scMultiChat 0.1.2__tar.gz → 0.2.0__tar.gz

{scmultichat-0.1.2 → scmultichat-0.2.0}/MultiChat/Plot/Visualization.py

@@ -11,6 +11,7 @@ from itertools import product
 from scipy import stats
 
 
+
    
 
 def get_sender_adj(Nei_adj, cell_type):
@@ -861,23 +862,23 @@ def plot_two_hop_signaling(
 
     # background cells
     plt.scatter(
-        coord_df['y'],
         coord_df['x'],
+        coord_df['y'],
         c=coord_df['color'],
         alpha=alpha,
         s=point_size,
         linewidths=0
     )
 
-    plt.gca().invert_yaxis()
+    # plt.gca().invert_yaxis()
 
     # first hop (X → Relay)
     for _, row in cur_xr.iterrows():
         lw = max(0.5, row['score'] * arrow_scale)
 
         arrow = FancyArrowPatch(
-            (row['sender_y'], row['sender_x']),
-            (row['receiver_y'], row['receiver_x']),
+            (row['sender_x'], row['sender_y']),
+            (row['receiver_x'], row['receiver_y']),
             connectionstyle=f"arc3,rad={rad}",
             arrowstyle=ArrowStyle("Simple", head_length=1.8, head_width=2, tail_width=0.01),
             color='#13393E',
@@ -891,8 +892,8 @@ def plot_two_hop_signaling(
         lw = max(0.5, row['score'] * arrow_scale)
 
         arrow = FancyArrowPatch(
-            (row['sender_y'], row['sender_x']),
-            (row['receiver_y'], row['receiver_x']),
+            (row['sender_x'], row['sender_y']),
+            (row['receiver_x'], row['receiver_y']),
             connectionstyle=f"arc3,rad={rad}",
             arrowstyle=ArrowStyle("Simple", head_length=1.8, head_width=2, tail_width=0.01),
             color='#B32142',
@@ -1043,4 +1044,463 @@ def plot_effective_two_hop_signaling(
     # ===== 8. Title =====
     plt.title(f'Effective two-hop signaling: \n{pair1} → {pair2}')
 
-    plt.show()
+    plt.show()
+
+
+def build_gene_relay_two_hop_events(sig_path, focus_gene):
+    """
+    Build two-hop signaling events centered on a focus gene.
+
+    Logic:
+    1. First hop:  X -> Relay, where path_symbol ends with focus_gene.
+    2. Second hop: Relay -> Y, where path_symbol starts with focus_gene.
+    3. Merge by Relay cell.
+
+    Parameters
+    ----------
+    sig_path : pd.DataFrame
+        Significant signaling path table.
+        Required columns:
+        from_cell, to_cell, source, target, path_symbol, comm_score, z_score
+
+    focus_gene : str
+        Focus gene used as relay signaling molecule, e.g. 'Hgf'.
+
+    Returns
+    -------
+    merged_df : pd.DataFrame
+        Two-hop signaling events joined by relay cell.
+    """
+
+    # First hop: upstream signal ending with focus_gene
+    one_hop_sig_path = sig_path[
+        sig_path["path_symbol"].str.endswith(focus_gene, na=False)
+    ].copy()
+
+    # Second hop: downstream signal starting with focus_gene
+    two_hop_sig_path = sig_path[
+        sig_path["path_symbol"].str.startswith(focus_gene, na=False)
+    ].copy()
+
+    one_hop_sig_path.rename(
+        columns={
+            "from_cell": "X_name",
+            "to_cell": "Relay_name",
+            "source": "X_Source",
+            "target": "Relay_Target",
+            "path_symbol": "X_Path_Symbol",
+            "comm_score": "X_Comm_Score",
+            "z_score": "X_Z_Score",
+        },
+        inplace=True
+    )
+
+    merged_df = pd.merge(
+        left=one_hop_sig_path,
+        right=two_hop_sig_path,
+        left_on="Relay_name",
+        right_on="from_cell",
+        how="inner"
+    )
+
+    return merged_df
+
+
+def plot_two_hop_cell_identity(
+    focus_gene,
+    base_path=None,
+    coord_df=None,
+    coord=None,
+    cell_type=None,
+    color_map=None,
+    merged_df=None,
+    figsize=(18, 5),
+    bg_color="#D3D3D3",
+    bg_size=15,
+    bg_alpha=1,
+    role_size=25,
+    role_alpha=0.8
+):
+    """
+    Plot source / relay / target cell identities for two-hop signaling events.
+
+    Parameters
+    ----------
+    focus_gene : str
+        Gene name, e.g. 'Vegfa'.
+    base_path : str
+        Dataset base path.
+    coord_df : pd.DataFrame, optional
+        Coordinate dataframe with x, y, color columns.
+    coord : pd.DataFrame, optional
+        Coordinate dataframe with x, y columns. Used when coord_df is not given.
+    cell_type : pd.DataFrame, optional
+        Cell type annotation with column 'cell_type'. Used when coord_df is not given.
+    color_map : dict, optional
+        Cell type color map. Used when coord_df is not given.
+    merged_df : pd.DataFrame, optional
+        Preloaded merged two-hop event dataframe.
+    """
+
+    # ===== Load merged two-hop event data =====
+    if merged_df is None:
+        if base_path is None:
+            raise ValueError("Please provide either merged_df or base_path + focus_gene.")
+        else:
+            print("Loading merged two-hop event data...")
+            merged_file = os.path.join(base_path,  f"{focus_gene}_merged_data.csv")
+            merged_df = pd.read_csv(merged_file)
+
+    df = merged_df.copy()
+
+    # ===== Build coord_df if not provided =====
+    if coord_df is None:
+        if coord is None or cell_type is None or color_map is None:
+            raise ValueError("Please provide either coord_df, or coord + cell_type + color_map.")
+
+        coord_df = coord.copy()
+
+        if "cell_type" not in cell_type.columns and "celltype" in cell_type.columns:
+            cell_type = cell_type.rename(columns={"celltype": "cell_type"})
+
+        coord_df["color"] = cell_type.loc[coord_df.index, "cell_type"].map(color_map)
+
+    # ===== Compatible column names =====
+    source_col = "X_name" if "X_name" in df.columns else "X_Name"
+    relay_col = "Relay_name" if "Relay_name" in df.columns else "Relay_Name"
+
+    if "to_cell" in df.columns:
+        target_col = "to_cell"
+    elif "Y_name" in df.columns:
+        target_col = "Y_name"
+    else:
+        target_col = "Y_Name"
+
+    # ===== Extract cells =====
+    source_cells = set(df[source_col].dropna())
+    relay_cells = set(df[relay_col].dropna())
+    target_cells = set(df[target_col].dropna())
+
+    # ===== Add role flags =====
+    plot_df = coord_df.copy()
+    plot_df["is_source"] = plot_df.index.isin(source_cells)
+    plot_df["is_relay"] = plot_df.index.isin(relay_cells)
+    plot_df["is_target"] = plot_df.index.isin(target_cells)
+
+    print("source cells:", plot_df["is_source"].sum())
+    print("relay cells:", plot_df["is_relay"].sum())
+    print("target cells:", plot_df["is_target"].sum())
+
+    # ===== Plot =====
+    fig, axes = plt.subplots(1, 3, figsize=figsize)
+
+    role_info = [
+        ("Source", "is_source"),
+        ("Relay", "is_relay"),
+        ("Target", "is_target"),
+    ]
+
+    for ax, (title, flag) in zip(axes, role_info):
+        ax.scatter(
+            plot_df["x"], plot_df["y"],
+            color=bg_color,
+            s=bg_size,
+            alpha=bg_alpha
+        )
+
+        sub = plot_df[plot_df[flag]]
+
+        ax.scatter(
+            sub["x"], sub["y"],
+            c=sub["color"],
+            s=role_size,
+            alpha=role_alpha
+        )
+
+        # ax.invert_yaxis()
+        ax.set_title(title)
+        ax.set_xlabel("X")
+        ax.set_ylabel("Y")
+
+    plt.tight_layout()
+    plt.show()
+
+    return plot_df, fig, axes
+
+
+def plot_two_hop_cell_identity_combined(
+    focus_gene,
+    base_path=None,
+    coord_df=None,
+    coord=None,
+    cell_type=None,
+    color_map=None,
+    merged_df=None,
+    figsize=(6, 5),
+    bg_color="#D3D3D3",
+    bg_size=15,
+    bg_alpha=1,
+    marker_map=None,
+    size_map=None,
+    linewidth_map=None,
+    role_color_map=None,
+    role_alpha=0.9,
+    invert_yaxis=False,
+    save=False,
+    fig_dir=None
+):
+    """
+    Plot source / relay / target cell identities in one combined panel.
+
+    Parameters
+    ----------
+    focus_gene : str
+        Gene name, e.g. 'Vegfa'.
+    base_path : str, optional
+        Dataset base path. Used to load {focus_gene}_merged_data.csv if merged_df is not provided.
+    coord_df : pd.DataFrame, optional
+        Coordinate dataframe with x, y, and color columns.
+    coord : pd.DataFrame, optional
+        Coordinate dataframe with x, y columns. Used when coord_df is not given.
+    cell_type : pd.DataFrame, optional
+        Cell type annotation with column 'cell_type'. Used when coord_df is not given.
+    color_map : dict, optional
+        Cell type color map. Used when coord_df is not given.
+    merged_df : pd.DataFrame, optional
+        Preloaded merged two-hop event dataframe.
+    save : bool
+        Whether to save figure.
+    fig_dir : str, optional
+        Directory for saving figure if save=True.
+    """
+
+    # ===== Load merged two-hop event data =====
+    if merged_df is None:
+        if base_path is None:
+            raise ValueError("Please provide either merged_df or base_path + focus_gene.")
+        print("Loading merged two-hop event data...")
+        merged_file = os.path.join(base_path, f"{focus_gene}_merged_data.csv")
+        merged_df = pd.read_csv(merged_file)
+
+    df = merged_df.copy()
+
+    # ===== Build coord_df if not provided =====
+    if coord_df is None:
+        if coord is None or cell_type is None or color_map is None:
+            raise ValueError("Please provide either coord_df, or coord + cell_type + color_map.")
+
+        coord_df = coord.copy()
+
+        if "cell_type" not in cell_type.columns and "celltype" in cell_type.columns:
+            cell_type = cell_type.rename(columns={"celltype": "cell_type"})
+
+        coord_df["color"] = cell_type.loc[coord_df.index, "cell_type"].map(color_map)
+
+    # ===== Compatible column names =====
+    source_col = "X_name" if "X_name" in df.columns else "X_Name"
+    relay_col = "Relay_name" if "Relay_name" in df.columns else "Relay_Name"
+
+    if "to_cell" in df.columns:
+        target_col = "to_cell"
+    elif "Y_name" in df.columns:
+        target_col = "Y_name"
+    else:
+        target_col = "Y_Name"
+
+    # ===== Extract cells =====
+    source_cells = set(df[source_col].dropna())
+    relay_cells = set(df[relay_col].dropna())
+    target_cells = set(df[target_col].dropna())
+
+    # ===== Add role flags =====
+    plot_df = coord_df.copy()
+    plot_df["is_source"] = plot_df.index.isin(source_cells)
+    plot_df["is_relay"] = plot_df.index.isin(relay_cells)
+    plot_df["is_target"] = plot_df.index.isin(target_cells)
+
+    print("source cells:", plot_df["is_source"].sum())
+    print("relay cells:", plot_df["is_relay"].sum())
+    print("target cells:", plot_df["is_target"].sum())
+
+    # ===== Default plotting style =====
+    if marker_map is None:
+        marker_map = {
+            "source": "^",
+            "relay": "+",
+            "target": "o"
+        }
+
+    if size_map is None:
+        size_map = {
+            "source": 40,
+            "relay": 70,
+            "target": 40
+        }
+
+    if linewidth_map is None:
+        linewidth_map = {
+            "source": 0.8,
+            "relay": 1.5,
+            "target": 0.8
+        }
+
+    if role_color_map is None:
+        role_color_map = {
+            "source": "#ab8adf",
+            "relay": "#23bdf5",
+            "target": "#fa7d8a"
+        }
+
+    # ===== Plot =====
+    fig, ax = plt.subplots(figsize=figsize)
+
+    # background
+    ax.scatter(
+        plot_df["x"], plot_df["y"],
+        color=bg_color,
+        s=bg_size,
+        alpha=bg_alpha
+    )
+
+    # overlay source / relay / target
+    for role, flag in zip(
+        ["source", "relay", "target"],
+        ["is_source", "is_relay", "is_target"]
+    ):
+        sub = plot_df[plot_df[flag]]
+
+        if role == "relay":
+            ax.scatter(
+                sub["x"], sub["y"],
+                c=role_color_map[role],
+                s=size_map[role],
+                marker=marker_map[role],
+                linewidths=linewidth_map[role],
+                alpha=role_alpha,
+                label=role
+            )
+        else:
+            ax.scatter(
+                sub["x"], sub["y"],
+                facecolors="none",
+                edgecolors=role_color_map[role],
+                s=size_map[role],
+                marker=marker_map[role],
+                linewidths=linewidth_map[role],
+                alpha=role_alpha,
+                label=role
+            )
+
+    if invert_yaxis:
+        ax.invert_yaxis()
+
+    ax.legend(title="Role")
+    ax.set_title(f"{focus_gene} - Cell Identity (Combined)")
+    ax.set_xlabel("X")
+    ax.set_ylabel("Y")
+
+    plt.tight_layout()
+    plt.show()
+
+    return plot_df, fig, ax
+
+
+def plot_top_signal_ranked_abundance(
+    focus_cell,
+    cell_type,
+    sig_pair_res=None,
+    sig_lrp=None,
+    top_n=20,
+    figsize=(12, 6),
+    palette="GnBu",
+    save=False,
+    figpath=None
+):
+    """
+    Plot top abundant significant paths targeting a focus cell type.
+
+    Parameters
+    ----------
+    focus_cell : str
+        Focus cell type, e.g. 'Astro'.
+    cell_type : pd.DataFrame
+        Cell annotation dataframe with column 'cell_type'.
+    sig_pair_res : pd.DataFrame
+        Significant path/pair result dataframe.
+    sig_lrp : pd.DataFrame, optional
+        Alias for sig_pair_res. Kept for compatibility.
+    top_n : int
+        Number of top paths to show.
+    figsize : tuple
+        Figure size.
+    palette : str
+        Seaborn palette.
+    save : bool
+        Whether to save figure.
+    figpath : str
+        Save path without extension.
+    """
+
+    if sig_pair_res is None:
+        if sig_lrp is None:
+            raise ValueError("Please provide sig_pair_res or sig_lrp.")
+        sig_pair_res = sig_lrp
+
+    if "cell_type" not in cell_type.columns and "celltype" in cell_type.columns:
+        cell_type = cell_type.rename(columns={"celltype": "cell_type"})
+
+    focus_samples = cell_type[cell_type["cell_type"] == focus_cell].index.tolist()
+
+    if len(focus_samples) == 0:
+        raise ValueError(f"No cells found for focus_cell: {focus_cell}")
+
+    if "to_cell" not in sig_pair_res.columns:
+        raise ValueError("sig_pair_res must contain column 'to_cell'.")
+
+    if "path_symbol" not in sig_pair_res.columns:
+        raise ValueError("sig_pair_res must contain column 'path_symbol'.")
+
+    focus_sig_lrp = sig_pair_res[
+        sig_pair_res["to_cell"].isin(focus_samples)
+    ].copy()
+
+    path_counts = focus_sig_lrp["path_symbol"].value_counts()
+
+    if len(path_counts) == 0:
+        raise ValueError(f"No significant paths targeting {focus_cell} cells.")
+
+    top_n = min(top_n, len(path_counts))
+    plot_counts = path_counts.head(top_n)
+
+    plt.figure(figsize=figsize)
+
+    ax = sns.barplot(
+        x=plot_counts.index,
+        y=plot_counts.values,
+        hue=plot_counts.values,
+        palette=palette,
+        legend=False
+    )
+
+    plt.title(
+        f"Communication abundance of significant signals targeting {focus_cell}",
+        fontsize=14
+    )
+    plt.xlabel("Communication signals", fontsize=12)
+    plt.ylabel("Communication abundance (n)", fontsize=12)
+    plt.xticks(rotation=45, ha="right")
+
+    for p in ax.patches:
+        ax.annotate(
+            f"{int(p.get_height())}",
+            (p.get_x() + p.get_width() / 2., p.get_height()),
+            ha="center",
+            va="center",
+            xytext=(0, 5),
+            textcoords="offset points"
+        )
+
+    plt.tight_layout()
+    plt.show()
+
+    return focus_sig_lrp, path_counts

{scmultichat-0.1.2 → scmultichat-0.2.0}/MultiChat/__init__.py

@@ -1,6 +1,6 @@
 """
 MultiChat
-# Version: 0.1.1
+# Version: 0.2.0
 # Author: Caiwei Zhen
 """
 
@@ -9,5 +9,5 @@ from .Analysis import Intra_strength as tl
 from .Analysis import Processing as pp
 from .Plot import Visualization as pl
 
-__version__ = "0.1.1"
+__version__ = "0.2.0"
 __author__ = "Caiwei Zhen"

scmultichat-0.2.0/PKG-INFO

@@ -0,0 +1,30 @@
+Metadata-Version: 2.4
+Name: scMultiChat
+Version: 0.2.0
+Summary: Cell-cell communication using MultiChat
+Author: Caiwei Zhen
+Author-email: cwzhen@whu.edu.cn
+Requires-Python: >=3.12
+Requires-Dist: anndata==0.12.2
+Requires-Dist: importlib_metadata==8.7.0
+Requires-Dist: importlib_resources==6.5.2
+Requires-Dist: matplotlib==3.10.5
+Requires-Dist: networkx==3.5
+Requires-Dist: numpy==2.2.0
+Requires-Dist: pandas==2.3.2
+Requires-Dist: polars==1.32.3
+Requires-Dist: scanpy==1.11.4
+Requires-Dist: scikit-learn==1.7.1
+Requires-Dist: scikit-misc==0.5.1
+Requires-Dist: scipy==1.16.1
+Requires-Dist: seaborn==0.13.2
+Requires-Dist: tables==3.10.2
+Requires-Dist: torch==2.8.0
+Requires-Dist: torchaudio==2.8.0
+Requires-Dist: torchvision==0.23.0
+Requires-Dist: tqdm==4.67.1
+Dynamic: author
+Dynamic: author-email
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary

scmultichat-0.2.0/requirements.txt

@@ -0,0 +1,18 @@
+anndata==0.12.2
+importlib_metadata==8.7.0
+importlib_resources==6.5.2
+matplotlib==3.10.5
+networkx==3.5
+numpy==2.2.0
+pandas==2.3.2
+polars==1.32.3
+scanpy==1.11.4
+scikit-learn==1.7.1
+scikit-misc==0.5.1
+scipy==1.16.1
+seaborn==0.13.2
+tables==3.10.2
+torch==2.8.0
+torchaudio==2.8.0
+torchvision==0.23.0
+tqdm==4.67.1

scmultichat-0.2.0/scMultiChat.egg-info/PKG-INFO

@@ -0,0 +1,30 @@
+Metadata-Version: 2.4
+Name: scMultiChat
+Version: 0.2.0
+Summary: Cell-cell communication using MultiChat
+Author: Caiwei Zhen
+Author-email: cwzhen@whu.edu.cn
+Requires-Python: >=3.12
+Requires-Dist: anndata==0.12.2
+Requires-Dist: importlib_metadata==8.7.0
+Requires-Dist: importlib_resources==6.5.2
+Requires-Dist: matplotlib==3.10.5
+Requires-Dist: networkx==3.5
+Requires-Dist: numpy==2.2.0
+Requires-Dist: pandas==2.3.2
+Requires-Dist: polars==1.32.3
+Requires-Dist: scanpy==1.11.4
+Requires-Dist: scikit-learn==1.7.1
+Requires-Dist: scikit-misc==0.5.1
+Requires-Dist: scipy==1.16.1
+Requires-Dist: seaborn==0.13.2
+Requires-Dist: tables==3.10.2
+Requires-Dist: torch==2.8.0
+Requires-Dist: torchaudio==2.8.0
+Requires-Dist: torchvision==0.23.0
+Requires-Dist: tqdm==4.67.1
+Dynamic: author
+Dynamic: author-email
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary

scmultichat-0.2.0/scMultiChat.egg-info/requires.txt

@@ -0,0 +1,18 @@
+anndata==0.12.2
+importlib_metadata==8.7.0
+importlib_resources==6.5.2
+matplotlib==3.10.5
+networkx==3.5
+numpy==2.2.0
+pandas==2.3.2
+polars==1.32.3
+scanpy==1.11.4
+scikit-learn==1.7.1
+scikit-misc==0.5.1
+scipy==1.16.1
+seaborn==0.13.2
+tables==3.10.2
+torch==2.8.0
+torchaudio==2.8.0
+torchvision==0.23.0
+tqdm==4.67.1

{scmultichat-0.1.2 → scmultichat-0.2.0}/setup.py

@@ -6,7 +6,7 @@ def read_requirements():
 
 setup(
     name="scMultiChat",
-    version="0.1.2",
+    version="0.2.0",
     packages=find_packages(),
     install_requires=read_requirements(),
     author="Caiwei Zhen",

scmultichat-0.1.2/PKG-INFO

@@ -1,30 +0,0 @@
-Metadata-Version: 2.4
-Name: scMultiChat
-Version: 0.1.2
-Summary: Cell-cell communication using MultiChat
-Author: Caiwei Zhen
-Author-email: cwzhen@whu.edu.cn
-Requires-Python: >=3.12
-Requires-Dist: adjustText==1.3.0
-Requires-Dist: adjustText==1.3.0
-Requires-Dist: anndata==0.12.10
-Requires-Dist: attr==0.3.2
-Requires-Dist: kneed==0.8.6
-Requires-Dist: matplotlib==3.10.8
-Requires-Dist: numpy==2.4.4
-Requires-Dist: pandas==3.0.2
-Requires-Dist: plotly==6.3.0
-Requires-Dist: pybedtools==0.12.0
-Requires-Dist: scanpy==1.12.1
-Requires-Dist: scikit_learn==1.8.0
-Requires-Dist: scipy==1.17.1
-Requires-Dist: seaborn==0.13.2
-Requires-Dist: statsmodels==0.14.5
-Requires-Dist: tables==3.10.2
-Requires-Dist: tqdm==4.67.1
-Requires-Dist: umap_learn==0.5.9.post2
-Dynamic: author
-Dynamic: author-email
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary

scmultichat-0.1.2/requirements.txt

@@ -1,18 +0,0 @@
-adjustText==1.3.0
-adjustText==1.3.0
-anndata==0.12.10
-attr==0.3.2
-kneed==0.8.6
-matplotlib==3.10.8
-numpy==2.4.4
-pandas==3.0.2
-plotly==6.3.0
-pybedtools==0.12.0
-scanpy==1.12.1
-scikit_learn==1.8.0
-scipy==1.17.1
-seaborn==0.13.2
-statsmodels==0.14.5
-tables==3.10.2
-tqdm==4.67.1
-umap_learn==0.5.9.post2

scmultichat-0.1.2/scMultiChat.egg-info/PKG-INFO

@@ -1,30 +0,0 @@
-Metadata-Version: 2.4
-Name: scMultiChat
-Version: 0.1.2
-Summary: Cell-cell communication using MultiChat
-Author: Caiwei Zhen
-Author-email: cwzhen@whu.edu.cn
-Requires-Python: >=3.12
-Requires-Dist: adjustText==1.3.0
-Requires-Dist: adjustText==1.3.0
-Requires-Dist: anndata==0.12.10
-Requires-Dist: attr==0.3.2
-Requires-Dist: kneed==0.8.6
-Requires-Dist: matplotlib==3.10.8
-Requires-Dist: numpy==2.4.4
-Requires-Dist: pandas==3.0.2
-Requires-Dist: plotly==6.3.0
-Requires-Dist: pybedtools==0.12.0
-Requires-Dist: scanpy==1.12.1
-Requires-Dist: scikit_learn==1.8.0
-Requires-Dist: scipy==1.17.1
-Requires-Dist: seaborn==0.13.2
-Requires-Dist: statsmodels==0.14.5
-Requires-Dist: tables==3.10.2
-Requires-Dist: tqdm==4.67.1
-Requires-Dist: umap_learn==0.5.9.post2
-Dynamic: author
-Dynamic: author-email
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary

scmultichat-0.1.2/scMultiChat.egg-info/requires.txt

@@ -1,18 +0,0 @@
-adjustText==1.3.0
-adjustText==1.3.0
-anndata==0.12.10
-attr==0.3.2
-kneed==0.8.6
-matplotlib==3.10.8
-numpy==2.4.4
-pandas==3.0.2
-plotly==6.3.0
-pybedtools==0.12.0
-scanpy==1.12.1
-scikit_learn==1.8.0
-scipy==1.17.1
-seaborn==0.13.2
-statsmodels==0.14.5
-tables==3.10.2
-tqdm==4.67.1
-umap_learn==0.5.9.post2