File size: 2,378 Bytes
715f504 12d3f02 e1678bf 12d3f02 e1678bf 12d3f02 e1678bf 12d3f02 e1678bf 12d3f02 e1678bf 12d3f02 e1678bf 12d3f02 e1678bf 12d3f02 e1678bf 12d3f02 e1678bf 12d3f02 e1678bf 715f504 e1678bf 12d3f02 e1678bf 12d3f02 715f504 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 |
# file: 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']
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):
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)
c = kmer_counts(seq, k)
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."
)
model, vocab = joblib.load(MODEL_PATH)
# --- Prediction Logic ---
def predict_sequence(sequence: str):
if not sequence or len(sequence.strip()) < 3:
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": round(prob, 3) if prob else "N/A"
}
# --- 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;">
Enter a DNA sequence to check for mutations using the 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)
# --- API Endpoint for Programmatic Access ---
def api_predict(payload: dict):
seq = payload.get("sequence", "")
return predict_sequence(seq)
if __name__ == "__main__":
# Launch Gradio with a public link
demo.launch(share=True, ssr_mode=False) |