Update app.py

app.py

@@ -25,6 +25,27 @@ import tensorflow as tf
 from huggingface_hub import hf_hub_url, cached_download
 
 
+class Sequence:
+    codes = {c: i+1 for i, c in enumerate(['A', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'K', 'L', 'M', 'N', 'P', 'Q', 'R', 'S', 'T', 'V', 'W', 'Y'])}
+
+    @classmethod
+    def integer_encoding(cls, data):
+        """
+        - Encodes code sequence to integer values.
+        - 20 common amino acids are taken into consideration
+        and remaining four are categorized as 0.
+        """
+        return np.array([cls.codes.get(code, 0) for code in data])
+
+    @classmethod
+    def prepare(cls, sequence):
+        ie = cls.integer_encoding(sequence)
+        max_length = 100
+        padded_ie = pad_sequences([ie], maxlen=max_length, padding='post', truncating='post')
+        all_ohe = np.array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20] + [0]*(100-21))
+        return to_categorical(np.array([padded_ie[0], all_ohe]))[0]
+
+
 def residual_block(data, filters, d_rate):
     """
     _data: input
@@ -76,7 +97,7 @@ def get_model():
 
 def greet(name):
     get_model()
-    return "Hello " + name + "!!"
+    return f"Input is {name}. Processed input is {Sequence.process(name)}"
 
 iface = gr.Interface(fn=greet, inputs="text", outputs="text")
 iface.launch()