maradoner 0.14.3__tar.gz → 0.16.0__tar.gz

{maradoner-0.14.3 → maradoner-0.16.0}/PKG-INFO

@@ -1,13 +1,11 @@
 Metadata-Version: 2.1
 Name: maradoner
-Version: 0.14.3
+Version: 0.16.0
 Summary: Variance-adjusted estimation of motif activities.
 Home-page: https://github.com/autosome-ru/maradoner
 Author: Georgy Meshcheryakov
 Author-email: iam@georgy.top
 Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Scientific/Engineering
 Classifier: Operating System :: OS Independent
 Requires-Python: >=3.11

{maradoner-0.14.3 → maradoner-0.16.0}/maradoner/__init__.py

@@ -1,5 +1,5 @@
 # -*- coding: utf-8 -*-
-__version__ = '0.14.3'
+__version__ = '0.16.0'
 import importlib
 
 

{maradoner-0.14.3 → maradoner-0.16.0}/maradoner/export.py

@@ -407,7 +407,45 @@ def export_results(project_name: str, output_folder: str,
             promoter_names_test = np.array(data.promoter_names)[fit.promoter_inds_to_drop]
             export_fov(test, os.path.join(folder, 'test'), promoter_names=promoter_names_test,
                        sample_names=sample_names)
-        
+
+def export_pairwise_test(project_name: str,  output_folder: str,
+                         group_a: str, group_b: str):
+    data = read_init(project_name)
+    fmt = data.fmt
+    motif_names = data.motif_names
+    prom_names = data.promoter_names
+    del data
+    with openers[fmt](f'{project_name}.fit.{fmt}', 'rb') as f:
+        fit: FitResult = dill.load(f)
+    if fit.promoter_inds_to_drop:
+        prom_names = np.delete(prom_names, fit.promoter_inds_to_drop)
+    group_names = fit.group_names
+    with openers[fmt](f'{project_name}.predict.{fmt}', 'rb') as f:
+        act: ActivitiesPrediction = dill.load(f)
+    if act.filtered_motifs is not None:
+        motif_names_filtered = np.delete(motif_names, act.filtered_motifs)
+    else:
+        motif_names_filtered = motif_names
+    i = group_names.index(group_a)
+    j = group_names.index(group_b)
+    variances_a = None
+    variances_b = None
+    for k, cov in enumerate(act.cov()):
+        if k == i:
+            variances_a = cov.diagonal()
+        elif k == j:
+            variances_b = cov.diagonal()
+    U = act.U
+    U_a = U[:, i]
+    U_b = U[:, j]
+    z_stat =  (U_b - U_a) / (variances_a + variances_b) ** 0.5
+    pval = 2 * norm.sf(np.abs(z_stat))
+    fdr = multitest.multipletests(pval, alpha=0.05, method='fdr_by')[1]
+    data = np.array([z_stat, pval, fdr]).T
+    filename = os.path.join(output_folder, f'{group_a}_vs_{group_b}.tsv')
+    os.makedirs(output_folder, exist_ok=True)
+    DF(data, columns=['z_stat', 'pval', 'fdr'],
+       index=motif_names_filtered).to_csv(filename, sep='\t')
             
 def export_loadings_product(project_name: str, output_folder: str,
                             use_hdf: bool = True, intercepts: bool = True,

{maradoner-0.14.3 → maradoner-0.16.0}/maradoner/grn.py

@@ -122,7 +122,7 @@ def bayesian_fdr_control(p0, alpha=0.05):
     return discoveries, threshold
 
 def grn(project_name: str,  output: str, use_hdf=False, save_stat=True,
-        fdr_alpha=0.05, prior_h1=1/100):
+        fdr_alpha=0.05, prior_h1=1/100, include_mean: bool = True):
     data = read_init(project_name)
     fmt = data.fmt
     with openers[fmt](f'{project_name}.fit.{fmt}', 'rb') as f:
@@ -178,13 +178,16 @@ def grn(project_name: str,  output: str, use_hdf=False, save_stat=True,
         os.makedirs(folder_stat, exist_ok=True)
     os.makedirs(folder_belief, exist_ok=True)
     for sigma, nu, name, inds in zip(promvar.T[..., None], nus,  group_names, group_inds):
-        # if name != 'anconeus':
-        #     continue
         print(name)
         var = (B_hat * nu + sigma)
-        Y_ = Y[:, inds][..., None, :] + BM
-        # theta = U[:, inds][..., None, :] + BM
-        theta = B[..., None] * U[:, inds] + BM
+        
+        Y_ = Y[:, inds][..., None, :] 
+        theta = B[..., None] * U[:, inds] 
+        if include_mean:
+            Y_ = Y_ + BM
+            theta = theta + BM
+            
+        
         loglr = 2 * B * (Y_ * theta).sum(axis=-1) - B_pow * (theta ** 2).sum(axis=-1)
         del Y_
         del theta

{maradoner-0.14.3 → maradoner-0.16.0}/maradoner/main.py

@@ -18,6 +18,7 @@ from .synthetic_data import generate_dataset
 from time import time
 from dill import __version__ as dill_version
 from .export import export_results, export_loadings_product, Standardization, ANOVAType
+from .export import export_pairwise_test
 from . import __version__ as project_version
 from .select import select_motifs_single
 import json
@@ -176,7 +177,7 @@ def _fit(name: str = Argument(..., help='Project name.'),
 
 @app.command('gof', help='Estimate GOFs given test/train data split. Provides test info only if [orange]test-chromosomes[/orange] is not None in [cyan]fit[/cyan].')
 def _gof(name: str = Argument(..., help='Project name.'),
-         use_groups: bool = Option(False, help='Compute statistic for sammples aggragated across groups.'), 
+         use_groups: bool = Option(False, help='Compute statistic for samples aggragated across groups.'), 
          stat_type: GOFStat = Option(GOFStat.fov, help='Statistic type to compute'),
          stat_mode: GOFStatMode = Option(GOFStatMode.total, help='Whether to compute stats for residuals or accumulate their effects'),
          gpu: bool = Option(False, help='Use GPU if available for most of computations.'), 
@@ -320,12 +321,13 @@ def _grn(name: str = Argument(..., help='Project name'),
                                            ' comparable to the expression file size.'),
          hdf: bool = Option(True, help='Use HDF format instead of tar.gz files. Typically eats much less space'),
          stat: bool = Option(True, help='Save statistics alongside probabilities.'),
-         prior_h1: float = Option(1/10, help='Prior belief on the expected fraction of motifs active per promoter.')):
+         prior_h1: float = Option(1/10, help='Prior belief on the expected fraction of motifs active per promoter.'),
+         means: bool = Option(True, help='Include motif-specific means in both H_0 and H_1 models, otherwise only activities deviations are being tested.')):
     t0 = time()
     p = Progress(SpinnerColumn(speed=0.5), TextColumn("[progress.description]{task.description}"), transient=True)
     p.add_task(description="Building GRN...", total=None)
     p.start()
-    grn(name, output=folder, use_hdf=hdf, save_stat=stat, prior_h1=prior_h1)
+    grn(name, output=folder, use_hdf=hdf, save_stat=stat, prior_h1=prior_h1, include_mean=means)
     p.stop()
     dt = time() - t0
     rprint(f'[green][bold]✔️[/bold] Done![/green]\t time: {dt:.2f} s.')
@@ -348,6 +350,26 @@ def _estimate_promoter_variance(name: str = Argument(..., help='Project name'),
     p.stop()
     dt = time() - t0
     rprint(f'[green][bold]✔️[/bold] Done![/green]\t time: {dt:.2f} s.')
+    
+@app.command('pairwise-difftest',
+             help='Perform pairwise differential test between 2 groups using posterior distribution of activities.'
+                  ' It computes difference in activities between group_b and group_a and performs a series of Z-tests for each motif.')
+def _pairwise_difftest(name: str = Argument(..., help='Project name'),
+                                group_a: str = Argument(...,
+                                                          help='Name of the first group.'
+                                                          ),
+                                group_b: str = Argument(...,
+                                                          help='Name of the second group.'
+                                                          ),
+                                output_folder: Path = Argument(..., help='Output folder.') ):
+    t0 = time()
+    p = Progress(SpinnerColumn(speed=0.5), TextColumn("[progress.description]{task.description}"), transient=True)
+    p.add_task(description="Performing and saving a pairwise test...", total=None)
+    p.start()
+    export_pairwise_test(name, output_folder, group_a, group_b)
+    p.stop()
+    dt = time() - t0
+    rprint(f'[green][bold]✔️[/bold] Done![/green]\t time: {dt:.2f} s.')
 
 def main():
     check_packages()

{maradoner-0.14.3 → maradoner-0.16.0}/maradoner.egg-info/PKG-INFO

@@ -1,13 +1,11 @@
 Metadata-Version: 2.1
 Name: maradoner
-Version: 0.14.3
+Version: 0.16.0
 Summary: Variance-adjusted estimation of motif activities.
 Home-page: https://github.com/autosome-ru/maradoner
 Author: Georgy Meshcheryakov
 Author-email: iam@georgy.top
 Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Scientific/Engineering
 Classifier: Operating System :: OS Independent
 Requires-Python: >=3.11

{maradoner-0.14.3 → maradoner-0.16.0}/setup.py

@@ -27,8 +27,6 @@ setup(
     url="https://github.com/autosome-ru/maradoner",
     classifiers=[
 	      "Programming Language :: Python :: 3.11",
-	      "Programming Language :: Python :: 3.12",
-	      "Programming Language :: Python :: 3.13",
 	      "Topic :: Scientific/Engineering",
               "Operating System :: OS Independent"]