celldetective 1.3.2__tar.gz → 1.3.4__tar.gz

{celldetective-1.3.2 → celldetective-1.3.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: celldetective
-Version: 1.3.2
+Version: 1.3.4
 Summary: description
 Home-page: http://github.com/remyeltorro/celldetective
 Author: Rémy Torro
@@ -41,6 +41,7 @@ Requires-Dist: pytest
 Requires-Dist: pytest-qt
 Requires-Dist: h5py
 Requires-Dist: cliffs_delta
+Requires-Dist: requests
 
 # Celldetective
 
@@ -172,20 +173,20 @@ For more information about how to get started, please check the [documentation](
 # How to cite?
 
 If you use this software in your research, please cite the
-[Celldetective](https://www.biorxiv.org/content/10.1101/2024.03.15.585250v1)
+[Celldetective](https://www.biorxiv.org/content/10.1101/2024.03.15.585250v3)
 paper (currently preprint):
 
 ``` raw
 @article {Torro2024.03.15.585250,
-    author = {R{\'e}my Torro and Beatriz D{\`\i}az-Bello and Dalia El Arawi and Lorna Ammer and Patrick Chames and Kheya Sengupta and Laurent Limozin},
+    author = {Torro, R{\'e}my and D{\'\i}az-Bello, Beatriz and Arawi, Dalia El and Dervanova, Ksenija and Ammer, Lorna and Dupuy, Florian and Chames, Patrick and Sengupta, Kheya and Limozin, Laurent},
     title = {Celldetective: an AI-enhanced image analysis tool for unraveling dynamic cell interactions},
     elocation-id = {2024.03.15.585250},
     year = {2024},
     doi = {10.1101/2024.03.15.585250},
     publisher = {Cold Spring Harbor Laboratory},
-    abstract = {A current key challenge in bioimaging is the analysis of multimodal and multidimensional data reporting dynamic interactions between diverse cell populations. We developed Celldetective, a software that integrates AI-based segmentation and tracking algorithms and automated signal analysis into a user-friendly graphical interface. It offers complete interactive visualization, annotation, and training capabilities. We demonstrate it by analyzing original experimental data of spreading immune effector cells as well as antibody-dependent cell cytotoxicity events using multimodal fluorescence microscopy.Competing Interest StatementThe authors have declared no competing interest.},
-    URL = {https://www.biorxiv.org/content/early/2024/03/17/2024.03.15.585250},
-    eprint = {https://www.biorxiv.org/content/early/2024/03/17/2024.03.15.585250.full.pdf},
+    abstract = {A current challenge in bioimaging for immunology and immunotherapy research lies in analyzing multimodal and multidimensional data that capture dynamic interactions between diverse cell populations. Here, we introduce Celldetective, an open-source Python-based software designed for high-performance, end-to-end analysis of image-based in vitro immune and immunotherapy assays. Purpose-built for multicondition, 2D multichannel time-lapse microscopy of mixed cell populations, Celldetective is optimized for the needs of immunology assays. The software seamlessly integrates AI-based segmentation, Bayesian tracking, and automated single-cell event detection, all within an intuitive graphical interface that supports interactive visualization, annotation, and training capabilities. We demonstrate its utility with original data on immune effector cell interactions with an activating surface, mediated by bispecific antibodies, and further showcase its potential for analyzing extensive sets of pairwise interactions in antibody-dependent cell cytotoxicity events.Competing Interest StatementThe authors have declared no competing interest.},
+    URL = {https://www.biorxiv.org/content/early/2024/11/13/2024.03.15.585250},
+    eprint = {https://www.biorxiv.org/content/early/2024/11/13/2024.03.15.585250.full.pdf},
     journal = {bioRxiv}
 }
 ```

{celldetective-1.3.2 → celldetective-1.3.4}/README.md

@@ -128,20 +128,20 @@ For more information about how to get started, please check the [documentation](
 # How to cite?
 
 If you use this software in your research, please cite the
-[Celldetective](https://www.biorxiv.org/content/10.1101/2024.03.15.585250v1)
+[Celldetective](https://www.biorxiv.org/content/10.1101/2024.03.15.585250v3)
 paper (currently preprint):
 
 ``` raw
 @article {Torro2024.03.15.585250,
-    author = {R{\'e}my Torro and Beatriz D{\`\i}az-Bello and Dalia El Arawi and Lorna Ammer and Patrick Chames and Kheya Sengupta and Laurent Limozin},
+    author = {Torro, R{\'e}my and D{\'\i}az-Bello, Beatriz and Arawi, Dalia El and Dervanova, Ksenija and Ammer, Lorna and Dupuy, Florian and Chames, Patrick and Sengupta, Kheya and Limozin, Laurent},
     title = {Celldetective: an AI-enhanced image analysis tool for unraveling dynamic cell interactions},
     elocation-id = {2024.03.15.585250},
     year = {2024},
     doi = {10.1101/2024.03.15.585250},
     publisher = {Cold Spring Harbor Laboratory},
-    abstract = {A current key challenge in bioimaging is the analysis of multimodal and multidimensional data reporting dynamic interactions between diverse cell populations. We developed Celldetective, a software that integrates AI-based segmentation and tracking algorithms and automated signal analysis into a user-friendly graphical interface. It offers complete interactive visualization, annotation, and training capabilities. We demonstrate it by analyzing original experimental data of spreading immune effector cells as well as antibody-dependent cell cytotoxicity events using multimodal fluorescence microscopy.Competing Interest StatementThe authors have declared no competing interest.},
-    URL = {https://www.biorxiv.org/content/early/2024/03/17/2024.03.15.585250},
-    eprint = {https://www.biorxiv.org/content/early/2024/03/17/2024.03.15.585250.full.pdf},
+    abstract = {A current challenge in bioimaging for immunology and immunotherapy research lies in analyzing multimodal and multidimensional data that capture dynamic interactions between diverse cell populations. Here, we introduce Celldetective, an open-source Python-based software designed for high-performance, end-to-end analysis of image-based in vitro immune and immunotherapy assays. Purpose-built for multicondition, 2D multichannel time-lapse microscopy of mixed cell populations, Celldetective is optimized for the needs of immunology assays. The software seamlessly integrates AI-based segmentation, Bayesian tracking, and automated single-cell event detection, all within an intuitive graphical interface that supports interactive visualization, annotation, and training capabilities. We demonstrate its utility with original data on immune effector cell interactions with an activating surface, mediated by bispecific antibodies, and further showcase its potential for analyzing extensive sets of pairwise interactions in antibody-dependent cell cytotoxicity events.Competing Interest StatementThe authors have declared no competing interest.},
+    URL = {https://www.biorxiv.org/content/early/2024/11/13/2024.03.15.585250},
+    eprint = {https://www.biorxiv.org/content/early/2024/11/13/2024.03.15.585250.full.pdf},
     journal = {bioRxiv}
 }
 ```

celldetective-1.3.4/celldetective/__main__.py

@@ -0,0 +1,66 @@
+#!/usr/bin/env python3
+import sys
+from PyQt5.QtWidgets import QApplication, QSplashScreen
+from PyQt5.QtGui import QPixmap
+from os import sep
+from celldetective.utils import get_software_location
+from time import time, sleep
+
+#os.environ['QT_DEBUG_PLUGINS'] = '1'
+
+if __name__ == "__main__":
+
+	splash=True
+	print('Loading the libraries...')
+
+	App = QApplication(sys.argv)
+	App.setStyle("Fusion")
+
+	software_location = get_software_location()
+
+	if splash:
+		start = time()
+		splash_pix = QPixmap(sep.join([software_location,'celldetective','icons','splash.png']))
+		splash = QSplashScreen(splash_pix)
+		splash.setMask(splash_pix.mask())
+		splash.show()
+		#App.processEvents(QEventLoop.AllEvents, 300)
+		while time() - start < 1:
+			sleep(0.001)
+			App.processEvents()
+
+	try:
+		
+		import requests
+		import re
+		from celldetective import __version__
+
+		package = 'celldetective'
+		response = requests.get(f'https://pypi.org/pypi/{package}/json')
+		latest_version = response.json()['info']['version']
+
+		latest_version_num = re.sub('[^0-9]','', latest_version)
+		current_version_num = re.sub('[^0-9]','',__version__)
+
+		if len(latest_version_num)!=len(current_version_num):
+			max_length = max([len(latest_version_num),len(current_version_num)])
+			latest_version_num = int(latest_version_num.zfill(max_length - len(latest_version_num)))
+			current_version_num = int(current_version_num.zfill(max_length - len(current_version_num)))
+
+		if latest_version_num > current_version_num:
+			print('Update is available...\nPlease update using `pip install --upgrade celldetective`...')
+	
+	except Exception as e:
+
+		print(f"{e=}")
+
+	from celldetective.gui.InitWindow import AppInitWindow
+
+	print('Libraries successfully loaded...')
+
+	window = AppInitWindow(App, software_location=software_location)
+
+	if splash:
+		splash.finish(window)
+
+	sys.exit(App.exec())

celldetective-1.3.4/celldetective/_version.py

@@ -0,0 +1 @@
+__version__ = "1.3.4"

{celldetective-1.3.2 → celldetective-1.3.4}/celldetective/extra_properties.py

@@ -29,6 +29,27 @@ from celldetective.utils import interpolate_nan, contour_of_instance_segmentatio
 
 # Percentiles
 
+def custom_area(regionmask):
+	return np.sum(regionmask)
+
+def intensity_area_under_one(regionmask, intensity_image):
+	
+	subregion = regionmask[intensity_image<1]
+	if len(subregion)>0:
+		return np.sum(subregion)
+	else:
+		return 0.0
+
+def intensity_fraction_of_area_under_one(regionmask, intensity_image):
+
+	subregion = regionmask[intensity_image<1]
+	area = np.sum(regionmask)
+
+	if len(subregion) > 0:
+		return float(np.sum(subregion)) / float(area)
+	else:
+		return 0.0
+
 def intensity_percentile_ninety_nine(regionmask, intensity_image):
 	return np.nanpercentile(intensity_image[regionmask],99)
 

{celldetective-1.3.2 → celldetective-1.3.4}/celldetective/filters.py

@@ -4,15 +4,19 @@ import scipy.ndimage as snd
 import numpy as np
 
 def gauss_filter(img, sigma, interpolate=True, *kwargs):
+
 	if interpolate:
 		img = interpolate_nan(img.astype(float))
+
 	return snd.gaussian_filter(img.astype(float), sigma, *kwargs)
 
 def median_filter(img, size, interpolate=True, *kwargs):
+
 	if interpolate:
 		img = interpolate_nan(img.astype(float))
 
 	size = int(size)
+	
 	return snd.median_filter(img, size, *kwargs)
 
 def maximum_filter(img, size, interpolate=True, *kwargs):
@@ -65,13 +69,17 @@ def std_filter(img, size, interpolate=True):
 
 	if interpolate:
 		img = interpolate_nan(img.astype(float))
+	
 	size = int(size)
 	img = img.astype(float)
+	
 	win_mean = snd.uniform_filter(img, (size,size), mode='wrap')
 	win_sqr_mean = snd.uniform_filter(img**2, (size, size), mode='wrap')
-	win_sqr_mean[win_sqr_mean!=win_sqr_mean] = 0.
 	win_sqr_mean[win_sqr_mean<=0.] = 0. # add this to prevent sqrt from breaking
-	img = np.sqrt(win_sqr_mean - win_mean**2)
+	
+	sub = np.subtract(win_sqr_mean,win_mean**2)
+	sub[sub<=0.] = 0.
+	img = np.sqrt(sub)
 
 	return img
 
@@ -96,16 +104,21 @@ def local_filter(img, *kwargs):
 	return binary.astype(float)
 
 def niblack_filter(img, *kwargs):
+
 	thresh = threshold_niblack(img, *kwargs)
 	binary = img >= thresh
 	return binary.astype(float)
 
 def sauvola_filter(img, *kwargs):
+
 	thresh = threshold_sauvola(img, *kwargs)
 	binary = img >= thresh
 	return binary.astype(float)
 
 def log_filter(img, sigma, *kwargs):
+
+	if interpolate:
+		img = interpolate_nan(img.astype(float))
 	return snd.gaussian_laplace(img.astype(float), sigma, *kwargs)
 
 def tophat_filter(img, size, connectivity=4, interpolate=True, *kwargs):

{celldetective-1.3.2 → celldetective-1.3.4}/celldetective/gui/InitWindow.py

@@ -1,48 +1,49 @@
-from PyQt5.QtWidgets import QApplication, QMainWindow
-from celldetective.utils import get_software_location, download_zenodo_file
 import os
+
+from PyQt5.QtWidgets import QApplication, QMainWindow
 from PyQt5.QtWidgets import QFileDialog, QWidget, QVBoxLayout, QCheckBox, QHBoxLayout, QLabel, QLineEdit, QPushButton, QMessageBox, QMenu, QAction
 from PyQt5.QtCore import Qt, QUrl
 from PyQt5.QtGui import QIcon, QDesktopServices, QIntValidator
+
 from glob import glob
 from superqt.fonticon import icon
 from fonticon_mdi6 import MDI6
-import gc
-from celldetective.gui import Styles, ControlPanel, ConfigNewExperiment
-from celldetective.gui.gui_utils import center_window
-import subprocess
-import os
+
 from celldetective.gui.about import AboutWidget
 from celldetective.io import correct_annotation
-import psutil
-import subprocess
+from celldetective.utils import download_zenodo_file
+from celldetective.gui.gui_utils import center_window
+from celldetective.gui import Styles, ControlPanel, ConfigNewExperiment
+
+import gc
+from subprocess import check_output, Popen
+from psutil import cpu_count
 import json
 
-class AppInitWindow(QMainWindow):
+class AppInitWindow(QMainWindow, Styles):
 
 	"""
 	Initial window to set the experiment folder or create a new one.
 	"""
 
-	def __init__(self, parent_window=None):
+	def __init__(self, parent_window=None, software_location=None):
+
 		super().__init__()
 
 		self.parent_window = parent_window
-		self.Styles = Styles()
-		self.init_styles()
 		self.setWindowTitle("celldetective")
 
-		self.n_threads = min([1,psutil.cpu_count()])
+		self.n_threads = min([1,cpu_count()])
 
 		try:
-			subprocess.check_output('nvidia-smi')
+			check_output('nvidia-smi')
 			print('NVIDIA GPU detected (activate or disable in Memory & Threads)...')
 			self.use_gpu = True
 		except Exception: # this command not being found can raise quite a few different errors depending on the configuration
 			print('No NVIDIA GPU detected...')
 			self.use_gpu = False
-			
-		self.soft_path = get_software_location()
+		
+		self.soft_path = software_location
 		self.onlyInt = QIntValidator()
 		self.setWindowIcon(QIcon(os.sep.join([self.soft_path,'celldetective','icons','logo.png'])))
 		center_window(self)
@@ -65,6 +66,7 @@ class AppInitWindow(QMainWindow):
 		self.show()
 	
 	def closeEvent(self, event):
+
 		QApplication.closeAllWindows()
 		event.accept()
 		gc.collect()
@@ -188,6 +190,9 @@ class AppInitWindow(QMainWindow):
 	def download_spreading_assay_demo(self):
 		
 		self.target_dir = str(QFileDialog.getExistingDirectory(self, 'Select Folder for Download'))
+		if self.target_dir=='':
+			return None
+		
 		if not os.path.exists(os.sep.join([self.target_dir,'demo_ricm'])):
 			download_zenodo_file('demo_ricm', self.target_dir)
 		self.experiment_path_selection.setText(os.sep.join([self.target_dir, 'demo_ricm']))
@@ -196,6 +201,9 @@ class AppInitWindow(QMainWindow):
 	def download_cytotoxicity_assay_demo(self):
 		
 		self.target_dir = str(QFileDialog.getExistingDirectory(self, 'Select Folder for Download'))
+		if self.target_dir=='':
+			return None
+
 		if not os.path.exists(os.sep.join([self.target_dir,'demo_adcc'])):
 			download_zenodo_file('demo_adcc', self.target_dir)
 		self.experiment_path_selection.setText(os.sep.join([self.target_dir, 'demo_adcc']))
@@ -302,9 +310,10 @@ class AppInitWindow(QMainWindow):
 		QDesktopServices.openUrl(doc_url)
 
 	def open_models_folder(self):
+		
 		path = os.sep.join([self.soft_path,'celldetective','models',os.sep])
 		try:
-			subprocess.Popen(f'explorer {os.path.realpath(path)}')
+			Popen(f'explorer {os.path.realpath(path)}')
 		except:
 
 			try:
@@ -312,9 +321,6 @@ class AppInitWindow(QMainWindow):
 			except:
 				return None
 
-
-		#os.system(f'start {os.path.realpath(path)}')
-
 	def create_buttons_hbox(self):
 
 		self.buttons_layout = QHBoxLayout()
@@ -344,18 +350,6 @@ class AppInitWindow(QMainWindow):
 		else:
 			self.validate_button.setEnabled(False)
 
-	def init_styles(self):
-
-		"""
-		Initialize styles.
-		"""
-		
-		self.qtab_style = self.Styles.qtab_style
-		self.button_style_sheet = self.Styles.button_style_sheet
-		self.button_style_sheet_2 = self.Styles.button_style_sheet_2
-		self.button_style_sheet_2_not_done = self.Styles.button_style_sheet_2_not_done
-		self.button_style_sheet_3 = self.Styles.button_style_sheet_3
-		self.button_select_all = self.Styles.button_select_all
 
 	def set_experiment_path(self, path):
 		self.experiment_path_selection.setText(path)
@@ -414,7 +408,7 @@ class AppInitWindow(QMainWindow):
 			self.experiment_path_selection.setText(self.foldername)
 		else:
 			return None
-		if not os.path.exists(self.foldername+"/config.ini"):
+		if not os.path.exists(os.sep.join([self.foldername,"config.ini"])):
 			msgBox = QMessageBox()
 			msgBox.setIcon(QMessageBox.Warning)
 			msgBox.setText("No configuration can be found in the selected folder...")

celldetective-1.3.4/celldetective/gui/analyze_block.py

@@ -0,0 +1,81 @@
+from PyQt5.QtWidgets import QFrame, QLabel, QPushButton, QVBoxLayout, \
+    QSpacerItem, QSizePolicy
+from PyQt5.QtCore import Qt, QSize
+from PyQt5.QtGui import QIcon
+from celldetective.gui.plot_measurements import ConfigMeasurementsPlot
+from celldetective.gui import ConfigSurvival, ConfigSignalPlot
+import os
+from celldetective.gui import Styles
+
+class AnalysisPanel(QFrame, Styles):
+	def __init__(self, parent_window, title=None):
+
+		super().__init__()		
+		self.parent_window = parent_window
+		self.title = title
+		if self.title is None:
+			self.title=''
+		self.exp_channels = self.parent_window.exp_channels
+		self.exp_dir = self.parent_window.exp_dir
+		self.soft_path = self.parent_window.parent_window.soft_path
+
+		self.setFrameStyle(QFrame.StyledPanel | QFrame.Raised)
+		self.grid = QVBoxLayout(self)
+		self.grid.setSpacing(20)
+		self.generate_header()
+	
+	def generate_header(self):
+
+		"""
+		Read the mode and prepare a collapsable block to process a specific cell population.
+
+		"""
+
+		panel_title = QLabel("Survival")
+		panel_title.setStyleSheet("""
+			font-weight: bold;
+			padding: 0px;
+			""")
+
+		self.grid.addWidget(panel_title, alignment=Qt.AlignCenter)
+
+		self.survival_btn = QPushButton("plot survival")
+		self.survival_btn.setIcon(QIcon(QIcon(os.sep.join([self.soft_path,'celldetective','icons','survival2.png']))))
+		self.survival_btn.setStyleSheet(self.button_style_sheet_2)
+		self.survival_btn.setIconSize(QSize(35, 35))
+		self.survival_btn.clicked.connect(self.configure_survival)
+		self.grid.addWidget(self.survival_btn)
+
+		signal_lbl = QLabel("Single-cell signals")
+		signal_lbl.setStyleSheet("""
+			font-weight: bold;
+			padding: 0px;
+			""")
+
+		self.grid.addWidget(signal_lbl, alignment=Qt.AlignCenter)
+
+		self.plot_signal_btn = QPushButton("plot signals")
+		self.plot_signal_btn.setIcon(QIcon(QIcon(os.sep.join([self.soft_path,'celldetective','icons','signals_icon.png']))))
+		self.plot_signal_btn.setStyleSheet(self.button_style_sheet_2)
+		self.plot_signal_btn.setIconSize(QSize(35, 35))
+		self.plot_signal_btn.clicked.connect(self.configure_plot_signals)
+		self.grid.addWidget(self.plot_signal_btn)
+
+		verticalSpacer = QSpacerItem(20, 40, QSizePolicy.Minimum, QSizePolicy.Expanding)
+		self.grid.addItem(verticalSpacer)
+
+	def configure_survival(self):
+		print('survival analysis starting!!!')
+		self.configSurvival = ConfigSurvival(self)
+		self.configSurvival.show()
+
+	def configure_plot_signals(self):
+		print('Configure a signal collapse representation...')
+		self.ConfigSignalPlot = ConfigSignalPlot(self)
+		self.ConfigSignalPlot.show()
+
+	def configure_plot_measurements(self):
+
+		print('plot measurements analysis starting!!!')
+		self.ConfigMeasurementsPlot_wg = ConfigMeasurementsPlot(self)
+		self.ConfigMeasurementsPlot_wg.show()

{celldetective-1.3.2 → celldetective-1.3.4}/celldetective/gui/classifier_widget.py

@@ -10,7 +10,7 @@ import numpy as np
 import matplotlib.pyplot as plt
 import json
 
-from celldetective.gui.gui_utils import FigureCanvas, center_window, color_from_status, help_generic, color_from_class
+from celldetective.gui.gui_utils import FigureCanvas, center_window, color_from_status, help_generic
 from celldetective.gui import Styles
 from celldetective.utils import get_software_location
 from celldetective.measure import classify_cells_from_query, interpret_track_classification