app.py

import streamlit as st
import numpy as np
import pandas as pd
import pickle
import sklearn
import xgboost

data = pd.read_csv("annotations_dataset.csv")
data = data.set_index("Gene")

model = pickle.load(open('fitted_model.sav', 'rb'))

predictions = list(model.predict(data))

output = pd.Series(data=predictions, index=data.index, name="XGB_Score")
df_total = pd.concat([data, output], axis=1)


st.title('Blood Pressure Gene Prioritisation Post-Genome-wide Association Study')
st.markdown("""
A machine learning pipeline for predicting disease-causing genes post-genome-wide association study in blood pressure.
""")

st.sidebar.header('Input Gene')
sepal_length = st.text_input(
    label='HGNC Gene Name')