Spaces:
Sleeping
Sleeping
import nltk | |
nltk.download('stopwords') | |
nltk.download('punkt') | |
import pandas as pd | |
import classify_abs | |
import extract_abs | |
pd.set_option('display.max_colwidth', None) | |
import streamlit as st | |
st.set_page_config(layout="wide") | |
import spacy | |
import tensorflow as tf | |
import pickle | |
import plotly.graph_objects as go | |
#### LOGO #### | |
st.markdown('''<img src="https://huggingface.co/spaces/ncats/EpiPipeline4GARD/resolve/main/Logo_GARD_fullres.png" alt="NIH Genetic and Rare Diseases Information Center Logo" width=550>''',unsafe_allow_html=True) | |
#st.markdown("![National Center for Advancing Translational Sciences (NCATS) Logo](https://huggingface.co/spaces/ncats/EpiPipeline4GARD/resolve/main/NCATS_logo.png)") | |
#st.markdown('''<img src="https://huggingface.co/spaces/ncats/EpiPipeline4GARD/raw/main/NCATS_logo.svg" alt="National Center for Advancing Translational Sciences Logo" width="800" height="300">''',unsafe_allow_html=True) | |
#### TITLE #### | |
st.title("Epidemiology Extraction Pipeline for Rare Diseases") | |
#st.subheader("National Center for Advancing Translational Sciences (NIH/NCATS)") | |
#### CHANGE SIDEBAR WIDTH ### | |
st.markdown( | |
""" | |
<style> | |
[data-testid="stSidebar"][aria-expanded="true"] > div:first-child { | |
width: 250px; | |
} | |
[data-testid="stSidebar"][aria-expanded="false"] > div:first-child { | |
width: 250px; | |
margin-left: -350px; | |
} | |
</style> | |
""", | |
unsafe_allow_html=True, | |
) | |
#### DESCRIPTION #### | |
st.markdown("This application was built by the [National Center for Advancing Translational Sciences (NCATS)](https://ncats.nih.gov/) for the [National Institutes of Health (NIH)](https://www.nih.gov/) [Genetic and Rare Diseases Information Center](https://rarediseases.info.nih.gov/) to automatically search PubMed abstracts for rare disease epidemiology information.") | |
#### SIDEBAR WIDGETS #### | |
#max_results is Maximum number of PubMed ID's to retrieve BEFORE filtering | |
max_results = st.sidebar.number_input("Maximum number of articles to find in PubMed", min_value=1, max_value=None, value=50) | |
filtering = st.sidebar.radio("What type of filtering would you like?",('Strict', 'Lenient', 'None')).lower() | |
extract_diseases = st.sidebar.checkbox("Extract Rare Diseases", value=False) | |
#### MODEL LOADING #### | |
def load_models_experimental(): | |
classify_model_vars = classify_abs.init_classify_model() | |
NER_pipeline, entity_classes = extract_abs.init_NER_pipeline() | |
GARD_dict, max_length = extract_abs.load_GARD_diseases() | |
return classify_model_vars, NER_pipeline, entity_classes, GARD_dict, max_length | |
#### DOWNLOAD FUNCTION #### | |
def convert_df(df): | |
# IMPORTANT: Cache the conversion to prevent computation on every rerun | |
return df.to_csv().encode('utf-8') | |
#### SANKEY FUNCTION #### | |
#@st.cache(allow_output_mutation=True) | |
def epi_sankey(sankey_data, disease_or_gard_id): | |
gathered, relevant, epidemiologic = sankey_data | |
fig = go.Figure(data=[go.Sankey( | |
node = dict( | |
pad = 15, | |
thickness = 20, | |
line = dict(color = "white", width = 0.5), | |
label = ["PubMed IDs Gathered", "Irrelevant Abstracts","Relevant Abstracts Gathered","Epidemiologic Abstracts","Not Epidemiologic"], | |
color = "purple" | |
), | |
#label = ["A1", "A2", "B1", "B2", "C1", "C2"] | |
link = dict( | |
source = [0, 0, 2, 2], | |
target = [2, 1, 3, 4], | |
value = [relevant, gathered-relevant, epidemiologic, relevant-epidemiologic] | |
))]) | |
fig.update_layout( | |
hovermode = 'x', | |
title="Search for the Epidemiology of "+disease_or_gard_id, | |
font=dict(size = 10, color = 'black'), | |
) | |
return fig | |
#### BEGIN APP #### | |
with st.spinner('Loading Epidemiology Models and Dependencies...'): | |
classify_model_vars, NER_pipeline, entity_classes, GARD_dict, max_length = load_models_experimental() | |
loaded = st.success('All Models and Dependencies Loaded!') | |
disease_or_gard_id = st.text_input("Input a rare disease term or GARD ID.") | |
loaded.empty() | |
st.markdown("Examples of rare diseases include [**Fellman syndrome**](https://rarediseases.info.nih.gov/diseases/1/gracile-syndrome), [**Classic Homocystinuria**](https://rarediseases.info.nih.gov/diseases/6667/classic-homocystinuria), [**7383**](https://rarediseases.info.nih.gov/diseases/7383/phenylketonuria), and [**GARD:0009941**](https://rarediseases.info.nih.gov/diseases/9941/fshmd1a).") | |
st.markdown("A full list of rare diseases tracked by GARD can be found [here](https://rarediseases.info.nih.gov/diseases/browse-by-first-letter).") | |
if disease_or_gard_id: | |
df, sankey_data = extract_abs.streamlit_extraction(disease_or_gard_id, max_results, filtering, | |
NER_pipeline, entity_classes, | |
extract_diseases,GARD_dict, max_length, | |
classify_model_vars) | |
st.dataframe(df, height=100) | |
csv = convert_df(df) | |
st.download_button( | |
label="Download epidemiology results for "+disease_or_gard_id+" as CSV", | |
data = csv, | |
file_name=disease_or_gard_id+'.csv', | |
mime='text/csv', | |
) | |
#st.dataframe(data=None, width=None, height=None) | |
fig = epi_sankey(sankey_data,disease_or_gard_id) | |
#if st.button('Display Sankey Diagram of Automated Search'): | |
st.plotly_chart(fig, use_container_width=True) | |
# st.code(body, language="python") |