gsMap 1.62__py3-none-any.whl → 1.63__py3-none-any.whl

gsMap/GNN_VAE/adjacency_matrix.py

@@ -66,7 +66,7 @@ def Construct_Adjacency_Matrix(adata,Params, verbose=True):
     #- 
     if verbose:
         print('The graph contains %d edges, %d cells.' %(Spatial_Net.shape[0], adata.n_obs))
-        print('%.4f neighbors per cell on average.' %(Spatial_Net.shape[0]/adata.n_obs))
+        print('%.2f neighbors per cell on average.' %(Spatial_Net.shape[0]/adata.n_obs))
     #-  
     cells = np.array(adata.obs.index)
     cells_id_tran = dict(zip(cells, range(cells.shape[0])))

gsMap/GNN_VAE/model.py

@@ -46,19 +46,19 @@ class GNN_VAE_Model(nn.Module):
         self.encoder.add_module('encoder_L2', full_block(params.feat_hidden1, params.feat_hidden2, params.p_drop))
         
         # GNN (GAT)
-        self.gn1 = GNN(params.feat_hidden2, params.gcn_hidden1, params.p_drop, act=F.relu,heads = params.nheads)
-        self.gn2 = GNN(params.gcn_hidden1*params.nheads, params.gcn_hidden2, params.p_drop, act=lambda x: x)
-        self.gn3 = GNN(params.gcn_hidden1*params.nheads, params.gcn_hidden2, params.p_drop, act=lambda x: x) 
+        self.gn1 = GNN(params.feat_hidden2, params.gat_hidden1, params.p_drop, act=F.relu,heads = params.nheads)
+        self.gn2 = GNN(params.gat_hidden1*params.nheads, params.gat_hidden2, params.p_drop, act=lambda x: x)
+        self.gn3 = GNN(params.gat_hidden1*params.nheads, params.gat_hidden2, params.p_drop, act=lambda x: x) 
         
         # Decoder
         self.decoder = nn.Sequential()
-        self.decoder.add_module('decoder_L1', full_block(params.gcn_hidden2, params.feat_hidden2, params.p_drop))
+        self.decoder.add_module('decoder_L1', full_block(params.gat_hidden2, params.feat_hidden2, params.p_drop))
         self.decoder.add_module('decoder_L2', full_block(params.feat_hidden2, params.feat_hidden1, params.p_drop))
         self.decoder.add_module('decoder_output', nn.Sequential(nn.Linear(params.feat_hidden1, input_dim)))
         
         # Cluster
         self.cluster = nn.Sequential()
-        self.cluster.add_module('cluster_L1', full_block(params.gcn_hidden2, params.feat_hidden2, params.p_drop))
+        self.cluster.add_module('cluster_L1', full_block(params.gat_hidden2, params.feat_hidden2, params.p_drop))
         self.cluster.add_module('cluster_output', nn.Linear(params.feat_hidden2, self.num_classes))
            
     def encode(self, x, adj):

gsMap/GNN_VAE/train.py

@@ -45,7 +45,7 @@ class Model_Train:
         # Set Model 
         self.model = GNN_VAE_Model(self.params.feat_cell,self.params,self.num_classes).to(device)
         self.optimizer = torch.optim.Adam(params = list(self.model.parameters()),
-                                          lr = self.params.gcn_lr, weight_decay = self.params.gcn_decay)               
+                                          lr = self.params.gat_lr, weight_decay = self.params.gcn_decay)               
     
     # Train    
     def run_train(self):

gsMap/__init__.py

@@ -2,4 +2,4 @@
 Genetics-informed pathogenic spatial mapping
 '''
 
-__version__ = '1.62'
+__version__ = '1.63'

gsMap/cauchy_combination_test.py

@@ -1,4 +1,4 @@
-import argparse
+import logging
 from pathlib import Path
 
 import numpy as np
@@ -6,7 +6,9 @@ import pandas as pd
 import scanpy as sc
 import scipy as sp
 
-from gsMap.config import CauchyCombinationConfig, add_Cauchy_combination_args
+from gsMap.config import CauchyCombinationConfig
+
+logger = logging.getLogger(__name__)
 
 # The fun of cauchy combination
 def acat_test(pvalues, weights=None):
@@ -32,10 +34,10 @@ def acat_test(pvalues, weights=None):
     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]):
-        print("Warn: p-values are exactly 0.")
+        logger.info("Warn: p-values are exactly 0.")
         return 0
     if any([i == 1 for i in pvalues]):
-        print("Warn: p-values are exactly 1.")
+        logger.info("Warn: p-values are exactly 1.")
         return 1
     if weights == None:
         weights = [1 / len(pvalues) for i in pvalues]
@@ -67,18 +69,18 @@ def acat_test(pvalues, weights=None):
 
 def run_Cauchy_combination(config:CauchyCombinationConfig):
     # Load the ldsc results
-    print(f'------Loading LDSC results of {config.input_ldsc_dir}...')
-    ldsc_input_file= Path(config.input_ldsc_dir)/f'{config.sample_name}_{config.trait_name}.csv.gz'
+    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
-        print(f'------Loading ST data of {config.input_hdf5_path}...')
-        spe = sc.read_h5ad(f'{config.input_hdf5_path}')
+        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,]
+        spe = spe[common_cell]
         ldsc = ldsc.loc[common_cell]
 
         # Add the annotation
@@ -86,7 +88,7 @@ def run_Cauchy_combination(config:CauchyCombinationConfig):
 
     elif config.meta is not None:
         # Or Load the additional annotation (just for the macaque data at this stage: 2023Nov25)
-        print(f'------Loading additional annotation...')
+        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)
@@ -115,7 +117,7 @@ def run_Cauchy_combination(config:CauchyCombinationConfig):
         
         # Outlier: -log10(p) < median + 3IQR && len(outlier set) < 20
         if (0 < n_remove < 20):
-            print(f'Remove {n_remove}/{len(p_temp)} outliers (median + 3IQR) for {ct}.')
+            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)
@@ -129,7 +131,7 @@ def run_Cauchy_combination(config:CauchyCombinationConfig):
     p_tissue = pd.DataFrame(data)
     p_tissue.columns = ['p_cauchy', 'p_median', 'annotation']
     # Save the results
-    output_dir = Path(config.output_cauchy_dir)
+    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(
@@ -137,27 +139,3 @@ def run_Cauchy_combination(config:CauchyCombinationConfig):
         compression='gzip',
         index=False,
     )
-
-
-if __name__ == '__main__':
-    TEST = True
-    if TEST:
-        test_dir = '/storage/yangjianLab/chenwenhao/projects/202312_gsMap/data/gsMap_test/Nature_Neuroscience_2021'
-        name = 'Cortex_151507'
-
-        config = CauchyCombinationConfig(
-            input_hdf5_path= f'{test_dir}/{name}/hdf5/{name}_add_latent.h5ad',
-            input_ldsc_dir=
-            f'/storage/yangjianLab/chenwenhao/projects/202312_gsMap/data/gsMap_test/Nature_Neuroscience_2021/snake_workdir/Cortex_151507/ldsc/',
-            sample_name=name,
-            annotation='layer_guess',
-            output_cauchy_dir='/storage/yangjianLab/chenwenhao/projects/202312_gsMap/data/gsMap_test/Nature_Neuroscience_2021/snake_workdir/Cortex_151507/cauchy/',
-            trait_name='adult1_adult2_onset_asthma',
-        )
-    else:
-
-        parser = argparse.ArgumentParser(description="Run Cauchy Combination Analysis")
-        add_Cauchy_combination_args(parser)
-        args = parser.parse_args()
-        config = CauchyCombinationConfig(**vars(args))
-    run_Cauchy_combination(config)