spacr 0.3.37__py3-none-any.whl → 0.3.41__py3-none-any.whl

spacr/toxo.py

@@ -4,8 +4,9 @@ import numpy as np
 from adjustText import adjust_text
 import pandas as pd
 from scipy.stats import fisher_exact
+from IPython.display import display
 
-def custom_volcano_plot(data_path, metadata_path, metadata_column='tagm_location', string_list=[], point_size=50, figsize=20):
+def custom_volcano_plot_v1(data_path, metadata_path, metadata_column='tagm_location', point_size=50, figsize=20, threshold=0):
     """
     Create a volcano plot with the ability to control the shape of points based on a categorical column, 
     color points based on a string list, annotate specific points based on p-value and coefficient thresholds,
@@ -19,7 +20,8 @@ def custom_volcano_plot(data_path, metadata_path, metadata_column='tagm_location
     - point_size: Fixed value to control the size of points.
     - figsize: Width of the plot (height is half the width).
     """
-    
+
+
     filename = 'volcano_plot.pdf'
     
     # Load the data
@@ -42,46 +44,65 @@ def custom_volcano_plot(data_path, metadata_path, metadata_column='tagm_location
     metadata['gene_nr'] = metadata['gene_nr'].astype(str)
     data['gene_nr'] = data['gene_nr'].astype(str)
 
+
     # Merge data and metadata on 'gene_nr'
     merged_data = pd.merge(data, metadata[['gene_nr', 'tagm_location']], on='gene_nr', how='left')
-    
-    # Controls handling
-    controls = ['000000', '000001', '000002', '000003', '000004', '000005', '000006', '000007', '000008', '000009', '000010', '000011']
-    merged_data.loc[merged_data['gene_nr'].isin(controls), metadata_column] = 'control'
+
     merged_data.loc[merged_data['gene_nr'].str.startswith('4'), metadata_column] = 'GT1_gene'
     merged_data.loc[merged_data['gene_nr'] == 'Intercept', metadata_column] = 'Intercept'
     
-    # Create a 'highlight_color' column based on the string_list
-    merged_data['highlight_color'] = merged_data['gene_nr'].apply(lambda x: 'red' if any(s in x for s in string_list) else 'blue')
-    
     # Create the volcano plot
     figsize_2 = figsize / 2
     plt.figure(figsize=(figsize_2, figsize))
+
+    palette = {
+        'pc': 'red',
+        'nc': 'green',
+        'control': 'black',
+        'other': 'gray'
+    }
+
+    merged_data['condition'] = pd.Categorical(
+        merged_data['condition'], 
+        categories=['pc', 'nc', 'control', 'other'], 
+        ordered=True
+    )
     
+    display(merged_data)
+
     # Create the scatter plot with fixed point size
     sns.scatterplot(
         data=merged_data, 
         x='coefficient', 
         y='-log10(p_value)', 
-        hue='highlight_color',
-        style=metadata_column if metadata_column else None,  # Control point shape with metadata_column
+        hue='condition',  # Controls color
+        style=metadata_column if metadata_column else None,  # Controls point shape
         s=point_size,  # Fixed size for all points
-        palette={'red': 'red', 'blue': 'blue'}
+        palette=palette,  # Color palette
+        alpha=1.0  # Transparency
     )
     
     # Set the plot title and labels
     plt.title('Custom Volcano Plot of Coefficients')
     plt.xlabel('Coefficient')
     plt.ylabel('-log10(p-value)')
+
+    if threshold > 0:
+        plt.gca().axvline(x=-abs(threshold), linestyle='--', color='black')
+        plt.gca().axvline(x=abs(threshold), linestyle='--', color='black')
     
     # Horizontal line at p-value threshold (0.05)
-    plt.axhline(y=-np.log10(0.05), color='red', linestyle='--')
+    plt.axhline(y=-np.log10(0.05), color='black', linestyle='--')
     
-    # Annotate points where p_value <= 0.05 and coefficient >= 0.25
     texts = []
     for i, row in merged_data.iterrows():
-        if row['p_value'] <= 0.05 and row['coefficient'] >= 0.25:
-            texts.append(plt.text(row['coefficient'], -np.log10(row['p_value']), row['gene_nr'], fontsize=9))
+        if row['p_value'] <= 0.05 and abs(row['coefficient']) >= abs(threshold):
+            texts.append(plt.text(
+                row['coefficient'], 
+                -np.log10(row['p_value']), 
+                row['variable'], 
+                fontsize=8
+            ))
     
     # Adjust text positions to avoid overlap
     adjust_text(texts, arrowprops=dict(arrowstyle='-', color='black'))
@@ -96,6 +117,171 @@ def custom_volcano_plot(data_path, metadata_path, metadata_column='tagm_location
     # Show the plot
     plt.show()
 
+def custom_volcano_plot(data_path, metadata_path, metadata_column='tagm_location', point_size=50, figsize=20, threshold=0, split_axis_lims = [10, None, None, 10]):
+    """
+    Create a volcano plot with the ability to control the shape of points based on a categorical column,
+    color points based on a condition, annotate specific points based on p-value and coefficient thresholds,
+    and control the size of points.
+    """
+
+    filename = 'volcano_plot.pdf'
+
+    # Load the data
+    if isinstance(data_path, pd.DataFrame):
+        data = data_path
+    else:
+        data = pd.read_csv(data_path)
+        
+    data['variable'] = data['feature'].str.extract(r'\[(.*?)\]')
+    data['variable'].fillna(data['feature'], inplace=True)
+    split_columns = data['variable'].str.split('_', expand=True)
+    data['gene_nr'] = split_columns[0]
+
+    # Load metadata
+    if isinstance(metadata_path, pd.DataFrame):
+        metadata = metadata_path
+    else:
+        metadata = pd.read_csv(metadata_path)
+
+    metadata['gene_nr'] = metadata['gene_nr'].astype(str)
+    data['gene_nr'] = data['gene_nr'].astype(str)
+
+    # Merge data and metadata on 'gene_nr'
+    merged_data = pd.merge(data, metadata[['gene_nr', 'tagm_location']], on='gene_nr', how='left')
+
+    merged_data.loc[merged_data['gene_nr'].str.startswith('4'), metadata_column] = 'GT1_gene'
+    merged_data.loc[merged_data['gene_nr'] == 'Intercept', metadata_column] = 'Intercept'
+    merged_data.loc[merged_data['condition'] == 'control', metadata_column] = 'control'
+
+    # Categorize condition for coloring
+    merged_data['condition'] = pd.Categorical(
+        merged_data['condition'],
+        categories=['other','pc', 'nc', 'control'],
+        ordered=True)
+
+    # Create subplots with a broken y-axis
+    figsize_2 = figsize / 2
+    fig, (ax1, ax2) = plt.subplots(
+        2, 1, figsize=(figsize_2, figsize), 
+        sharex=True, gridspec_kw={'height_ratios': [1, 3]}
+    )
+
+    # Define color palette
+    palette = {
+        'pc': 'red',
+        'nc': 'green',
+        'control': 'white',
+        'other': 'gray'}
+
+    # Scatter plot on both axes
+    sns.scatterplot(
+        data=merged_data,
+        x='coefficient',
+        y='-log10(p_value)',
+        hue='condition',
+        style=metadata_column if metadata_column else None,
+        s=point_size,
+        edgecolor='black', 
+        palette=palette,
+        alpha=0.8,
+        ax=ax2  # Lower plot
+    )
+
+    sns.scatterplot(
+        data=merged_data[merged_data['-log10(p_value)'] > 10],
+        x='coefficient',
+        y='-log10(p_value)',
+        hue='condition',
+        style=metadata_column if metadata_column else None,
+        s=point_size,
+        palette=palette,
+        edgecolor='black', 
+        alpha=0.8,
+        ax=ax1  # Upper plot
+    )
+
+    if isinstance(split_axis_lims, list):
+        if len(split_axis_lims) == 4:
+            ylim_min_ax1 = split_axis_lims[0]
+            if split_axis_lims[1] is None:
+                ylim_max_ax1 = merged_data['-log10(p_value)'].max() + 5
+            else:
+                ylim_max_ax1 = split_axis_lims[1]
+            ylim_min_ax2 = split_axis_lims[2]
+            ylim_max_ax2 = split_axis_lims[3]
+        else:
+            ylim_min_ax1 = None
+            ylim_max_ax1 = merged_data['-log10(p_value)'].max() + 5
+            ylim_min_ax2 = 0
+            ylim_max_ax2 = None
+
+    # Set axis limits and hide unnecessary parts
+    ax1.set_ylim(ylim_min_ax1, ylim_max_ax1)
+    ax2.set_ylim(0, ylim_max_ax2)
+    ax1.spines['bottom'].set_visible(False)
+    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.tick_params(axis='x', which='both', bottom=False, top=False, labelbottom=False)
+
+    # Add vertical threshold lines to both plots
+    if threshold > 0:
+        for ax in (ax1, ax2):
+            ax.axvline(x=-abs(threshold), linestyle='--', color='black')
+            ax.axvline(x=abs(threshold), linestyle='--', color='black')
+
+    # Add a horizontal line at p-value threshold (0.05)
+    ax2.axhline(y=-np.log10(0.05), color='black', linestyle='--')
+
+    # Annotate significant points on both axes
+    texts_ax1 = []
+    texts_ax2 = []
+
+    for i, row in merged_data.iterrows():
+        if row['p_value'] <= 0.05 and abs(row['coefficient']) >= abs(threshold):
+            # Select the appropriate axis for the annotation
+            #ax = ax1 if row['-log10(p_value)'] > 10 else ax2
+
+            ax = ax1 if row['-log10(p_value)'] >= ax1.get_ylim()[0] else ax2
+
+
+            # Create the annotation on the selected axis
+            text = ax.text(
+                row['coefficient'],
+                -np.log10(row['p_value']),
+                row['variable'],
+                fontsize=8,
+                ha='center',
+                va='bottom',
+            )
+
+            # Store the text annotation in the correct list
+            if ax == ax1:
+                texts_ax1.append(text)
+            else:
+                texts_ax2.append(text)
+
+    # Adjust text positions to avoid overlap for both axes
+    adjust_text(texts_ax1, arrowprops=dict(arrowstyle='-', color='black'), ax=ax1)
+    adjust_text(texts_ax2, arrowprops=dict(arrowstyle='-', color='black'), ax=ax2)
+
+    # Move the legend outside the lower plot
+    ax2.legend(bbox_to_anchor=(1.05, 1), loc='upper left', borderaxespad=0.)
+
+    # Adjust the spacing between subplots and move the title
+    plt.subplots_adjust(hspace=0.05)
+    fig.suptitle('Custom Volcano Plot of Coefficients', y=1.02, fontsize=16)  # Title above the top plot
+
+    # Save the plot as PDF
+    plt.savefig(filename, format='pdf', bbox_inches='tight')
+    print(f'Saved Volcano plot: {filename}')
+
+    # Show the plot
+    plt.show()
+
 def go_term_enrichment_by_column(significant_df, metadata_path, go_term_columns=['Computed GO Processes', 'Curated GO Components', 'Curated GO Functions', 'Curated GO Processes']):
     """
     Perform GO term enrichment analysis for each GO term column and generate plots.

spacr/utils.py

@@ -326,6 +326,8 @@ def save_settings(settings, name='settings', show=False):
     
     if isinstance(settings['src'], list):
         src = settings['src'][0]
+        #if os.path.exists(src):
+
         name = f"{name}_list"
     else:
         src = settings['src']
@@ -4712,10 +4714,10 @@ def merge_regression_res_with_metadata(results_file, metadata_file, name='_metad
     df_metadata['gene'] = df_metadata['Gene ID'].apply(lambda x: x.split('_')[1] if '_' in x else None)
     
     # Drop rows where gene extraction failed
-    df_results = df_results.dropna(subset=['gene'])
+    #df_results = df_results.dropna(subset=['gene'])
     
     # Merge the two dataframes on the gene column
-    merged_df = pd.merge(df_results, df_metadata, on='gene')
+    merged_df = pd.merge(df_results, df_metadata, on='gene', how='left')
     
     # Generate the new file name
     base, ext = os.path.splitext(results_file)
@@ -5047,6 +5049,7 @@ 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:
@@ -5060,7 +5063,7 @@ def add_column_to_database(settings):
     # 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
+    # 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)
@@ -5073,12 +5076,10 @@ 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}"
@@ -5086,8 +5087,8 @@ 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
@@ -5095,6 +5096,10 @@ 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']}
@@ -5107,7 +5112,4 @@ 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-0.3.37.dist-info → spacr-0.3.41.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: spacr
-Version: 0.3.37
+Version: 0.3.41
 Summary: Spatial phenotype analysis of crisp screens (SpaCr)
 Home-page: https://github.com/EinarOlafsson/spacr
 Author: Einar Birnir Olafsson

{spacr-0.3.37.dist-info → spacr-0.3.41.dist-info}/RECORD

@@ -8,26 +8,26 @@ spacr/app_measure.py,sha256=_K7APYIeOKpV6e_LcqabBjvEi7mfq9Fch8175x1x0k8,162
 spacr/app_sequencing.py,sha256=DjG26jy4cpddnV8WOOAIiExtOe9MleVMY4MFa5uTo5w,157
 spacr/app_umap.py,sha256=ZWAmf_OsIKbYvolYuWPMYhdlVe-n2CADoJulAizMiEo,153
 spacr/cellpose.py,sha256=zv4BzhaP2O-mtQ-pUfYvpOyxgn1ke_bDWgdHD5UWm9I,13942
-spacr/core.py,sha256=G_x-w7FRIHNfSOoPaIZPSf_A7mVj7PA7o9HQZ4nIu5o,48231
+spacr/core.py,sha256=dW9RrAKFLfVsFhX0-kaVMc2T7b47Ky0pTXK-CEVOeWQ,48235
 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=w-S1MZdyxt5O3DsNAHNNXy_WGfwBPg0NhwQtCsJeiao,137071
 spacr/gui_utils.py,sha256=7e9DsZIuV7-jh97kEf7v1In_cFzlFueV4SGcGYGpTxw,45454
-spacr/io.py,sha256=AARmqn1fMmTgVDwWy8bEYK6SjH-6DZIulgCSPdBTyf0,143370
+spacr/io.py,sha256=LN_gJq_oqjbf8y-lBtLLZtJi8DLbNdyoGEcBYyOjbhQ,143606
 spacr/logger.py,sha256=lJhTqt-_wfAunCPl93xE65Wr9Y1oIHJWaZMjunHUeIw,1538
 spacr/measure.py,sha256=BThn_sALgKrwGKnLOGpT4FyoJeRVoTZoP9SXbCtCMRw,54857
 spacr/mediar.py,sha256=FwLvbLQW5LQzPgvJZG8Lw7GniA2vbZx6Jv6vIKu7I5c,14743
-spacr/ml.py,sha256=ItibDL_q0cKwEsJdwpBtVqfpRQGPXGbb0BX5UB5iH5s,49342
+spacr/ml.py,sha256=e6nUQaiKBPwcDN_aZZKsbZG6qEa5k9B42wtuL8ipv3Q,50287
 spacr/openai.py,sha256=5vBZ3Jl2llYcW3oaTEXgdyCB2aJujMUIO5K038z7w_A,1246
-spacr/plot.py,sha256=QYj2bV0-6UqKRTWeSj3eOOgr6dNMmCCc4TdRGTniQ4c,118083
+spacr/plot.py,sha256=TDGMwiIHjvk6v94WFlIvemU-6JfEik_GmSez51vyvCc,135869
 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=3SBf5yeeU3u9MVsIWeYmcHjhwqs8LJ6m9UF0wBSNq8M,216304
+spacr/toxo.py,sha256=7dUJe5_HSvDCP16OIXtbYLyshh9LXb2JQ80Vtn-XdPk,15979
+spacr/utils.py,sha256=_8OxwGVCZaMNBiweB4_YOxBkqQX1LR9YstPSIFmeQKA,216420
 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-0.3.37.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,,
+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,,