M3Drop 0.4.59__py3-none-any.whl → 0.4.60__py3-none-any.whl

m3Drop/CoreCPU.py

@@ -332,9 +332,17 @@ def NBumiFitDispVsMeanCPU(fit: dict, suppress_plot=True):
     tjs = vals['tjs'].values
     mean_expression = tjs / vals['nc']
     
-    forfit = (np.isfinite(size_g)) & (size_g < 1e6) & (mean_expression > 1e-3) & (size_g > 0)
+    # [FIX] Filter out the 10,000 imputation values.
+    # We treat 10,000 as an error code for "Under-Dispersed/Poissonian".
+    # Masking these prevents artificial gravity from pulling the regression line up.
+    forfit = (np.isfinite(size_g)) & \
+             (size_g < 9999.0) & \
+             (mean_expression > 1e-3) & \
+             (size_g > 0)
+
     log2_mean_expr = np.log2(mean_expression, where=(mean_expression > 0))
     
+    # Heuristic: If we have enough high-expression genes, focus fit there
     higher = log2_mean_expr > 4
     if np.sum(higher & forfit) > 2000:
         forfit = higher & forfit
@@ -347,8 +355,10 @@ def NBumiFitDispVsMeanCPU(fit: dict, suppress_plot=True):
     
     if not suppress_plot:
         plt.figure(figsize=(7, 6))
-        plt.scatter(x, y, alpha=0.5, s=1)
-        plt.plot(x, model.fittedvalues, color='red')
+        # Plot ALL points (grey) vs FITTED points (blue)
+        plt.scatter(np.log(mean_expression), np.log(size_g), alpha=0.3, s=1, c='grey', label='All Genes')
+        plt.scatter(x, y, alpha=0.5, s=1, c='blue', label='Used for Fit')
+        plt.plot(x, model.fittedvalues, color='red', label='Regression Fit')
         plt.show()
 
     return model.params

m3Drop/CoreGPU.py

@@ -324,9 +324,14 @@ def NBumiFitDispVsMeanGPU(fit: dict, suppress_plot=True):
     tjs = vals['tjs'].values
     mean_expression = tjs / vals['nc']
     
-    forfit = (np.isfinite(size_g)) & (size_g < 1e6) & (mean_expression > 1e-3) & (size_g > 0)
+    forfit = (np.isfinite(size_g)) & \
+             (size_g < 9999.0) & \
+             (mean_expression > 1e-3) & \
+             (size_g > 0)
+    
     log2_mean_expr = np.log2(mean_expression, where=(mean_expression > 0))
     
+    # Heuristic: If we have enough high-expression genes, focus fit there
     higher = log2_mean_expr > 4
     if np.sum(higher & forfit) > 2000:
         forfit = higher & forfit
@@ -339,7 +344,8 @@ def NBumiFitDispVsMeanGPU(fit: dict, suppress_plot=True):
     
     if not suppress_plot:
         plt.figure(figsize=(7, 6))
-        plt.scatter(x, y, alpha=0.5, s=1)
+        # Visual check only - code below handles the production plot
+        plt.scatter(x, y, alpha=0.5, s=1, c='blue')
         plt.plot(x, model.fittedvalues, color='red')
         plt.show()
 

m3Drop/DiagnosticsCPU.py

@@ -4,6 +4,7 @@ import matplotlib.pyplot as plt
 import h5py
 import os
 import time
+import sys
 import pickle
 import gc
 from scipy import sparse
@@ -385,9 +386,11 @@ def NBumiPlotDispVsMeanCPU(
     mean_expression = fit['vals']['tjs'].values / fit['vals']['nc']
     sizes = fit['sizes'].values
     
+    # 1. Get calibrated coefficients (using the fixed CoreCPU logic)
     coeffs = NBumiFitDispVsMeanCPU(fit, suppress_plot=True)
     intercept, slope = coeffs[0], coeffs[1]
 
+    # 2. Calculate the regression line
     log_mean_expr_range = np.linspace(
         np.log(mean_expression[mean_expression > 0].min()),
         np.log(mean_expression.max()),
@@ -396,8 +399,19 @@ def NBumiPlotDispVsMeanCPU(
     log_fitted_sizes = intercept + slope * log_mean_expr_range
     fitted_sizes = np.exp(log_fitted_sizes)
 
+    # 3. [FIX] Mask the 10k outliers for the SCATTER PLOT
+    # We create a visualization mask to hide the distracting "roof" at y=10000
+    mask_viz = (sizes < 9999.0) & (sizes > 0)
+    
+    mean_expr_clean = mean_expression[mask_viz]
+    sizes_clean = sizes[mask_viz]
+
     plt.figure(figsize=(8, 6))
-    plt.scatter(mean_expression, sizes, label='Observed Dispersion', alpha=0.5, s=8)
+    
+    # Plot only the clean data
+    plt.scatter(mean_expr_clean, sizes_clean, label='Observed Dispersion', alpha=0.5, s=8)
+    
+    # Plot the regression line (calculated correctly via CoreCPU)
     plt.plot(np.exp(log_mean_expr_range), fitted_sizes, color='red', label='Regression Fit', linewidth=2)
 
     plt.xscale('log')

m3Drop/DiagnosticsGPU.py

@@ -9,6 +9,7 @@ import time
 import pickle
 import psutil
 import gc
+import sys
 from scipy import sparse
 from scipy import stats
 import anndata
@@ -403,9 +404,11 @@ def NBumiPlotDispVsMeanGPU(
     mean_expression = fit['vals']['tjs'].values / fit['vals']['nc']
     sizes = fit['sizes'].values
     
+    # 1. Get calibrated coefficients (using the fixed CoreGPU logic)
     coeffs = NBumiFitDispVsMeanGPU(fit, suppress_plot=True)
     intercept, slope = coeffs[0], coeffs[1]
 
+    # 2. Calculate the regression line
     log_mean_expr_range = np.linspace(
         np.log(mean_expression[mean_expression > 0].min()),
         np.log(mean_expression.max()),
@@ -414,8 +417,19 @@ def NBumiPlotDispVsMeanGPU(
     log_fitted_sizes = intercept + slope * log_mean_expr_range
     fitted_sizes = np.exp(log_fitted_sizes)
 
+    # 3. [FIX] Mask the 10k outliers for the SCATTER PLOT
+    # We create a visualization mask to hide the distracting "roof" at y=10000
+    mask_viz = (sizes < 9999.0) & (sizes > 0)
+    
+    mean_expr_clean = mean_expression[mask_viz]
+    sizes_clean = sizes[mask_viz]
+
     plt.figure(figsize=(8, 6))
-    plt.scatter(mean_expression, sizes, label='Observed Dispersion', alpha=0.5, s=8)
+    
+    # Plot only the clean data
+    plt.scatter(mean_expr_clean, sizes_clean, label='Observed Dispersion', alpha=0.5, s=8)
+    
+    # Plot the regression line (which was calculated correctly via CoreGPU)
     plt.plot(np.exp(log_mean_expr_range), fitted_sizes, color='red', label='Regression Fit', linewidth=2)
 
     plt.xscale('log')

{m3drop-0.4.59.dist-info → m3drop-0.4.60.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: M3Drop
-Version: 0.4.59
+Version: 0.4.60
 Summary: A Python implementation of the M3Drop single-cell RNA-seq analysis tool.
 Home-page: https://github.com/PragalvhaSharma/m3DropNew
 Author: Tallulah Andrews

m3drop-0.4.60.dist-info/RECORD

@@ -0,0 +1,14 @@
+m3Drop/ControlDeviceCPU.py,sha256=8P-hxd4thc2wSeon73b9rz3clIGkE3x0cEE82RiGFds,8880
+m3Drop/ControlDeviceGPU.py,sha256=4nzPtgyV0RsEOeezwCVJ7oyDOsp9-dRVLczlduUocpU,9143
+m3Drop/CoreCPU.py,sha256=EVGh6JFka-PlUHF034z6UOjKsmMdjWJxP0a4Sg1mq4M,19475
+m3Drop/CoreGPU.py,sha256=e-dZhtQgRmOdy6Ill_X9YaLEM7GXOWu4R8VO7SNkr8E,20439
+m3Drop/DiagnosticsCPU.py,sha256=CjuP773llDZuvll3xl0Yjl1BAxMx5vDZY9P4tM-kHyE,14072
+m3Drop/DiagnosticsGPU.py,sha256=qWtH0lGaWwTxaY-7c5oDA2gJff_y0-r18-RqarWZz7E,15521
+m3Drop/NormalizationCPU.py,sha256=Qfj2IRMQyxkvJaAlbH9_H6SMFIWs_UCw3LhY2mOTFSA,13038
+m3Drop/NormalizationGPU.py,sha256=FJLzfYdEB96v9OXld64FZO7r5_M9AU00OSuSlaM0ThY,15541
+m3Drop/__init__.py,sha256=W_TQ9P8_7Tdsa6kDZ6IJKT0FMkX_JFvBqiP821CZIrk,2180
+m3drop-0.4.60.dist-info/licenses/LICENSE,sha256=44Iqpp8Fc10Xzd5T7cT9UhO31Qftk3gBiCjtpwilP_k,1074
+m3drop-0.4.60.dist-info/METADATA,sha256=FDFnoP0RnBjbl0gLkJNsEWcdIUkJwDLtIv9kYQbW9gA,5248
+m3drop-0.4.60.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+m3drop-0.4.60.dist-info/top_level.txt,sha256=AEULFEFIgFtAwS-KBlIFoYXrqczX_rwqrEcdK46GIrA,7
+m3drop-0.4.60.dist-info/RECORD,,

m3drop-0.4.59.dist-info/RECORD

@@ -1,14 +0,0 @@
-m3Drop/ControlDeviceCPU.py,sha256=8P-hxd4thc2wSeon73b9rz3clIGkE3x0cEE82RiGFds,8880
-m3Drop/ControlDeviceGPU.py,sha256=4nzPtgyV0RsEOeezwCVJ7oyDOsp9-dRVLczlduUocpU,9143
-m3Drop/CoreCPU.py,sha256=bJ-4eSW5Q5FXIRdxv6Q8Aj-hF4VhvVq0fFJpTPZGwDA,18922
-m3Drop/CoreGPU.py,sha256=phOUJ6PyOCczY3x_9FzVuOtC-oyHOkDte8bqA1yX7b4,20227
-m3Drop/DiagnosticsCPU.py,sha256=YnKK6mkPEUS8IkQ-vKPE3aZaVJQBsSUp3YsO98sPNV0,13569
-m3Drop/DiagnosticsGPU.py,sha256=wtVC2O48vcfS0sEl7RlXTHGZRBNDehszXEtxgLOqTJc,14994
-m3Drop/NormalizationCPU.py,sha256=Qfj2IRMQyxkvJaAlbH9_H6SMFIWs_UCw3LhY2mOTFSA,13038
-m3Drop/NormalizationGPU.py,sha256=FJLzfYdEB96v9OXld64FZO7r5_M9AU00OSuSlaM0ThY,15541
-m3Drop/__init__.py,sha256=W_TQ9P8_7Tdsa6kDZ6IJKT0FMkX_JFvBqiP821CZIrk,2180
-m3drop-0.4.59.dist-info/licenses/LICENSE,sha256=44Iqpp8Fc10Xzd5T7cT9UhO31Qftk3gBiCjtpwilP_k,1074
-m3drop-0.4.59.dist-info/METADATA,sha256=S9HaM8uJ_X5BfUnho10yRoYV62o8yXkBfm9oWYCKWY4,5248
-m3drop-0.4.59.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-m3drop-0.4.59.dist-info/top_level.txt,sha256=AEULFEFIgFtAwS-KBlIFoYXrqczX_rwqrEcdK46GIrA,7
-m3drop-0.4.59.dist-info/RECORD,,