Update app.py

app.py

@@ -571,6 +571,18 @@ def analyze_sequence_comparison(file1, file2, fasta1="", fasta2=""):
 # 11. GENE FEATURE ANALYSIS
 ###############################################################################
 
+import io
+from io import BytesIO
+from PIL import Image, ImageDraw, ImageFont
+import numpy as np
+import pandas as pd
+import tempfile
+import os
+from typing import List, Dict, Tuple, Optional, Any
+import matplotlib.pyplot as plt
+from matplotlib.colors import LinearSegmentedColormap
+import seaborn as sns
+
 def parse_gene_features(text: str) -> List[Dict[str, Any]]:
     """Parse gene features from text file in FASTA-like format"""
     genes = []
@@ -643,174 +655,6 @@ def compute_gene_statistics(gene_shap: np.ndarray) -> Dict[str, float]:
         'pos_fraction': float(np.mean(gene_shap > 0))
     }
 
-def create_simple_genome_diagram(gene_results: List[Dict[str, Any]], genome_length: int) -> Image.Image:
-    """
-    Create a simple genome diagram using PIL, forcing a minimum color intensity
-    so that small SHAP values don't appear white.
-    """
-    from PIL import Image, ImageDraw, ImageFont
-    
-    # Validate inputs
-    if not gene_results or genome_length <= 0:
-        img = Image.new('RGB', (800, 100), color='white')
-        draw = ImageDraw.Draw(img)
-        draw.text((10, 40), "Error: Invalid input data", fill='black')
-        return img
-        
-    # Ensure all gene coordinates are valid integers
-    for gene in gene_results:
-        gene['start'] = max(0, int(gene['start']))
-        gene['end'] = min(genome_length, int(gene['end']))
-        if gene['start'] >= gene['end']:
-            print(f"Warning: Invalid coordinates for gene {gene.get('gene_name','?')}: {gene['start']}-{gene['end']}")
-    
-    # Image dimensions
-    width = 1500
-    height = 600
-    margin = 50
-    track_height = 40
-    
-    # Create image with white background
-    img = Image.new('RGB', (width, height), 'white')
-    draw = ImageDraw.Draw(img)
-    
-    # Try to load font, fall back to default if unavailable
-    try:
-        font = ImageFont.truetype("/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf", 12)
-        title_font = ImageFont.truetype("/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf", 16)
-    except:
-        font = ImageFont.load_default()
-        title_font = ImageFont.load_default()
-    
-    # Draw title
-    draw.text((margin, margin // 2), "Genome SHAP Analysis", fill='black', font=title_font or font)
-    
-    # Draw genome line
-    line_y = height // 2
-    draw.line([(int(margin), int(line_y)), (int(width - margin), int(line_y))], fill='black', width=2)
-    
-    # Calculate scale factor
-    scale = float(width - 2 * margin) / float(genome_length)
-    
-    # Determine a reasonable step for scale markers
-    num_ticks = 10
-    if genome_length < num_ticks:
-        step = 1
-    else:
-        step = genome_length // num_ticks
-    
-    # Draw scale markers
-    for i in range(0, genome_length + 1, step):
-        x_coord = margin + i * scale
-        draw.line([
-            (int(x_coord), int(line_y - 5)), 
-            (int(x_coord), int(line_y + 5))
-        ], fill='black', width=1)
-        draw.text((int(x_coord - 20), int(line_y + 10)), f"{i:,}", fill='black', font=font)
-    
-    # Sort genes by absolute SHAP value for drawing
-    sorted_genes = sorted(gene_results, key=lambda x: abs(x['avg_shap']))
-    
-    # Draw genes
-    for idx, gene in enumerate(sorted_genes):
-        # Calculate position and ensure integers
-        start_x = margin + int(gene['start'] * scale)
-        end_x   = margin + int(gene['end'] * scale)
-        
-        # Calculate color based on SHAP value
-        avg_shap = gene['avg_shap']
-        
-        # Convert shap -> color intensity (0 to 255)
-        # Then clamp to a minimum intensity so it never ends up plain white
-        intensity = int(abs(avg_shap) * 500)
-        intensity = max(50, min(255, intensity))  # clamp between 50 and 255
-
-        if avg_shap > 0:
-            # Red-ish for positive
-            color = (255, 255 - intensity, 255 - intensity)
-        else:
-            # Blue-ish for negative or zero
-            color = (255 - intensity, 255 - intensity, 255)
-        
-        # Draw gene rectangle
-        draw.rectangle([
-            (int(start_x), int(line_y - track_height // 2)),
-            (int(end_x),   int(line_y + track_height // 2))
-        ], fill=color, outline='black')
-        
-        # Prepare gene name label
-        label = str(gene.get('gene_name','?'))
-        
-        # If getsize() or textsize() is missing, use getmask(...).size as fallback
-        # But if your Pillow version supports font.getsize, you can do:
-        # label_width, label_height = font.getsize(label)
-        label_mask = font.getmask(label)
-        label_width, label_height = label_mask.size
-        
-        # Alternate label positions above/below line
-        if idx % 2 == 0:
-            text_y = line_y - track_height - 15
-        else:
-            text_y = line_y + track_height + 5
-        
-        # Decide whether to rotate text based on space
-        gene_width = end_x - start_x
-        if gene_width > label_width:
-            text_x = start_x + (gene_width - label_width) // 2
-            draw.text((int(text_x), int(text_y)), label, fill='black', font=font)
-        elif gene_width > 20:
-            txt_img = Image.new('RGBA', (label_width, label_height), (255, 255, 255, 0))
-            txt_draw = ImageDraw.Draw(txt_img)
-            txt_draw.text((0, 0), label, font=font, fill='black')
-            rotated_img = txt_img.rotate(90, expand=True)
-            img.paste(rotated_img, (int(start_x), int(text_y)), rotated_img)
-    
-    # Draw legend
-    legend_x = margin
-    legend_y = height - margin
-    draw.text((int(legend_x), int(legend_y - 60)), "SHAP Values:", fill='black', font=font)
-    
-    # Draw legend boxes
-    box_width = 20
-    box_height = 20
-    spacing = 15
-    
-    # Strong human-like
-    draw.rectangle([
-        (int(legend_x), int(legend_y - 45)), 
-        (int(legend_x + box_width), int(legend_y - 45 + box_height))
-    ], fill=(255, 0, 0), outline='black')
-    draw.text((int(legend_x + box_width + spacing), int(legend_y - 45)), 
-              "Strong human-like signal", fill='black', font=font)
-    
-    # Weak human-like
-    draw.rectangle([
-        (int(legend_x), int(legend_y - 20)), 
-        (int(legend_x + box_width), int(legend_y - 20 + box_height))
-    ], fill=(255, 200, 200), outline='black')
-    draw.text((int(legend_x + box_width + spacing), int(legend_y - 20)), 
-              "Weak human-like signal", fill='black', font=font)
-    
-    # Weak non-human-like
-    draw.rectangle([
-        (int(legend_x + 250), int(legend_y - 45)), 
-        (int(legend_x + 250 + box_width), int(legend_y - 45 + box_height))
-    ], fill=(200, 200, 255), outline='black')
-    draw.text((int(legend_x + 250 + box_width + spacing), int(legend_y - 45)), 
-              "Weak non-human-like signal", fill='black', font=font)
-    
-    # Strong non-human-like
-    draw.rectangle([
-        (int(legend_x + 250), int(legend_y - 20)), 
-        (int(legend_x + 250 + box_width), int(legend_y - 20 + box_height))
-    ], fill=(0, 0, 255), outline='black')
-    draw.text((int(legend_x + 250 + box_width + spacing), int(legend_y - 20)), 
-              "Strong non-human-like signal", fill='black', font=font)
-    
-    return img
-
-
-
 def create_simple_genome_diagram(gene_results, genome_length):
     from PIL import Image, ImageDraw, ImageFont
 
@@ -958,6 +802,121 @@ def create_simple_genome_diagram(gene_results, genome_length):
     return img
 
 
+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"""
+    # 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]:
+        return f"Error in sequence analysis: {sequence_results[0]}", None, None
+        
+    # Get SHAP values
+    shap_means = sequence_results[3]["shap_means"]
+    
+    # Parse gene features
+    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
+            
+    # Analyze each gene
+    gene_results = []
+    for gene in genes:
+        try:
+            location = gene['metadata'].get('location', '')
+            if not location:
+                continue
+                
+            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]
+            stats = compute_gene_statistics(gene_shap)
+            
+            gene_results.append({
+                'gene_name': gene['metadata'].get('gene', 'Unknown'),
+                'location': location,
+                'start': start,
+                'end': end,
+                'locus_tag': gene['metadata'].get('locus_tag', ''),
+                '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
+            
+    # Sort genes by absolute SHAP value
+    sorted_genes = sorted(gene_results, key=lambda x: abs(x['avg_shap']), reverse=True)
+    
+    # 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"
+    
+    results_text += "Top 10 most distinctive genes:\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:
+        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
+    try:
+        temp_dir = tempfile.gettempdir()
+        temp_path = os.path.join(temp_dir, f"gene_analysis_{os.urandom(4).hex()}.csv")
+        
+        with open(temp_path, 'w') as f:
+            f.write(csv_content)
+    except Exception as e:
+        print(f"Error saving CSV: {str(e)}")
+        temp_path = None
+    
+    # Create visualization
+    try:
+        diagram_img = create_simple_genome_diagram(gene_results, len(shap_means))
+    except Exception as e:
+        print(f"Error creating visualization: {str(e)}")
+        # Create error image
+        diagram_img = Image.new('RGB', (800, 100), color='white')
+        draw = ImageDraw.Draw(diagram_img)
+        draw.text((10, 40), f"Error creating visualization: {str(e)}", fill='black')
+    
+    return results_text, temp_path, diagram_img
 
 ###############################################################################
 # 12. DOWNLOAD FUNCTIONS