update for the reproducibility of MicroEnvs

stereo/algorithm/cell_cell_communication/spatial_scoloc.py

@@ -34,7 +34,8 @@ def main(self,
              min_num: int = 30,
              binsize: float = 2,
              eps: float = 1e-20,
-             output_path: str = None
+             output_path: str = None,
+             seed_used: int = 1024
              ):
         """
         Generate the micro-environment file used for the CCC analysis.
@@ -90,8 +91,9 @@ def main(self,
         for col in type_name:
             pairwise_kl_df[col] = pairwise_kl_df[col].apply(lambda x: [])
         # do bootstrap
+        np.random.seed(seed_used)
         for i in range(n_boot):
-            random.seed(i)
+            # random.seed(i)
             # Get the bootstrap sample
             idx = np.random.choice(range(n_cell), round(n_cell * boot_prop), replace=True)
             data_boot = data.iloc[idx,]

stereo/algorithm/gen_ccc_micro_envs.py

@@ -22,6 +22,7 @@ def main(
             binsize: float = 2,
             eps: float = 1e-20,
             show_dividing_by_thresholds: bool = True,
+            seed_used: int = 1024,
             method: str = 'split',
             threshold: float = None,
             output_path: str = None,
@@ -80,6 +81,7 @@ def main(
                         which is then used to construct the microenvironments.
         :param eps: fill eps to zero kde to avoid inf KL divergence.
         :param show_dividing_by_thresholds: whether to display the result while running the first part of this function.
+        :param seed_used: the seed used for random number generator, fix it for reproducibility.
         :param method: define micro environments using two methods:
                         1) minimum spanning tree, or
                         2) pruning the fully connected tree based on a given threshold of KL, then split the graph into multiple strongly connected component.
@@ -129,7 +131,8 @@ def main(
                 min_num=min_num,
                 binsize=binsize,
                 eps=eps,
-                output_path=output_path
+                output_path=output_path,
+                seed_used=seed_used
             )
             self.pipeline_res[res_key] = {
                 'output_path': output_path,