spacr 0.3.41__py3-none-any.whl → 0.3.42__py3-none-any.whl

spacr/measure.py

@@ -710,7 +710,7 @@ def _measure_crop_core(index, time_ls, file, settings):
         else:
             cell_mask = np.zeros_like(data[:, :, 0])
             settings['cytoplasm'] = False
-            settings['include_uninfected'] = True
+            settings['uninfected'] = True
 
         if settings['nucleus_mask_dim'] is not None:
             nucleus_mask = data[:, :, settings['nucleus_mask_dim']].astype(data_type)
@@ -762,7 +762,7 @@ def _measure_crop_core(index, time_ls, file, settings):
             cytoplasm_mask = _filter_object(cytoplasm_mask, settings['cytoplasm_min_size'])
 
         if settings['cell_mask_dim'] is not None:
-            cell_mask, nucleus_mask, pathogen_mask, cytoplasm_mask = _exclude_objects(cell_mask, nucleus_mask, pathogen_mask, cytoplasm_mask, include_uninfected=settings['include_uninfected'])
+            cell_mask, nucleus_mask, pathogen_mask, cytoplasm_mask = _exclude_objects(cell_mask, nucleus_mask, pathogen_mask, cytoplasm_mask, uninfected=settings['uninfected'])
 
         # Update data with the new masks
         if settings['cell_mask_dim'] is not None:
@@ -979,9 +979,9 @@ def measure_crop(settings):
                 #_create_database(source_folder+'/measurements/measurements.db')
             
             if settings['cell_mask_dim'] is None:
-                settings['include_uninfected'] = True
+                settings['uninfected'] = True
             if settings['pathogen_mask_dim'] is None:
-                settings['include_uninfected'] = True
+                settings['uninfected'] = True
             if settings['cell_mask_dim'] is not None and settings['pathogen_min_size'] is not None:
                 settings['cytoplasm'] = True
             elif settings['cell_mask_dim'] is not None and settings['nucleus_min_size'] is not None:

spacr/ml.py

@@ -449,26 +449,28 @@ def perform_regression(settings):
             return df, n_gene
         else:
             return df
+        
+
     
     settings = get_perform_regression_default_settings(settings)
     count_data_df, score_data_df = _perform_regression_read_data(settings)
     results_path, results_path_gene, results_path_grna, hits_path, res_folder, csv_path = _perform_regression_set_paths(settings)
     save_settings(settings, name='regression', show=True)
+
+    if isinstance(settings['filter_value'], list):
+        filter_value = settings['filter_value']
+    else:
+        filter_value = []
+    if isinstance(settings['filter_column'], str):
+        filter_column = settings['filter_column']
     
-    score_data_df = clean_controls(score_data_df, settings['pc'], settings['nc'], settings['other'])
+    score_data_df = clean_controls(score_data_df, settings['filter_value'], settings['filter_column'])
     print(f"Dependent variable after clean_controls: {len(score_data_df)}")
 
     dependent_df, dependent_variable = process_scores(score_data_df, settings['dependent_variable'], settings['plate'], settings['min_cell_count'], settings['agg_type'], settings['transform'])
     print(f"Dependent variable after process_scores: {len(dependent_df)}")
 
-    filter_value = [settings['nc'], settings['pc']]
-
-    if settings['other'] is not None:
-        if isinstance(settings['other'], str):
-            settings['other'] = [settings['other']]
-        filter_value.extend(settings['other'])
-
-    independent_df = process_reads(count_data_df, settings['fraction_threshold'], settings['plate'], filter_column=settings['location_column'], filter_value=filter_value)
+    independent_df = process_reads(count_data_df, settings['fraction_threshold'], settings['plate'], filter_column=filter_column, filter_value=filter_value)
     independent_df, n_grna, n_gene = _count_variable_instances(independent_df, column_1='grna', column_2='gene')
 
     print(f"Independent variable after process_reads: {len(independent_df)}")
@@ -498,12 +500,14 @@ def perform_regression(settings):
     if settings['controls'] is not None:
         control_coef_df = grna_coef_df[grna_coef_df['grna'].isin(settings['controls'])]
         mean_coef = control_coef_df['coefficient'].mean()
-        variance_coef = control_coef_df['coefficient'].var()
-        std_coef = control_coef_df['coefficient'].std()
-        reg_threshold = mean_coef + (3 * std_coef)
-    
-    print('coef_df')
-    display(coef_df)
+        
+        if settings['threshold_method'] in ['var','variance']:
+            coef_mes = control_coef_df['coefficient'].var()
+        elif settings['threshold_method'] in ['std', 'standard_deveation']:
+            coef_mes = control_coef_df['coefficient'].std()
+        else:
+            raise ValueError(f"Unsupported threshold method {settings['threshold_method']}. Supported methods: ['var','variance','std','standard_deveation']")
+        reg_threshold = mean_coef + (settings['threshold_multiplier'] * coef_mes)
     
     coef_df.to_csv(results_path, index=False)
     gene_coef_df.to_csv(results_path_gene, index=False)
@@ -596,7 +600,7 @@ def process_reads(csv_path, fraction_threshold, plate, filter_column=None, filte
     if isinstance(filter_value, str):
         filter_value = [filter_value]
 
-    if isinstance(filter_column, list):
+    if isinstance(filter_column, list):            
         for filter_col in filter_column:
             for value in filter_value:
                 csv_df = csv_df[csv_df[filter_col] != value]
@@ -659,16 +663,12 @@ def check_normality(data, variable_name, verbose=False):
             print(f"Normal distribution: The data for {variable_name} is not normally distributed.")
         return False
 
-def clean_controls(df,pc,nc,other):
-    if 'col' in df.columns:
-        df['column'] = df['col']
-    if nc != None:
-        df = df[~df['column'].isin([nc])]
-    if pc != None:
-        df = df[~df['column'].isin([pc])]
-    if other != None:
-        df = df[~df['column'].isin([other])]
-        print(f'Removed data from {nc, pc, other}')
+def clean_controls(df,values, column):
+    if column in df.columns:
+        if isinstance(values, list):
+            for value in values:
+                df = df[~df[column].isin([value])]
+                print(f'Removed data from {value}')
     return df
 
 def process_scores(df, dependent_variable, plate, min_cell_count=25, agg_type='mean', transform=None, regression_type='ols'):

spacr/settings.py

@@ -261,7 +261,7 @@ def get_measure_crop_settings(settings={}):
     settings.setdefault('nucleus_mask_dim',None)
     settings.setdefault('pathogen_mask_dim',None)
     settings.setdefault('cytoplasm',False)
-    settings.setdefault('include_uninfected',True)
+    settings.setdefault('uninfected',True)
     settings.setdefault('cell_min_size',0)
     settings.setdefault('nucleus_min_size',0)
     settings.setdefault('pathogen_min_size',0)
@@ -527,26 +527,31 @@ def set_generate_dataset_defaults(settings):
     return settings
 
 def get_perform_regression_default_settings(settings):
-    settings.setdefault('highlight','239740')
-    settings.setdefault('dependent_variable','predictions')
+    settings.setdefault('count_data','list of paths')
+    settings.setdefault('score_data','list of paths')
+    settings.setdefault('positive_control','239740')
+    settings.setdefault('negative_control','233460')
+    settings.setdefault('controls',['000000_1','000000_10','000000_11','000000_12','000000_13','000000_14','000000_15','000000_16','000000_17','000000_18','000000_19','000000_20','000000_21','000000_22','000000_23','000000_24','000000_25','000000_26','000000_27','000000_28','000000_29','000000_3','000000_30','000000_31','000000_32','000000_4','000000_5','000000_6','000000_8','000000_9'])
+    settings.setdefault('fraction_threshold',0.12)
+    settings.setdefault('dependent_variable','pred')
+    settings.setdefault('threshold_method','std')
+    settings.setdefault('threshold_multiplier',3)
     settings.setdefault('transform',None)
     settings.setdefault('agg_type','mean')
     settings.setdefault('min_cell_count',25)
     settings.setdefault('regression_type','ols')
     settings.setdefault('random_row_column_effects',False)
+    settings.setdefault('split_axis_lims','')
+    settings.setdefault('plate','')
+    settings.setdefault('cov_type',None)
     settings.setdefault('alpha',1)
-    settings.setdefault('fraction_threshold',0.1)
-    settings.setdefault('location_column','column')
-    settings.setdefault('nc','c1')
-    settings.setdefault('pc','c2')
-    settings.setdefault('other','c3')
+    settings.setdefault('filter_value',['c1', 'c2', 'c3'])
+    settings.setdefault('filter_column','column')
     settings.setdefault('plate','plate1')
     settings.setdefault('class_1_threshold',None)
-    settings.setdefault('cov_type',None)
     settings.setdefault('metadata_files',['/home/carruthers/Documents/TGME49_Summary.csv','/home/carruthers/Documents/TGGT1_Summary.csv'])
     settings.setdefault('toxo', True)
 
-    
     if settings['regression_type'] == 'quantile':
         print(f"Using alpha as quantile for quantile regression, alpha: {settings['alpha']}")
         settings['agg_type'] = None
@@ -664,7 +669,7 @@ expected_types = {
     "png_dims": list,
     "normalize_by": str,
     "save_measurements": bool,
-    "include_uninfected": bool,
+    "uninfected": bool,
     "dialate_pngs": bool,
     "dialate_png_ratios": list,
     "n_jobs": int,
@@ -893,7 +898,7 @@ expected_types = {
 categories = {"Paths":[ "src", "grna", "barcodes", "custom_model_path", "dataset","model_path","grna_csv","row_csv","column_csv"],
              "General": ["metadata_type", "custom_regex", "experiment", "channels", "magnification", "channel_dims", "apply_model_to_dataset", "generate_training_dataset", "train_DL_model", "segmentation_mode"],
              "Cellpose":["from_scratch", "n_epochs", "width_height", "model_name", "custom_model", "resample", "rescale", "CP_prob", "flow_threshold", "percentiles", "circular", "invert", "diameter", "grayscale", "background", "Signal_to_noise", "resize", "target_height", "target_width"],
-             "Cell": ["cell_intensity_range", "cell_size_range", "cell_chann_dim", "cell_channel", "cell_background", "cell_Signal_to_noise", "cell_CP_prob", "cell_FT", "remove_background_cell", "cell_min_size", "cell_mask_dim", "cytoplasm", "cytoplasm_min_size", "include_uninfected", "merge_edge_pathogen_cells", "adjust_cells", "cells", "cell_loc"],
+             "Cell": ["cell_intensity_range", "cell_size_range", "cell_chann_dim", "cell_channel", "cell_background", "cell_Signal_to_noise", "cell_CP_prob", "cell_FT", "remove_background_cell", "cell_min_size", "cell_mask_dim", "cytoplasm", "cytoplasm_min_size", "uninfected", "merge_edge_pathogen_cells", "adjust_cells", "cells", "cell_loc"],
              "Nucleus": ["nucleus_intensity_range", "nucleus_size_range", "nucleus_chann_dim", "nucleus_channel", "nucleus_background", "nucleus_Signal_to_noise", "nucleus_CP_prob", "nucleus_FT", "remove_background_nucleus", "nucleus_min_size", "nucleus_mask_dim", "nucleus_loc"],
              "Pathogen": ["pathogen_intensity_range", "pathogen_size_range", "pathogen_chann_dim", "pathogen_channel", "pathogen_background", "pathogen_Signal_to_noise", "pathogen_CP_prob", "pathogen_FT", "pathogen_model", "remove_background_pathogen", "pathogen_min_size", "pathogen_mask_dim", "pathogens", "pathogen_loc", "pathogen_types", "pathogen_plate_metadata", ],
              "Measurements": ["remove_image_canvas", "remove_highly_correlated", "homogeneity", "homogeneity_distances", "radial_dist", "calculate_correlation", "manders_thresholds", "save_measurements", "tables", "image_nr", "dot_size", "filter_by", "remove_highly_correlated_features", "remove_low_variance_features", "channel_of_interest"],
@@ -1083,7 +1088,7 @@ def generate_fields(variables, scrollable_frame):
         "nuclei_limit": "(int) - Whether to include multinucleated cells in the analysis.",
         "pathogen_limit": "(int) - Whether to include multi-infected cells in the analysis.",
         "uninfected": "(bool) - Whether to include non-infected cells in the analysis.",
-        "include_uninfected": "(bool) - Whether to include uninfected cells in the analysis.",
+        "uninfected": "(bool) - Whether to include uninfected cells in the analysis.",
         "init_weights": "(bool) - Whether to initialize weights for the model.",
         "src": "(str) - Path to the folder containing the images.",
         "intermedeate_save": "(bool) - Whether to save intermediate results.",

spacr/toxo.py

@@ -136,6 +136,7 @@ def custom_volcano_plot(data_path, metadata_path, metadata_column='tagm_location
     data['variable'].fillna(data['feature'], inplace=True)
     split_columns = data['variable'].str.split('_', expand=True)
     data['gene_nr'] = split_columns[0]
+    data = data[data['variable'] != 'Intercept']
 
     # Load metadata
     if isinstance(metadata_path, pd.DataFrame):
@@ -158,11 +159,14 @@ def custom_volcano_plot(data_path, metadata_path, metadata_column='tagm_location
         merged_data['condition'],
         categories=['other','pc', 'nc', 'control'],
         ordered=True)
+    
+
+    display(merged_data)
 
     # Create subplots with a broken y-axis
     figsize_2 = figsize / 2
     fig, (ax1, ax2) = plt.subplots(
-        2, 1, figsize=(figsize_2, figsize), 
+        2, 1, figsize=(figsize, figsize), 
         sharex=True, gridspec_kw={'height_ratios': [1, 3]}
     )
 
@@ -178,11 +182,12 @@ def custom_volcano_plot(data_path, metadata_path, metadata_column='tagm_location
         data=merged_data,
         x='coefficient',
         y='-log10(p_value)',
-        hue='condition',
-        style=metadata_column if metadata_column else None,
+        hue='condition',  # Keep colors but prevent them from showing in the final legend
+        style=metadata_column if metadata_column else None,  # Shape-based legend
         s=point_size,
         edgecolor='black', 
         palette=palette,
+        legend='brief',  # Capture the full legend initially
         alpha=0.8,
         ax=ax2  # Lower plot
     )
@@ -196,6 +201,7 @@ def custom_volcano_plot(data_path, metadata_path, metadata_column='tagm_location
         s=point_size,
         palette=palette,
         edgecolor='black', 
+        legend=False,  # Suppress legend for upper plot
         alpha=0.8,
         ax=ax1  # Upper plot
     )
@@ -222,9 +228,24 @@ def custom_volcano_plot(data_path, metadata_path, metadata_column='tagm_location
     ax2.spines['top'].set_visible(False)
     ax1.tick_params(labelbottom=False)
 
-    ax1.legend_.remove()
     if ax1.get_legend() is not None:
-        ax1.get_legend().remove()
+        ax1.legend_.remove()
+        ax1.get_legend().remove()    # Extract handles and labels from the legend
+    handles, labels = ax2.get_legend_handles_labels()
+
+    # Identify shape-based legend entries (skip color-based entries)
+    shape_handles = handles[len(set(merged_data['condition'])):]
+    shape_labels = labels[len(set(merged_data['condition'])):]
+
+    # Set the legend with only shape-based entries
+    ax2.legend(
+        shape_handles,
+        shape_labels,
+        bbox_to_anchor=(1.05, 1),
+        loc='upper left',
+        borderaxespad=0.
+    )
+
     ax1.tick_params(axis='x', which='both', bottom=False, top=False, labelbottom=False)
 
     # Add vertical threshold lines to both plots

spacr/utils.py

@@ -2912,7 +2912,7 @@ def _relabel_parent_with_child_labels(parent_mask, child_mask):
 
     return parent_mask_new, child_mask
     
-def _exclude_objects(cell_mask, nucleus_mask, pathogen_mask, cytoplasm_mask, include_uninfected=True):
+def _exclude_objects(cell_mask, nucleus_mask, pathogen_mask, cytoplasm_mask, uninfected=True):
     """
     Exclude objects from the masks based on certain criteria.
 
@@ -2921,7 +2921,7 @@ def _exclude_objects(cell_mask, nucleus_mask, pathogen_mask, cytoplasm_mask, inc
         nucleus_mask (ndarray): Mask representing nucleus.
         pathogen_mask (ndarray): Mask representing pathogens.
         cytoplasm_mask (ndarray): Mask representing cytoplasm.
-        include_uninfected (bool, optional): Whether to include uninfected cells. Defaults to True.
+        uninfected (bool, optional): Whether to include uninfected cells. Defaults to True.
 
     Returns:
         tuple: A tuple containing the filtered cell mask, nucleus mask, pathogen mask, and cytoplasm mask.
@@ -2936,7 +2936,7 @@ def _exclude_objects(cell_mask, nucleus_mask, pathogen_mask, cytoplasm_mask, inc
         has_nucleus = np.any(nucleus_mask[cell_region])
         has_cytoplasm = np.any(cytoplasm_mask[cell_region])
         has_pathogen = np.any(pathogen_mask[cell_region])
-        if include_uninfected:
+        if uninfected:
             if has_nucleus and has_cytoplasm:
                 filtered_cells[cell_region] = cell_label
         else:

{spacr-0.3.41.dist-info → spacr-0.3.42.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: spacr
-Version: 0.3.41
+Version: 0.3.42
 Summary: Spatial phenotype analysis of crisp screens (SpaCr)
 Home-page: https://github.com/EinarOlafsson/spacr
 Author: Einar Birnir Olafsson

{spacr-0.3.41.dist-info → spacr-0.3.42.dist-info}/RECORD

@@ -16,18 +16,18 @@ spacr/gui_elements.py,sha256=w-S1MZdyxt5O3DsNAHNNXy_WGfwBPg0NhwQtCsJeiao,137071
 spacr/gui_utils.py,sha256=7e9DsZIuV7-jh97kEf7v1In_cFzlFueV4SGcGYGpTxw,45454
 spacr/io.py,sha256=LN_gJq_oqjbf8y-lBtLLZtJi8DLbNdyoGEcBYyOjbhQ,143606
 spacr/logger.py,sha256=lJhTqt-_wfAunCPl93xE65Wr9Y1oIHJWaZMjunHUeIw,1538
-spacr/measure.py,sha256=BThn_sALgKrwGKnLOGpT4FyoJeRVoTZoP9SXbCtCMRw,54857
+spacr/measure.py,sha256=KdboGXoi85BO5-_6er7932FgjFI7G7tuaQDnWSiEuew,54817
 spacr/mediar.py,sha256=FwLvbLQW5LQzPgvJZG8Lw7GniA2vbZx6Jv6vIKu7I5c,14743
-spacr/ml.py,sha256=e6nUQaiKBPwcDN_aZZKsbZG6qEa5k9B42wtuL8ipv3Q,50287
+spacr/ml.py,sha256=vzuEnbQd96mn7T8h3GRsEDnpWSSpxd3ApGMXTiG6b2o,50507
 spacr/openai.py,sha256=5vBZ3Jl2llYcW3oaTEXgdyCB2aJujMUIO5K038z7w_A,1246
 spacr/plot.py,sha256=TDGMwiIHjvk6v94WFlIvemU-6JfEik_GmSez51vyvCc,135869
 spacr/sequencing.py,sha256=t18mgpK6rhWuB1LtFOsPxqgpFXxuUmrD06ecsaVQ0Gw,19655
-spacr/settings.py,sha256=AzP9NGiXI1MqT69bHObxwDSCUk0kdstBVvl1JpcD_-w,75960
+spacr/settings.py,sha256=x3zcOpVbsxGvq4neW-H08CxzNl8thacy4WOxcIG4TAc,76607
 spacr/sim.py,sha256=1xKhXimNU3ukzIw-3l9cF3Znc_brW8h20yv8fSTzvss,71173
 spacr/submodules.py,sha256=AB7s6-cULsaqz-haAaCtXfGEIi8uPZGT4xoCslUJC3Y,18391
 spacr/timelapse.py,sha256=FSYpUtAVy6xc3lwprRYgyDTT9ysUhfRQ4zrP9_h2mvg,39465
-spacr/toxo.py,sha256=7dUJe5_HSvDCP16OIXtbYLyshh9LXb2JQ80Vtn-XdPk,15979
-spacr/utils.py,sha256=_8OxwGVCZaMNBiweB4_YOxBkqQX1LR9YstPSIFmeQKA,216420
+spacr/toxo.py,sha256=MVDfkfTl6fhbzg3izLWdtr2arARYIhI1TdScnHtPVqI,16770
+spacr/utils.py,sha256=Z8lmQJc8sdPvHi0ZmYOahuKtUmDcrYtRYlT4qNZORXU,216396
 spacr/version.py,sha256=axH5tnGwtgSnJHb5IDhiu4Zjk5GhLyAEDRe-rnaoFOA,409
 spacr/resources/MEDIAR/.gitignore,sha256=Ff1q9Nme14JUd-4Q3jZ65aeQ5X4uttptssVDgBVHYo8,152
 spacr/resources/MEDIAR/LICENSE,sha256=yEj_TRDLUfDpHDNM0StALXIt6mLqSgaV2hcCwa6_TcY,1065
@@ -150,9 +150,9 @@ 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-0.3.41.dist-info/LICENSE,sha256=SR-2MeGc6SCM1UORJYyarSWY_A-JaOMFDj7ReSs9tRM,1083
-spacr-0.3.41.dist-info/METADATA,sha256=zGZO-9iZjljHTjnVg9kAxQJjr2vqpobl7S7ZSQlgxP8,5949
-spacr-0.3.41.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
-spacr-0.3.41.dist-info/entry_points.txt,sha256=BMC0ql9aNNpv8lUZ8sgDLQMsqaVnX5L535gEhKUP5ho,296
-spacr-0.3.41.dist-info/top_level.txt,sha256=GJPU8FgwRXGzKeut6JopsSRY2R8T3i9lDgya42tLInY,6
-spacr-0.3.41.dist-info/RECORD,,
+spacr-0.3.42.dist-info/LICENSE,sha256=SR-2MeGc6SCM1UORJYyarSWY_A-JaOMFDj7ReSs9tRM,1083
+spacr-0.3.42.dist-info/METADATA,sha256=_nbP3IjQELrampyAYyt6hfrQBukDHuhlS7CApsMPsQ0,5949
+spacr-0.3.42.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
+spacr-0.3.42.dist-info/entry_points.txt,sha256=BMC0ql9aNNpv8lUZ8sgDLQMsqaVnX5L535gEhKUP5ho,296
+spacr-0.3.42.dist-info/top_level.txt,sha256=GJPU8FgwRXGzKeut6JopsSRY2R8T3i9lDgya42tLInY,6
+spacr-0.3.42.dist-info/RECORD,,