"Model"

app.py

@@ -1,7 +1,42 @@
 import gradio as gr
+import numpy as np
+import pandas as pd
+from sklearn.feature_extraction.text import CountVectorizer
+from sklearn.naive_bayes import MultinomialNB
+import pickle
+import sys
 
 def greet(name):
     return "Hello " + name + "!!"
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+# load the CountVectorizer from disk
+cv = pickle.load(open('countVectTrain.pkl', 'rb'))
+
+# load the model from disk
+filename = 'corona_pred.pkl'
+model = pickle.load(open(filename, 'rb'))
+
+# function to convert sequence string into k-mer words, default size = 6 (hexamer words)
+kmer_size = 6
+def getKmers(sequence, size=kmer_size):
+    return [sequence[x:x+size].lower() for x in range(len(sequence) - size + 1)]
+
+# define the Gradio interface
+def classify_sequence(sequence):
+    # convert the input sequence into k-mer words
+    words = getKmers(sequence)
+    # convert the k-mer words into a list of space-separated strings
+    text = ' '.join(words)
+    # vectorize the text using Count Vectorization
+    X = cv.transform([text])
+    # make predictions using the pre-trained model
+    pred_label = model.predict(X)[0]
+    pred_prob_percentage = model.predict_proba(X).max()*100
+    # return the predicted class and probability
+    return {'predicted_class': pred_label, 'probability': pred_prob_percentage}
+
+iface = gr.Interface(fn=classify_sequence, inputs="text", outputs=["text"], 
+                     title="Coronavirus Sequence Classifier", 
+                     description="Enter a coronavirus sequence to predict its class and probability.")
+
+iface.launch() 

corona_pred.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55025601de7a3c95b6b902e14284cc6b89464c6d847f764a7941a430af3823f2
+size 11555492

countVectTrain.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2af80dee2648aa8c62746a1d574757b666e185e946701700bac71852671b3968
+size 6189395