
-
-   sudo apt-get install python3-tk
-
-Install SpaCr with pip::
-
-   pip install spacr
-
-Run SpaCr GUI::
-
-   spacr