maradoner 0.12__tar.gz → 0.14__tar.gz

{maradoner-0.12 → maradoner-0.14}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: maradoner
-Version: 0.12
+Version: 0.14
 Summary: Variance-adjusted estimation of motif activities.
 Home-page: https://github.com/autosome-ru/nemara
 Author: Georgy Meshcheryakov

{maradoner-0.12 → maradoner-0.14}/maradoner/__init__.py

@@ -1,5 +1,5 @@
 # -*- coding: utf-8 -*-
-__version__ = '0.12'
+__version__ = '0.14'
 import importlib
 
 

{maradoner-0.12 → maradoner-0.14}/maradoner/create.py

@@ -74,6 +74,14 @@ def create_project(project_name: str, promoter_expression_filename: str, loading
     logger_print('Reading dataset...', verbose)
     promoter_expression = dt.fread(promoter_expression_filename).to_pandas()
     promoter_expression = promoter_expression.set_index(promoter_expression.columns[0])
+    
+    if sample_groups:
+        cols = set()
+        for vals in sample_groups.values():
+            cols.update(vals)
+        cols = list(cols)
+        promoter_expression = promoter_expression[cols]
+    
     proms = promoter_expression.index
     sample_names = promoter_expression.columns
     loading_matrices = [dt.fread(f).to_pandas() for f in loading_matrix_filenames]

{maradoner-0.12 → maradoner-0.14}/maradoner/dataset_filter.py

@@ -141,6 +141,5 @@ def filter_lowexp(expression: pd.DataFrame, cutoff=0.95, max_mode=True,
     inds[:k] = False
     # print(inds)
     # inds[:] = 1
-    print(x[inds].mean(), x[~inds].mean())
     inds = inds[inds_inv]
     return inds, ws

{maradoner-0.12 → maradoner-0.14}/maradoner/grn.py

@@ -79,7 +79,7 @@ def estimate_promoter_variance(project_name: str, prior_top=0.90):
     
 
 def grn(project_name: str,  output: str, use_hdf=False, save_stat=True,
-        prior_h1=1/100):
+        fdr_alpha=0.05, prior_h1=1/100):
     data = read_init(project_name)
     fmt = data.fmt
     with openers[fmt](f'{project_name}.fit.{fmt}', 'rb') as f:
@@ -153,10 +153,20 @@ def grn(project_name: str,  output: str, use_hdf=False, save_stat=True,
         lr = lr[inds]
         belief = belief[inds]
         belief = belief.astype(np.half)
+        sorted_beliefs = np.sort(belief)
+        cumulative_fdr = np.cumsum(sorted_beliefs) / (np.arange(len(sorted_beliefs)) + 1)
+        try:
+            k = np.max(np.where(cumulative_fdr <= fdr_alpha)[0])
+            fdr_threshold = sorted_beliefs[k-1]
+        except ValueError:
+            fdr_threshold = 1.0
+        filename = os.path.join(folder_belief, f'{name}.txt')
+        with open(filename, 'w') as f:
+            f.write(f'{fdr_threshold}')
+
         
-        proms = list(np.array(prom_names)[inds])
         
-        # pvalue = n.sf(lr) * (theta > 0) + n.cdf(lr) * (theta <= 0)
+        proms = list(np.array(prom_names)[inds])
         if use_hdf:
             if save_stat:
                 lr = lr.astype(np.half)

{maradoner-0.12 → maradoner-0.14}/maradoner/main.py

@@ -212,7 +212,7 @@ def _gof(name: str = Argument(..., help='Project name.'),
 
 @app.command('predict', help='Estimate deviations of motif activities from their means.')
 def _predict(name: str = Argument(..., help='Project name.'),
-         filter_motifs: bool = Option(False, help='Do not predict deviations from motifs whose variance is low.'),
+         filter_motifs: bool = Option(True, help='Do not predict deviations from motifs whose variance is low.'),
          filter_order: int = Option(7, help='Motif variance is considered low if it is [orange]filter-order[/orange] orders of magnitude smaller that a median motif variance.'),
          tau_search: bool = Option(False, help='Search for tau multiplier using CV'),
          cv_repeats: int = Option(3, help='CV repeats in [orange]RepeatedKFold[/orange]'),

{maradoner-0.12 → maradoner-0.14}/maradoner.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: maradoner
-Version: 0.12
+Version: 0.14
 Summary: Variance-adjusted estimation of motif activities.
 Home-page: https://github.com/autosome-ru/nemara
 Author: Georgy Meshcheryakov