Update app.py

app.py

@@ -1,5 +1,7 @@
 import os
+# Disable GPU to avoid CUDA errors
 os.environ["CUDA_VISIBLE_DEVICES"] = ""
+# Suppress TensorFlow warnings
 os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
 
 import gradio as gr
@@ -26,7 +28,7 @@ import stat
 import time
 import asyncio
 from fastapi import FastAPI, File, UploadFile, Form, HTTPException
-from fastapi.responses import FileResponse
+from fastapi.responses import HTMLResponse, FileResponse
 from pydantic import BaseModel
 from typing import Optional
 import uvicorn
@@ -38,14 +40,15 @@ log_handler.setFormatter(log_formatter)
 try:
     file_handler = logging.FileHandler('/tmp/app.log')
     file_handler.setFormatter(log_formatter)
-    logging.basicConfig(level=logging.DEBUG, handlers=[log_handler, file_handler])
+    logging.basicConfig(level=logging.INFO, handlers=[log_handler, file_handler])
 except Exception as e:
-    logging.basicConfig(level=logging.DEBUG, handlers=[log_handler])
+    logging.basicConfig(level=logging.INFO, handlers=[log_handler])
     logging.warning(f"Failed to set up file logging: {e}")
+
 logger = logging.getLogger(__name__)
 logger.info(f"Gradio version: {gr.__version__}")
 
-# Set event loop policy
+# Set event loop policy for compatibility with Gradio Spaces
 try:
     asyncio.set_event_loop_policy(asyncio.DefaultEventLoopPolicy())
 except Exception as e:
@@ -60,10 +63,11 @@ TREE_PATH = os.path.join(BASE_DIR, "f_gene_sequences.phy.treefile")
 QUERY_OUTPUT_DIR = os.path.join(BASE_DIR, "queries")
 os.makedirs(QUERY_OUTPUT_DIR, exist_ok=True)
 
+# Model repository and file paths
 MODEL_REPO = "GGproject10/best_boundary_aware_model"
-CSV_PATH = "f_cleaned.csv"
+CSV_PATH = "f cleaned.csv"
 
-# Initialize models
+# Initialize models as None
 boundary_model = None
 keras_model = None
 kmer_to_index = None
@@ -74,35 +78,51 @@ def load_models_safely():
     global boundary_model, keras_model, kmer_to_index, analyzer
     logger.info("🔍 Loading models...")
     try:
-        boundary_path = hf_hub_download(repo_id=MODEL_REPO, filename="best_boundary_aware_model.pth", token=None)
+        boundary_path = hf_hub_download(
+            repo_id=MODEL_REPO,
+            filename="best_boundary_aware_model.pth",
+            token=None
+        )
         if os.path.exists(boundary_path):
             boundary_model = EnhancedGenePredictor(boundary_path)
-            logger.info("✅ Boundary model loaded.")
+            logger.info("✅ Boundary model loaded successfully.")
         else:
-            logger.error("❌ Boundary model file not found.")
+            logger.error(f"❌ Boundary model file not found after download.")
     except Exception as e:
-        logger.error(f"❌ Failed to load boundary model: {e}", exc_info=True)
+        logger.error(f"❌ Failed to load boundary model: {e}")
         boundary_model = None
     try:
-        keras_path = hf_hub_download(repo_id=MODEL_REPO, filename="best_model.keras", token=None)
-        kmer_path = hf_hub_download(repo_id=MODEL_REPO, filename="kmer_to_index.pkl", token=None)
+        keras_path = hf_hub_download(
+            repo_id=MODEL_REPO,
+            filename="best_model.keras",
+            token=None
+        )
+        kmer_path = hf_hub_download(
+            repo_id=MODEL_REPO,
+            filename="kmer_to_index.pkl",
+            token=None
+        )
         if os.path.exists(keras_path) and os.path.exists(kmer_path):
             keras_model = load_model(keras_path)
             with open(kmer_path, "rb") as f:
                 kmer_to_index = pickle.load(f)
-            logger.info("✅ Keras model loaded.")
+            logger.info("✅ Keras model and k-mer index loaded successfully.")
         else:
-            logger.error("❌ Keras model files not found.")
+            logger.error(f"❌ Keras model or k-mer files not found.")
     except Exception as e:
-        logger.error(f"❌ Failed to load Keras model: {e}", exc_info=True)
+        logger.error(f"❌ Failed to load Keras model: {e}")
         keras_model = None
         kmer_to_index = None
     try:
         logger.info("🌳 Initializing tree analyzer...")
         analyzer = PhylogeneticTreeAnalyzer()
         csv_candidates = [
-            CSV_PATH, os.path.join(BASE_DIR, CSV_PATH), os.path.join(BASE_DIR, "app", CSV_PATH),
-            os.path.join(os.path.dirname(__file__), CSV_PATH), "f_cleaned.csv", os.path.join(BASE_DIR, "f_cleaned.csv")
+            CSV_PATH,
+            os.path.join(BASE_DIR, CSV_PATH),
+            os.path.join(BASE_DIR, "app", CSV_PATH),
+            os.path.join(os.path.dirname(__file__), CSV_PATH),
+            "f_cleaned.csv",
+            os.path.join(BASE_DIR, "f_cleaned.csv")
         ]
         csv_loaded = False
         for csv_candidate in csv_candidates:
@@ -114,22 +134,24 @@ def load_models_safely():
                         csv_loaded = True
                         break
                 except Exception as e:
-                    logger.warning(f"CSV load failed for {csv_candidate}: {e}", exc_info=True)
+                    logger.warning(f"CSV load failed for {csv_candidate}: {e}")
+                    continue
         if not csv_loaded:
-            logger.error("❌ Failed to load CSV data.")
+            logger.error("❌ Failed to load CSV data from any candidate location.")
             analyzer = None
         else:
             try:
                 if analyzer.train_ai_model():
-                    logger.info("✅ AI model training completed.")
+                    logger.info("✅ AI model training completed successfully")
                 else:
-                    logger.warning("⚠️ AI model training failed.")
+                    logger.warning("⚠️ AI model training failed; proceeding with basic analysis.")
             except Exception as e:
-                logger.warning(f"⚠️ AI model training failed: {e}", exc_info=True)
+                logger.warning(f"⚠️ AI model training failed: {e}")
     except Exception as e:
-        logger.error(f"❌ Tree analyzer initialization failed: {e}", exc_info=True)
+        logger.error(f"❌ Tree analyzer initialization failed: {e}")
         analyzer = None
 
+# Load models at startup
 load_models_safely()
 
 # --- Tool Detection ---
@@ -140,7 +162,7 @@ def setup_binary_permissions():
                 os.chmod(binary, os.stat(binary).st_mode | stat.S_IEXEC)
                 logger.info(f"Set executable permission on {binary}")
             except Exception as e:
-                logger.warning(f"Failed to set permission on {binary}: {e}", exc_info=True)
+                logger.warning(f"Failed to set permission on {binary}: {e}")
 
 def check_tool_availability():
     setup_binary_permissions()
@@ -150,7 +172,12 @@ def check_tool_availability():
     for candidate in mafft_candidates:
         if shutil.which(candidate) or os.path.exists(candidate):
             try:
-                result = subprocess.run([candidate, "--help"], capture_output=True, text=True, timeout=5)
+                result = subprocess.run(
+                    [candidate, "--help"],
+                    capture_output=True,
+                    text=True,
+                    timeout=5
+                )
                 if result.returncode == 0 or "mafft" in result.stderr.lower():
                     mafft_available = True
                     mafft_cmd = candidate
@@ -164,7 +191,12 @@ def check_tool_availability():
     for candidate in iqtree_candidates:
         if shutil.which(candidate) or os.path.exists(candidate):
             try:
-                result = subprocess.run([candidate, "--help"], capture_output=True, text=True, timeout=5)
+                result = subprocess.run(
+                    [candidate, "--help"],
+                    capture_output=True,
+                    text=True,
+                    timeout=5
+                )
                 if result.returncode == 0 or "iqtree" in result.stderr.lower():
                     iqtree_available = True
                     iqtree_cmd = candidate
@@ -176,7 +208,6 @@ def check_tool_availability():
 
 # --- Pipeline Functions ---
 def phylogenetic_placement(sequence: str, mafft_cmd: str, iqtree_cmd: str):
-    query_fasta = None
     try:
         if len(sequence.strip()) < 100:
             return False, "Sequence too short (<100 bp).", None, None
@@ -207,48 +238,41 @@ def phylogenetic_placement(sequence: str, mafft_cmd: str, iqtree_cmd: str):
         logger.error(f"Phylogenetic placement failed: {e}", exc_info=True)
         return False, f"Error: {str(e)}", None, None
     finally:
-        if query_fasta and os.path.exists(query_fasta):
+        if 'query_fasta' in locals() and os.path.exists(query_fasta):
             try:
                 os.unlink(query_fasta)
-                logger.debug(f"Cleaned up {query_fasta}")
-            except Exception as e:
-                logger.warning(f"Failed to clean up {query_fasta}: {e}", exc_info=True)
+            except Exception as e:  # Fixed bare 'except'
+                logger.warning(f"Failed to clean up {query_fasta}: {e}")
 
 def analyze_sequence_for_tree(sequence: str, matching_percentage: float):
     try:
         logger.debug("Starting tree analysis...")
         if not analyzer:
-            logger.error("Tree analyzer not initialized")
             return "❌ Tree analyzer not initialized.", None, None
-        logger.debug("Validating sequence...")
         if not sequence or len(sequence.strip()) < 10:
-            logger.error("Invalid sequence: too short or empty")
             return "❌ Invalid sequence.", None, None
         if not (1 <= matching_percentage <= 99):
-            logger.error(f"Invalid matching percentage: {matching_percentage}")
             return "❌ Matching percentage must be 1-99.", None, None
-        logger.debug("Calling find_query_sequence...")
+        logger.debug("Finding query sequence...")
         if not analyzer.find_query_sequence(sequence):
-            logger.error("Sequence not accepted by analyzer")
             return "❌ Sequence not accepted.", None, None
-        logger.debug("Calling find_similar_sequences...")
+        logger.debug("Finding similar sequences...")
         matched_ids, actual_percentage = analyzer.find_similar_sequences(matching_percentage)
         if not matched_ids:
-            logger.warning(f"No similar sequences found at {matching_percentage}% threshold")
             return f"❌ No similar sequences at {matching_percentage}% threshold.", None, None
-        logger.debug("Calling build_tree_structure_with_ml_safe...")
+        logger.debug("Building tree structure...")
         analyzer.build_tree_structure_with_ml_safe(matched_ids)
-        logger.debug("Calling create_interactive_tree...")
+        logger.debug("Creating interactive tree...")
         fig = analyzer.create_interactive_tree(matched_ids, actual_percentage)
         query_id = analyzer.query_id or f"query_{int(time.time())}"
         tree_html_path = os.path.join("/tmp", f'phylogenetic_tree_{query_id}.html')
         logger.debug(f"Saving tree to {tree_html_path}")
         fig.write_html(tree_html_path)
         analyzer.matching_percentage = matching_percentage
-        logger.debug("Calling generate_detailed_report...")
+        logger.debug("Generating detailed report...")
         report_success = analyzer.generate_detailed_report(matched_ids, actual_percentage)
         report_html_path = os.path.join("/tmp", f'detailed_report_{query_id}.html') if report_success else None
-        logger.debug(f"Tree analysis completed: {len(matched_ids)} matches at {actual_percentage:.2f}%")
+        logger.debug(f"Tree analysis completed: {len(matched_ids)} matches")
         return f"✅ Found {len(matched_ids)} sequences at {actual_percentage:.2f}% similarity.", tree_html_path, report_html_path
     except Exception as e:
         logger.error(f"Tree analysis failed: {e}", exc_info=True)
@@ -256,12 +280,9 @@ def analyze_sequence_for_tree(sequence: str, matching_percentage: float):
 
 def predict_with_keras(sequence):
     try:
-        logger.debug("Starting Keras prediction...")
         if not keras_model or not kmer_to_index:
-            logger.error("Keras model or kmer index not available")
             return "❌ Keras model not available."
         if len(sequence) < 6:
-            logger.error("Sequence too short for Keras prediction")
             return "❌ Sequence too short (<6 bp)."
         kmers = [sequence[i:i+6] for i in range(len(sequence)-5)]
         indices = [kmer_to_index.get(kmer, 0) for kmer in kmers]
@@ -269,7 +290,6 @@ def predict_with_keras(sequence):
         prediction = keras_model.predict(input_arr, verbose=0)[0]
         f_gene_prob = prediction[-1]
         percentage = min(100, max(0, int(f_gene_prob * 100 + 5)))
-        logger.debug(f"Keras prediction completed: {percentage}% confidence")
         return f"✅ {percentage}% F gene confidence"
     except Exception as e:
         logger.error(f"Keras prediction failed: {e}", exc_info=True)
@@ -277,9 +297,7 @@ def predict_with_keras(sequence):
 
 def read_fasta_file(file_obj):
     try:
-        logger.debug("Reading FASTA file...")
         if file_obj is None:
-            logger.error("No file object provided")
             return ""
         if isinstance(file_obj, str):
             with open(file_obj, "r") as f:
@@ -288,19 +306,15 @@ def read_fasta_file(file_obj):
             content = file_obj.read().decode("utf-8")
         lines = content.strip().split("\n")
         seq_lines = [line.strip() for line in lines if not line.startswith(">")]
-        sequence = ''.join(seq_lines)
-        logger.debug(f"FASTA file read successfully: {len(sequence)} bp")
-        return sequence
+        return ''.join(seq_lines)
     except Exception as e:
         logger.error(f"Failed to read FASTA file: {e}", exc_info=True)
         return ""
 
 def run_pipeline(dna_input, similarity_score=95.0, build_ml_tree=False):
     try:
-        logger.debug("Starting pipeline...")
         dna_input = dna_input.upper().strip()
         if not dna_input:
-            logger.error("Empty input sequence")
             return "❌ Empty input", "", "", "", "", None, None, None, None, "No input", "No input", None, None
         if not re.match('^[ACTGN]+$', dna_input):
             dna_input = ''.join(c if c in 'ACTGN' else 'N' for c in dna_input)
@@ -319,7 +333,6 @@ def run_pipeline(dna_input, similarity_score=95.0, build_ml_tree=False):
             except Exception as e:
                 boundary_output = f"❌ Boundary prediction error: {str(e)}"
                 processed_sequence = dna_input
-                logger.error(f"Boundary prediction error: {e}", exc_info=True)
         else:
             boundary_output = f"⚠️ Boundary model not available. Using full input: {len(dna_input)} bp"
         keras_output = predict_with_keras(processed_sequence) if processed_sequence and len(processed_sequence) >= 6 else "❌ Sequence too short."
@@ -338,7 +351,6 @@ def run_pipeline(dna_input, similarity_score=95.0, build_ml_tree=False):
                     ml_tree_output = "❌ MAFFT or IQ-TREE not available"
             except Exception as e:
                 ml_tree_output = f"❌ ML tree error: {str(e)}"
-                logger.error(f"ML tree error: {e}", exc_info=True)
         elif build_ml_tree:
             ml_tree_output = "❌ Sequence too short for placement (<100 bp)."
         else:
@@ -366,7 +378,6 @@ def run_pipeline(dna_input, similarity_score=95.0, build_ml_tree=False):
                 simplified_ml_output = f"❌ Tree analysis error: {str(e)}"
                 tree_html_content = f"<div style='color: red;'>{simplified_ml_output}</div>"
                 report_html_content = f"<div style='color: red;'>{simplified_ml_output}</div>"
-                logger.error(f"Tree analysis error: {e}", exc_info=True)
         else:
             simplified_ml_output = "❌ Tree analyzer not available." if not analyzer else "❌ Sequence too short (<10 bp)."
             tree_html_content = f"<div style='color: orange;'>{simplified_ml_output}</div>"
@@ -418,7 +429,7 @@ async def run_pipeline_from_file(fasta_file_obj, similarity_score, build_ml_tree
             try:
                 os.unlink(temp_file_path)
             except Exception as e:
-                logger.warning(f"Failed to delete temp file {temp_file_path}: {e}", exc_info=True)
+                logger.warning(f"Failed to delete temp file {temp_file_path}: {e}")
 
 # --- Pydantic Models ---
 class AnalysisRequest(BaseModel):
@@ -467,6 +478,10 @@ async def health_check():
                 "tree_analyzer": analyzer is not None,
                 "mafft_available": mafft_available,
                 "iqtree_available": iqtree_available
+            },
+            "paths": {
+                "base_dir": BASE_DIR,
+                "query_output_dir": QUERY_OUTPUT_DIR
             }
         }
     except Exception as e:
@@ -532,7 +547,7 @@ async def analyze_file(
             try:
                 os.unlink(temp_file_path)
             except Exception as e:
-                logger.warning(f"Failed to clean up {temp_file_path}: {e}", exc_info=True)
+                logger.warning(f"Failed to clean up {temp_file_path}: {e}")
 
 @app.get("/download/{file_type}/{query_id}")
 async def download_file(file_type: str, query_id: str):
@@ -551,10 +566,9 @@ async def download_file(file_type: str, query_id: str):
 # --- Gradio Interface ---
 def create_gradio_interface():
     try:
-        logger.debug("Creating Gradio interface...")
         with gr.Blocks(
             title="🧬 Gene Analysis Pipeline",
-            theme="default",
+            theme=gr.themes.Soft(),
             css="""
             .gradio-container { max-width: 1200px !important; }
             .status-box { padding: 10px; border-radius: 5px; margin: 5px 0; }
@@ -577,13 +591,14 @@ def create_gradio_interface():
                     </div>
                     """)
             with gr.Tabs():
-                with gr.TabItem("Text Input"):
+                with gr.TabItem("📝 Text Input"):
                     with gr.Row():
                         with gr.Column(scale=2):
                             dna_input = gr.Textbox(
-                                label="DNA Sequence",
+                                label="🧬 DNA Sequence",
                                 placeholder="Enter DNA sequence (ATCG format)...",
-                                lines=5
+                                lines=5,
+                                description="Paste your DNA sequence here"
                             )
                         with gr.Column(scale=1):
                             similarity_score = gr.Slider(
@@ -591,19 +606,22 @@ def create_gradio_interface():
                                 maximum=99,
                                 value=95.0,
                                 step=1.0,
-                                label="Similarity Threshold (%)"
+                                label="🎯 Similarity Threshold (%)",
+                                description="Minimum similarity for tree analysis"
                             )
                             build_ml_tree = gr.Checkbox(
-                                label="Build ML Tree",
-                                value=False
+                                label="🌲 Build ML Tree",
+                                value=False,
+                                description="Generate phylogenetic placement (slower)"
                             )
-                            analyze_btn = gr.Button("Analyze Sequence", variant="primary")
-                with gr.TabItem("File Upload"):
+                            analyze_btn = gr.Button("🔬 Analyze Sequence", variant="primary")
+                with gr.TabItem("📁 File Upload"):
                     with gr.Row():
                         with gr.Column(scale=2):
                             file_input = gr.File(
-                                label="Upload FASTA File",
-                                file_types=[".fasta", ".fa", ".fas", ".txt"]
+                                label="📄 Upload FASTA File",
+                                file_types=[".fasta", ".fa", ".fas", ".txt"],
+                                description="Upload a FASTA file containing your sequence"
                             )
                         with gr.Column(scale=1):
                             file_similarity_score = gr.Slider(
@@ -611,122 +629,145 @@ def create_gradio_interface():
                                 maximum=99,
                                 value=95.0,
                                 step=1.0,
-                                label="Similarity Threshold (%)"
+                                label="🎯 Similarity Threshold (%)",
+                                description="Minimum similarity for tree analysis"
                             )
                             file_build_ml_tree = gr.Checkbox(
-                                label="Build ML Tree",
-                                value=False
+                                label="🌲 Build ML Tree",
+                                value=False,
+                                description="Generate phylogenetic placement (slower)"
                             )
-                            analyze_file_btn = gr.Button("Analyze File", variant="primary")
-            gr.Markdown("## Analysis Results")
+                            analyze_file_btn = gr.Button("🔬 Analyze File", variant="primary")
+            gr.Markdown("## 📊 Analysis Results")
             with gr.Row():
                 with gr.Column():
-                    boundary_output = gr.Textbox(label="Boundary Detection", interactive=False, lines=2)
-                    keras_output = gr.Textbox(label="F Gene Validation", interactive=False, lines=2)
+                    boundary_output = gr.Textbox(
+                        label="🎯 Boundary Detection",
+                        interactive=False,
+                        lines=2
+                    )
+                    keras_output = gr.Textbox(
+                        label="🧠 F Gene Validation",
+                        interactive=False,
+                        lines=2
+                    )
                 with gr.Column():
-                    ml_tree_output = gr.Textbox(label="Phylogenetic Placement", interactive=False, lines=2)
-                    tree_analysis_output = gr.Textbox(label="Tree Analysis", interactive=False, lines=2)
-            summary_output = gr.Textbox(label="Summary", interactive=False, lines=8)
-            with gr.Tabs():
-                with gr.TabItem("Interactive Tree"):
-                    tree_html = gr.HTML(value="Run analysis to see phylogenetic tree")
-                with gr.TabItem("Detailed Report"):
-                    report_html = gr.HTML(value="Run analysis to see detailed report")
-            with gr.Row():
-                aligned_file = gr.File(label="Alignment File", visible=False)
-                tree_file = gr.File(label="Tree File", visible=False)
-                tree_html_file = gr.File(label="Tree HTML", visible=False)
-                report_html_file = gr.File(label="Report HTML", visible=False)
-            def process_text_input(dna_seq, similarity, build_tree):
-                if not dna_seq or not dna_seq.strip():
-                    return (
-                        "❌ Please enter a DNA sequence", "", "", "", "",
-                        None, None, None, None,
-                        "<div style='color: red;'>No input provided</div>",
-                        "<div style='color: red;'>No input provided</div>",
-                        None, None
+                    ml_tree_output = gr.Textbox(
+                        label="🌲 Phylogenetic Placement",
+                        interactive=False,
+                        lines=2
                     )
-                results = run_pipeline(dna_seq, similarity, build_tree)
-                return (
-                    results[0], results[1], results[2], results[3], results[4],
-                    results[5], results[6], results[11], results[12],
-                    results[9], results[10],
-                    results[11], results[12]
-                )
-            def process_file_input(file_path, similarity, build_tree):
-                if not file_path:
-                    return (
-                        "❌ Please upload a file", "", "", "", "",
-                        None, None, None, None,
-                        "<div style='color: red;'>No file provided</div>",
-                        "<div style='color: red;'>No file provided</div>",
-                        None, None
+                    tree_analysis_output = gr.Textbox(
+                        label="🌳 Tree Analysis",
+                        interactive=False,
+                        lines=2
                     )
-                sequence = read_fasta_file(file_path)
-                if not sequence:
-                    return (
-                        "❌ Failed to read sequence from file", "", "", "", "",
-                        None, None, None, None,
-                        "<div style='color: red;'>Invalid file format</div>",
-                        "<div style='color: red;'>Invalid file format</div>",
-                        None, None
+            summary_output = gr.Textbox(
+                label="📋 Summary",
+                interactive=False,
+                lines=8
+            )
+            with gr.Row():
+                aligned_file = gr.File(label="📄 Alignment File", visible=False)
+                tree_file = gr.File(label="🌲 Tree File", visible=False)
+                tree_html_file = gr.File(label="🌳 Simplified Tree HTML", visible=False)
+                report_html_file = gr.File(label="📊 Detailed Report HTML", visible=False)
+            with gr.Tabs():
+                with gr.TabItem("🌳 Interactive Tree"):
+                    tree_html = gr.HTML(
+                        value="<div style='text-align: center; color: #666; padding: 20px;'>No tree generated yet. Run analysis to see results.</div>"
                     )
-                results = run_pipeline(sequence, similarity, build_tree)
+                with gr.TabItem("📊 Detailed Report"):
+                    report_html = gr.HTML(
+                        label="Analysis Report",
+                        value="<div style='text-align: center; color: #666; padding: 20px;'>No report generated yet. Run analysis to see results.</div>"
+                    )
+
+            # Event handlers
+            def handle_analysis_output(*outputs):
+                boundary_output, keras_output, ml_tree_output, simplified_ml_output, summary_output, aligned_file, phy_file, _, _, tree_html_content, report_html_content, tree_html_path, report_html_path = outputs
                 return (
-                    results[0], results[1], results[2], results[3], results[4],
-                    results[5], results[6], results[11], results[12],
-                    results[9], results[10],
-                    results[11], results[12]
+                    boundary_output, keras_output, ml_tree_output, simplified_ml_output, summary_output,
+                    gr.File.update(value=aligned_file, visible=aligned_file is not None),
+                    gr.File.update(value=phy_file, visible=phy_file is not None),
+                    gr.File.update(value=tree_html_path, visible=tree_html_path is not None),
+                    gr.File.update(value=report_html_path, visible=report_html_path is not None),
+                    tree_html_content,
+                    report_html_content
                 )
+
             analyze_btn.click(
-                fn=process_text_input,
+                fn=run_pipeline,
                 inputs=[dna_input, similarity_score, build_ml_tree],
                 outputs=[
                     boundary_output, keras_output, ml_tree_output, tree_analysis_output, summary_output,
-                    aligned_file, tree_file, tree_html_file, report_html_file, tree_html, report_html,
-                    tree_html_file, report_html_file
-                ]
+                    aligned_file, tree_file, tree_html_file, report_html_file, tree_html, report_html
+                ],
+                _js="""(outputs) => {
+                    return outputs;
+                }"""
             )
+
             analyze_file_btn.click(
-                fn=process_file_input,
+                fn=run_pipeline_from_file,
                 inputs=[file_input, file_similarity_score, file_build_ml_tree],
                 outputs=[
                     boundary_output, keras_output, ml_tree_output, tree_analysis_output, summary_output,
-                    aligned_file, tree_file, tree_html_file, report_html_file, tree_html, report_html,
-                    tree_html_file, report_html_file
-                ]
+                    aligned_file, tree_file, tree_html_file, report_html_file, tree_html, report_html
+                ],
+                _js="""(outputs) => {
+                    return outputs;
+                }"""
             )
+
+            # Examples
             gr.Examples(
                 examples=[
-                    ["ATCG" * 100, 85.0, False],
-                    ["CGAT" * 100, 90.0, True]
+                    ["ATCG" * 250, 85.0, False],
+                    ["CGATCG" * 150, 90.0, True]
                 ],
                 inputs=[dna_input, similarity_score, build_ml_tree],
                 label="Example Sequences"
             )
-        logger.debug("Gradio interface created successfully")
+
+            gr.Markdown("""
+            ## 📚 Instructions
+            1. **Input**: Enter a DNA sequence (ATCG format) or upload a FASTA file
+            2. **Parameters**: 
+               - Set similarity threshold for phylogenetic analysis (1-99%)
+               - Choose whether to build ML tree (slower but more accurate)
+            3. **Analysis**: Click analyze to run the complete pipeline
+            4. **Results**: View results in different tabs - summary, tree visualization, and detailed report
+            5. **Downloads**: Download alignment, tree, simplified tree HTML, and detailed report HTML files
+            ### 🔬 Pipeline Components:
+            - **Boundary Detection**: Identifies F gene regions
+            - **F Gene Validation**: Validates F gene using ML
+            - **Phylogenetic Placement**: Places sequence in reference tree (optional)
+            - **Tree Analysis**: Builds phylogenetic tree with similar sequences
+            """)
+
         return iface
     except Exception as e:
         logger.error(f"Gradio interface creation failed: {e}", exc_info=True)
         return gr.Interface(
-            fn=lambda x: f"Interface creation failed: {str(e)}",
-            inputs=gr.Textbox(label="Input"),
-            outputs=gr.Textbox(label="Output"),
-            title="🧬 Gene Analysis Pipeline - Error"
+            fn=lambda x: f"Error: {str(e)}",
+            inputs=gr.Textbox(label="DNA Sequence"),
+            outputs=gr.Textbox(label="Error"),
+            title="🧬 Gene Analysis Pipeline (Error Mode)"
         )
 
 # --- Application Startup ---
 def run_application():
     try:
-        logger.debug("Starting application...")
         gradio_app = create_gradio_interface()
-        logger.debug("Mounting Gradio app to FastAPI...")
         gradio_app = gr.mount_gradio_app(app, gradio_app, path="/gradio")
         logger.info("🚀 Starting Gene Analysis Pipeline...")
+        logger.info("📊 FastAPI docs available at: http://localhost:7860/docs")
+        logger.info("🧬 Gradio interface available at: http://localhost:7860/gradio")
         uvicorn.run(
             app,
             host="0.0.0.0",
-            port=int(os.getenv("PORT", 7860)),
+            port=7860,
             log_level="info"
         )
     except Exception as e:
@@ -736,24 +777,24 @@ def run_application():
             gradio_app = create_gradio_interface()
             gradio_app.launch(
                 server_name="0.0.0.0",
-                server_port=int(os.getenv("PORT", 7860)),
-                share=bool(os.getenv("SPACE_ID")),
-                show_error=True
+                server_port=7860,
+                share=False,
+                debug=False
             )
         except Exception as fallback_error:
             logger.error(f"Fallback failed: {fallback_error}", exc_info=True)
-            sys.exit(1)
+            print("❌ Application failed to start. Check logs for details.")
 
 # --- Main Entry Point ---
 if __name__ == "__main__":
-    logger.info("🧬 Gene Analysis Pipeline Starting...")
-    logger.info("=" * 50)
-    logger.info("🔍 Checking system components...")
+    print("🧬 Gene Analysis Pipeline Starting...")
+    print("=" * 50)
+    print("🔍 Checking system components...")
     mafft_available, iqtree_available, _, _ = check_tool_availability()
-    logger.info(f"🤖 Boundary Model: {'✅' if boundary_model else '❌'}")
-    logger.info(f"🧠 Keras Model: {'✅' if keras_model else '❌'}")
-    logger.info(f"🌳 Tree Analyzer: {'✅' if analyzer else '❌'}")
-    logger.info(f"🧬 MAFFT: {'✅' if mafft_available else '❌'}")
-    logger.info(f"🌲 IQ-TREE: {'✅' if iqtree_available else '❌'}")
-    logger.info("=" * 50)
+    print(f"🤖 Boundary Model: {'✅' if boundary_model else '❌'}")
+    print(f"🧠 Keras Model: {'✅' if keras_model else '❌'}")
+    print(f"🌳 Tree Analyzer: {'✅' if analyzer else '❌'}")
+    print(f"🧬 MAFFT: {'✅' if mafft_available else '❌'}")
+    print(f"🌲 IQ-TREE: {'✅' if iqtree_available else '❌'}")
+    print("=" * 50)
     run_application()