Spaces:
Sleeping
Sleeping
import streamlit as st | |
import numpy as np | |
import pandas as pd | |
import sklearn | |
import xgboost | |
seed=42 | |
data = pd.read_csv("annotations_dataset.csv") | |
data = data.set_index("Gene") | |
training_data = pd.read_csv("./selected_features_training_data.csv", header=0) | |
training_data.columns = [ | |
regex.sub("_", col) if any(x in str(col) for x in set(("[", "]", "<"))) else col | |
for col in training_data.columns.values | |
] | |
training_data["BPlabel_encoded"] = training_data["BPlabel"].map( | |
{"most likely": 1, "probable": 0.75, "least likely": 0.1} | |
) | |
Y = training_data["BPlabel_encoded"] | |
X = training_data.drop(columns=["BPlabel_encoded","BPlabel"]) | |
xgb = xgboost.XGBRegressor( | |
n_estimators=40, | |
learning_rate=0.2, | |
max_depth=4, | |
reg_alpha=1, | |
reg_lambda=1, | |
random_state=seed, | |
objective="reg:squarederror", | |
) | |
xgb.fit(X, Y) | |
predictions = list(xgb.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') | |
gene_name = st.text_input( | |
label='HGNC Gene Name') |