Spaces:
Sleeping
Sleeping
| import nltk | |
| nltk.data.path.append("/home/user/app/nltk_data") | |
| #nltk.download('stopwords') | |
| #nltk.download('punkt') | |
| from epi_pipeline import ( | |
| streamlit_extraction, | |
| NER_Pipeline, | |
| GARD_Search, | |
| Classify_Pipeline | |
| ) | |
| 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("") | |
| #### 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 #### | |
| def load_models_experimental(): | |
| epi_classify = Classify_Pipeline() | |
| epi_extract = NER_Pipeline() | |
| rd_identify = GARD_Search() | |
| return epi_classify, epi_extract, rd_identify | |
| #### 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): | |
| 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...'): | |
| epi_classify, epi_extract, rd_identify = 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 = streamlit_extraction(disease_or_gard_id, max_results, filtering, | |
| epi_ner, GARD_Search, extract_diseases, epi_classify) | |
| #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) |