gsMap 1.71__py3-none-any.whl → 1.71.1__py3-none-any.whl

gsMap/GNN/adjacency_matrix.py

@@ -1,75 +1,75 @@
-import numpy as np
-import pandas as pd
-import scipy.sparse as sp
-from sklearn.neighbors import NearestNeighbors
-import torch
-
-def cal_spatial_net(adata, n_neighbors=5, verbose=True):
-    """Construct the spatial neighbor network."""
-    if verbose:
-        print('------Calculating spatial graph...')
-    coor = pd.DataFrame(adata.obsm['spatial'], index=adata.obs.index)
-    nbrs = NearestNeighbors(n_neighbors=n_neighbors).fit(coor)
-    distances, indices = nbrs.kneighbors(coor)
-    n_cells, n_neighbors = indices.shape
-    cell_indices = np.arange(n_cells)
-    cell1 = np.repeat(cell_indices, n_neighbors)
-    cell2 = indices.flatten()
-    distance = distances.flatten()
-    knn_df = pd.DataFrame({'Cell1': cell1, 'Cell2': cell2, 'Distance': distance})
-    knn_df = knn_df[knn_df['Distance'] > 0].copy()
-    cell_id_map = dict(zip(cell_indices, coor.index))
-    knn_df['Cell1'] = knn_df['Cell1'].map(cell_id_map)
-    knn_df['Cell2'] = knn_df['Cell2'].map(cell_id_map)
-    return knn_df
-
-def sparse_mx_to_torch_sparse_tensor(sparse_mx):
-    """Convert a scipy sparse matrix to a torch sparse tensor."""
-    sparse_mx = sparse_mx.tocoo().astype(np.float32)
-    indices = torch.from_numpy(
-        np.vstack((sparse_mx.row, sparse_mx.col)).astype(np.int64)
-    )
-    values = torch.from_numpy(sparse_mx.data)
-    shape = torch.Size(sparse_mx.shape)
-    return  torch.sparse_coo_tensor(indices, values, shape)
-
-def preprocess_graph(adj):
-    """Symmetrically normalize the adjacency matrix."""
-    adj = sp.coo_matrix(adj)
-    adj_ = adj + sp.eye(adj.shape[0])
-    rowsum = np.array(adj_.sum(1)).flatten()
-    degree_mat_inv_sqrt = sp.diags(np.power(rowsum, -0.5))
-    adj_normalized = adj_.dot(degree_mat_inv_sqrt).transpose().dot(degree_mat_inv_sqrt).tocoo()
-    return sparse_mx_to_torch_sparse_tensor(adj_normalized)
-
-def construct_adjacency_matrix(adata, params, verbose=True):
-    """Construct the adjacency matrix from spatial data."""
-    spatial_net = cal_spatial_net(adata, n_neighbors=params.n_neighbors, verbose=verbose)
-    if verbose:
-        num_edges = spatial_net.shape[0]
-        num_cells = adata.n_obs
-        print(f'The graph contains {num_edges} edges, {num_cells} cells.')
-        print(f'{num_edges / num_cells:.2f} neighbors per cell on average.')
-    cell_ids = {cell: idx for idx, cell in enumerate(adata.obs.index)}
-    spatial_net['Cell1'] = spatial_net['Cell1'].map(cell_ids)
-    spatial_net['Cell2'] = spatial_net['Cell2'].map(cell_ids)
-    if params.weighted_adj:
-        distance_normalized = spatial_net['Distance'] / (spatial_net['Distance'].max() + 1)
-        weights = np.exp(-0.5 * distance_normalized ** 2)
-        adj_org = sp.coo_matrix(
-            (weights, (spatial_net['Cell1'], spatial_net['Cell2'])),
-            shape=(adata.n_obs, adata.n_obs)
-        )
-    else:
-        adj_org = sp.coo_matrix(
-            (np.ones(spatial_net.shape[0]), (spatial_net['Cell1'], spatial_net['Cell2'])),
-            shape=(adata.n_obs, adata.n_obs)
-        )
-    adj_norm = preprocess_graph(adj_org)
-    norm_value = adj_org.shape[0] ** 2 / ((adj_org.shape[0] ** 2 - adj_org.sum()) * 2)
-    graph_dict = {
-        "adj_org": adj_org,
-        "adj_norm": adj_norm,
-        "norm_value": norm_value
-    }
-    return graph_dict
+import numpy as np
+import pandas as pd
+import scipy.sparse as sp
+from sklearn.neighbors import NearestNeighbors
+import torch
+
+def cal_spatial_net(adata, n_neighbors=5, verbose=True):
+    """Construct the spatial neighbor network."""
+    if verbose:
+        print('------Calculating spatial graph...')
+    coor = pd.DataFrame(adata.obsm['spatial'], index=adata.obs.index)
+    nbrs = NearestNeighbors(n_neighbors=n_neighbors).fit(coor)
+    distances, indices = nbrs.kneighbors(coor)
+    n_cells, n_neighbors = indices.shape
+    cell_indices = np.arange(n_cells)
+    cell1 = np.repeat(cell_indices, n_neighbors)
+    cell2 = indices.flatten()
+    distance = distances.flatten()
+    knn_df = pd.DataFrame({'Cell1': cell1, 'Cell2': cell2, 'Distance': distance})
+    knn_df = knn_df[knn_df['Distance'] > 0].copy()
+    cell_id_map = dict(zip(cell_indices, coor.index))
+    knn_df['Cell1'] = knn_df['Cell1'].map(cell_id_map)
+    knn_df['Cell2'] = knn_df['Cell2'].map(cell_id_map)
+    return knn_df
+
+def sparse_mx_to_torch_sparse_tensor(sparse_mx):
+    """Convert a scipy sparse matrix to a torch sparse tensor."""
+    sparse_mx = sparse_mx.tocoo().astype(np.float32)
+    indices = torch.from_numpy(
+        np.vstack((sparse_mx.row, sparse_mx.col)).astype(np.int64)
+    )
+    values = torch.from_numpy(sparse_mx.data)
+    shape = torch.Size(sparse_mx.shape)
+    return  torch.sparse_coo_tensor(indices, values, shape)
+
+def preprocess_graph(adj):
+    """Symmetrically normalize the adjacency matrix."""
+    adj = sp.coo_matrix(adj)
+    adj_ = adj + sp.eye(adj.shape[0])
+    rowsum = np.array(adj_.sum(1)).flatten()
+    degree_mat_inv_sqrt = sp.diags(np.power(rowsum, -0.5))
+    adj_normalized = adj_.dot(degree_mat_inv_sqrt).transpose().dot(degree_mat_inv_sqrt).tocoo()
+    return sparse_mx_to_torch_sparse_tensor(adj_normalized)
+
+def construct_adjacency_matrix(adata, params, verbose=True):
+    """Construct the adjacency matrix from spatial data."""
+    spatial_net = cal_spatial_net(adata, n_neighbors=params.n_neighbors, verbose=verbose)
+    if verbose:
+        num_edges = spatial_net.shape[0]
+        num_cells = adata.n_obs
+        print(f'The graph contains {num_edges} edges, {num_cells} cells.')
+        print(f'{num_edges / num_cells:.2f} neighbors per cell on average.')
+    cell_ids = {cell: idx for idx, cell in enumerate(adata.obs.index)}
+    spatial_net['Cell1'] = spatial_net['Cell1'].map(cell_ids)
+    spatial_net['Cell2'] = spatial_net['Cell2'].map(cell_ids)
+    if params.weighted_adj:
+        distance_normalized = spatial_net['Distance'] / (spatial_net['Distance'].max() + 1)
+        weights = np.exp(-0.5 * distance_normalized ** 2)
+        adj_org = sp.coo_matrix(
+            (weights, (spatial_net['Cell1'], spatial_net['Cell2'])),
+            shape=(adata.n_obs, adata.n_obs)
+        )
+    else:
+        adj_org = sp.coo_matrix(
+            (np.ones(spatial_net.shape[0]), (spatial_net['Cell1'], spatial_net['Cell2'])),
+            shape=(adata.n_obs, adata.n_obs)
+        )
+    adj_norm = preprocess_graph(adj_org)
+    norm_value = adj_org.shape[0] ** 2 / ((adj_org.shape[0] ** 2 - adj_org.sum()) * 2)
+    graph_dict = {
+        "adj_org": adj_org,
+        "adj_norm": adj_norm,
+        "norm_value": norm_value
+    }
+    return graph_dict

gsMap/GNN/model.py

@@ -1,89 +1,90 @@
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-from torch_geometric.nn import GATConv
-
-def full_block(in_features, out_features, p_drop):
-    return nn.Sequential(
-        nn.Linear(in_features, out_features),
-        nn.BatchNorm1d(out_features),
-        nn.ELU(),
-        nn.Dropout(p=p_drop)
-    )
-
-class GATModel(nn.Module):
-    def __init__(self, input_dim, params, num_classes=1):
-        super().__init__()
-        self.var = params.var
-        self.num_classes = num_classes
-        self.params = params
-
-        # Encoder
-        self.encoder = nn.Sequential(
-            full_block(input_dim, params.feat_hidden1, params.p_drop),
-            full_block(params.feat_hidden1, params.feat_hidden2, params.p_drop)
-        )
-
-        # GAT Layers
-        self.gat1 = GATConv(
-            in_channels=params.feat_hidden2,
-            out_channels=params.gat_hidden1,
-            heads=params.nheads,
-            dropout=params.p_drop
-        )
-        self.gat2 = GATConv(
-            in_channels=params.gat_hidden1 * params.nheads,
-            out_channels=params.gat_hidden2,
-            heads=1,
-            concat=False,
-            dropout=params.p_drop
-        )
-        if self.var:
-            self.gat3 = GATConv(
-                in_channels=params.gat_hidden1 * params.nheads,
-                out_channels=params.gat_hidden2,
-                heads=1,
-                concat=False,
-                dropout=params.p_drop
-            )
-
-        # Decoder
-        self.decoder = nn.Sequential(
-            full_block(params.gat_hidden2, params.feat_hidden2, params.p_drop),
-            full_block(params.feat_hidden2, params.feat_hidden1, params.p_drop),
-            nn.Linear(params.feat_hidden1, input_dim)
-        )
-
-        # Clustering Layer
-        self.cluster = nn.Sequential(
-            full_block(params.gat_hidden2, params.feat_hidden2, params.p_drop),
-            nn.Linear(params.feat_hidden2, self.num_classes)
-        )
-
-    def encode(self, x, edge_index):
-        x = self.encoder(x)
-        x = self.gat1(x, edge_index)
-        x = F.relu(x)
-        x = F.dropout(x, p=self.params.p_drop, training=self.training)
-
-        mu = self.gat2(x, edge_index)
-        if self.var:
-            logvar = self.gat3(x, edge_index)
-            return mu, logvar
-        else:
-            return mu, None
-
-    def reparameterize(self, mu, logvar):
-        if self.training and logvar is not None:
-            std = torch.exp(0.5 * logvar)
-            eps = torch.randn_like(std)
-            return eps * std + mu
-        else:
-            return mu
-
-    def forward(self, x, edge_index):
-        mu, logvar = self.encode(x, edge_index)
-        z = self.reparameterize(mu, logvar)
-        x_reconstructed = self.decoder(z)
-        pred_label = F.softmax(self.cluster(z), dim=1)
-        return pred_label, x_reconstructed, z, mu, logvar
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from torch_geometric.nn import GATConv
+
+def full_block(in_features, out_features, p_drop):
+    return nn.Sequential(
+        nn.Linear(in_features, out_features),
+        nn.BatchNorm1d(out_features),
+        nn.ELU(),
+        nn.Dropout(p=p_drop)
+    )
+
+class GATModel(nn.Module):
+    def __init__(self, input_dim, params, num_classes=1):
+        super().__init__()
+        self.var = params.var
+        self.num_classes = num_classes
+        self.params = params
+
+        # Encoder
+        self.encoder = nn.Sequential(
+            full_block(input_dim, params.feat_hidden1, params.p_drop),
+            full_block(params.feat_hidden1, params.feat_hidden2, params.p_drop)
+        )
+
+        # GAT Layers
+        self.gat1 = GATConv(
+            in_channels=params.feat_hidden2,
+            out_channels=params.gat_hidden1,
+            heads=params.nheads,
+            dropout=params.p_drop
+        )
+        self.gat2 = GATConv(
+            in_channels=params.gat_hidden1 * params.nheads,
+            out_channels=params.gat_hidden2,
+            heads=1,
+            concat=False,
+            dropout=params.p_drop
+        )
+        if self.var:
+            self.gat3 = GATConv(
+                in_channels=params.gat_hidden1 * params.nheads,
+                out_channels=params.gat_hidden2,
+                heads=1,
+                concat=False,
+                dropout=params.p_drop
+            )
+
+        # Decoder
+        self.decoder = nn.Sequential(
+            full_block(params.gat_hidden2, params.feat_hidden2, params.p_drop),
+            full_block(params.feat_hidden2, params.feat_hidden1, params.p_drop),
+            nn.Linear(params.feat_hidden1, input_dim)
+        )
+
+        # Clustering Layer
+        self.cluster = nn.Sequential(
+            full_block(params.gat_hidden2, params.feat_hidden2, params.p_drop),
+            nn.Linear(params.feat_hidden2, self.num_classes)
+        )
+
+    def encode(self, x, edge_index):
+        x = self.encoder(x)
+        x = self.gat1(x, edge_index)
+        x = F.relu(x)
+        x = F.dropout(x, p=self.params.p_drop, training=self.training)
+
+        mu = self.gat2(x, edge_index)
+        if self.var:
+            logvar = self.gat3(x, edge_index)
+            return mu, logvar
+        else:
+            return mu, None
+
+    def reparameterize(self, mu, logvar):
+        if self.training and logvar is not None:
+            std = torch.exp(0.5 * logvar)
+            eps = torch.randn_like(std)
+            return eps * std + mu
+        else:
+            return mu
+
+    def forward(self, x, edge_index):
+        mu, logvar = self.encode(x, edge_index)
+        z = self.reparameterize(mu, logvar)
+        x_reconstructed = self.decoder(z)
+        # pred_label = F.softmax(self.cluster(z), dim=1)
+        pred_label = self.cluster(z)
+        return pred_label, x_reconstructed, z, mu, logvar

gsMap/__init__.py

@@ -1,5 +1,5 @@
-'''
-Genetics-informed pathogenic spatial mapping
-'''
-
-__version__ = '1.71'
+'''
+Genetics-informed pathogenic spatial mapping
+'''
+
+__version__ = '1.71.1'

gsMap/__main__.py

@@ -1,3 +1,3 @@
-from .main import main
-if __name__ == '__main__':
+from .main import main
+if __name__ == '__main__':
     main()

gsMap/cauchy_combination_test.py

@@ -1,141 +1,141 @@
-import logging
-from pathlib import Path
-
-import numpy as np
-import pandas as pd
-import scanpy as sc
-import scipy as sp
-
-from gsMap.config import CauchyCombinationConfig
-
-logger = logging.getLogger(__name__)
-
-# The fun of cauchy combination
-def acat_test(pvalues, weights=None):
-    '''acat_test()
-    Aggregated Cauchy Assocaition Test
-    A p-value combination method using the Cauchy distribution.
-
-    Inspired by: https://github.com/yaowuliu/ACAT/blob/master/R/ACAT.R
-    Inputs:
-        pvalues: <list or numpy array>
-            The p-values you want to combine.
-        weights: <list or numpy array>, default=None
-            The weights for each of the p-values. If None, equal weights are used.
-
-    Returns:
-        pval: <float>
-            The ACAT combined p-value.
-    '''
-    if any(np.isnan(pvalues)):
-        raise Exception("Cannot have NAs in the p-values.")
-    if any([(i > 1) | (i < 0) for i in pvalues]):
-        raise Exception("P-values must be between 0 and 1.")
-    if any([i == 1 for i in pvalues]) & any([i == 0 for i in pvalues]):
-        raise Exception("Cannot have both 0 and 1 p-values.")
-    if any([i == 0 for i in pvalues]):
-        logger.info("Warn: p-values are exactly 0.")
-        return 0
-    if any([i == 1 for i in pvalues]):
-        logger.info("Warn: p-values are exactly 1.")
-        return 1
-    if weights == None:
-        weights = [1 / len(pvalues) for i in pvalues]
-    elif len(weights) != len(pvalues):
-        raise Exception("Length of weights and p-values differs.")
-    elif any([i < 0 for i in weights]):
-        raise Exception("All weights must be positive.")
-    else:
-        weights = [i / len(weights) for i in weights]
-
-    pvalues = np.array(pvalues)
-    weights = np.array(weights)
-
-    if any([i < 1e-16 for i in pvalues]) == False:
-        cct_stat = sum(weights * np.tan((0.5 - pvalues) * np.pi))
-    else:
-        is_small = [i < (1e-16) for i in pvalues]
-        is_large = [i >= (1e-16) for i in pvalues]
-        cct_stat = sum((weights[is_small] / pvalues[is_small]) / np.pi)
-        cct_stat += sum(weights[is_large] * np.tan((0.5 - pvalues[is_large]) * np.pi))
-
-    if cct_stat > 1e15:
-        pval = (1 / cct_stat) / np.pi
-    else:
-        pval = 1 - sp.stats.cauchy.cdf(cct_stat)
-
-    return pval
-
-
-def run_Cauchy_combination(config:CauchyCombinationConfig):
-    # Load the ldsc results
-    logger.info(f'------Loading LDSC results of {config.ldsc_save_dir}...')
-    ldsc_input_file= config.get_ldsc_result_file(config.trait_name)
-    ldsc = pd.read_csv(ldsc_input_file, compression='gzip')
-    ldsc.spot = ldsc.spot.astype(str).replace('\.0', '', regex=True)
-    ldsc.index = ldsc.spot
-    if config.meta is None:
-        # Load the spatial data
-        logger.info(f'------Loading ST data of {config.hdf5_with_latent_path}...')
-        spe = sc.read_h5ad(f'{config.hdf5_with_latent_path}')
-
-        common_cell = np.intersect1d(ldsc.index, spe.obs_names)
-        spe = spe[common_cell]
-        ldsc = ldsc.loc[common_cell]
-
-        # Add the annotation
-        ldsc['annotation'] = spe.obs.loc[ldsc.spot][config.annotation].to_list()
-
-    elif config.meta is not None:
-        # Or Load the additional annotation (just for the macaque data at this stage: 2023Nov25)
-        logger.info(f'------Loading additional annotation...')
-        meta = pd.read_csv(config.meta, index_col=0)
-        meta = meta.loc[meta.slide == config.slide]
-        meta.index = meta.cell_id.astype(str).replace('\.0', '', regex=True)
-
-        common_cell = np.intersect1d(ldsc.index, meta.index)
-        meta = meta.loc[common_cell]
-        ldsc = ldsc.loc[common_cell]
-
-        # Add the annotation
-        ldsc['annotation'] = meta.loc[ldsc.spot][config.annotation].to_list()
-    # Perform the Cauchy combination based on the given annotations
-    p_cauchy = []
-    p_median = []
-    for ct in np.unique(ldsc.annotation):
-        p_temp = ldsc.loc[ldsc['annotation'] == ct, 'p']
-        
-        # The Cauchy test is sensitive to very small p-values, so extreme outliers should be considered for removal...
-        # to enhance robustness, particularly in cases where spot annotations may be incorrect. 
-        # p_cauchy_temp = acat_test(p_temp[p_temp != np.min(p_temp)])
-        p_temp_log = -np.log10(p_temp)
-        median_log = np.median(p_temp_log)
-        IQR_log = np.percentile(p_temp_log, 75) - np.percentile(p_temp_log, 25)
-        
-        p_use = p_temp[p_temp_log < median_log + 3*IQR_log]
-        n_remove = len(p_temp) - len(p_use)
-        
-        # Outlier: -log10(p) < median + 3IQR && len(outlier set) < 20
-        if (0 < n_remove < 20):
-            logger.info(f'Remove {n_remove}/{len(p_temp)} outliers (median + 3IQR) for {ct}.')
-            p_cauchy_temp = acat_test(p_use)
-        else:
-             p_cauchy_temp = acat_test(p_temp)
-                
-        p_median_temp = np.median(p_temp)
-
-        p_cauchy.append(p_cauchy_temp)
-        p_median.append(p_median_temp)
-    #     p_tissue = pd.DataFrame(p_cauchy,p_median,np.unique(ldsc.annotation))
-    data = {'p_cauchy': p_cauchy, 'p_median': p_median, 'annotation': np.unique(ldsc.annotation)}
-    p_tissue = pd.DataFrame(data)
-    p_tissue.columns = ['p_cauchy', 'p_median', 'annotation']
-    # Save the results
-    output_dir = Path(config.cauchy_save_dir)
-    output_dir.mkdir(parents=True, exist_ok=True, mode=0o755)
-    output_file = output_dir / f'{config.sample_name}_{config.trait_name}.Cauchy.csv.gz'
-    p_tissue.to_csv(
-        output_file,
-        compression='gzip',
-        index=False,
-    )
+import logging
+from pathlib import Path
+
+import numpy as np
+import pandas as pd
+import scanpy as sc
+import scipy as sp
+
+from gsMap.config import CauchyCombinationConfig
+
+logger = logging.getLogger(__name__)
+
+# The fun of cauchy combination
+def acat_test(pvalues, weights=None):
+    '''acat_test()
+    Aggregated Cauchy Assocaition Test
+    A p-value combination method using the Cauchy distribution.
+
+    Inspired by: https://github.com/yaowuliu/ACAT/blob/master/R/ACAT.R
+    Inputs:
+        pvalues: <list or numpy array>
+            The p-values you want to combine.
+        weights: <list or numpy array>, default=None
+            The weights for each of the p-values. If None, equal weights are used.
+
+    Returns:
+        pval: <float>
+            The ACAT combined p-value.
+    '''
+    if any(np.isnan(pvalues)):
+        raise Exception("Cannot have NAs in the p-values.")
+    if any([(i > 1) | (i < 0) for i in pvalues]):
+        raise Exception("P-values must be between 0 and 1.")
+    if any([i == 1 for i in pvalues]) & any([i == 0 for i in pvalues]):
+        raise Exception("Cannot have both 0 and 1 p-values.")
+    if any([i == 0 for i in pvalues]):
+        logger.info("Warn: p-values are exactly 0.")
+        return 0
+    if any([i == 1 for i in pvalues]):
+        logger.info("Warn: p-values are exactly 1.")
+        return 1
+    if weights == None:
+        weights = [1 / len(pvalues) for i in pvalues]
+    elif len(weights) != len(pvalues):
+        raise Exception("Length of weights and p-values differs.")
+    elif any([i < 0 for i in weights]):
+        raise Exception("All weights must be positive.")
+    else:
+        weights = [i / len(weights) for i in weights]
+
+    pvalues = np.array(pvalues)
+    weights = np.array(weights)
+
+    if any([i < 1e-16 for i in pvalues]) == False:
+        cct_stat = sum(weights * np.tan((0.5 - pvalues) * np.pi))
+    else:
+        is_small = [i < (1e-16) for i in pvalues]
+        is_large = [i >= (1e-16) for i in pvalues]
+        cct_stat = sum((weights[is_small] / pvalues[is_small]) / np.pi)
+        cct_stat += sum(weights[is_large] * np.tan((0.5 - pvalues[is_large]) * np.pi))
+
+    if cct_stat > 1e15:
+        pval = (1 / cct_stat) / np.pi
+    else:
+        pval = 1 - sp.stats.cauchy.cdf(cct_stat)
+
+    return pval
+
+
+def run_Cauchy_combination(config:CauchyCombinationConfig):
+    # Load the ldsc results
+    logger.info(f'------Loading LDSC results of {config.ldsc_save_dir}...')
+    ldsc_input_file= config.get_ldsc_result_file(config.trait_name)
+    ldsc = pd.read_csv(ldsc_input_file, compression='gzip')
+    ldsc.spot = ldsc.spot.astype(str).replace('\.0', '', regex=True)
+    ldsc.index = ldsc.spot
+    if config.meta is None:
+        # Load the spatial data
+        logger.info(f'------Loading ST data of {config.hdf5_with_latent_path}...')
+        spe = sc.read_h5ad(f'{config.hdf5_with_latent_path}')
+
+        common_cell = np.intersect1d(ldsc.index, spe.obs_names)
+        spe = spe[common_cell]
+        ldsc = ldsc.loc[common_cell]
+
+        # Add the annotation
+        ldsc['annotation'] = spe.obs.loc[ldsc.spot][config.annotation].to_list()
+
+    elif config.meta is not None:
+        # Or Load the additional annotation (just for the macaque data at this stage: 2023Nov25)
+        logger.info(f'------Loading additional annotation...')
+        meta = pd.read_csv(config.meta, index_col=0)
+        meta = meta.loc[meta.slide == config.slide]
+        meta.index = meta.cell_id.astype(str).replace('\.0', '', regex=True)
+
+        common_cell = np.intersect1d(ldsc.index, meta.index)
+        meta = meta.loc[common_cell]
+        ldsc = ldsc.loc[common_cell]
+
+        # Add the annotation
+        ldsc['annotation'] = meta.loc[ldsc.spot][config.annotation].to_list()
+    # Perform the Cauchy combination based on the given annotations
+    p_cauchy = []
+    p_median = []
+    for ct in np.unique(ldsc.annotation):
+        p_temp = ldsc.loc[ldsc['annotation'] == ct, 'p']
+        
+        # The Cauchy test is sensitive to very small p-values, so extreme outliers should be considered for removal...
+        # to enhance robustness, particularly in cases where spot annotations may be incorrect. 
+        # p_cauchy_temp = acat_test(p_temp[p_temp != np.min(p_temp)])
+        p_temp_log = -np.log10(p_temp)
+        median_log = np.median(p_temp_log)
+        IQR_log = np.percentile(p_temp_log, 75) - np.percentile(p_temp_log, 25)
+        
+        p_use = p_temp[p_temp_log < median_log + 3*IQR_log]
+        n_remove = len(p_temp) - len(p_use)
+        
+        # Outlier: -log10(p) < median + 3IQR && len(outlier set) < 20
+        if (0 < n_remove < 20):
+            logger.info(f'Remove {n_remove}/{len(p_temp)} outliers (median + 3IQR) for {ct}.')
+            p_cauchy_temp = acat_test(p_use)
+        else:
+             p_cauchy_temp = acat_test(p_temp)
+                
+        p_median_temp = np.median(p_temp)
+
+        p_cauchy.append(p_cauchy_temp)
+        p_median.append(p_median_temp)
+    #     p_tissue = pd.DataFrame(p_cauchy,p_median,np.unique(ldsc.annotation))
+    data = {'p_cauchy': p_cauchy, 'p_median': p_median, 'annotation': np.unique(ldsc.annotation)}
+    p_tissue = pd.DataFrame(data)
+    p_tissue.columns = ['p_cauchy', 'p_median', 'annotation']
+    # Save the results
+    output_dir = Path(config.cauchy_save_dir)
+    output_dir.mkdir(parents=True, exist_ok=True, mode=0o755)
+    output_file = output_dir / f'{config.sample_name}_{config.trait_name}.Cauchy.csv.gz'
+    p_tissue.to_csv(
+        output_file,
+        compression='gzip',
+        index=False,
+    )