spacr 0.3.36__tar.gz → 0.3.38__tar.gz

{spacr-0.3.36/spacr.egg-info → spacr-0.3.38}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: spacr
-Version: 0.3.36
+Version: 0.3.38
 Summary: Spatial phenotype analysis of crisp screens (SpaCr)
 Home-page: https://github.com/EinarOlafsson/spacr
 Author: Einar Birnir Olafsson

{spacr-0.3.36 → spacr-0.3.38}/setup.py

@@ -67,7 +67,7 @@ dependencies = [
 
 setup(
     name="spacr",
-    version="0.3.36",
+    version="0.3.38",
     author="Einar Birnir Olafsson",
     author_email="olafsson@med.umich.com",
     description="Spatial phenotype analysis of crisp screens (SpaCr)",

{spacr-0.3.36 → spacr-0.3.38}/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-0.3.36 → spacr-0.3.38}/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-0.3.36 → spacr-0.3.38}/spacr/plot.py

@@ -2152,10 +2152,12 @@ class spacrGraph:
     def preprocess_data(self):
         """Preprocess the data: remove NaNs, sort/order the grouping column, and optionally group by 'prc'."""
         # Remove NaNs in both the grouping column and each data column
-        df = self.df.dropna(subset=[self.grouping_column] + self.data_column)  # Handle multiple data columns
+        df = self.df.dropna(subset=[self.grouping_column] + self.data_column)
         # Group by 'prc' column if representation is 'well'
         if self.representation == 'well':
             df = df.groupby(['prc', self.grouping_column])[self.data_column].agg(self.summary_func).reset_index()
+        if self.representation == 'plate':
+            df = df.groupby(['plate', self.grouping_column])[self.data_column].agg(self.summary_func).reset_index()
         if self.order:
             df[self.grouping_column] = pd.Categorical(df[self.grouping_column], categories=self.order, ordered=True)
         else:
@@ -2591,35 +2593,75 @@ 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 +2674,7 @@ 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-0.3.36 → spacr-0.3.38}/spacr/utils.py

@@ -5047,6 +5047,7 @@ def add_column_to_database(settings):
     """
     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.
+    NaN values will remain as NULL in the database.
     
     Parameters:
     - settings: A dictionary containing the following keys:
@@ -5060,6 +5061,11 @@ def add_column_to_database(settings):
     # Read the DataFrame from the provided CSV path
     df = pd.read_csv(settings['csv_path'])
 
+    # Replace 0 values with 2 in the update column
+    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()
@@ -5068,12 +5074,10 @@ def add_column_to_database(settings):
     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
+    # Add a suffix 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}"
@@ -5081,8 +5085,8 @@ def add_column_to_database(settings):
     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")
+    # Add the new column with INTEGER type to the database table
+    cursor.execute(f"ALTER TABLE {settings['table_name']} ADD COLUMN {new_column_name} INTEGER")
     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
@@ -5090,6 +5094,10 @@ def add_column_to_database(settings):
         value_to_update = row[settings['update_column']]
         match_value = row[settings['match_column']]
 
+        # Handle NaN values by converting them to None (SQLite equivalent of NULL)
+        if pd.isna(value_to_update):
+            value_to_update = None
+
         # Prepare and execute the SQL update query
         query = f"""
             UPDATE {settings['table_name']}
@@ -5102,7 +5110,4 @@ def add_column_to_database(settings):
     conn.commit()
     conn.close()
 
-    print(f"Updated '{new_column_name}' in '{settings['table_name']}' using '{settings['match_column']}'.")
-
-
-
+    print(f"Updated '{new_column_name}' in '{settings['table_name']}' using '{settings['match_column']}'.")

{spacr-0.3.36 → spacr-0.3.38/spacr.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: spacr
-Version: 0.3.36
+Version: 0.3.38
 Summary: Spatial phenotype analysis of crisp screens (SpaCr)
 Home-page: https://github.com/EinarOlafsson/spacr
 Author: Einar Birnir Olafsson