JAK_ML / hello.py
eikoenchine's picture
Upload 137 files
5b07bd4
raw history blame
No virus
1.54 kB
import streamlit as st
from rdkit.Chem import MACCSkeys
from rdkit import Chem
import numpy as np
import pandas as pd
import xgboost as xgb
# import torch
# import torch.nn as nn
# import torch.nn.functional as F
# from torch.autograd import Variable
# from torch.utils.data import Dataset
# import torch.utils.data
# from torch_geometric.data import DataLoader
# from torch_geometric.data import Data
# from torch_geometric.nn import GATConv, RGCNConv, GCNConv, global_add_pool, global_mean_pool, global_max_pool, GlobalAttention, Set2Set
from sklearn.metrics import f1_score, accuracy_score, average_precision_score, roc_auc_score
import rdkit
from rdkit.Chem.Scaffolds import MurckoScaffold
# from itertools import compress
# import random
# from collections import defaultdict
import pickle
device = 'cpu'
model_path = 'model/'
st.set_page_config(
page_title='Hello'
)
st.write('# JAK inhibiition prediction app')
st.sidebar.success('Select a page above')
st.markdown(
"""
* This is an open-source app framework built specifically for JAK inhibition of a certain drug with its SMILES as input.
* Suitable model(s) could be chosen for prediction based on your need (in JAK page).
* Simple machine learning models, tree models, graph-based models and bert models are trained ane evaluated (results in Model Evaluation page).
* Area uder the curve could also be drawn based on our test set results (in Plot AUC page).
Prediction should be used with caution and just for reference.
""")