ProtHGT_app.py

import os
import streamlit as st
from rapidfuzz import process
import random

# with st.spinner("Initializing the environment... This may take up to 10 minutes at the start of each session."):
#     # Create a temporary placeholder for the message
#     loading_placeholder = st.empty()

#     # Show the info message only while the spinner is active
#     loading_placeholder.info("""
#     **Note:** This initialization is required at the start of each session.  
#     Once the app is ready, you can run multiple predictions without re-initializing by clicking the **Reset** button in the sidebar.
#     """)

#     # 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")

# # ❌ Remove the info message after initialization is complete
# loading_placeholder.empty()


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

def reset_prediction_state():
    st.session_state.generating_predictions = False
    st.session_state.submitted = False
    st.session_state.predictions_df = None
    st.session_state.previous_inputs = None

def set_generating_predictions():
    st.session_state.generating_predictions = True
    st.session_state.submitted = True

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.
    - **Knowledge graph visualization for interpretability**: To improve model explainability, we are developing an interactive **knowledge graph visualization** feature. This will allow users to explore the biological relationships that contributed to ProtHGT’s predictions for a given protein. Users will be able to inspect **protein interactions, GO annotations, domains, pathways, and other key connections** in a structured graphical format, making it easier to interpret and validate predictions.

    Stay tuned for updates and future publications!
    """)

with st.sidebar:

    disabled = st.session_state.generating_predictions

    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()
    
    if 'example_proteins' not in st.session_state:
        st.session_state.example_proteins = random.sample(available_proteins, 5)

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

    if selection_method == "Use example query":
        selected_proteins = st.session_state.example_proteins
        st.write(f"Selected proteins:")
        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(selected_proteins)}
            </div>
            """, 
            unsafe_allow_html=True
        )

    elif selection_method == "Search proteins":
        
        # User enters search term
        search_query = st.text_input(
            "1\\. Start typing a protein ID (at least 3 characters) and press Enter to see search results in the dropdown menu below (2)",
            "", 
            disabled=disabled
        )

        # Apply fuzzy search only if query length is >= 3
        filtered_proteins = []
        if len(search_query) >= 3:
            # Case-insensitive search by converting query and proteins to lowercase
            matches = process.extract(
                search_query.upper(), 
                {p: p.upper() for p in available_proteins}, 
                limit=50
            )
            filtered_proteins = [match[0] for match in matches]  # Show top 50 matches

        with st.container():
            selected_proteins = st.multiselect(
                "2\\. Select proteins from search results",
                options=filtered_proteins,
                placeholder="Start typing a protein ID above (1) to see search results...",
                max_selections=100,
                disabled=disabled,
                key="protein_selector"
            )
            # Apply custom CSS to make container scrollable
            st.markdown("""
                <style>
                div[data-testid="stMultiSelect"] div:nth-child(2) {
                    max-height: 250px;
                    overflow-y: auto;
                }
                </style>
                """, unsafe_allow_html=True)

    else:  # Upload file option
        uploaded_file = st.file_uploader(
            "Upload a text file with UniProt IDs (one per line, max 100)*",
            type=['txt'],
            disabled=disabled
        )

        if uploaded_file:
            protein_list = [line.strip() for line in uploaded_file.read().decode('utf-8').splitlines()]

            # 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) > 100:
                st.error("Please upload a file with maximum 100 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:
        st.write(f"Total proteins selected: {len(selected_proteins)}")
        # Add download button
        proteins_text = '\n'.join(selected_proteins)
        st.download_button(
            label="Download Selected Proteins List",
            data=proteins_text,
            file_name="selected_proteins.txt",
            mime="text/plain",
            key="download_selected_proteins"
        )

        # 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.",
            disabled=disabled
        )

    if selected_proteins and selected_go_category:
        
        button_disabled = st.session_state.submitted

        # Add custom CSS for red button
        st.markdown("""
            <style>
            div.stButton > button:first-child {
                background-color: #ff4b4b;
                color: white;
            }
            div.stButton > button:hover {
                background-color: #ff0000;
                color: white;
            }
            div.stButton > button:focus {
                background-color: #ff0000;
                color: white;
            }
            </style>
        """, unsafe_allow_html=True)

        if st.button("Generate Predictions", 
                    disabled=button_disabled, 
                    key="generate_predictions",
                    on_click=set_generating_predictions):
            pass

        # Create a tuple of current inputs to track changes
        current_inputs = (tuple(selected_proteins), selected_go_category)
        
        # Check if inputs have changed
        if st.session_state.previous_inputs != current_inputs:
            st.session_state.predictions_df = None
            st.session_state.submitted = False
            st.session_state.previous_inputs = current_inputs
            
    st.warning("⚠️ Due to memory and computational constraints, the maximum number of proteins that can be processed at once is limited to 100 proteins. For larger datasets, please consider running the model locally using our [GitHub repository](https://github.com/HUBioDataLab/ProtHGT).")

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
        
            # Reset only the generating_predictions flag to release the sidebar
            st.session_state.generating_predictions = False
            st.rerun()

        # Display and filter predictions
        st.success("Predictions generated successfully!")
        st.markdown("### Filter and View Predictions")
        
        # Create filters
        col1, col2, col3, col4 = st.columns(4)
        
        with col1:
            # Extract UniProt IDs from URLs for the selectbox
            uniprot_ids = st.session_state.predictions_df['UniProt_ID'].apply(
                lambda x: x.split('/')[-2]  # Gets the ID part from the URL
            ).unique().tolist()
            
            # Protein filter
            selected_protein = st.selectbox(
                "Filter by Protein",
                options=['All'] + sorted(uniprot_ids)
            )

        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:
            # GO term filter
            go_term_filter = st.text_input(
                "Filter by GO Term ID",
                placeholder="e.g., GO:0003674",
                help="Enter a GO term ID to filter results"
            ).strip()
            
        with col4:
            # 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['UniProt_ID'].str.contains(selected_protein)]
                        
        if selected_category != 'All':
            filtered_df = filtered_df[filtered_df['GO_category'] == selected_category]

        if go_term_filter:
            filtered_df = filtered_df[filtered_df['GO_ID'].str.contains(go_term_filter, case=False, na=False)]
            
        filtered_df = filtered_df[(filtered_df['Probability'] >= min_probability_threshold) & 
                                (filtered_df['Probability'] <= max_probability_threshold)]

        # Custom CSS to increase table width and improve layout
        st.markdown("""
            <style>
                .stDataFrame {
                    width: 100%;
                }
                .stDataFrame > div {
                    width: 100%;
                }
                .stDataFrame [data-testid="stDataFrameResizable"] {
                    width: 100%;
                    min-width: 100%;
                }
                .pagination-info {
                    font-size: 14px;
                    color: #666;
                    padding: 10px 0;
                }
                .page-controls {
                    display: flex;
                    align-items: center;
                    justify-content: center;
                    gap: 20px;
                    padding: 10px 0;
                }
            </style>
        """, unsafe_allow_html=True)

        # Add pagination controls
        col1, col2, col3 = st.columns([2, 1, 2])
        with col2:
            rows_per_page = st.selectbox("Rows per page", [50, 100, 200, 500], index=1)

        total_rows = len(filtered_df)
        total_pages = (total_rows + rows_per_page - 1) // rows_per_page

        # Initialize page number in session state
        if "page_number" not in st.session_state:
            st.session_state.page_number = 0

        # Calculate start and end indices for current page
        start_idx = st.session_state.page_number * rows_per_page
        end_idx = min(start_idx + rows_per_page, total_rows)

        st.dataframe(
            filtered_df.iloc[start_idx:end_idx],
            hide_index=True,
            use_container_width=True,
            column_config={
                "UniProt_ID": st.column_config.LinkColumn(
                    "UniProt ID",
                    help="Click to view protein in UniProt",
                    validate="^https://www\\.uniprot\\.org/uniprotkb/[A-Z0-9]+/entry$",
                    display_text="^https://www\\.uniprot\\.org/uniprotkb/([A-Z0-9]+)/entry$"
                ),
                "GO_ID": st.column_config.LinkColumn(
                    "GO ID",
                    help="Click to view GO term in QuickGO",
                    validate="^https://www\\.ebi\\.ac\\.uk/QuickGO/term/GO:[0-9]+$",
                    display_text="^https://www\\.ebi\\.ac\\.uk/QuickGO/term/(GO:[0-9]+)$"
                ),
                "Probability": st.column_config.ProgressColumn(
                    "Probability",
                    format="%.2f",
                    min_value=0,
                    max_value=1,
                ),
                "Protein": st.column_config.TextColumn(
                    "Protein",
                    help="Protein Name",
                ),
                "GO_category": st.column_config.TextColumn(
                    "GO Category",
                    help="Gene Ontology Category",
                ),
                "GO_term": st.column_config.TextColumn(
                    "GO Term",
                    help="Gene Ontology Term Name",
                ),
            }
        )
        # Pagination controls with better layout
        col1, col2, col3 = st.columns([1, 3, 1])
        with col1:
            if st.button("Previous", disabled=st.session_state.page_number == 0):
                st.session_state.page_number -= 1
                st.rerun()

        with col2:
            st.markdown(f"""
                <div class="pagination-info" style="text-align: center">
                    Page {st.session_state.page_number + 1} of {total_pages}<br>
                    Showing rows {start_idx + 1} to {end_idx} of {total_rows}
                </div>
            """, unsafe_allow_html=True)

        with col3:
            if st.button("Next", disabled=st.session_state.page_number >= total_pages - 1):
                st.session_state.page_number += 1
                st.rerun()


        # 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"
        )