dspin 1.3.3__tar.gz → 1.3.5__tar.gz

{dspin-1.3.3/dspin.egg-info → dspin-1.3.5}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: dspin
-Version: 1.3.3
+Version: 1.3.5
 Summary: Regulatory network models from single-cell perturbation profiling
 Home-page: https://github.com/JialongJiang/DSPIN
 Author: Jialong Jiang
@@ -25,6 +25,18 @@ Requires-Dist: scanpy
 Requires-Dist: tqdm
 Requires-Dist: igraph
 Requires-Dist: leidenalg
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
 
 # D-SPIN: Constructing regulatory network models from scRNA-seq perturbation profiling  
 

{dspin-1.3.3 → dspin-1.3.5}/dspin/annotate.py

@@ -4,7 +4,6 @@
 @Author  :   Jialong Jiang
 '''
 
-
 import csv
 import pandas as pd
 from typing import List

{dspin-1.3.3 → dspin-1.3.5}/dspin/compute.py

@@ -108,7 +108,7 @@ def summary_components(all_components: np.array,
         gene_weight = np.sum(all_components ** 2, axis=0) ** 0.5
         gene_sele_filt = gene_weight > np.mean(gene_weight)
         all_components_sub = all_components[:, gene_sele_filt]
-        kmeans_gene = KMeans(n_clusters=2 * num_spin, random_state=0, n_init=10).fit(all_components_sub.T)
+        kmeans_gene = KMeans(n_clusters=min(2 * num_spin, all_components_sub.shape[1]), random_state=0, n_init=10).fit(all_components_sub.T)
 
         # Initialize an array to store the average component for each cluster.
         components_kmeans = np.zeros((num_spin, num_gene))

{dspin-1.3.3 → dspin-1.3.5}/dspin/dspin.py

@@ -207,6 +207,7 @@ class AbstractDSPIN(ABC):
             self._samp_list = self._samp_list[example_list_ind]
             raw_data = raw_data[example_list_ind]
             self._raw_data = raw_data
+            print("Using a subset of {} samples for network inference.".format(len(self._samp_list)))
 
         num_sample = len(raw_data)
         params = {'num_epoch': 400,
@@ -497,6 +498,42 @@ class ProgramDSPIN(AbstractDSPIN):
     def onmf_decomposition(self, value):
         self._onmf_summary = value
 
+    def compute_onmf_expression(self, 
+                                sample_matrix: np.ndarray,
+                                gene_group_ind: List[List[int]]):
+        """
+        Compute the oNMF expression for a given sample matrix and gene components of each program.
+
+        Parameters
+        ----------
+        sample_matrix : np.ndarray
+            The sample matrix containing gene expressions.
+        gene_group_ind : List[List[int]]
+            List of lists containing indices of genes for each program component.
+
+        Returns
+        -------
+        NMF
+            An NMF object containing the computed components.
+        """
+        num_spin = self.num_spin
+        adata = self.adata
+
+        # Initialize and compute the summary matrix
+        components_summary = np.zeros((num_spin, adata.shape[1]))
+        for ii in range(num_spin):
+            sub_matrix = sample_matrix[:, gene_group_ind[ii]]
+            sub_onmf = NMF(n_components=1, init='random', random_state=0).fit(sub_matrix)
+            components_summary[ii, gene_group_ind[ii]] = sub_onmf.components_
+
+        # Normalize the summary components and finalize the onmf_summary object
+        components_summary = normalize(components_summary, axis=1, norm='l2')
+        onmf_summary = NMF(n_components=num_spin, init='random', random_state=0)
+        onmf_summary.components_ = components_summary
+
+        return onmf_summary
+
+
     def summarize_onmf_result(self,
                               large_subsample_matrix: np.ndarray,
                               num_onmf_components: int,
@@ -517,10 +554,6 @@ class ProgramDSPIN(AbstractDSPIN):
         NMF
             An NMF object containing the summarized components.
         """
-
-        # Retrieve the number of spins and annotated data
-        num_spin = self.num_spin
-        adata = self.adata
         prior_programs_mask = self.prior_programs_mask
         seed_list = self.onmf_parameters['seed_list']
         summary_method = self.onmf_parameters['summary_method']
@@ -533,7 +566,7 @@ class ProgramDSPIN(AbstractDSPIN):
             cur_onmf = np.load(self.save_path + f'onmf/onmf_components_{num_onmf_components}_repeat_{cur_seed}.npy', allow_pickle=True).item()
             rec_components[ii] = cur_onmf.components_
 
-        all_components = rec_components.reshape(-1, np.sum(prior_programs_mask))
+        all_components = rec_components.reshape(- 1, np.sum(prior_programs_mask))
 
         gene_group_ind = summary_components(all_components, num_onmf_components, summary_method=summary_method, figure_folder=self.fig_folder)
 
@@ -542,17 +575,8 @@ class ProgramDSPIN(AbstractDSPIN):
         gene_group_ind = [sub_mask_ind[gene_list] for gene_list in gene_group_ind]
         gene_group_ind += self.prior_programs_ind
 
-        # Initialize and compute the summary matrix
-        components_summary = np.zeros((num_spin, adata.shape[1]))
-        for ii in range(num_spin):
-            sub_matrix = large_subsample_matrix[:, gene_group_ind[ii]]
-            sub_onmf = NMF(n_components=1, init='random', random_state=0).fit(sub_matrix)
-            components_summary[ii, gene_group_ind[ii]] = sub_onmf.components_
-
-        # Normalize the summary components and finalize the onmf_summary object
-        components_summary = normalize(components_summary, axis=1, norm='l2')
-        onmf_summary = NMF(n_components=num_spin, init='random', random_state=0)
-        onmf_summary.components_ = components_summary
+        # Evaluate the expression level of each program and the weights for each gene in the program 
+        onmf_summary = self.compute_onmf_expression(large_subsample_matrix, gene_group_ind)
 
         return onmf_summary
 
@@ -585,9 +609,9 @@ class ProgramDSPIN(AbstractDSPIN):
             Parameters for discretization of the oNMF representation. Default is an empty dictionary.
         """
 
-        if mode not in ['compute_summary', 'compute_only', 'summary_only']:
+        if mode not in ['compute_summary', 'compute_only', 'summary_only', 'precomputed']:
             raise ValueError(
-                'Mode must be one of compute_summary, compute_only, or summary_only')
+                'Mode must be one of compute_summary, compute_only, summary_only, or precomputed.')
         
         adata = self.adata
         num_spin = self.num_spin
@@ -607,6 +631,7 @@ class ProgramDSPIN(AbstractDSPIN):
         
         if onmf_parameters['num_subsample_large'] is None:
             onmf_parameters['num_subsample_large'] = min(onmf_parameters['num_subsample'] * 5, adata.shape[0])
+            # print(onmf_parameters['num_subsample_large'])
 
         if onmf_parameters['balance_method'] not in ['equal', 'proportional', 'squareroot', None]:
             raise ValueError('balance_method must be one of equal, proportional, squareroot, or None')
@@ -619,7 +644,13 @@ class ProgramDSPIN(AbstractDSPIN):
             prior_program_ind = [[np.where(adata.var_names == gene)[0][0] for gene in gene_list] for gene_list in prior_programs]
             preprogram_flat = [gene for program in prior_programs for gene in program]
             if len(prior_programs) > num_spin:
-                raise ValueError('Number of prior_programs must be less than the number of spins')
+                raise ValueError('Number of prior programs must be less than the number of programs')
+            elif len(prior_programs) == num_spin:
+                warnings.warn('Number of prior programs is equal to the number of programs. No oNMF is performed.')
+                mode = 'summary_only'
+            elif len(prior_programs) == 0:
+                warnings.warn('Empty prior programs')
+
             # Generate mask to exclude genes in prior programs from the annotated data
             prior_program_mask = ~ np.isin(adata.var_names, preprogram_flat)
             onmf_parameters['num_onmf_components'] -= len(prior_programs)
@@ -650,20 +681,36 @@ class ProgramDSPIN(AbstractDSPIN):
 
                 compute_onmf_decomposition(sub_gene_matrix_normed, num_onmf_components, seed=cur_seed, params=onmf_parameters, save_path=self.save_path + f'onmf/onmf_components_{num_onmf_components}_repeat_{cur_seed}.npy')
             
-        if mode == 'compute_summary' or mode == 'summary_only':
+        if mode == 'compute_summary' or mode == 'summary_only' or mode == 'precomputed':
+            
+            cluster_label_raw = adata.obs[cluster_key].values
+            cluster_label = pd.factorize(cluster_label_raw)[0]
 
             # Perform subsampling and standard deviation clipping on the matrix
-            std_clipped, sub_large_gene_matrix_normed = subsample_normalize_gene_matrix(cur_gene_matrix, cluster_label, num_subsample=onmf_parameters['num_subsample_large'], seed=seed + rep, params=onmf_parameters)
+            std_clipped, sub_large_gene_matrix_normed = subsample_normalize_gene_matrix(adata.X, cluster_label, num_subsample=onmf_parameters['num_subsample_large'], seed=seed, params=onmf_parameters)
             self.matrix_std = std_clipped
-            
-            # Summarize the oNMF decompositions
-            onmf_summary = self.summarize_onmf_result(sub_large_gene_matrix_normed, num_onmf_components, num_repeat)
+
+            if mode != 'precomputed':
+                # Summarize the oNMF decompositions
+                if num_onmf_components > 0:
+                    onmf_summary = self.summarize_onmf_result(sub_large_gene_matrix_normed, num_onmf_components, num_repeat)
+                else:
+                    onmf_summary = self.compute_onmf_expression(sub_large_gene_matrix_normed, prior_program_ind)
+                
+                onmf_save_path = self.save_path + f'onmf/onmf_summary_total_{num_spin}_onmf_{num_onmf_components}_prior_{len(prior_program_ind)}.npy'
+                np.save(onmf_save_path, onmf_summary)
+                print(f"Consensus oNMF results saved to {onmf_save_path}")
+            else:
+                assert 'precomputed_onmf_path' in params.keys(), "For precomputed mode, 'precomputed_onmf_path' must be provided in params."
+                onmf_summary = np.load(params['precomputed_onmf_path'], allow_pickle=True).item()
             
             self._onmf_summary = onmf_summary
 
             # Save the gene programs to a CSV file
             file_path = onmf_to_csv(onmf_summary.components_, adata.var_names, self.save_path + f'gene_programs_total_{num_spin}_onmf_{num_onmf_components}_prior_{len(prior_program_ind)}.csv', thres=0.01)
-            print('Gene programs saved to {}'.format(file_path))
+            print('Gene program information saved to {}'.format(file_path))
+            file_wpath = onmf_to_csv(onmf_summary.components_, adata.var_names, self.save_path + f'gene_programs_total_{num_spin}_onmf_{num_onmf_components}_prior_{len(prior_program_ind)}_weights.csv', thres=0.01, if_write_weights=True)
+            # print('Gene programs saved to {}'.format(file_path))
             self.gene_program_csv = file_path
 
             gene_matrix = self.adata.X

{dspin-1.3.3 → dspin-1.3.5}/dspin/plot.py

@@ -21,7 +21,7 @@ from scipy import optimize
 from scipy.spatial.distance import pdist
 
 
-def onmf_to_csv(features, gene_name, file_path, thres=0.01):
+def onmf_to_csv(features, gene_name, file_path, thres=0.01, if_write_weights=False):
     """
     Extract gene names in ONMF to CSV.
 
@@ -30,6 +30,7 @@ def onmf_to_csv(features, gene_name, file_path, thres=0.01):
     gene_name (List[str]): Names of the genes corresponding to feature indices.
     file_path (str): Path of the file where the CSV will be written.
     thres (float): Threshold value for filtering features.
+    if_write_weights (bool): If True, writes weights to the CSV file.
 
     Returns:
     str: Path of the created CSV file.
@@ -51,6 +52,11 @@ def onmf_to_csv(features, gene_name, file_path, thres=0.01):
             cur_line.insert(0, spin)
             write.writerow(cur_line)  # Write the current line to the CSV file
 
+            if if_write_weights:
+                cur_line = [features[spin, ind].round(6) for ind in gene_ind]
+                cur_line.insert(0, f'Weights_{spin}')
+                write.writerow(cur_line)
+
     # Read the created CSV, transpose it and save it again
     pd_csv = pd.read_csv(file_path, names=range(rec_max_gene + 1))
     pd_csv = pd_csv.transpose()

{dspin-1.3.3 → dspin-1.3.5/dspin.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: dspin
-Version: 1.3.3
+Version: 1.3.5
 Summary: Regulatory network models from single-cell perturbation profiling
 Home-page: https://github.com/JialongJiang/DSPIN
 Author: Jialong Jiang
@@ -25,6 +25,18 @@ Requires-Dist: scanpy
 Requires-Dist: tqdm
 Requires-Dist: igraph
 Requires-Dist: leidenalg
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
 
 # D-SPIN: Constructing regulatory network models from scRNA-seq perturbation profiling  
 

{dspin-1.3.3 → dspin-1.3.5}/setup.py

@@ -21,7 +21,7 @@ install_requires = [
 # ]
 
 # Managing your version (adjust accordingly)
-version = "1.3.3"  # You can manage versioning in a more sophisticated way if needed
+version = "1.3.5"  # You can manage versioning in a more sophisticated way if needed
 
 # Long description (usually a README file)
 readme = open("README_PyPI.md").read()  # Adjust the file name if necessary