celldetective 1.2.2.post2__py3-none-any.whl → 1.3.0.post1__py3-none-any.whl

celldetective/measure.py

@@ -980,7 +980,6 @@ def blob_detection(image, label, threshold, diameter):
 
 ### Classification ####
 
-
 def estimate_time(df, class_attr, model='step_function', class_of_interest=[2], r2_threshold=0.5):
 
 	"""
@@ -1027,6 +1026,7 @@ def estimate_time(df, class_attr, model='step_function', class_of_interest=[2],
 	df = df.sort_values(by=sort_cols,ignore_index=True)
 	df = df.reset_index(drop=True)
 
+
 	for tid,group in df.loc[df[class_attr].isin(class_of_interest)].groupby(sort_cols):
 		
 		indices = group.index
@@ -1034,21 +1034,19 @@ def estimate_time(df, class_attr, model='step_function', class_of_interest=[2],
 
 		group_clean = group.dropna(subset=status_col)
 		status_signal = group_clean[status_col].values
+		if np.all(np.array(status_signal)==1):
+			continue
+
 		timeline = group_clean['FRAME'].values
-		
 		frames = group_clean['FRAME'].to_numpy()
 		status_values = group_clean[status_col].to_numpy()
 		t_first = group['t_firstdetection'].to_numpy()[0]
 
 		try:
-
-			popt, pcov = curve_fit(eval(model), timeline.astype(int), status_signal, p0=[df['FRAME'].max()//2, 0.8],maxfev=30000)
+			popt, pcov = curve_fit(eval(model), timeline.astype(int), status_signal, p0=[max(timeline)//2, 0.8],maxfev=100000)
 			values = [eval(model)(t, *popt) for t in timeline]
 			r2 = r2_score(status_signal,values)
-
-		except Exception as e:
-
-			print(e)
+		except Exception:
 			df.loc[indices, class_attr] = 2.0
 			df.loc[indices, class_attr.replace('class','t')] = -1
 			continue
@@ -1064,7 +1062,7 @@ def estimate_time(df, class_attr, model='step_function', class_of_interest=[2],
 	return df
 
 
-def interpret_track_classification(df, class_attr, irreversible_event=False, unique_state=False,r2_threshold=0.5):
+def interpret_track_classification(df, class_attr, irreversible_event=False, unique_state=False,r2_threshold=0.5, percentile_recovery=50):
 
 	"""
 	Interpret and classify tracked cells based on their status signals.
@@ -1123,15 +1121,15 @@ def interpret_track_classification(df, class_attr, irreversible_event=False, uni
 
 	if irreversible_event:
 
-		df = classify_irreversible_events(df, class_attr, r2_threshold=0.5)
-
+		df = classify_irreversible_events(df, class_attr, r2_threshold=r2_threshold, percentile_recovery=percentile_recovery)
+	
 	elif unique_state:
 		
 		df = classify_unique_states(df, class_attr, percentile=50)
 
 	return df
 
-def classify_irreversible_events(df, class_attr, r2_threshold=0.5, percentile_recovery=95):
+def classify_irreversible_events(df, class_attr, r2_threshold=0.5, percentile_recovery=50):
 
 	"""
 	Classify irreversible events in a tracked dataset based on the status of cells and transitions.
@@ -1179,6 +1177,12 @@ def classify_irreversible_events(df, class_attr, r2_threshold=0.5, percentile_re
 	stat_col = class_attr.replace('class','status')
 
 	for tid,track in df.groupby(sort_cols):
+		
+		# Set status to 0.0 before first detection
+		t_firstdetection = track['t_firstdetection'].values[0]
+		indices_pre_detection = track.loc[track['FRAME']<=t_firstdetection,class_attr].index
+		track.loc[indices_pre_detection,stat_col] = 0.0
+		df.loc[indices_pre_detection,stat_col] = 0.0
 
 		track_valid = track.dropna(subset=stat_col)
 		indices_valid = track_valid[class_attr].index
@@ -1193,16 +1197,20 @@ def classify_irreversible_events(df, class_attr, r2_threshold=0.5, percentile_re
 		elif np.all([s==1 for s in status_values]):
 			# all positive, event already observed
 			df.loc[indices, class_attr] = 2
-			df.loc[indices, class_attr.replace('class','status')] = 2
+			#df.loc[indices, class_attr.replace('class','status')] = 2
 		else:
 			# ambiguity, possible transition
 			df.loc[indices, class_attr] = 2
 	
+	print("Classes after initial pass: ",df.loc[df['FRAME']==0,class_attr].value_counts())
+
 	df.loc[df[class_attr]!=2, class_attr.replace('class', 't')] = -1
 	df = estimate_time(df, class_attr, model='step_function', class_of_interest=[2],r2_threshold=r2_threshold)
-	
+	print("Classes after fit: ", df.loc[df['FRAME']==0,class_attr].value_counts())
+
 	# Revisit class 2 cells to classify as neg/pos with percentile tolerance
 	df.loc[df[class_attr]==2,:] = classify_unique_states(df.loc[df[class_attr]==2,:].copy(), class_attr, percentile_recovery)
+	print("Classes after unique state recovery: ",df.loc[df['FRAME']==0,class_attr].value_counts())
 	
 	return df
 
@@ -1251,14 +1259,17 @@ def classify_unique_states(df, class_attr, percentile=50):
 
 	stat_col = class_attr.replace('class','status')
 
+
 	for tid,track in df.groupby(sort_cols):
 
+
 		track_valid = track.dropna(subset=stat_col)
 		indices_valid = track_valid[class_attr].index
 
 		indices = track[class_attr].index
 		status_values = track_valid[stat_col].to_numpy()
 
+
 		frames = track_valid['FRAME'].to_numpy()
 		t_first = track['t_firstdetection'].to_numpy()[0]
 		perc_status = np.nanpercentile(status_values[frames>=t_first], percentile)
@@ -1324,10 +1335,14 @@ def classify_cells_from_query(df, status_attr, query):
 
 
 	# Initialize all states to 0
-	df[status_attr] = 0
+	if not status_attr.startswith('status_'):
+		status_attr = 'status_'+status_attr
+
+	df = df.copy()
+	df.loc[:,status_attr] = 0
+
 	cols = extract_cols_from_query(query)
 	cols_in_df = np.all([c in list(df.columns) for c in cols], axis=0)
-
 	if query=='':
 		print('The provided query is empty...')
 	else:
@@ -1340,8 +1355,21 @@ def classify_cells_from_query(df, status_attr, query):
 				df.loc[selection, status_attr] = 1
 			else:
 				df.loc[:, status_attr] = np.nan
-
 		except Exception as e:
-			print("The query could not be understood. No filtering was applied. {e}...")
+			print(f"The query could not be understood. No filtering was applied. {e}...")
 			return None
+	return df.copy()
+
+def classify_tracks_from_query(df, event_name, query, irreversible_event=True, unique_state=False, r2_threshold=0.5, percentile_recovery=50):
+	
+	status_attr = "status_"+event_name
+	df = classify_cells_from_query(df, status_attr, query)
+	class_attr = "class_"+event_name
+
+	name_map = {status_attr: class_attr}
+	df = df.drop(list(set(name_map.values()) & set(df.columns)), axis=1).rename(columns=name_map)
+	df.reset_index(inplace=True, drop=True)
+
+	df = interpret_track_classification(df, class_attr, irreversible_event=irreversible_event, unique_state=unique_state, r2_threshold=r2_threshold, percentile_recovery=percentile_recovery)
+
 	return df

celldetective/segmentation.py

@@ -28,7 +28,7 @@ import subprocess
 abs_path = os.sep.join([os.path.split(os.path.dirname(os.path.realpath(__file__)))[0],'celldetective'])
 
 def segment(stack, model_name, channels=None, spatial_calibration=None, view_on_napari=False,
-			use_gpu=True, channel_axis=-1):
+			use_gpu=True, channel_axis=-1, cellprob_threshold=None, flow_threshold=None):
 	
 	"""
 	
@@ -50,10 +50,6 @@ def segment(stack, model_name, channels=None, spatial_calibration=None, view_on_
 		Whether to visualize the segmentation results using Napari. Default is False.
 	use_gpu : bool, optional
 		Whether to use GPU acceleration if available. Default is True.
-	time_flat_normalization : bool, optional
-		Whether to perform time-flat normalization on the stack before segmentation. Default is False.
-	time_flat_percentiles : tuple, optional
-		The percentiles used for time-flat normalization. Default is (0.0, 99.99).
 
 	Returns
 	-------
@@ -95,6 +91,9 @@ def segment(stack, model_name, channels=None, spatial_calibration=None, view_on_
 		assert len(channels)==stack.shape[-1],f'The channel names provided do not match with the expected number of channels in the stack: {stack.shape[-1]}.'
 
 	required_channels = input_config['channels']
+	channel_intersection = [ch for ch in channels if ch in required_channels]
+	assert len(channel_intersection)>0,'None of the channels required by the model can be found in the images to segment... Abort.'
+
 	channel_indices = _extract_channel_indices(channels, required_channels)
 
 	required_spatial_calibration = input_config['spatial_calibration']
@@ -108,10 +107,13 @@ def segment(stack, model_name, channels=None, spatial_calibration=None, view_on_
 		diameter = input_config['diameter']
 		# if diameter!=30:
 		# 	required_spatial_calibration = None
-		cellprob_threshold = input_config['cellprob_threshold']
-		flow_threshold = input_config['flow_threshold']
+		if cellprob_threshold is None:
+			cellprob_threshold = input_config['cellprob_threshold']
+		if flow_threshold is None:
+			flow_threshold = input_config['flow_threshold']
 
 	scale = _estimate_scale_factor(spatial_calibration, required_spatial_calibration)
+	print(f"{spatial_calibration=} {required_spatial_calibration=} Scale = {scale}...")
 
 	if model_type=='stardist':
 
@@ -145,13 +147,19 @@ def segment(stack, model_name, channels=None, spatial_calibration=None, view_on_
 		channel_indices = np.array(channel_indices)
 		none_channel_indices = np.where(channel_indices==None)[0]
 		channel_indices[channel_indices==None] = 0
-		print(channel_indices)
 
-		frame = stack[t,:,:,channel_indices.astype(int)].astype(float)
+		frame = stack[t]
+		#frame = stack[t,:,:,channel_indices.astype(int)].astype(float)
 		if frame.ndim==2:
 			frame = frame[:,:,np.newaxis]
 		if frame.ndim==3 and np.array(frame.shape).argmin()==0:
 			frame = np.moveaxis(frame,0,-1)
+
+		frame_to_segment = np.zeros((frame.shape[0], frame.shape[1], len(required_channels))).astype(float)
+		for ch in channel_intersection:
+			idx = required_channels.index(ch)
+			frame_to_segment[:,:,idx] = frame[:,:,channels.index(ch)]
+		frame = frame_to_segment
 		template = frame.copy()
 
 		values = []

celldetective/utils.py

@@ -26,6 +26,8 @@ import re
 from scipy.ndimage.morphology import distance_transform_edt
 from scipy import ndimage
 from skimage.morphology import disk
+from scipy.stats import ks_2samp
+from cliffs_delta import cliffs_delta
 
 def contour_of_instance_segmentation(label, distance):
 
@@ -1183,27 +1185,10 @@ def _extract_channel_indices(channels, required_channels):
 				ch_idx = channels.index(c)
 				channel_indices.append(ch_idx)
 			except Exception as e:
-				print(f"Error {e}. The channel required by the model is not available in your data... Check the configuration file.")
-				channels = None
-				break
+				channel_indices.append(None)
 		else:
 			channel_indices.append(None)
 
-	# if channels is not None:
-	# 	channel_indices = []
-	# 	for ch in required_channels:
-			
-	# 		try:
-	# 			idx = channels.index(ch)
-	# 		except ValueError:
-	# 			print('Mismatch between the channels required by the model and the provided channels.')
-	# 			return None
-
-	# 		channel_indices.append(idx)
-	# 	channel_indices = np.array(channel_indices)
-	# else:
-	# 	channel_indices = np.arange(len(required_channels))
-
 	return channel_indices
 
 def ConfigSectionMap(path,section):
@@ -2044,8 +2029,8 @@ def augmenter(x, y, flip=True, gauss_blur=True, noise_option=True, shift=True,
 		if channel_extinction:
 			assert extinction_probability <= 1.,'The extinction probability must be a number between 0 and 1.'
 			channel_off = [np.random.random() < extinction_probability for i in range(x.shape[-1])]
-			if not np.all(channel_off):
-				x[:,:,np.array(channel_off, dtype=bool)] = 0.
+			channel_off[0] = False
+			x[:,:,np.array(channel_off, dtype=bool)] = 0.
 
 	return x, y
 
@@ -2318,9 +2303,9 @@ def get_zenodo_files(cat=None):
 	for f in all_files_short:
 		if f.startswith('CP') or f.startswith('SD'):
 			category = os.sep.join(['models','segmentation_generic'])
-		elif f.startswith('MCF7'):
+		elif f.startswith('MCF7') or f.startswith('mcf7'):
 			category = os.sep.join(['models','segmentation_targets'])
-		elif f.startswith('primNK'):
+		elif f.startswith('primNK') or f.startswith('lymphocytes'):
 			category = os.sep.join(['models','segmentation_effectors'])
 		elif f.startswith('demo'):
 			category = 'demos'
@@ -2362,9 +2347,7 @@ def download_zenodo_file(file, output_dir):
 	if len(file_to_rename)>0 and not file_to_rename[0].endswith(os.sep) and not file.startswith('demo'):
 		os.rename(file_to_rename[0], os.sep.join([output_dir,file,file]))
 
-	if file=="db_mcf7_nuclei_w_primary_NK":
-		os.rename(os.sep.join([output_dir,file.replace('db_','')]), os.sep.join([output_dir,file]))
-	if file=="db_primary_NK_w_mcf7":
+	if file.startswith('db_'):
 		os.rename(os.sep.join([output_dir,file.replace('db_','')]), os.sep.join([output_dir,file]))
 	if file=='db-si-NucPI':
 		os.rename(os.sep.join([output_dir,'db2-NucPI']), os.sep.join([output_dir,file]))
@@ -2476,4 +2459,77 @@ def step_function(t, t_shift, dt):
 	array([0.26894142, 0.37754067, 0.5       , 0.62245933, 0.73105858, 0.81757448])
 	"""
 
-	return 1/(1+np.exp(-(t-t_shift)/dt))
+	return 1/(1+np.exp(-(t-t_shift)/dt))
+
+
+def test_2samp_generic(data, feature=None, groupby_cols=None, method="ks_2samp", *args, **kwargs):
+
+	"""
+	Performs pairwise statistical tests between groups of data, comparing a specified feature using a chosen method.
+	
+	The function applies two-sample statistical tests, such as the Kolmogorov-Smirnov (KS) test or Cliff's Delta,
+	to compare distributions of a given feature across groups defined by `groupby_cols`. It returns the test results
+	in a pivot table format with each group's pairwise comparison.
+
+	Parameters
+	----------
+	data : pandas.DataFrame
+		The input dataset containing the feature to be tested.
+	feature : str
+		The name of the column representing the feature to compare between groups.
+	groupby_cols : list or str
+		The column(s) used to group the data. These columns define the groups that will be compared pairwise.
+	method : str, optional, default="ks_2samp"
+		The statistical test to use. Options:
+		- "ks_2samp": Two-sample Kolmogorov-Smirnov test (default).
+		- "cliffs_delta": Cliff's Delta for effect size between two distributions.
+	*args, **kwargs : 
+		Additional arguments and keyword arguments for the selected test method.
+
+	Returns
+	-------
+	pivot : pandas.DataFrame
+		A pivot table containing the pairwise test results (p-values or effect sizes). 
+		The rows and columns represent the unique groups defined by `groupby_cols`, 
+		and the values represent the test result (e.g., p-values or effect sizes) between each group.
+
+	Notes
+	-----
+	- The function compares all unique pairwise combinations of the groups based on `groupby_cols`.
+	- For the "ks_2samp" method, the test compares the distributions using the Kolmogorov-Smirnov test.
+	- For the "cliffs_delta" method, the function calculates the effect size between two distributions.
+	- The results are returned in a symmetric pivot table where each cell represents the test result for the corresponding group pair.
+	
+	"""
+
+
+	assert groupby_cols is not None,"Please set a valid groupby_cols..."
+	assert feature is not None,"Please set a feature to test..."
+
+	results = []
+
+	for lbl1,group1 in data.dropna(subset=feature).groupby(groupby_cols):
+		for lbl2,group2 in data.dropna(subset=feature).groupby(groupby_cols):
+
+			dist1 = group1[feature].values
+			dist2 = group2[feature].values
+			if method=="ks_2samp":
+				test = ks_2samp(list(dist1),list(dist2), alternative='less', mode='auto', *args, **kwargs)
+				val = test.pvalue
+			elif method=="cliffs_delta":
+				test = cliffs_delta(list(dist1),list(dist2), *args, **kwargs)
+				val = test[0]
+
+			results.append({"cdt1": lbl1, "cdt2": lbl2, "value": val})
+	
+	results = pd.DataFrame(results)
+	results['cdt1'] = results['cdt1'].astype(str)
+	results['cdt2'] = results['cdt2'].astype(str)
+
+	pivot = results.pivot(index='cdt1', columns='cdt2', values='value')
+	pivot.reset_index(inplace=True)
+	pivot.columns.name = None
+	pivot.set_index("cdt1",drop=True, inplace=True)
+	pivot.index.name = None
+
+	return pivot

{celldetective-1.2.2.post2.dist-info → celldetective-1.3.0.post1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: celldetective
-Version: 1.2.2.post2
+Version: 1.3.0.post1
 Summary: description
 Home-page: http://github.com/remyeltorro/celldetective
 Author: Rémy Torro
@@ -38,6 +38,8 @@ Requires-Dist: matplotlib-scalebar
 Requires-Dist: numpy==1.26.4
 Requires-Dist: pytest
 Requires-Dist: pytest-qt
+Requires-Dist: h5py
+Requires-Dist: cliffs-delta
 
 # Celldetective
 

{celldetective-1.2.2.post2.dist-info → celldetective-1.3.0.post1.dist-info}/RECORD

@@ -1,32 +1,33 @@
-celldetective/__init__.py,sha256=PH25g2_AZt7N5Jg1KB3YT9wFvfMr9lIb2WxYzmDqlX4,105
+celldetective/__init__.py,sha256=bi3SGTMo6s2qQBsJAaKy-a4xaGcTQVW8zsqaiX5XKeY,139
 celldetective/__main__.py,sha256=_H9B620ntENFx9RBvlV6ybxpvtHzCbv5NnIPmDBr9Z0,1127
-celldetective/events.py,sha256=D07LyzBerq4QkXKRhMj0ZChzNkqBrW45E9TgBtEa3tk,4735
+celldetective/_version.py,sha256=psRKPA5pfVLLl8tIZkft2nS2RjrlphliNDLiwS7_UEA,28
+celldetective/events.py,sha256=hPnGSeQtQEwLM7Ks9_7AnuXgEVjQXD_LZeoayE4v7x0,4847
 celldetective/extra_properties.py,sha256=8DkxTvVs7gASsnnGurVZ3_zt6uR0pvvJhBKO2LC6hGk,5118
 celldetective/filters.py,sha256=b0qKwHor1fvNA_dHovP17nQz8EsW5YlyhT2TJnayn08,3615
-celldetective/io.py,sha256=Jld2Nt1cRZyJxUz2wdX-izrd0mp4DJ2P_AMwCDOLUfs,86273
-celldetective/measure.py,sha256=7bfCUdLfJbGmFWWwhu_C9-l1buj_-We7izBaFWTe4ok,54910
+celldetective/io.py,sha256=erGKB0ALcLe5ffuo7pkuACDBC2DR-ZBmJHUcKfCLkrM,86442
+celldetective/measure.py,sha256=S2aEhAAdwNk2p2d8rGG78MoN1g19zTUxYQhCQ-febQI,56328
 celldetective/neighborhood.py,sha256=GjF_fTmtcU8jq5XZT-DnDSp28VDTrsaHjIGJG7W2Ppk,52799
 celldetective/preprocessing.py,sha256=iV5or20s8XPJXQZDsWzis7OBaqzPDyAo_cwcDVDuX5A,38188
 celldetective/relative_measurements.py,sha256=qPHC6gtUaICNGKh6Qfh8y6NA4OUJauGcaj9_TUbrswg,24998
-celldetective/segmentation.py,sha256=H_6BH_RKaG6injUPZ3gQzQ112pMyzQ33u5GEpLE9dsQ,30426
+celldetective/segmentation.py,sha256=NjAVaVpZufpJ-LIvBx5UFH6j5kjRKE6EVLjttDrqaqs,30826
 celldetective/signals.py,sha256=485axzJwE3xsSsN4AmBQlZ2at7uWu9QRg0XrUHvLBUE,120552
 celldetective/tracking.py,sha256=HGeOtfQ-nmpaea9_Q-sq2WcwZfdPXRH028JyFlt6eUs,37901
-celldetective/utils.py,sha256=yuPsRGsw2tYE1IApGulC83dtHOhsIhbts-46b6V83QA,86375
+celldetective/utils.py,sha256=4Nf6jGMdd6kOcF3z0Q_3J8LLZ7Y3fOJKYUwGzUlzk3Q,88768
 celldetective/datasets/segmentation_annotations/blank,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 celldetective/datasets/signal_annotations/blank,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 celldetective/gui/InitWindow.py,sha256=M0v58BmOuZ05em2WSXHpDar3tp2AeS6pr44ZBtiYz-4,13683
 celldetective/gui/__init__.py,sha256=2_r2xfOj4_2xj0yBkCTIfzlF94AHKm-j6Pvpd7DddQc,989
-celldetective/gui/about.py,sha256=fed6nh-WwKy6bEbavy6L62P0CQB8VsOO0PajOjHsnFk,1694
+celldetective/gui/about.py,sha256=FJZrj6C-p6uqp_3UaprKosuW-Sw9_HPNQAvFbis9Gdk,1749
 celldetective/gui/analyze_block.py,sha256=sat8RECEeZxlaconZZIxI0IrIjwJo121PcBXqJmA1-o,24756
 celldetective/gui/btrack_options.py,sha256=OrvbG5coZhLRk5jtXiLFJu34z1hWHN9kHkBiZ7XMZoI,39269
-celldetective/gui/classifier_widget.py,sha256=hyonoHikEkqEsxtE1PZ6cFAn72KcxfSIp8H8PlFPL1c,15822
+celldetective/gui/classifier_widget.py,sha256=cjCuBGvNPI9OQeBeLlLI2h9mDUHHslWkJRjn4JIuVOw,16098
 celldetective/gui/configure_new_exp.py,sha256=Eyr-M4FH-4xrUJbIGNdKXAtXb_ULr8lCol26JSzXEww,20125
-celldetective/gui/control_panel.py,sha256=vU6dfjiO2nmDiY-qF2xCzcwDih6M87ItYTJOeOP51c8,19006
+celldetective/gui/control_panel.py,sha256=JbS47IFeVHc1D2olWiUB_Lo9Bn20QJCPVwhXnRdlFec,18990
 celldetective/gui/generic_signal_plot.py,sha256=OzlFr2RxspkyxW1YIhl_c3q63RXAngMPouYPhEtk0S0,29509
-celldetective/gui/gui_utils.py,sha256=snYUefDEFpIP8RlsNG4QhfI0rLiVE9_t1E8Q7dMIj4k,27747
+celldetective/gui/gui_utils.py,sha256=afqJTeVyMa49QEbSmT0hAiXGd7EiKzckOD5tMvUr-aY,27901
 celldetective/gui/json_readers.py,sha256=Su3angSobroeGrrumGgQcs3Cr_9l9p52-Hfm3qneVcI,3664
 celldetective/gui/layouts.py,sha256=feeAYh7I21ZgH-x4I7lg2DAvz5PBm71D7MovCrtb9QE,47325
-celldetective/gui/measurement_options.py,sha256=fDm8mlak8o9jC8OHhmou9kAmrVY8fCZ8ZKZ0bimhuPo,47133
+celldetective/gui/measurement_options.py,sha256=0CAxM61NqfWVsBaHD1cuC04kMER96-Tgom1p8G5X7Qg,39249
 celldetective/gui/neighborhood_options.py,sha256=BvWwsIX1KWogUgHWRZptqY3ZRmH1aj7r8tiLmbRFhW4,19783
 celldetective/gui/plot_measurements.py,sha256=SBFkY3542hW4H_vllOCMxMOgBz09KUE2FLhhgI8avXk,51024
 celldetective/gui/plot_signals_ui.py,sha256=dQINAOyOmAOHMfmjfCsx1hJ7HGeCgNCq8kESuADbQqo,15864
@@ -34,12 +35,12 @@ celldetective/gui/process_block.py,sha256=PdgKKEfr-GFad3P1y0n9LB_OaIBvuBuaQdBRtz
 celldetective/gui/retrain_segmentation_model_options.py,sha256=eGGrimwmNfJXRPRpZ6NZ74TWx6TK70HoNRHnJl1_8XQ,22292
 celldetective/gui/retrain_signal_model_options.py,sha256=XigNdGlNu3KWB_MYBcKQhfXjcWwVZNMmu0qmxNoo14E,21919
 celldetective/gui/seg_model_loader.py,sha256=vWvPMU6nkTiQfI-x2WjQHrdJGFdV4a4Ne-4YIOq_YZ8,18153
-celldetective/gui/signal_annotator.py,sha256=5Ho7o6lze3BWUbCKJ-53Jh4S46QlTmUq237FAAOfECA,87069
+celldetective/gui/signal_annotator.py,sha256=z205XhTZjKPo9L4lzt-g-uLiu9vk6V1w5zUlxu3bWqQ,87379
 celldetective/gui/signal_annotator2.py,sha256=Y43JSCg3bO_QL7zsqdeQ-FY8TNq_5WiV1cHO-knK0QE,109375
 celldetective/gui/signal_annotator_options.py,sha256=ztFFgA70SJ0QkntxYGsgDNCvSuSR5GjF7_J6pYVYc1g,11020
 celldetective/gui/styles.py,sha256=fup0_U1Zk0IJAjyruHde_r-X7d7cTMcrpPLPl-HuKAM,4820
 celldetective/gui/survival_ui.py,sha256=tzvtI0eC0bgd7Lfm20HqU7rfCJ60gy9a_Sc9cZLSKhs,9439
-celldetective/gui/tableUI.py,sha256=9yJ4CjeNAQoYdHXfsVvD0qr_IdYWuQwIBhvfU3QoNtc,40602
+celldetective/gui/tableUI.py,sha256=sHmXjRhMYjYY4qCrUyMKZf4O-PorvJuMzHbVwshSNVs,46167
 celldetective/gui/thresholds_gui.py,sha256=t1hTDdaJTJWHBt9vtRCE4B1TsVHhobQwCpKfntVgaQI,50510
 celldetective/gui/viewers.py,sha256=mCyE9DaUX2rGq65oYEwyEfNtEUPrHdoFNg2MRp1kXs4,27701
 celldetective/gui/help/DL-segmentation-strategy.json,sha256=59jVtn8pECbCqPQwJifgViVYTF1AxLQDIkNJMS7CJuk,1143
@@ -62,7 +63,7 @@ celldetective/icons/splash0.png,sha256=qVXsrYUinm5g6-vbHcqwyjh8SIqs9lEqPWnPa1Wij
 celldetective/icons/survival2.png,sha256=8zsualD7d9VPAecoFA4Om9TFARErqpJzMg6U7XANXf4,4479
 celldetective/icons/vignette_signals2.png,sha256=hsVOdQDpEfMGM45aaSeacEm3lvxbquRKKYutiS9qoS0,20743
 celldetective/icons/vignette_signals2.svg,sha256=muGNcQudV1jG-bmFd9FwV-Wb8PcrRV5osdZ7pHR7Ekk,5947
-celldetective/links/zenodo.json,sha256=7WKRuZY7MHTR-IChWBbU0i47H_479NtlxsCGaJn9-xM,22728
+celldetective/links/zenodo.json,sha256=qxbRAWRRXgeM4GMPhcvuRFWviI_W0pwovQOq_k5I6Uw,30216
 celldetective/models/pair_signal_detection/blank,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 celldetective/models/segmentation_effectors/blank,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 celldetective/models/segmentation_generic/blank,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -87,13 +88,13 @@ tests/test_measure.py,sha256=FEUAs1rVHylvIvubCb0bJDNGZLVmkgXNgI3NaGQ1dA8,4542
 tests/test_neighborhood.py,sha256=gk5FmoI7ANEczUtNXYRxc48KzkfYzemwS_eYaLq4_NI,2093
 tests/test_preprocessing.py,sha256=FI-Wk-kc4wWmOQg_NLCUIZC1oti396wr5cC-BauBai0,1436
 tests/test_qt.py,sha256=eYqOoff-vfvZAZM6H_IY19IqK7qzyETcyj54f9T0bQA,3906
-tests/test_segmentation.py,sha256=_HB8CCq-Ci6amf0xAmDIUuwtBUU_EGpgqLvcvSHrGug,3427
+tests/test_segmentation.py,sha256=k1b_zIZdlytEdJcHjAUQEO3gTBAHtv5WvrwQN2xD4kc,3470
 tests/test_signals.py,sha256=No4cah6KxplhDcKXnU8RrA7eDla4hWw6ccf7xGnBokU,3599
 tests/test_tracking.py,sha256=8hebWSqEIuttD1ABn-6dKCT7EXKRR7-4RwyFWi1WPFo,8800
 tests/test_utils.py,sha256=NKRCAC1d89aBK5cWjTb7-pInYow901RrT-uBlIdz4KI,3692
-celldetective-1.2.2.post2.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-celldetective-1.2.2.post2.dist-info/METADATA,sha256=WT8GY_72_xK3YgqdZ97FwTWh857CGSzzNPJLKBJRIhI,9923
-celldetective-1.2.2.post2.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-celldetective-1.2.2.post2.dist-info/entry_points.txt,sha256=2NU6_EOByvPxqBbCvjwxlVlvnQreqZ3BKRCVIKEv3dg,62
-celldetective-1.2.2.post2.dist-info/top_level.txt,sha256=6rsIKKfGMKgud7HPuATcpq6EhdXwcg_yknBVWn9x4C4,20
-celldetective-1.2.2.post2.dist-info/RECORD,,
+celldetective-1.3.0.post1.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+celldetective-1.3.0.post1.dist-info/METADATA,sha256=QzPTXc4_K4xgHDJ60xC7CaHbejQ9wjSXGwOEGj1LYrc,9971
+celldetective-1.3.0.post1.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
+celldetective-1.3.0.post1.dist-info/entry_points.txt,sha256=2NU6_EOByvPxqBbCvjwxlVlvnQreqZ3BKRCVIKEv3dg,62
+celldetective-1.3.0.post1.dist-info/top_level.txt,sha256=6rsIKKfGMKgud7HPuATcpq6EhdXwcg_yknBVWn9x4C4,20
+celldetective-1.3.0.post1.dist-info/RECORD,,

tests/test_segmentation.py

@@ -21,11 +21,12 @@ class TestDLMCF7Segmentation(unittest.TestCase):
 		with open(TEST_CONFIG_FILENAME) as config_file:
 			self.config = json.load(config_file)
 		self.channels = self.config['channels']
+		print(f'{self.channels=}')
 		self.spatial_calibration = self.config['spatial_calibration']
 
 	def test_correct_segmentation_with_multimodal_model(self):
 		
-		labels = segment(self.stack, "MCF7_bf_pi_cfse_h", channels=self.channels, spatial_calibration=self.spatial_calibration, view_on_napari=False,
+		labels = segment(self.stack, "mcf7_nuc_multimodal", channels=self.channels, spatial_calibration=self.spatial_calibration, view_on_napari=False,
 						use_gpu=False)
 		np.testing.assert_array_equal(labels[0], labels[1])
 
@@ -39,11 +40,11 @@ class TestDLMCF7Segmentation(unittest.TestCase):
 		m.update_state(self.binary_label_true, label_binary)
 		score = m.result().numpy()
 
-		self.assertGreater(score,0.9)
+		self.assertGreater(score,0.85)
 
 	def test_correct_segmentation_with_transferred_model(self):
 		
-		labels = segment(self.stack, "MCF7_h_versatile", channels=self.channels, spatial_calibration=self.spatial_calibration, view_on_napari=False,
+		labels = segment(self.stack, "mcf7_nuc_stardist_transfer", channels=self.channels, spatial_calibration=self.spatial_calibration, view_on_napari=False,
 			use_gpu=True)
 		np.testing.assert_array_equal(labels[0], labels[1])
 
@@ -57,7 +58,7 @@ class TestDLMCF7Segmentation(unittest.TestCase):
 		m.update_state(self.binary_label_true, label_binary)
 		score = m.result().numpy()
 
-		self.assertGreater(score,0.9)
+		self.assertGreater(score,0.85)
 
 
 class TestThresholdMCF7Segmentation(unittest.TestCase):