model update

app.py

@@ -4,7 +4,7 @@ from transformers import AutoTokenizer
 import pandas as pd
 
 # title
-st.title('Raven AI')
+st.title('Ravens AI')
 
 # text input with label
 sequence = st.text_input('Enter Amino Acid Sequence')
@@ -14,8 +14,8 @@ model_type = st.radio(
     ('Linear T-Cells (MHC Class I Restriction)', 'Linear T-Cells (MHC Class II Restriction)', 'Linear B-Cell'))
 
 # windows length slider
-length = st.slider('Window Length', 1, 20, 10)
-threshold = st.slider('Probability Threshold', 0.0, 1.0, 0.5)
+length = st.slider('Window Length', 1, 50, 10)
+threshold = st.slider('Probability Threshold', 0.0, 1.0, 0.75)
 
 model_checkpoint = "facebook/esm2_t6_8M_UR50D"
 
@@ -29,34 +29,37 @@ elif model_type == 'Linear B-Cell':
     model = TFAutoModelForSequenceClassification.from_pretrained('bcell')
 # submit button
 if st.button('Submit'):
-    # run model
-    locations = []
-    for i in range(len(sequence) - length):
-        peptide_name = sequence[i:i+length]
-        peptide = tokenizer(peptide_name, return_tensors="tf")
-        output = model(peptide)
-        locations.append([peptide_name, output.logits.numpy()[0][0]])
-    
-    locations = pd.DataFrame(locations, columns = ['Peptide', 'Probability'])
-
-    # display table with sequence and probability as the headers
-    def color_survived(x: float): # x between 0 and 1
-        # red to green scale based on x
-        # 0 -> red
-        # 0.5 -> clear
-        # 1 -> green
-
-        # red
-        if x < threshold:
-            r = 179
-            g = 40
-            b = 2
-        # green
-        else:
-            r = 18
-            g = 150
-            b = 6
-
-        return f'background-color: rgb({r}, {g}, {b})'
-
-    st.table(locations.style.applymap(color_survived, subset=['Probability']))
+    if(length > len(sequence)):
+        st.write("Please make sure that your window length is less than the sequence length!")
+    else:
+        # run model
+        locations = []
+        for i in range(len(sequence) - length + 1):
+            peptide_name = sequence[i:i+length]
+            peptide = tokenizer(peptide_name, return_tensors="tf")
+            output = model(peptide)
+            locations.append([peptide_name, output.logits.numpy()[0][0]])
+        
+        locations = pd.DataFrame(locations, columns = ['Peptide', 'Probability'])
+
+        # display table with sequence and probability as the headers
+        def color_survived(x: float): # x between 0 and 1
+            # red to green scale based on x
+            # 0 -> red
+            # 0.5 -> clear
+            # 1 -> green
+
+            # red
+            if x < threshold:
+                r = 179
+                g = 40
+                b = 2
+            # green
+            else:
+                r = 18
+                g = 150
+                b = 6
+
+            return f'background-color: rgb({r}, {g}, {b})'
+
+        st.table(locations.style.applymap(color_survived, subset=['Probability']))

bcell/tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc764936c96b97e3e5678e26e08f8e96eb7a1effaabc4b8cc1173471f0c3eb5d
+oid sha256:4e1cffc07e744025c7efe0ae8a4e3081fbb5f68f6b9c88b3ccfe0b96979929f1
 size 30211508