Update app.py

app.py

@@ -11,10 +11,12 @@ import tensorflow as tf
 import pickle
 import plotly.graph_objects as go
 
-########## Title for the Web App ##########
+#### 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)") 
 
@@ -34,8 +36,11 @@ st.markdown(
     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)
 
@@ -43,6 +48,8 @@ filtering = st.sidebar.radio("What type of filtering would you like?",('Strict',
 
 extract_diseases = st.sidebar.checkbox("Extract Rare Diseases", value=False)
 
+#### MODEL LOADING ####
+
 @st.experimental_singleton(show_spinner=False)
 def load_models_experimental():
     classify_model_vars = classify_abs.init_classify_model()
@@ -50,26 +57,15 @@ def load_models_experimental():
     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
+#### DOWNLOAD FUNCTION ####
 
 @st.cache
 def convert_df(df):
     # IMPORTANT: Cache the conversion to prevent computation on every rerun
     return df.to_csv().encode('utf-8')
     
-#@st.experimental_memo
+#### SANKEY FUNCTION ####
+
 @st.cache(allow_output_mutation=True)
 def epi_sankey(sankey_data,disease_or_gard_id):
     gathered, relevant, epidemiologic = sankey_data
@@ -96,6 +92,8 @@ def epi_sankey(sankey_data,disease_or_gard_id):
     
     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()
     #classify_tokenizer, classify_model, NER_pipeline, entity_classes, GARD_dict, max_length = load_models()
@@ -104,9 +102,13 @@ with st.spinner('Loading Epidemiology Models and Dependencies...'):
     #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!')
+
 st.markdown("Input a rare disease term or GARD ID.")
-disease_or_gard_id = st.text_input()
+
+disease_or_gard_id = st.text_input('')
+
 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).")