Update app.py

app.py

@@ -8,10 +8,14 @@ import matplotlib.pyplot as plt
 import matplotlib.colors as mcolors
 import io 
 from io import BytesIO # Import io then BytesIO 
-from PIL import Image, ImageDraw
+from PIL import Image, ImageDraw, ImageFont
 from Bio.Graphics import GenomeDiagram
 from Bio.SeqFeature import SeqFeature, FeatureLocation
 from reportlab.lib import colors
+import pandas as pd
+import tempfile
+import os
+from typing import List, Dict, Tuple, Optional, Any
 
 ###############################################################################
 # 1. MODEL DEFINITION
@@ -563,8 +567,16 @@ def analyze_sequence_comparison(file1, file2, fasta1="", fasta2=""):
 # 11. GENE FEATURE ANALYSIS
 ###############################################################################
 
-def parse_gene_features(text):
-    """Parse gene features from text file in FASTA-like format"""
+def parse_gene_features(text: str) -> List[Dict[str, Any]]:
+    """
+    Parse gene features from text file in FASTA-like format
+    
+    Args:
+        text (str): Input text in FASTA format with gene metadata
+        
+    Returns:
+        List[Dict]: List of gene dictionaries containing sequence and metadata
+    """
     genes = []
     current_header = None
     current_sequence = []
@@ -573,6 +585,7 @@ def parse_gene_features(text):
         line = line.strip()
         if not line:
             continue
+            
         if line.startswith('>'):
             if current_header:
                 genes.append({
@@ -594,8 +607,16 @@ def parse_gene_features(text):
     
     return genes
 
-def parse_gene_metadata(header):
-    """Extract metadata from gene header"""
+def parse_gene_metadata(header: str) -> Dict[str, str]:
+    """
+    Extract metadata from gene header
+    
+    Args:
+        header (str): Gene header line starting with '>'
+        
+    Returns:
+        Dict[str, str]: Dictionary of metadata key-value pairs
+    """
     metadata = {}
     parts = header.split()
     
@@ -607,8 +628,92 @@ def parse_gene_metadata(header):
                 
     return metadata
 
-def analyze_gene_features(sequence_file, features_file, fasta_text="", features_text=""):
-    """Analyze SHAP values for each gene feature"""
+def parse_location(location_str: str) -> Tuple[Optional[int], Optional[int]]:
+    """
+    Parse gene location string, handling both forward and complement strands
+    
+    Args:
+        location_str (str): Location string (e.g., "1234..5678" or "complement(1234..5678)")
+        
+    Returns:
+        Tuple[Optional[int], Optional[int]]: Start and end positions, or (None, None) if parsing fails
+    """
+    try:
+        # Handle complement strand
+        is_complement = location_str.startswith('complement(')
+        clean_loc = location_str.replace('complement(', '').replace(')', '')
+        
+        # Split on '..' and convert to integers
+        if '..' in clean_loc:
+            start, end = map(int, clean_loc.split('..'))
+            return start, end
+        else:
+            return None, None
+            
+    except Exception as e:
+        print(f"Error parsing location {location_str}: {str(e)}")
+        return None, None
+
+def save_results_to_temp(results: str, prefix: str = "analysis") -> Optional[str]:
+    """
+    Save results to a temporary file
+    
+    Args:
+        results (str): Content to save
+        prefix (str): Prefix for the temporary file name
+        
+    Returns:
+        Optional[str]: Path to temporary file, or None if save fails
+    """
+    try:
+        temp_dir = tempfile.gettempdir()
+        temp_path = os.path.join(temp_dir, f"{prefix}_{os.urandom(4).hex()}.csv")
+        
+        with open(temp_path, 'w') as f:
+            f.write(results)
+        return temp_path
+    except Exception as e:
+        print(f"Error saving results: {str(e)}")
+        return None
+
+def compute_gene_statistics(gene_shap: np.ndarray) -> Dict[str, float]:
+    """
+    Compute statistical measures for gene SHAP values
+    
+    Args:
+        gene_shap (np.ndarray): Array of SHAP values for a gene
+        
+    Returns:
+        Dict[str, float]: Dictionary of statistical measures
+    """
+    return {
+        'avg_shap': float(np.mean(gene_shap)),
+        'median_shap': float(np.median(gene_shap)),
+        'std_shap': float(np.std(gene_shap)),
+        'max_shap': float(np.max(gene_shap)),
+        'min_shap': float(np.min(gene_shap)),
+        'pos_fraction': float(np.mean(gene_shap > 0))
+    }
+
+def analyze_gene_features(sequence_file: str, 
+                        features_file: str, 
+                        fasta_text: str = "", 
+                        features_text: str = "") -> Tuple[str, Optional[str], Optional[Image.Image]]:
+    """
+    Analyze SHAP values for each gene feature
+    
+    Args:
+        sequence_file (str): Path to FASTA file
+        features_file (str): Path to features file
+        fasta_text (str): FASTA content if provided as text
+        features_text (str): Features content if provided as text
+        
+    Returns:
+        Tuple[str, Optional[str], Optional[Image.Image]]: 
+            - Analysis results text
+            - Path to CSV file
+            - Genome diagram image
+    """
     # First analyze whole sequence
     sequence_results = analyze_sequence(sequence_file, top_kmers=10, fasta_text=fasta_text)
     if isinstance(sequence_results[0], str) and "Error" in sequence_results[0]:
@@ -618,14 +723,14 @@ def analyze_gene_features(sequence_file, features_file, fasta_text="", features_
     shap_means = sequence_results[3]["shap_means"]
     
     # Parse gene features
-    if features_text.strip():
-        genes = parse_gene_features(features_text)
-    else:
-        try:
+    try:
+        if features_text.strip():
+            genes = parse_gene_features(features_text)
+        else:
             with open(features_file, 'r') as f:
                 genes = parse_gene_features(f.read())
-        except Exception as e:
-            return f"Error reading features file: {str(e)}", None, None
+    except Exception as e:
+        return f"Error reading features file: {str(e)}", None, None
             
     # Analyze each gene
     gene_results = []
@@ -635,78 +740,142 @@ def analyze_gene_features(sequence_file, features_file, fasta_text="", features_
             if not location:
                 continue
                 
-            # Parse location (assuming format like "21729..22861")
-            start, end = map(int, location.split('..'))
-            
+            start, end = parse_location(location)
+            if start is None or end is None:
+                continue
+                
             # Get SHAP values for this region
             gene_shap = shap_means[start:end]
-            avg_shap = float(np.mean(gene_shap))
+            stats = compute_gene_statistics(gene_shap)
             
             gene_results.append({
                 'gene_name': gene['metadata'].get('gene', 'Unknown'),
                 'location': location,
-                'avg_shap': avg_shap,
                 'start': start,
                 'end': end,
                 'locus_tag': gene['metadata'].get('locus_tag', ''),
-                'classification': 'Human' if avg_shap > 0 else 'Non-human',
-                'confidence': abs(avg_shap)
+                'avg_shap': stats['avg_shap'],
+                'median_shap': stats['median_shap'],
+                'std_shap': stats['std_shap'],
+                'max_shap': stats['max_shap'],
+                'min_shap': stats['min_shap'],
+                'pos_fraction': stats['pos_fraction'],
+                'classification': 'Human' if stats['avg_shap'] > 0 else 'Non-human',
+                'confidence': abs(stats['avg_shap'])
             })
             
         except Exception as e:
             print(f"Error processing gene {gene['metadata'].get('gene', 'Unknown')}: {str(e)}")
             continue
+    
+    if not gene_results:
+        return "No valid genes could be processed", None, None
             
-    # Create CSV output
-    csv_output = "gene_name,location,avg_shap,classification,confidence,locus_tag\n"
-    for result in gene_results:
-        csv_output += f"{result['gene_name']},{result['location']},{result['avg_shap']:.4f},"
-        csv_output += f"{result['classification']},{result['confidence']:.4f},{result['locus_tag']}\n"
-        
-    # Create genome diagram
-    diagram_img = create_genome_diagram(gene_results, len(shap_means))
-    
-    return gene_results, csv_output, diagram_img
-
-def create_genome_diagram(gene_results, genome_length):
-    """Create genome diagram using BioPython"""
-    from Bio.Graphics import GenomeDiagram
-    from Bio.SeqFeature import SeqFeature, FeatureLocation
-    from reportlab.lib import colors
-    from io import BytesIO
-    from PIL import Image
-    import io  # Ensure io is imported at the top level
-    
-    # Create diagram
-    gd_diagram = GenomeDiagram.Diagram("Genome SHAP Analysis")
-    gd_track = gd_diagram.new_track(1, name="Genes")
-    gd_feature_set = gd_track.new_set()
-    
-    # Add features
+    # Create results text
+    results_text = "Gene Analysis Results:\n\n"
+    results_text += f"Total genes analyzed: {len(gene_results)}\n"
+    results_text += f"Human-like genes: {sum(1 for g in gene_results if g['classification'] == 'Human')}\n"
+    results_text += f"Non-human-like genes: {sum(1 for g in gene_results if g['classification'] == 'Non-human')}\n\n"
+    
+    # Sort genes by absolute SHAP value for reporting
+    sorted_genes = sorted(gene_results, key=lambda x: abs(x['avg_shap']), reverse=True)
+    
+    results_text += "Top 10 genes by signal strength:\n"
+    for gene in sorted_genes[:10]:
+        results_text += (
+            f"Gene: {gene['gene_name']}\n"
+            f"Location: {gene['location']}\n"
+            f"Classification: {gene['classification']} "
+            f"(confidence: {gene['confidence']:.4f})\n"
+            f"Average SHAP: {gene['avg_shap']:.4f}\n\n"
+        )
+    
+    # Create CSV content
+    csv_content = "gene_name,location,avg_shap,median_shap,std_shap,max_shap,min_shap,"
+    csv_content += "pos_fraction,classification,confidence,locus_tag\n"
+    
     for gene in gene_results:
-        # Create feature
-        feature = SeqFeature(
-            FeatureLocation(gene['start'], gene['end']),
-            type="gene"
+        csv_content += (
+            f"{gene['gene_name']},{gene['location']},{gene['avg_shap']:.4f},"
+            f"{gene['median_shap']:.4f},{gene['std_shap']:.4f},{gene['max_shap']:.4f},"
+            f"{gene['min_shap']:.4f},{gene['pos_fraction']:.4f},{gene['classification']},"
+            f"{gene['confidence']:.4f},{gene['locus_tag']}\n"
         )
+    
+    # Save CSV to temp file
+    csv_path = save_results_to_temp(csv_content, "gene_analysis")
+    
+    try:
+        # Create genome diagram
+        diagram_img = create_genome_diagram(gene_results, len(shap_means))
+    except Exception as e:
+        print(f"Error creating genome diagram: {str(e)}")
+        diagram_img = create_error_image(str(e))
+    
+    return results_text, csv_path, diagram_img
+
+def create_error_image(error_message: str) -> Image.Image:
+    """
+    Create an error image with message
+    
+    Args:
+        error_message (str): Error message to display
         
-        # Calculate color based on SHAP value
-        if gene['avg_shap'] > 0:
-            intensity = min(1.0, abs(gene['avg_shap']) * 2)
-            color = colors.Color(1-intensity, 1-intensity, 1)  # Red
-        else:
-            intensity = min(1.0, abs(gene['avg_shap']) * 2)
-            color = colors.Color(1-intensity, 1-intensity, 1)  # Blue
-            
-        # Add to diagram
-        gd_feature_set.add_feature(
-            feature,
-            color=color,
-            label=True,
-            name=f"{gene['gene_name']}\n(SHAP: {gene['avg_shap']:.3f})"
-        )
+    Returns:
+        Image.Image: Error image
+    """
+    img = Image.new('RGB', (800, 100), color='white')
+    draw = ImageDraw.Draw(img)
+    try:
+        font = ImageFont.truetype("/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf", 12)
+    except:
+        font = None
+    draw.text((10, 40), f"Error creating genome diagram: {error_message}", 
+              fill='black', font=font)
+    return img
+
+def create_genome_diagram(gene_results: List[Dict[str, Any]], 
+                        genome_length: int) -> Image.Image:
+    """
+    Create genome diagram using BioPython
+    
+    Args:
+        gene_results (List[Dict]): List of gene analysis results
+        genome_length (int): Total length of the genome
         
+    Returns:
+        Image.Image: Genome diagram image
+    """
     try:
+        # Create diagram
+        gd_diagram = GenomeDiagram.Diagram("Genome SHAP Analysis")
+        gd_track = gd_diagram.new_track(1, name="Genes")
+        gd_feature_set = gd_track.new_set()
+        
+        # Add features
+        for gene in gene_results:
+            # Create feature
+            feature = SeqFeature(
+                FeatureLocation(gene['start'], gene['end']),
+                type="gene"
+            )
+            
+            # Calculate color based on SHAP value
+            if gene['avg_shap'] > 0:
+                intensity = min(1.0, abs(gene['avg_shap']) * 2)
+                color = colors.Color(1-intensity, 1-intensity, 1)  # Red
+            else:
+                intensity = min(1.0, abs(gene['avg_shap']) * 2)
+                color = colors.Color(1-intensity, 1-intensity, 1)  # Blue
+                
+            # Add to diagram
+            gd_feature_set.add_feature(
+                feature,
+                color=color,
+                label=True,
+                name=f"{gene['gene_name']}\n(SHAP: {gene['avg_shap']:.3f})"
+            )
+        
         # Draw diagram
         gd_diagram.draw(
             format="linear",
@@ -722,13 +891,10 @@ def create_genome_diagram(gene_results, genome_length):
         gd_diagram.write(buffer, "PNG")
         buffer.seek(0)
         return Image.open(buffer)
+        
     except Exception as e:
         print(f"Error creating genome diagram: {str(e)}")
-        # Create a simple error image
-        error_img = Image.new('RGB', (800, 100), color='white')
-        draw = ImageDraw.Draw(error_img)
-        draw.text((10, 40), f"Error creating genome diagram: {str(e)}", fill='black')
-        return error_img
+        return create_error_image(str(e))
 
 ###############################################################################
 # 12. DOWNLOAD FUNCTIONS
@@ -822,7 +988,7 @@ with gr.Blocks(css=css) as iface:
         Upload a FASTA file and corresponding gene features file to analyze SHAP values per gene.
         Gene features should be in the format:
         ```
-        >gene_name [gene=X] [locus_tag=Y] [location=start..end]
+        >gene_name [gene=X] [locus_tag=Y] [location=start..end] or [location=complement(start..end)]
         SEQUENCE
         ```
         The genome viewer will show genes color-coded by their contribution:
@@ -841,7 +1007,7 @@ with gr.Blocks(css=css) as iface:
         analyze_genes_btn = gr.Button("Analyze Gene Features", variant="primary")
         gene_results = gr.Textbox(label="Gene Analysis Results", lines=12, interactive=False)
         gene_diagram = gr.Image(label="Genome Diagram with Gene Features")
-        download_gene_results = gr.File(label="Download Gene Analysis", visible=False, elem_classes="download-button")
+        download_gene_results = gr.File(label="Download Gene Analysis (CSV)", visible=True)
         
         analyze_genes_btn.click(
             analyze_gene_features,