LCNE-patchseq-analysis 0.24.2__tar.gz → 0.26.0__tar.gz

{lcne_patchseq_analysis-0.24.2 → lcne_patchseq_analysis-0.26.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: LCNE-patchseq-analysis
-Version: 0.24.2
+Version: 0.26.0
 Summary: Generated from aind-library-template
 Author: Allen Institute for Neural Dynamics
 Author-email: Han Hou <han.hou@alleninstitute.org>
@@ -70,7 +70,7 @@ Dynamic: license-file
 [![License](https://img.shields.io/badge/license-MIT-brightgreen)](LICENSE)
 ![Code Style](https://img.shields.io/badge/code%20style-black-black)
 [![semantic-release: angular](https://img.shields.io/badge/semantic--release-angular-e10079?logo=semantic-release)](https://github.com/semantic-release/semantic-release)
-![Interrogate](https://img.shields.io/badge/interrogate-90.5%25-brightgreen)
+![Interrogate](https://img.shields.io/badge/interrogate-90.6%25-brightgreen)
 ![Coverage](https://img.shields.io/badge/coverage-100%25-brightgreen?logo=codecov)
 ![Python](https://img.shields.io/badge/python->=3.9-blue?logo=python)
 

{lcne_patchseq_analysis-0.24.2 → lcne_patchseq_analysis-0.26.0}/README.md

@@ -3,7 +3,7 @@
 [![License](https://img.shields.io/badge/license-MIT-brightgreen)](LICENSE)
 ![Code Style](https://img.shields.io/badge/code%20style-black-black)
 [![semantic-release: angular](https://img.shields.io/badge/semantic--release-angular-e10079?logo=semantic-release)](https://github.com/semantic-release/semantic-release)
-![Interrogate](https://img.shields.io/badge/interrogate-90.5%25-brightgreen)
+![Interrogate](https://img.shields.io/badge/interrogate-90.6%25-brightgreen)
 ![Coverage](https://img.shields.io/badge/coverage-100%25-brightgreen?logo=codecov)
 ![Python](https://img.shields.io/badge/python->=3.9-blue?logo=python)
 

{lcne_patchseq_analysis-0.24.2 → lcne_patchseq_analysis-0.26.0}/src/LCNE_patchseq_analysis/__init__.py

@@ -6,12 +6,12 @@ import os
 logger = logging.getLogger(__name__)
 
 
-__version__ = "0.24.2"
+__version__ = "0.26.0"
 
 # Get the path of this file
 PACKAGE_DIRECTORY = os.path.dirname(os.path.abspath(__file__))
 if os.name == "posix":  # Mac/Linux
-    RAW_DIRECTORY = os.path.join(PACKAGE_DIRECTORY, "../../data/LCNE-patchseq-ephys/raw/")
+    RAW_DIRECTORY = "/Users/han.hou/Scripts/LCNE-patchseq-analysis/data/LCNE-patchseq-ephys/raw"
 else:  # Windows
     RAW_DIRECTORY = os.path.join(R"E:\s3\aind-patchseq-data\raw")
 RESULTS_DIRECTORY = os.path.join(PACKAGE_DIRECTORY, "../../results/")

{lcne_patchseq_analysis-0.24.2 → lcne_patchseq_analysis-0.26.0}/src/LCNE_patchseq_analysis/figures/fig_3a.py

@@ -70,7 +70,7 @@ def figure_3a_ccf_projection(if_save_fig: bool = True) -> tuple:
         ax.scatter(region_data['x'], region_data['y'], 
                   c=region_colors[i], alpha=0.7, s=50, 
                   edgecolors='black', linewidth=0.5,
-                  label=f'{region} (n={len(region_data)})')
+                  label=f'{region} (n={len(region_data)}, {region_data["x"].isnull().sum()} missing data)')
     
     # Add labels and title
     ax.set_xlabel('X Coordinate (μm)', fontsize=12)
@@ -111,10 +111,6 @@ def figure_3a_ccf_projection(if_save_fig: bool = True) -> tuple:
     # Print summary statistics
     logger.info("\nSummary statistics:")
     logger.info(f"- Total filtered cells: {len(df_filtered)}")
-    if len(df_filtered) > 0:
-        logger.info(f"- X coordinate range: {df_filtered['x'].min():.1f} to {df_filtered['x'].max():.1f}")
-        logger.info(f"- Y coordinate range: {df_filtered['y'].min():.1f} to {df_filtered['y'].max():.1f}")
-        logger.info(f"- Injection regions: {', '.join(unique_regions)}")
     
     return fig, ax, df_filtered
 

{lcne_patchseq_analysis-0.24.2 → lcne_patchseq_analysis-0.26.0}/src/LCNE_patchseq_analysis/pipeline_util/ephys.py

@@ -97,5 +97,5 @@ if __name__ == "__main__":
     logging.basicConfig(level=logging.DEBUG)
 
     trigger_patchseq_upload(
-        os.path.expanduser(R"~\Downloads\IVSCC_LC_summary.xlsx"), upload_raw_data=False
+        os.path.expanduser(R"~\Downloads\IVSCC_LC_summary_0709.xlsx"), upload_raw_data=False
     )

{lcne_patchseq_analysis-0.24.2 → lcne_patchseq_analysis-0.26.0}/src/LCNE_patchseq_analysis/pipeline_util/metadata.py

@@ -34,7 +34,7 @@ def read_brian_spreadsheet(file_path=metadata_path, add_lims=True):
     df_tab_master = pd.read_excel(file_path, sheet_name=tab_master)
 
     # Get ephys features
-    tab_ephys_fx = "ipfx_ephys_fx_250611"
+    tab_ephys_fx = "ipfx_ephys_250709"
     df_tab_ephys_fx = pd.read_excel(file_path, sheet_name=tab_ephys_fx)
 
     # Add "ipfx_" prefix to ephys_fx columns except for "cell_specimen_id"
@@ -49,7 +49,7 @@ def read_brian_spreadsheet(file_path=metadata_path, add_lims=True):
         how="outer",
         suffixes=("_tab_master", "_tab_ephys_fx"),
     ).sort_values("Date", ascending=False)
-
+    
     if add_lims:
         logger.info("Querying and adding LIMS data...")
         df_lims = get_lims_LCNE_patchseq()
@@ -114,6 +114,17 @@ def read_brian_spreadsheet(file_path=metadata_path, add_lims=True):
             right_on="cell_specimen_id",
             how="left",
         )
+        
+    # Logging the latest cell that has a column and the total number of cells with that column
+    column_to_log = ["recording_date", "x", "ipfx_tau"]
+    for col in column_to_log:
+        if col in df_merged.columns:
+            last_date = df_merged.loc[df_merged[col].notnull(), "Date"].max()
+            total_cells = df_merged[col].notnull().sum()
+            logger.info(
+                f"Last date with {col}: {last_date}, "
+                f"Total cells with {col}: {total_cells}"
+            )
 
     return {
         "df_merged": df_merged,

{lcne_patchseq_analysis-0.24.2 → lcne_patchseq_analysis-0.26.0}/src/LCNE_patchseq_analysis/pipeline_util/sequencing.py

@@ -14,16 +14,23 @@ logger = logging.getLogger(__name__)
 
 # Define the preselected columns of interest
 SEQ_COLUMNS = [
-    # Coordinates and clusters
+    # --- New columns added in 0620 ---
+    "RNA_QC", # RNA quality control score
+    "imp_pscores",  # Imputed pseudocluster scores
+
+    # --- Imputation to other experiments ---
     "imp_ML",
     "imp_DV",
     "imp_AP",
     "imp_pseudoclusters",
-    # Noradrenergic markers
+
+    # --- Noradrenergic markers ---
     "Dbh",  # Dopamine beta-hydroxylase
     "Th",  # Tyrosine hydroxylase
     "Slc18a2",  # Vesicular monoamine transporter 2 (VMAT2)
     "Slc6a2",  # Norepinephrine transporter (NET)
+
+    # --- Active ion channels ---
     # Sodium channels (important for action potential initiation and upstroke)
     "Scn1a",  # Nav1.1, important for AP initiation
     "Scn2a",  # Nav1.2, expressed in axon initial segment
@@ -46,8 +53,41 @@ SEQ_COLUMNS = [
     # HCN channels (important for pacemaking and resonance)
     "Hcn1",  # Fast-activating HCN, affects rebound spiking
     "Hcn2",  # Slower-activating HCN, contributes to resonance
+    "Hcn3", 
     "Hcn4",  # Slowest-activating HCN, important in pacemaking
-    # Other common markers
+
+    # --- Leak channels and other important channels ---
+    # K2P (Two-pore-domain potassium) leak channels
+    "Kcnk1",  # TWIK-1, weak inward-rectifying K+ leak channel
+    "Kcnk2",  # TREK-1, mechanosensitive and temperature-sensitive K2P channel
+    "Kcnk3",  # TASK-1, pH-sensitive background K+ current
+    "Kcnk4",  # TRAAK, mechanosensitive leak K+ channel
+    "Kcnk9",  # TASK-3, regulates resting potential and excitability
+    "Kcnk10",  # TREK-2, contributes to leak K+ conductance
+    # Sodium leak channels and associated regulators
+    "Nalcn",  # Na+ leak channel, controls resting Na+ conductance and excitability
+    "Unc79",  # NALCN complex component
+    "Unc80",  # NALCN complex component
+    "Fam155a",  # Regulatory subunit of NALCN complex
+    # Chloride leak channels
+    "Clcn2",  # Voltage-gated Cl- channel, contributes to inhibitory tone
+
+    # Inward-rectifier and GPCR-modulated K+ channels (affect resting potential)
+    "Kcnj2",  # Kir2.1, stabilizes resting membrane potential
+    "Kcnj10",  # Kir4.1, highly expressed in glia and neurons, contributes to K+ buffering
+    "Kcnj3",  # GIRK1, G-protein-regulated inward-rectifying K+ channel
+    "Kcnj6",  # GIRK2, major component of GIRK channels in CNS
+
+    # --- Gap junctions and connexins ---
+    # Gap junction–related genes (CNS)
+    "Gja1",  # Connexin 43, major astrocytic gap junction protein
+    "Gjb6",  # Connexin 30, co-expressed with Gja1 in glia
+    "Gjd2",  # Connexin 36, neuronal gap junction, key for electrical synapses
+    "Gjd3",  # Connexin 31.9, expressed in some CNS neurons
+    "Panx1",  # Pannexin 1, forms large-pore channels in neurons and glia
+    "Panx2",  # Pannexin 2, CNS-specific, neuron-enriched
+
+    # --- Other common markers ---
     "Slc17a7",  # Excitatory marker
     "Gad1",  # Inhibitory marker
     "Sst",  # Somatostatin
@@ -80,8 +120,8 @@ def extract_preselected_columns():
     src_dir = src_dir.resolve()
     dst_dir = dst_dir.resolve()
 
-    src_file = src_dir / "log_normed_df.csv"
-    id_mapping_file = src_dir / "exp_component_ids_for_han.csv"  # Aux file for mapping ids
+    src_file = src_dir / "log_normed_df_more_0620.csv"
+    id_mapping_file = src_dir / "exp_component_ids_for_han_0620.csv"  # Aux file for mapping ids
     dst_file = dst_dir / "seq_preselected.csv"
 
     logger.info(f"Reading log-normalized data from {src_file}")

{lcne_patchseq_analysis-0.24.2 → lcne_patchseq_analysis-0.26.0}/src/LCNE_patchseq_analysis/population_analysis/filters.py

@@ -33,6 +33,13 @@ q_mapmycells_dbh = 'mapmycells_subclass_name.str.contains("DBH", case=False, na=
 q_mapmycells_has_data = (
     "mapmycells_subclass_name == mapmycells_subclass_name"  # True for non-NaN values
 )
+
+q_nucleus_present = '`jem-nucleus_post_patch` == "nucleus_present"'
+q_nucleus_present_has_data = '`jem-nucleus_post_patch` == `jem-nucleus_post_patch`'
+
+q_RNA_QC = '`gene_RNA_QC (log_normed)` == True'
+q_RNA_QC_has_data = '`gene_RNA_QC (log_normed)` == `gene_RNA_QC (log_normed)`'
+
 q_retro = '`injection region` != "Non-Retro"'
 
 
@@ -63,8 +70,10 @@ def create_filter_conditions(df_meta):
         "Fluorescence": [if_fluorescence_positive, if_fluorescence_has_data],
         "Marker Gene Any Positive": [if_marker_gene_any_positive, if_marker_gene_has_data],
         "Marker Gene All Positive": [if_marker_gene_all_positive, if_marker_gene_has_data],
-        "Marker Gene DBH Positive": [if_marker_gene_dbh_positive, if_marker_gene_has_data],
-        "Is DBH Subclass": [if_mapmycells_dbh, if_mapmycells_has_data],
+        "Marker Gene Dbh Positive": [if_marker_gene_dbh_positive, if_marker_gene_has_data],
+        "MapMyCells Dbh Subclass": [if_mapmycells_dbh, if_mapmycells_has_data],
+        "RNA QC": [df_meta.eval(q_RNA_QC), df_meta.eval(q_RNA_QC_has_data)],
+        "Nucleus Present": [df_meta.eval(q_nucleus_present), df_meta.eval(q_nucleus_present_has_data)],
     }
 
     return condition_mapper
@@ -109,25 +118,51 @@ def compute_confusion_matrix(condition_mapper, name1, name2):
     print(f"Any of them does not have data: {unknown.sum()}")
     return confusion_matrix
 
-def plot_venn_three_filters(filter1, filter2, filter3, labels=("Filter 1", "Filter 2", "Filter 3"), ax=None):
+
+def plot_venn_three_filters(condition_mapper, to_compare: list, ax=None):
     """
-    Plot a Venn diagram for three boolean filters or sets.
-    Accepts either boolean arrays (same length) or sets of indices.
+    Plot a Venn diagram for three boolean filters from condition_mapper.
+    
+    Parameters:
+    -----------
+    condition_mapper : dict
+        Dictionary mapping filter names to [positive_condition, has_data_condition] pairs
+    to_compare : list
+        List of 3 filter names to compare (must be keys in condition_mapper)
+    ax : matplotlib.axes.Axes, optional
+        Axes to plot on. If None, creates new figure and axes.
+        
+    Returns:
+    --------
+    matplotlib.axes.Axes
+        The axes containing the plot
     """
-    # Convert boolean arrays to sets of indices if needed
+    if len(to_compare) != 3:
+        raise ValueError("to_compare must contain exactly 3 filter names")
+
+    # Get the positive conditions (first element) for each filter
+    filter1 = condition_mapper[to_compare[0]][0]  # positive condition
+    filter2 = condition_mapper[to_compare[1]][0]  # positive condition  
+    filter3 = condition_mapper[to_compare[2]][0]  # positive condition
+
+    # Convert boolean arrays to sets of indices
     def to_set(f):
         if isinstance(f, (pd.Series, np.ndarray)) and f.dtype == bool:
-            return set(np.where(f)[0])
+            return set(np.flatnonzero(f))
         elif isinstance(f, (pd.Series, np.ndarray)):
             return set(f)
         elif isinstance(f, set):
             return f
         else:
             return set(list(f))
+
     set1, set2, set3 = to_set(filter1), to_set(filter2), to_set(filter3)
+
     if ax is None:
         fig, ax = plt.subplots(figsize=(6, 6), dpi=300)
 
+    # Use the filter names as labels
+    labels = to_compare
     v = venn3([set1, set2, set3], set_labels=labels, ax=ax)
     c = venn3_circles([set1, set2, set3], ax=ax)
 
@@ -135,11 +170,45 @@ def plot_venn_three_filters(filter1, filter2, filter3, labels=("Filter 1", "Filt
     for i, color in enumerate(("black", "blue", "green")):
         c[i].set_edgecolor(color)
         v.get_label_by_id(["A", "B", "C"][i]).set_color(color)
-    
+
     # Clear all patch color
     for patch in v.patches:
         if patch:  # Some patches might be None
             patch.set_facecolor('none')
 
-
     return ax
+
+
+def plot_venn_summary(
+    df_lists,
+    compare_lists=[
+        ["Fluorescence", "Marker Gene Dbh Positive", "MapMyCells Dbh Subclass"],
+        ["Fluorescence", "Marker Gene All Positive", "MapMyCells Dbh Subclass"],
+        ["Fluorescence", "Marker Gene Any Positive", "MapMyCells Dbh Subclass"],
+        ["RNA QC", "Nucleus Present", "MapMyCells Dbh Subclass"],
+    ],
+):
+    """
+    Plot a summary of Venn diagrams for multiple DataFrames and filter conditions.
+
+    Parameters:
+    -----------
+    df_lists : list of pd.DataFrame
+        List of DataFrames containing metadata for different cell populations
+    compare_lists : list of list of str, optional
+        List of filter names to compare in Venn diagrams. Default includes common filters.
+
+    Returns:
+    --------
+    matplotlib.figure.Figure
+        Figure containing the Venn diagrams for each comparison.
+    """
+    fig, ax = plt.subplots(len(compare_lists), 2, figsize=(12, len(compare_lists) * 4), dpi=200)
+
+    for i, df in enumerate(df_lists):
+        condition_mapper = create_filter_conditions(df)
+        for j, filters in enumerate(compare_lists):
+            plot_venn_three_filters(condition_mapper, filters, ax=ax[j, i])
+
+    plt.tight_layout()
+    return fig

{lcne_patchseq_analysis-0.24.2 → lcne_patchseq_analysis-0.26.0}/src/LCNE_patchseq_analysis.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: LCNE-patchseq-analysis
-Version: 0.24.2
+Version: 0.26.0
 Summary: Generated from aind-library-template
 Author: Allen Institute for Neural Dynamics
 Author-email: Han Hou <han.hou@alleninstitute.org>
@@ -70,7 +70,7 @@ Dynamic: license-file
 [![License](https://img.shields.io/badge/license-MIT-brightgreen)](LICENSE)
 ![Code Style](https://img.shields.io/badge/code%20style-black-black)
 [![semantic-release: angular](https://img.shields.io/badge/semantic--release-angular-e10079?logo=semantic-release)](https://github.com/semantic-release/semantic-release)
-![Interrogate](https://img.shields.io/badge/interrogate-90.5%25-brightgreen)
+![Interrogate](https://img.shields.io/badge/interrogate-90.6%25-brightgreen)
 ![Coverage](https://img.shields.io/badge/coverage-100%25-brightgreen?logo=codecov)
 ![Python](https://img.shields.io/badge/python->=3.9-blue?logo=python)