SURE-tools 2.2.7__tar.gz → 2.2.15__tar.gz

{sure_tools-2.2.7 → sure_tools-2.2.15}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: SURE-tools
-Version: 2.2.7
+Version: 2.2.15
 Summary: Succinct Representation of Single Cells
 Home-page: https://github.com/ZengFLab/SURE
 Author: Feng Zeng

{sure_tools-2.2.7 → sure_tools-2.2.15}/SURE/DensityFlow.py

@@ -696,7 +696,7 @@ class DensityFlow(nn.Module):
         """
         Return the mean part of metacell codebook
         """
-        cb = self._get_metacell_coordinates()
+        cb = self._get_codebook()
         cb = tensor_to_numpy(cb)
         return cb
 
@@ -842,47 +842,42 @@ class DensityFlow(nn.Module):
         
         return counts, zs
     
-    def _cell_response(self, xs, factor_idx, perturb):
+    def _cell_response(self, zs, perturb_idx, perturb):
         #zns,_ = self.encoder_zn(xs)    
-        zns,_ = self._get_basal_embedding(xs)   
+        #zns,_ = self._get_basal_embedding(xs)   
+        zns = zs
         if perturb.ndim==2:
-            ms = self.cell_factor_effect[factor_idx]([zns, perturb])
+            ms = self.cell_factor_effect[perturb_idx]([zns, perturb])
         else:
-            ms = self.cell_factor_effect[factor_idx]([zns, perturb.reshape(-1,1)])
+            ms = self.cell_factor_effect[perturb_idx]([zns, perturb.reshape(-1,1)])
             
         return ms 
 
     def get_cell_response(self, 
-                             xs, 
-                             factor_idx,
-                             perturb,
+                             zs, 
+                             perturb_idx,
+                             perturb_us,
                              batch_size: int = 1024):
         """
         Return cells' changes in the latent space induced by specific perturbation of a factor
 
         """
-        xs = self.preprocess(xs)
-        xs = convert_to_tensor(xs, device=self.get_device())
-        ps = convert_to_tensor(perturb, device=self.get_device())
-        dataset = CustomDataset2(xs,ps)
+        #xs = self.preprocess(xs)
+        zs = convert_to_tensor(zs, device=self.get_device())
+        ps = convert_to_tensor(perturb_us, device=self.get_device())
+        dataset = CustomDataset2(zs,ps)
         dataloader = DataLoader(dataset, batch_size=batch_size, shuffle=False)
 
         Z = []
         with tqdm(total=len(dataloader), desc='', unit='batch') as pbar:
-            for X_batch, P_batch, _ in dataloader:
-                zns = self._cell_response(X_batch, factor_idx, P_batch)
+            for Z_batch, P_batch, _ in dataloader:
+                zns = self._cell_response(Z_batch, perturb_idx, P_batch)
                 Z.append(tensor_to_numpy(zns))
                 pbar.update(1)
 
         Z = np.concatenate(Z)
         return Z
     
-    def get_metacell_response(self, factor_idx, perturb):
-        zs = self._get_codebook()
-        ps = convert_to_tensor(perturb, device=self.get_device())         
-        ms = self.cell_factor_effect[factor_idx]([zs,ps])
-        return tensor_to_numpy(ms)
-    
     def _get_expression_response(self, delta_zs):
         return self.decoder_concentrate(delta_zs)
     
@@ -907,7 +902,7 @@ class DensityFlow(nn.Module):
         R = np.concatenate(R)
         return R
     
-    def _count(self,concentrate, library_size=None):
+    def _count(self, concentrate, library_size=None):
         if self.loss_func == 'bernoulli':
             #counts = self.sigmoid(concentrate)
             counts = dist.Bernoulli(logits=concentrate).to_event(1).mean
@@ -917,18 +912,8 @@ class DensityFlow(nn.Module):
             counts = theta * library_size
         return counts
     
-    def _count_sample(self,concentrate):
-        if self.loss_func == 'bernoulli':
-            logits = concentrate
-            counts = dist.Bernoulli(logits=logits).to_event(1).sample()
-        else:
-            counts = self._count(concentrate=concentrate)
-            counts = dist.Poisson(rate=counts).to_event(1).sample()
-        return counts
-    
     def get_counts(self, zs, library_sizes,
-                        batch_size: int = 1024, 
-                        use_sampler: bool = False):
+                        batch_size: int = 1024):
 
         zs = convert_to_tensor(zs, device=self.get_device())
         
@@ -945,10 +930,7 @@ class DensityFlow(nn.Module):
         with tqdm(total=len(dataloader), desc='', unit='batch') as pbar:
             for Z_batch, L_batch, _ in dataloader:
                 concentrate = self._get_expression_response(Z_batch)
-                if use_sampler:
-                    counts = self._count_sample(concentrate)
-                else:
-                    counts = self._count(concentrate, L_batch)
+                counts = self._count(concentrate, L_batch)
                 E.append(tensor_to_numpy(counts))
                 pbar.update(1)
         
@@ -1093,9 +1075,6 @@ class DensityFlow(nn.Module):
                 # Update progress bar
                 pbar.set_postfix({'loss': str_loss})
                 pbar.update(1)
-        
-        if self.loss_func == 'negbinomial':
-            self.inverse_dispersion = pyro.param("inverse_dispersion")
                 
     @classmethod
     def save_model(cls, model, file_path, compression=False):

{sure_tools-2.2.7 → sure_tools-2.2.15}/SURE/perturb/perturb.py

@@ -1,5 +1,6 @@
 import re
 import numpy as np
+import pandas as pd
 from numba import njit
 from itertools import chain
 from joblib import Parallel, delayed
@@ -8,6 +9,8 @@ from typing import Literal
 class LabelMatrix:
     def __init__(self):
         self.labels_ = None
+        self.control_label = None 
+        self.sep_pattern = None
     
     def fit_transform(self, labels, control_label=None, sep_pattern=r'[,;_\s]', speedup: Literal['none','vectorize','parallel']='none'):
         if speedup=='none':
@@ -24,8 +27,31 @@ class LabelMatrix:
             mat = np.delete(mat, idx, axis=1)
             self.labels_ = np.delete(self.labels_, idx)
             
+        self.control_label = control_label
+        self.sep_pattern=sep_pattern
+        
         return mat
-            
+    
+    def transform(self, labels, speedup: Literal['none','vectorize','parallel']='none'):
+        sep_pattern = self.sep_pattern
+        if speedup=='none':
+            mat, labels_ = label_to_matrix(labels=labels, sep_pattern=sep_pattern)
+        elif speedup=='vectorize':
+            mat, labels_ = vectorized_label_to_matrix(labels=labels, sep_pattern=sep_pattern)
+        elif speedup=='parallel':
+            mat, labels_ = parallel_label_to_matrix(labels=labels, sep_pattern=sep_pattern)
+          
+        mat_df = pd.DataFrame(mat, columns=labels_)
+        
+        labels_valid = [x for x in labels_ if x in self.labels_]  
+        mat_df = mat_df[labels_valid]
+        
+        mat_valid = np.zeros([mat.shape[0], len(self.labels_)])
+        mat_valid_df = pd.DataFrame(mat_valid, columns=self.labels_)
+        mat_valid_df[labels_valid] = mat_df 
+        
+        return mat_valid_df.values
+        
     def inverse_transform(self, matrix):
         return matrix_to_labels(matrix=matrix, unique_labels=self.labels_)
 

{sure_tools-2.2.7 → sure_tools-2.2.15}/SURE_tools.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: SURE-tools
-Version: 2.2.7
+Version: 2.2.15
 Summary: Succinct Representation of Single Cells
 Home-page: https://github.com/ZengFLab/SURE
 Author: Feng Zeng

{sure_tools-2.2.7 → sure_tools-2.2.15}/setup.py

@@ -5,7 +5,7 @@ with open("README.md", "r") as fh:
 
 setup(
     name='SURE-tools',
-    version='2.2.7',
+    version='2.2.15',
     description='Succinct Representation of Single Cells',
     long_description=long_description,
     long_description_content_type="text/markdown",