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
import spacy
import tensorflow as tf
import pickle
import plotly.graph_objects as go
########## Title for the Web App ##########
st.markdown('''
''',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('''
''',unsafe_allow_html=True)
st.title("Epidemiology Extraction Pipeline for Rare Diseases")
#st.subheader("National Center for Advancing Translational Sciences (NIH/NCATS)")
#### CHANGE SIDEBAR WIDTH ###
st.markdown(
"""
""",
unsafe_allow_html=True,
)
#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'))
extract_diseases = st.sidebar.checkbox("Extract Rare Diseases", value=False)
@st.experimental_singleton(show_spinner=False)
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
@st.cache(allow_output_mutation=True)
def load_models():
# load the tokenizer
with open('tokenizer.pickle', 'rb') as handle:
classify_tokenizer = pickle.load(handle)
# load the model
classify_model = tf.keras.models.load_model("LSTM_RNN_Model")
#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_tokenizer, classify_model, NER_pipeline, entity_classes, GARD_dict, max_length
@st.experimental_memo
def epi_sankey(sankey_data):
gathered, relevant, epidemiologic = sankey_data
fig = go.Figure(data=[go.Sankey(
node = dict(
pad = 15,
thickness = 20,
line = dict(color = "black", width = 0.5),
label = ["PubMed IDs Gathered", "Irrelevant Abstracts","Relevant Abstracts Gathered","Epidemiologic Abstracts","Not Epidemiologic"],
color = "blue"
),
#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]
))])
return fig
with st.spinner('Loading Epidemiology Models and Dependencies...'):
classify_model_vars, NER_pipeline, entity_classes, GARD_dict, max_length = load_models_experimental()
#classify_tokenizer, classify_model, NER_pipeline, entity_classes, GARD_dict, max_length = load_models()
#Load spaCy models which cannot be cached due to hash function error
#nlp = spacy.load('en_core_web_lg')
#nlpSci = spacy.load("en_ner_bc5cdr_md")
#nlpSci2 = spacy.load('en_ner_bionlp13cg_md')
#classify_model_vars = (nlp, nlpSci, nlpSci2, classify_model, classify_tokenizer)
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), [**phenylketonuria**](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)
st.download_button(
label="Download epidemiology results for "+disease_or_gard_id+" as CSV",
data=df.to_csv().encode('utf-8'),
file_name=disease_or_gard_id+'.csv',
mime='text/csv',
)
#st.dataframe(data=None, width=None, height=None)
fig = epi_sankey(sankey_data)
if st.button('Display Sankey Diagram'):
st.plotly_chart(fig, use_container_width=True)
# st.code(body, language="python")