SURE-tools 2.1.37__tar.gz → 2.1.39__tar.gz

{sure_tools-2.1.37 → sure_tools-2.1.39}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: SURE-tools
-Version: 2.1.37
+Version: 2.1.39
 Summary: Succinct Representation of Single Cells
 Home-page: https://github.com/ZengFLab/SURE
 Author: Feng Zeng

sure_tools-2.1.39/SURE/perturb/__init__.py

@@ -0,0 +1 @@
+from .perturb import LabelMatrix,DoseMatrix

{sure_tools-2.1.37 → sure_tools-2.1.39}/SURE/perturb/perturb.py

@@ -1,5 +1,6 @@
 import re
 import numpy as np
+from numba import njit
 from itertools import chain
 from joblib import Parallel, delayed
 from typing import Literal
@@ -27,6 +28,20 @@ class LabelMatrix:
             
     def inverse_transform(self, matrix):
         return matrix_to_labels(matrix=matrix, unique_labels=self.labels_)
+
+class DoseMatrix:
+    def __init__(self):
+        self.labels_ = None 
+        
+    def fit_transform(self, labels, label_dose, control_label=None):
+        mat, self.labels_ = dose_to_matrix(labels, label_dose)
+        
+        if control_label is not None:
+            idx = np.where(self.labels_==control_label)[0]
+            mat = np.delete(mat, idx, axis=1)
+            self.labels_ = np.delete(self.labels_, idx)
+            
+        return mat 
         
 def label_to_matrix(labels, sep_pattern=r'[;_\-\s]'):
     """
@@ -91,3 +106,45 @@ def parallel_label_to_matrix(labels, sep_pattern=r'[;_\-\s]', n_jobs=4):
 def matrix_to_labels(matrix, unique_labels):
     return [';'.join([unique_labels[i] for i in np.where(row)[0]]) 
             for row in matrix]
+
+
+
+
+
+
+
+@njit(parallel=True)
+def _numba_fill_matrix(dose_matrix, label_indices, label_doses):
+    """Numba 加速的矩阵填充函数"""
+    for i in range(len(label_indices)):
+        for j, dose in zip(label_indices[i], label_doses[i]):
+            dose_matrix[i, j] = dose
+
+def dose_to_matrix(labels, label_dose, all_labels=None):
+    """
+    使用 Numba 的终极加速版本（需预先安装 numba）
+    """
+    if all_labels is None:
+        all_labels = sorted(set().union(*labels))
+    
+    label_to_idx = {label: idx for idx, label in enumerate(all_labels)}
+    n_samples = len(labels)
+    n_labels = len(all_labels)
+    dose_matrix = np.zeros((n_samples, n_labels), dtype=np.float64)
+    
+    # 预处理为 Numba 兼容格式
+    label_indices = []
+    label_doses = []
+    for sample_labels in labels:
+        indices = []
+        doses = []
+        if sample_labels:
+            for label in sample_labels:
+                indices.append(label_to_idx[label])
+                doses.append(label_dose[label])
+        label_indices.append(np.array(indices, dtype=np.int64))
+        label_doses.append(np.array(doses, dtype=np.float64))
+    
+    # 调用 Numba 加速函数
+    _numba_fill_matrix(dose_matrix, label_indices, label_doses)
+    return dose_matrix,all_labels

{sure_tools-2.1.37 → sure_tools-2.1.39}/SURE_tools.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: SURE-tools
-Version: 2.1.37
+Version: 2.1.39
 Summary: Succinct Representation of Single Cells
 Home-page: https://github.com/ZengFLab/SURE
 Author: Feng Zeng

{sure_tools-2.1.37 → sure_tools-2.1.39}/setup.py

@@ -5,7 +5,7 @@ with open("README.md", "r") as fh:
 
 setup(
     name='SURE-tools',
-    version='2.1.37',
+    version='2.1.39',
     description='Succinct Representation of Single Cells',
     long_description=long_description,
     long_description_content_type="text/markdown",

sure_tools-2.1.37/SURE/perturb/__init__.py

@@ -1 +0,0 @@
-from .perturb import LabelMatrix