ProtHGT_app.py

import os
import streamlit as st
import time
import streamlit.components.v1 as components
import pandas as pd


with st.spinner("Please wait while we prepare the environment. This may take up to 10 minutes on the first run..."):
    # Run setup script if not already executed
    if not os.path.exists(".setup_done"):
        start_time = time.time()
        os.system("bash setup.sh")
        end_time = time.time()
        print(f"Environment prepared in {end_time - start_time:.2f} seconds")
        with open(".setup_done", "w") as f:
            f.write("done")

from run_prothgt_app import *

def convert_df(df):
   return df.to_csv(index=False).encode('utf-8')

# Initialize session state variables
if 'predictions_df' not in st.session_state:
    st.session_state.predictions_df = None
if 'submitted' not in st.session_state:
    st.session_state.submitted = False

with st.expander("🚀 Upcoming Features"):
    st.info("""
    We are actively working on enhancing ProtHGT application with new capabilities:
    
    - **Real-time data retrieval for new proteins**: Currently, ProtHGT can only generate predictions for proteins that already exist in our knowledge graph. We are developing a new feature that will allow users to **predict functions for entirely new proteins starting from their sequences**. This will work by **retrieving relevant relationship data in real time from external source databases** (e.g., UniProt, STRING, and other biological repositories). The system will dynamically construct a knowledge graph for the query protein, incorporating its interactions, domains, pathways, and other biological associations before running function prediction. This approach will enable ProtHGT to analyze newly discovered or less-studied proteins even if they are not pre-annotated in our dataset.  
    - **Expanded embedding options**: Currently, this application represents proteins using **TAPE embeddings**, which serve as the initial numerical representations of protein sequences before being processed in the heterogeneous graph model. We are working on integrating **ProtT5** and **ESM-2** as alternative initial embeddings, allowing users to choose different sequence representations that may enhance performance for specific tasks. A detailed comparison of how these embeddings influence function prediction accuracy will be included in our upcoming publication.
    
    Stay tuned for updates and future publications!
    """)

with st.sidebar:
    st.markdown("""
        <style>
        .title {
            font-size: 35px;
            font-weight: bold;
            color: #424242;
            margin-bottom: 0px;
        }
        .subtitle {
            font-size: 20px;
            color: #424242;
            margin-bottom: 20px;
            line-height: 1.5;
        }
        .badges {
            margin-top: 10px;
            margin-bottom: 20px;
        }
        </style>
        
        <div class="title">ProtHGT</div>
        <div class="subtitle">Heterogeneous Graph Transformers for Automated Protein Function Prediction Using Knowledge Graphs and Language Models</div>
        <div class="badges">
            <a href="https://github.com/HUBioDataLab/ProtHGT">
                <img src="https://img.shields.io/badge/GitHub-black?logo=github" alt="github-repository">
            </a>
        </div>
    """, unsafe_allow_html=True)

    available_proteins = get_available_proteins() 

    selected_proteins = []
    
    # Add protein selection methods
    selection_method = st.radio(
        "Choose input method:",
        ["Search proteins", "Upload protein ID file"]
    )

    if selection_method == "Search proteins":
        # Add custom CSS to make multiselect scrollable
        st.markdown("""
            <style>
            [data-testid="stMultiSelect"] div:nth-child(2) {
                max-height: 200px;
                overflow-y: auto;
            }
            </style>
            """, unsafe_allow_html=True)
            
        selected_proteins = st.multiselect(
            "Select or search for proteins (UniProt IDs)",
            options=available_proteins,
            placeholder="Start typing to search...",
            max_selections=1000
        )

        if selected_proteins:
            st.write(f"Selected {len(selected_proteins)} proteins")
            
    else:
        uploaded_file = st.file_uploader(
            "Upload a text file with UniProt IDs (one per line, max 1000)*",
            type=['txt']
        )        

        if uploaded_file:
            protein_list = [line.decode('utf-8').strip() for line in uploaded_file]
            # Remove empty lines and duplicates
            protein_list = list(filter(None, protein_list))
            protein_list = list(dict.fromkeys(protein_list))
            
            # Check for proteins not in available_proteins
            proteins_not_found = [p for p in protein_list if p not in available_proteins]
            # Filter to keep only available proteins
            protein_list = [p for p in protein_list if p in available_proteins]

            if len(protein_list) > 1000:
                st.error("Please upload a file with maximum 1000 protein IDs.")
                selected_proteins = []
            else:
                selected_proteins = protein_list
                st.write(f"Loaded {len(selected_proteins)} proteins")

                if proteins_not_found:
                    st.warning(f"""
                    The following proteins were not found in our input knowledge graph and have been discarded: 
                    """)
                    with st.expander("View Discarded Proteins"):
                        # Create scrollable container with fixed height
                        st.markdown(
                            f"""
                            <div style="
                                height: 150px; 
                                overflow-y: scroll;
                                border: 1px solid #ccc;
                                border-radius: 4px;
                                padding: 8px;
                                margin-bottom: 16px;
                                background-color: white;">
                                {'<br>'.join(proteins_not_found)}
                            </div>
                            """, 
                            unsafe_allow_html=True
                        )
                        
                    st.warning(f"""
                    Currently, our system can only generate predictions for proteins that are already included in our knowledge graph. **Real-time retrieval of relationship data from external source databases is not yet supported.**  
                    We are actively working on integrating this capability in future updates. Stay tuned!
                    """)
    if selected_proteins:
        with st.expander("View Selected Proteins"):
            st.write(f"Total proteins selected: {len(selected_proteins)}")
            
            # Create scrollable container with fixed height
            st.markdown(
                f"""
                <div style="
                    height: 150px; 
                    overflow-y: scroll;
                    border: 1px solid #ccc;
                    border-radius: 4px;
                    padding: 8px;
                    background-color: white;">
                    {'<br>'.join(selected_proteins)}
                </div>
                """, 
                unsafe_allow_html=True
            )

            st.markdown("<div style='padding-top: 10px;'></div>", unsafe_allow_html=True)

            # Add download button
            proteins_text = '\n'.join(selected_proteins)
            st.download_button(
                label="Download List",
                data=proteins_text,
                file_name="selected_proteins.txt",
                mime="text/plain",
                key="download_button"
            )

        # Add GO category selection
        go_category_options = {
            'All Categories': None,
            'Molecular Function': 'GO_term_F',
            'Biological Process': 'GO_term_P',
            'Cellular Component': 'GO_term_C'
        }
        selected_go_category = st.selectbox(
            "Select GO Category for predictions",
            options=list(go_category_options.keys()),
            help="Choose which GO category to generate predictions for. Selecting 'All Categories' will generate predictions for all three categories."
        )

    st.warning("⚠️ Due to memory and computational constraints, the maximum number of proteins that can be processed at once is limited to 1000 proteins. For larger datasets, please consider running the model locally using our GitHub repository.")

    if selected_proteins and selected_go_category:
        # Add a button to trigger predictions
        if st.button("Generate Predictions"):
            st.session_state.submitted = True

if st.session_state.submitted:
    with st.spinner("Generating predictions..."):
        # Generate predictions only if not already in session state
        if st.session_state.predictions_df is None:

            # Load model config from JSON file
            import json
            import os

            # Define data directory path
            data_dir = "data"
            models_dir = os.path.join(data_dir, "models")

            # Load model configuration
            model_config_paths = {
                'GO_term_F': os.path.join(models_dir, "prothgt-config-molecular-function.yaml"),
                'GO_term_P': os.path.join(models_dir, "prothgt-config-biological-process.yaml"),
                'GO_term_C': os.path.join(models_dir, "prothgt-config-cellular-component.yaml")
            }

            # Paths for model and data
            model_paths = {
                'GO_term_F': os.path.join(models_dir, "prothgt-model-molecular-function.pt"),
                'GO_term_P': os.path.join(models_dir, "prothgt-model-biological-process.pt"),
                'GO_term_C': os.path.join(models_dir, "prothgt-model-cellular-component.pt")
            }

            # Get the selected GO category
            go_category = go_category_options[selected_go_category]

            # If a specific category is selected, use that model path
            if go_category:
                model_config_paths = [model_config_paths[go_category]]
                model_paths = [model_paths[go_category]]
                go_categories = [go_category]
            else:
                model_config_paths = [model_config_paths[cat] for cat in ['GO_term_F', 'GO_term_P', 'GO_term_C']]
                model_paths = [model_paths[cat] for cat in ['GO_term_F', 'GO_term_P', 'GO_term_C']]
                go_categories = ['GO_term_F', 'GO_term_P', 'GO_term_C']

            # Generate predictions
            predictions_df = generate_prediction_df(
                protein_ids=selected_proteins,
                model_paths=model_paths,
                model_config_paths=model_config_paths,
                go_category=go_categories
            )

            st.session_state.predictions_df = predictions_df
        
        # Display and filter predictions
        st.success("Predictions generated successfully!")
        st.markdown("### Filter and View Predictions")
        
        # Create filters
        st.markdown("### Filter Predictions")
        col1, col2, col3 = st.columns(3)
        
        with col1:
            # Protein filter
            selected_protein = st.selectbox(
                "Filter by Protein",
                options=['All'] + sorted(st.session_state.predictions_df['Protein'].unique().tolist())
            )
            
        with col2:
            # GO category filter
            selected_category = st.selectbox(
                "Filter by GO Category",
                options=['All'] + sorted(st.session_state.predictions_df['GO_category'].unique().tolist())
            )
            
        with col3:
            # Probability threshold
            min_probability_threshold = st.slider(
                "Minimum Probability",
                min_value=0.0,
                max_value=1.0,
                value=0.5,
                step=0.05
            )

            max_probability_threshold = st.slider(
                "Maximum Probability",
                min_value=0.0,
                max_value=1.0,
                value=1.0,
                step=0.05
            )

        # Filter the dataframe using session state data
        filtered_df = st.session_state.predictions_df.copy()

        if selected_protein != 'All':
            filtered_df = filtered_df[filtered_df['Protein'] == selected_protein]
            
        if selected_category != 'All':
            filtered_df = filtered_df[filtered_df['GO_category'] == selected_category]
            
        filtered_df = filtered_df[(filtered_df['Probability'] >= min_probability_threshold) & 
                                (filtered_df['Probability'] <= max_probability_threshold)]

        # Sort by probability
        filtered_df = filtered_df.sort_values('Probability', ascending=False)


        # Display the filtered dataframe
        st.dataframe(
            filtered_df,
            hide_index=True,
            column_config={
                "Probability": st.column_config.ProgressColumn(
                    "Probability",
                    format="%.2f",
                    min_value=0,
                    max_value=1,
                ),
                "Protein": st.column_config.TextColumn(
                    "Protein",
                    help="UniProt ID",
                ),
                "GO_category": st.column_config.TextColumn(
                    "GO Category",
                    help="Gene Ontology Category",
                ),
                "GO_term": st.column_config.TextColumn(
                    "GO Term",
                    help="Gene Ontology Term ID",
                ),
            }
        )

        # Download filtered results
        st.download_button(
            label="Download Filtered Results",
            data=convert_df(filtered_df),
            file_name="filtered_predictions.csv",
            mime="text/csv",
            key="download_filtered_predictions"
        )

# Add a reset button in the sidebar
with st.sidebar:
    if st.session_state.submitted:
        if st.button("Reset"):
            st.session_state.predictions_df = None
            st.session_state.submitted = False
            st.rerun()