modified tokenizer

bio_clip_recommender.py

@@ -38,13 +38,12 @@ class ProteinEmbedder:
         print("ProtT5 Online!")
 
     def embed_raw_sequence(self, sequence: str):
-        """Converts a raw string of amino acids into the 1024D vector."""
         seq = re.sub(r"[UZOB]", "X", sequence.upper())
         
         seq_spaced = " ".join(list(seq))
         
         with torch.no_grad():
-            ids = self.tokenizer.batch_encode_plus([seq_spaced], add_special_tokens=True, padding=True, return_tensors="pt")
+            ids = self.tokenizer([seq_spaced], add_special_tokens=True, padding=True, return_tensors="pt")
             input_ids = ids['input_ids'].to(self.device)
             attention_mask = ids['attention_mask'].to(self.device)