added fuzzy search feature

ProtHGT_app.py

@@ -1,10 +1,6 @@
 import os
 import streamlit as st
-import time
-import streamlit.components.v1 as components
-import pandas as pd
-
-
+from rapidfuzz import process
 
 # 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
@@ -92,26 +88,25 @@ with st.sidebar:
     )
 
     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)
-            
+        # User enters search term
+        search_query = st.text_input("Start typing a protein ID (at least 3 characters)", "")
+
+        # Apply fuzzy search only if query length is >= 3
+        filtered_proteins = []
+        if len(search_query) >= 3:
+            filtered_proteins = [match[0] for match in process.extract(search_query, available_proteins, limit=50)]  # Show top 50 matches
+
+        # Multi-select for filtered results
         selected_proteins = st.multiselect(
-            "Select or search for proteins (UniProt IDs)",
-            options=available_proteins,
+            "Select proteins from search results",
+            options=filtered_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)*",

requirements.txt

@@ -6,4 +6,5 @@ torch==1.12.1+cpu
 torch_sparse==0.6.15
 torch_scatter==2.1.0
 torch_geometric==2.2.0
-gdown
+gdown
+rapidfuzz