spacr 0.3.35__py3-none-any.whl → 0.3.37__py3-none-any.whl

spacr/gui_elements.py

@@ -2267,14 +2267,24 @@ class AnnotateApp:
         self.grid_rows = max(1, self.grid_rows)
 
     def prefilter_paths_annotations(self):
-        from .io import _read_and_join_tables
+        from .io import _read_and_join_tables, _read_db
         from .utils import is_list_of_lists
 
         if self.measurement and self.threshold is not None:
             df = _read_and_join_tables(self.db_path)
+            png_list_df = _read_db(self.db_path, tables=['png_list'])[0]
+            png_list_df = png_list_df.set_index('prcfo')
+            df = df.merge(png_list_df, left_index=True, right_index=True)
             df[self.annotation_column] = None
             before = len(df)
 
+            if isinstance(self.threshold, int):
+                if isinstance(self.measurement, list):
+                    mes = self.measurement[0]
+                if isinstance(self.measurement, str):
+                    mes = self.measurement
+                df = df[df[f'{mes}'] == self.threshold]
+
             if is_list_of_lists(self.measurement):
                 if isinstance(self.threshold, list) or is_list_of_lists(self.threshold):
                     if len(self.measurement) == len(self.threshold):

spacr/ml.py

@@ -763,7 +763,7 @@ def generate_ml_scores(settings):
             raise ValueError("The 'png_list_df' DataFrame must contain 'prcfo' and 'test' columns.")
         annotated_df = png_list_df[['prcfo', settings['annotation_column']]].set_index('prcfo')
         df = annotated_df.merge(df, left_index=True, right_index=True)
-        display(df)
+        #display(df)
         unique_values = df[settings['annotation_column']].dropna().unique()
         if len(unique_values) == 1:
             unannotated_rows = df[df[settings['annotation_column']].isna()].index
@@ -846,6 +846,7 @@ def generate_ml_scores(settings):
     return [output, plate_heatmap]
 
 def ml_analysis(df, channel_of_interest=3, location_column='col', positive_control='c2', negative_control='c1', exclude=None, n_repeats=10, top_features=30, n_estimators=100, test_size=0.2, model_type='xgboost', n_jobs=-1, remove_low_variance_features=True, remove_highly_correlated_features=True, verbose=False):
+    
     """
     Calculates permutation importance for numerical features in the dataframe,
     comparing groups based on specified column values and uses the model to predict 
@@ -878,7 +879,6 @@ def ml_analysis(df, channel_of_interest=3, location_column='col', positive_contr
     if 'cells_per_well' in df.columns:
         df = df.drop(columns=['cells_per_well'])
 
-    
     df_metadata = df[[location_column]].copy()
 
     df, features = filter_dataframe_features(df, channel_of_interest, exclude, remove_low_variance_features, remove_highly_correlated_features, verbose)

spacr/plot.py

@@ -2591,35 +2591,71 @@ class spacrGraph:
         return self.fig
 
 def plot_data_from_db(settings):
-    from .io import _read_db
+    from .io import _read_db, _read_and_merge_data
     from .utils import annotate_conditions
     """
     Extracts the specified table from the SQLite database and plots a specified column.
 
     Args:
         db_path (str): The path to the SQLite database.
-        table_name (str): The name of the table to extract.
+        table_names (str): The name of the table to extract.
         column_name (str): The column to plot from the table.
 
     Returns:
         df (pd.DataFrame): The extracted table as a DataFrame.
     """
+
+    if isinstance(settings['src'], str):
+        srcs = [settings['src']]
+    elif isinstance(settings['src'], list):
+        srcs = settings['src']
+        if isinstance(settings['database'], str):
+            settings['database'] = [settings['database'] for _ in range(len(srcs))]
+    else:
+        raise ValueError("src must be a string or a list of strings.")
     
-    db_loc = os.path.join(settings['src'], 'measurements',settings['database'])
-    
-    [df] = _read_db(db_loc, tables=[settings['table_name']])
+    dfs = []
+    for i, src in enumerate(srcs):
+
+        db_loc = os.path.join(src, 'measurements', settings['database'][i])
         
-    df = annotate_conditions(df, 
-                             cells=settings['cell_types'], 
-                             cell_loc=settings['cell_plate_metadata'], 
-                             pathogens=settings['pathogen_types'],
-                             pathogen_loc=settings['pathogen_plate_metadata'],
-                             treatments=settings['treatments'], 
-                             treatment_loc=settings['treatment_plate_metadata'])
-    
+        if settings['table_names'] in ['saliency_image_correlations']:
+            [df1] = _read_db(db_loc, tables=[settings['table_names']])
+        else:
+            df1, _ = _read_and_merge_data(locs=[db_loc],
+                                    tables = ['cell', 'nucleus', 'pathogen','cytoplasm'],
+                                    verbose=settings['verbose'],
+                                    nuclei_limit=settings['nuclei_limit'],
+                                    pathogen_limit=settings['pathogen_limit'],
+                                    uninfected=settings['uninfected'])
+                                    
+        dft = annotate_conditions(df1, 
+                                cells=settings['cell_types'], 
+                                cell_loc=settings['cell_plate_metadata'], 
+                                pathogens=settings['pathogen_types'],
+                                pathogen_loc=settings['pathogen_plate_metadata'],
+                                treatments=settings['treatments'], 
+                                treatment_loc=settings['treatment_plate_metadata'])
+        dfs.append(dft)
+        
+    df = pd.concat(dfs, axis=0)
     df['prc'] = df['plate'].astype(str) + '_' + df['row'].astype(str) + '_' + df['col'].astype(str)
+    df['recruitment'] = df['pathogen_channel_1_mean_intensity'] / df['cytoplasm_channel_1_mean_intensity']
+
+    if settings['cell_plate_metadata'] !=  None:
+        df = df.dropna(subset='host_cell')
+
+    if settings['pathogen_plate_metadata'] !=  None:
+        df = df.dropna(subset='pathogen')
+
+    if settings['treatment_plate_metadata'] !=  None:
+        df = df.dropna(subset='treatment')
+
     df = df.dropna(subset=settings['column_name'])
-    df['class'] = df['png_path'].apply(lambda x: 'class_1' if 'class_1' in x else ('class_0' if 'class_0' in x else None))
+    df = df.dropna(subset=settings['grouping_column'])
+    #display(df)
+
+    #df['class'] = df['png_path'].apply(lambda x: 'class_1' if 'class_1' in x else ('class_0' if 'class_0' in x else None))
     
     spacr_graph = spacrGraph(
         df=df,                                       # Your DataFrame
@@ -2632,7 +2668,7 @@ def plot_data_from_db(settings):
         save=settings['save'],                       # Whether to save the plot and results
         y_lim=settings['y_lim'],                     # Starting point for y-axis (optional)
         error_bar_type='std',                        # Type of error bar ('std' or 'sem')
-        representation='well',
+        representation=settings['representation'],
         theme=settings['theme'],                     # Seaborn color palette theme (e.g., 'pastel', 'muted')
     )
 

spacr/utils.py

@@ -5045,25 +5045,52 @@ def generate_cytoplasm_mask(nucleus_mask, cell_mask):
 
 def add_column_to_database(settings):
     """
-    Updates a column in the database by matching on a common column from the DataFrame.
-
+    Adds a new column to the database table by matching on a common column from the DataFrame.
+    If the column already exists in the database, it adds the column with a suffix.
+    
     Parameters:
     - settings: A dictionary containing the following keys:
         - 'csv_path': Path to the CSV file with the data to be added.
         - 'db_path': Path to the SQLite database (or connection string for other databases).
         - 'table_name': The name of the table in the database.
-        - 'update_column': The column to update in the database.
+        - 'update_column': The name of the new column in the DataFrame to add to the database.
         - 'match_column': The common column used to match rows.
     """
 
     # Read the DataFrame from the provided CSV path
     df = pd.read_csv(settings['csv_path'])
 
+    # Check for any 0 values in the update column and replace them with 2
+    if (df[settings['update_column']] == 0).any():
+        print("Replacing all 0 values with 2 in the update column.")
+        df[settings['update_column']].replace(0, 2, inplace=True)
+
     # Connect to the SQLite database
     conn = sqlite3.connect(settings['db_path'])
     cursor = conn.cursor()
 
-    # Iterate over the DataFrame and update the database
+    # Get the existing columns in the database table
+    cursor.execute(f"PRAGMA table_info({settings['table_name']})")
+    columns_in_db = [col[1] for col in cursor.fetchall()]
+
+    # Check if the update column already exists in the database
+    if settings['update_column'] in columns_in_db:
+        # Add a suffix to the column name (e.g., '_new', '_1', or similar)
+        suffix = 1
+        new_column_name = f"{settings['update_column']}_{suffix}"
+        # Ensure uniqueness by incrementing the suffix if needed
+        while new_column_name in columns_in_db:
+            suffix += 1
+            new_column_name = f"{settings['update_column']}_{suffix}"
+        print(f"Column '{settings['update_column']}' already exists. Using new column name: '{new_column_name}'")
+    else:
+        new_column_name = settings['update_column']
+
+    # Add the new column to the database table
+    cursor.execute(f"ALTER TABLE {settings['table_name']} ADD COLUMN {new_column_name} TEXT")
+    print(f"Added new column '{new_column_name}' to the table '{settings['table_name']}'.")
+
+    # Iterate over the DataFrame and update the new column in the database
     for index, row in df.iterrows():
         value_to_update = row[settings['update_column']]
         match_value = row[settings['match_column']]
@@ -5071,7 +5098,7 @@ def add_column_to_database(settings):
         # Prepare and execute the SQL update query
         query = f"""
             UPDATE {settings['table_name']}
-            SET {settings['update_column']} = ?
+            SET {new_column_name} = ?
             WHERE {settings['match_column']} = ?
         """
         cursor.execute(query, (value_to_update, match_value))
@@ -5080,6 +5107,7 @@ def add_column_to_database(settings):
     conn.commit()
     conn.close()
 
-    print(f"Updated '{settings['update_column']}' in '{settings['table_name']}' using '{settings['match_column']}'.")
+    print(f"Updated '{new_column_name}' in '{settings['table_name']}' using '{settings['match_column']}'.")
+
 
 

{spacr-0.3.35.dist-info → spacr-0.3.37.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: spacr
-Version: 0.3.35
+Version: 0.3.37
 Summary: Spatial phenotype analysis of crisp screens (SpaCr)
 Home-page: https://github.com/EinarOlafsson/spacr
 Author: Einar Birnir Olafsson

{spacr-0.3.35.dist-info → spacr-0.3.37.dist-info}/RECORD

@@ -12,22 +12,22 @@ spacr/core.py,sha256=G_x-w7FRIHNfSOoPaIZPSf_A7mVj7PA7o9HQZ4nIu5o,48231
 spacr/deep_spacr.py,sha256=HdOcNU8cHcE_19nP7_5uTz-ih3E169ffr2Hm--NvMvA,43255
 spacr/gui.py,sha256=ARyn9Q_g8HoP-cXh1nzMLVFCKqthY4v2u9yORyaQqQE,8230
 spacr/gui_core.py,sha256=LV_HX5zreu3Bye6sQFDbOuk8Dfj4StMoohy6hsrDEXA,41363
-spacr/gui_elements.py,sha256=puDqf7PJJ_UMA01fjqODk-zsfSmvzVXpvaZ1BYV988w,136554
+spacr/gui_elements.py,sha256=w-S1MZdyxt5O3DsNAHNNXy_WGfwBPg0NhwQtCsJeiao,137071
 spacr/gui_utils.py,sha256=7e9DsZIuV7-jh97kEf7v1In_cFzlFueV4SGcGYGpTxw,45454
 spacr/io.py,sha256=AARmqn1fMmTgVDwWy8bEYK6SjH-6DZIulgCSPdBTyf0,143370
 spacr/logger.py,sha256=lJhTqt-_wfAunCPl93xE65Wr9Y1oIHJWaZMjunHUeIw,1538
 spacr/measure.py,sha256=BThn_sALgKrwGKnLOGpT4FyoJeRVoTZoP9SXbCtCMRw,54857
 spacr/mediar.py,sha256=FwLvbLQW5LQzPgvJZG8Lw7GniA2vbZx6Jv6vIKu7I5c,14743
-spacr/ml.py,sha256=Wy_H_bI5cD_N4xIZCo3_M-73wVvmCC35tJbLspMOWbg,49341
+spacr/ml.py,sha256=ItibDL_q0cKwEsJdwpBtVqfpRQGPXGbb0BX5UB5iH5s,49342
 spacr/openai.py,sha256=5vBZ3Jl2llYcW3oaTEXgdyCB2aJujMUIO5K038z7w_A,1246
-spacr/plot.py,sha256=PtCSoBmLFlGC7ebmsk-vMlyd7q2ahXgRVaTtAq3w_po,116513
+spacr/plot.py,sha256=QYj2bV0-6UqKRTWeSj3eOOgr6dNMmCCc4TdRGTniQ4c,118083
 spacr/sequencing.py,sha256=t18mgpK6rhWuB1LtFOsPxqgpFXxuUmrD06ecsaVQ0Gw,19655
 spacr/settings.py,sha256=AzP9NGiXI1MqT69bHObxwDSCUk0kdstBVvl1JpcD_-w,75960
 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=us3pQyULtMTyfTq0MWPn4QJTTmQ6BwAJKChNf75jo3I,10082
-spacr/utils.py,sha256=hqxgN3tZTUyYvntaDc7tCRxgqlST0suAtkV3HYfbOO4,214847
+spacr/utils.py,sha256=3SBf5yeeU3u9MVsIWeYmcHjhwqs8LJ6m9UF0wBSNq8M,216304
 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-0.3.35.dist-info/LICENSE,sha256=SR-2MeGc6SCM1UORJYyarSWY_A-JaOMFDj7ReSs9tRM,1083
-spacr-0.3.35.dist-info/METADATA,sha256=xBdKUQpQuuru72Lgt9dirwo_Of5GdAwOKqs7bH7Sd0k,5949
-spacr-0.3.35.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
-spacr-0.3.35.dist-info/entry_points.txt,sha256=BMC0ql9aNNpv8lUZ8sgDLQMsqaVnX5L535gEhKUP5ho,296
-spacr-0.3.35.dist-info/top_level.txt,sha256=GJPU8FgwRXGzKeut6JopsSRY2R8T3i9lDgya42tLInY,6
-spacr-0.3.35.dist-info/RECORD,,
+spacr-0.3.37.dist-info/LICENSE,sha256=SR-2MeGc6SCM1UORJYyarSWY_A-JaOMFDj7ReSs9tRM,1083
+spacr-0.3.37.dist-info/METADATA,sha256=Y65Rn3Py1AHsgydWiBFLsd0_vPVhxubiYizcIpfFIbE,5949
+spacr-0.3.37.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
+spacr-0.3.37.dist-info/entry_points.txt,sha256=BMC0ql9aNNpv8lUZ8sgDLQMsqaVnX5L535gEhKUP5ho,296
+spacr-0.3.37.dist-info/top_level.txt,sha256=GJPU8FgwRXGzKeut6JopsSRY2R8T3i9lDgya42tLInY,6
+spacr-0.3.37.dist-info/RECORD,,