Create old_app.py

old_app.py

@@ -0,0 +1,160 @@
+import nltk
+nltk.data.path.append("/home/user/app/nltk_data")
+#nltk.download('stopwords')
+#nltk.download('punkt')
+import classify_abs
+import extract_abs
+import pandas as pd
+#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 re
+import plotly.graph_objects as go
+
+#### LOGO ####
+st.markdown('''<img src="https://huggingface.co/spaces/ncats/EpiPipeline4RD/raw/main/ncats.svg" alt="National Center for Advancing Translational Sciences Logo">''',unsafe_allow_html=True)
+st.markdown("")
+st.markdown('''<img src="https://huggingface.co/spaces/ncats/EpiPipeline4RD/resolve/main/Logo_GARD_fullres.png" alt="NIH Genetic and Rare Diseases Information Center Logo"  width=400>''',unsafe_allow_html=True)
+
+
+#st.markdown('''<img src="https://huggingface.co/spaces/ncats/EpiPipeline4GARD/raw/main/ncats.svg" alt="National Center for Advancing Translational Sciences Logo" width=800>''',unsafe_allow_html=True)
+#st.markdown("")
+#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=800>''',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)")
+
+#### TITLE ####
+st.title("Epidemiological Information 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/) to automatically search and extract rare disease epidemiology information from PubMed abstracts.")
+
+#### 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 ####
+
+@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
+
+#### 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')
+
+#### SANKEY FUNCTION ####
+
+#@st.cache(allow_output_mutation=True)
+@st.experimental_singleton()
+def epi_sankey(sankey_data, disease_or_gard_id):
+    found, 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, found-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 NIH 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). A full list of rare diseases tracked by the NIH Genetic and Rare Diseases Information Center (GARD) can be found [here](https://rarediseases.info.nih.gov/diseases/browse-by-first-letter).")
+
+if disease_or_gard_id:
+    df, sankey_data, name_gardID = extract_abs.streamlit_extraction(disease_or_gard_id, max_results, filtering,
+                                NER_pipeline, entity_classes,
+                                extract_diseases, GARD_dict, max_length,
+                                classify_model_vars)
+    #IF it returns something, then continue.
+    if sankey_data:
+        df.replace(to_replace='None', value="None")
+        st.dataframe(df, height=200)
+        csv = convert_df(df)
+        disease, gardID = name_gardID
+        #if the user input does not have a number in it (i.e. weak proxy for if it is a GARD ID), then preserve the user input as the disease term.
+        if not bool(re.search(r'\d', disease_or_gard_id)):
+            disease = disease_or_gard_id
+            
+        st.download_button(
+            label="Download epidemiology results for "+disease+" as CSV",
+            data = csv,
+            file_name=disease+'.csv',
+            mime='text/csv',
+            )
+        
+        st.markdown('See the NIH GARD page for ['+disease+'](https://rarediseases.info.nih.gov/diseases/'+str(re.sub('GARD:|0','',gardID))+'/'+str('-'.join(disease.split()))+')')
+        
+        fig = epi_sankey(sankey_data,disease)
+        st.plotly_chart(fig, use_container_width=True)
+        
+        if 'IDS' in list(df.columns):
+            st.markdown('''COLUMNS: \\
+                       - PROB_OF_EPI: Probability that the paper is an epidemiologic study based on its abstract. \\
+                       - IsEpi: If it is an epidemiologic study (If PROB_OF_EPI >0.5) \\
+                       - DIS: Rare disease terms or synonyms identified in the abstract from the GARD Dictionary
+                       - IDS: GARD IDs identified in the abstract from the GARD Dictionary \\
+                       - EPI: Epidemiology Types are the metrics used to estimate disease burden such as "incidence", "prevalence rate", or "occurrence"
+                       - STAT: Epidemiology Rates describe how many people are afflicted by a disease.
+                       - DATE: The dates when the epidemiologic studies were conducted
+                       - LOC: Where the epidemiologic studies were conducted.
+                       - SEX: The biological sexes mentioned in the abstract. Useful for diseases that disproportionately affect one sex over the other or may provide context to composition of the study population
+                       - ETHN: Ethnicities, races, and nationalities of those represented in the epidemiologic study.
+                    ''')
+        else:
+            st.subheader("Categories of Results")
+            st.markdown("    - **PROB_OF_EPI**: Probability that the paper is an epidemiologic study based on its abstract.  \n  - **IsEpi**: If it is an epidemiologic study (If PROB_OF_EPI >0.5)  \n  - **EPI**: Epidemiology Types are the metrics used to estimate disease burden such as 'incidence', 'prevalence rate', or 'occurrence'  \n  - **STAT**: Epidemiology Rates describe how many people are afflicted by a disease.  \n  - **DATE**: The dates when the epidemiologic studies were conducted  \n  - **LOC**: Where the epidemiologic studies were conducted.  \n  - **SEX**: The biological sexes mentioned in the abstract. Useful for diseases that disproportionately affect one sex over the other or may provide context to composition of the study population  \n  - **ETHN**: Ethnicities, races, and nationalities of those represented in the epidemiologic study.")
+        #st.dataframe(data=None, width=None, height=None)