GenePooler

geneformer/emb_extractor.py

@@ -411,7 +411,7 @@ class EmbExtractor:
         self,
         model_type="Pretrained",
         num_classes=0,
-        emb_mode="cls",
+        emb_mode="cell",
         cell_emb_style="mean_pool",
         gene_emb_style="mean_pool",
         filter_data=None,
@@ -719,12 +719,6 @@ class EmbExtractor:
             )
             raise
 
-        if self.emb_label is not None:
-            logger.error(
-                "For extracting state embs, emb_label should be None since labels are based on state embs dict keys."
-            )
-            raise
-        
         state_embs_dict = dict()
         state_key = cell_states_to_model["state_key"]
         for k, v in cell_states_to_model.items():

geneformer/in_silico_perturber_stats.py

@@ -640,16 +640,10 @@ def isp_stats_mixture_model(cos_sims_df, dict_list, combos, anchor_token):
         cos_sims_full_df = pd.concat([cos_sims_full_df, cos_sims_df_i])
 
     # quantify number of detections of each gene
-    if anchor_token is None:
-        cos_sims_full_df["N_Detections"] = [
-            n_detections(i, dict_list, "cell", anchor_token)
-            for i in cos_sims_full_df["Gene"]
-        ]
-    else:
-        cos_sims_full_df["N_Detections"] = [
-            n_detections(i, dict_list, "gene", anchor_token)
-            for i in cos_sims_full_df["Gene"]
-        ]
+    cos_sims_full_df["N_Detections"] = [
+        n_detections(i, dict_list, "gene", anchor_token)
+        for i in cos_sims_full_df["Gene"]
+    ]
 
     if combos == 0:
         cos_sims_full_df = cos_sims_full_df.sort_values(