Update app.py

app.py

@@ -1,55 +1,81 @@
-# app.py
 import gradio as gr
 import joblib
 import numpy as np
 from collections import Counter
 from typing import List
+import os
+
+# --- Helper Functions ---
+BASES = ['A', 'T', 'C', 'G']
 
-# helper: k-mer extraction / vectorize (k=3)
 def kmer_counts(seq: str, k=3):
     seq = seq.strip().upper()
     counts = Counter()
     if len(seq) < k:
         return counts
-    for i in range(len(seq)-k+1):
+    for i in range(len(seq) - k + 1):
         counts[seq[i:i+k]] += 1
     return counts
 
 def vectorize_single(seq: str, vocab: List[str], k=3):
-    x = np.zeros((1, len(vocab)), dtype=float)
+    X = np.zeros((1, len(vocab)), dtype=float)
     c = kmer_counts(seq, k)
-    for j,kmer in enumerate(vocab):
-        x[0,j] = c.get(kmer, 0)
-    return x
+    for j, kmer in enumerate(vocab):
+        X[0, j] = c.get(kmer, 0)
+    return X
+
+# --- Load Model ---
+MODEL_PATH = "mutation_model.joblib"
+
+if not os.path.exists(MODEL_PATH):
+    raise FileNotFoundError(
+        f"⚠️ Model file '{MODEL_PATH}' not found. "
+        "Please upload 'mutation_model.joblib' along with this app."
+    )
 
-# load model+vocab (mutation_model.joblib must be uploaded too)
-model, vocab = joblib.load("mutation_model.joblib")
+model, vocab = joblib.load(MODEL_PATH)
 
+# --- Prediction Logic ---
 def predict_sequence(sequence: str):
     if not sequence or len(sequence.strip()) < 3:
-        return {"error":"sequence too short"}
+        return {"error": "Please enter a valid DNA sequence (≥3 bases)."}
+
     X = vectorize_single(sequence, vocab=vocab, k=3)
     pred = model.predict(X)[0]
     prob = float(model.predict_proba(X).max()) if hasattr(model, "predict_proba") else None
+
     return {
         "sequence": sequence,
         "mutation_detected": bool(pred),
-        "confidence": prob
+        "confidence": round(prob, 3) if prob else "N/A"
     }
 
-# Gradio UI
-with gr.Blocks() as demo:
-    gr.Markdown("# DNA Mutation Detector (Quick Space)")
-    seq_in = gr.Textbox(label="DNA sequence", placeholder="ATGCGTACGTTAGC...")
-    btn = gr.Button("Analyze")
-    out = gr.JSON()
-    btn.click(fn=predict_sequence, inputs=seq_in, outputs=out)
+# --- Gradio Interface ---
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown(
+        """
+        <h1 style="text-align:center;">🧬 DNA Mutation Analyzer</h1>
+        <p style="text-align:center;">
+        Upload or paste a DNA sequence to check for possible mutations using a Random Forest ML model.
+        </p>
+        """
+    )
+    
+    with gr.Row():
+        seq_input = gr.Textbox(
+            label="DNA Sequence",
+            placeholder="Enter sequence like ATGCGTACGTTAGC...",
+            lines=2,
+        )
+    analyze_btn = gr.Button("🔍 Analyze Sequence")
+    result = gr.JSON(label="Analysis Result")
+    
+    analyze_btn.click(fn=predict_sequence, inputs=seq_input, outputs=result)
 
-# Expose a simple inference API endpoint (Gradio provides /api/predict automatically)
-# but we also expose a programmatic function name for convenience:
+# --- API Endpoint for Programmatic Access ---
 def api_predict(payload: dict):
     seq = payload.get("sequence", "")
     return predict_sequence(seq)
 
 if __name__ == "__main__":
-    demo.launch() change
+    demo.launch()