Update

.ipynb_checkpoints/app-checkpoint.py

@@ -208,18 +208,39 @@ def process_pdb(pdb_id_or_file, segment):
     residue_scores = [(resi, score) for resi, score in zip(sequence_id, normalized_scores)]
 
     
-    # Identify high scoring residues (> 0.5)
-    high_score_residues = [resi for resi, score in residue_scores if score > 0.5]
+    # Define the score brackets
+    score_brackets = {
+        "0.0-0.2": (0.0, 0.2),
+        "0.2-0.4": (0.2, 0.4),
+        "0.4-0.6": (0.4, 0.6),
+        "0.6-0.8": (0.6, 0.8),
+        "0.8-1.0": (0.8, 1.0)
+    }
     
-    # Preparing the result: only print high scoring residues
+    # Initialize a dictionary to store residues by bracket
+    residues_by_bracket = {bracket: [] for bracket in score_brackets}
+    
+    # Categorize residues into brackets
+    for resi, score in residue_scores:
+        for bracket, (lower, upper) in score_brackets.items():
+            if lower <= score < upper:
+                residues_by_bracket[bracket].append(resi)
+                break
+    
+    # Preparing the result string
     current_time = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
     result_str = f"Prediction for PDB: {pdb_id}, Chain: {segment}\nDate: {current_time}\n\n"
-    result_str += "High-scoring Residues (Score > 0.5):\n"
-    result_str += "Columns: Residue Name, Residue Number, One-letter Code, Normalized Score\n\n"
-    result_str += "\n".join([
-        f"{res.resname} {res.id[1]} {sequence[i]} {normalized_scores[i]:.2f}" 
-        for i, res in enumerate(protein_residues) if res.id[1] in high_score_residues
-    ])
+    result_str += "Residues by Score Brackets:\n\n"
+    
+    # Add residues for each bracket
+    for bracket, residues in residues_by_bracket.items():
+        result_str += f"Bracket {bracket}:\n"
+        result_str += "Columns: Residue Name, Residue Number, One-letter Code, Normalized Score\n"
+        result_str += "\n".join([
+            f"{res.resname} {res.id[1]} {sequence[i]} {normalized_scores[i]:.2f}" 
+            for i, res in enumerate(protein_residues) if res.id[1] in residues
+        ])
+        result_str += "\n\n"
 
     # Create chain-specific PDB with scores in B-factor
     scored_pdb = create_chain_specific_pdb(pdb_path, segment, residue_scores, protein_residues)
@@ -232,24 +253,32 @@ def process_pdb(pdb_id_or_file, segment):
     pymol_commands = f"Prediction for PDB: {pdb_id}, Chain: {segment}\nDate: {current_time}\n\n"
     
     pymol_commands += f"""
-# PyMOL Visualization Commands
-load {os.path.abspath(pdb_path)}, protein
-hide everything, all
-show cartoon, chain {segment}
-color white, chain {segment}
-"""
+    # PyMOL Visualization Commands
+    load {os.path.abspath(pdb_path)}, protein
+    hide everything, all
+    show cartoon, chain {segment}
+    color white, chain {segment}
+    """
+    
+    # Define colors for each score bracket
+    bracket_colors = {
+        "0.0-0.2": "white",
+        "0.2-0.4": "lightorange",
+        "0.4-0.6": "orange",
+        "0.6-0.8": "orangered",
+        "0.8-1.0": "red"
+    }
     
-    # Color specific residues
-    for score_range, color in [
-        (high_score_residues, "red")
-    ]:
-        if score_range:
-            resi_list = '+'.join(map(str, score_range))
+    # Add PyMOL commands for each score bracket
+    for bracket, residues in residues_by_bracket.items():
+        if residues:  # Only add commands if there are residues in this bracket
+            color = bracket_colors[bracket]
+            resi_list = '+'.join(map(str, residues))
             pymol_commands += f"""
-select high_score_residues, resi {resi_list} and chain {segment}
-show sticks, high_score_residues
-color {color}, high_score_residues
-"""
+    select bracket_{bracket.replace('.', '').replace('-', '_')}, resi {resi_list} and chain {segment}
+    show sticks, bracket_{bracket.replace('.', '').replace('-', '_')}
+    color {color}, bracket_{bracket.replace('.', '').replace('-', '_')}
+    """
     # Create prediction and scored PDB files
     prediction_file = f"{pdb_id}_binding_site_residues.txt"
     with open(prediction_file, "w") as f:
@@ -294,7 +323,7 @@ def molecule(input_pdb, residue_scores=None, segment='A'):
         class2Model.setStyle({}, {});
         class2Model.setStyle(
             {"chain": "%s", "resi": [%s]}, 
-            {"stick": {"color": "0xFFD580", "opacity": 0.5}}
+            {"stick": {"color": "0xFFD580", "opacity": 0.7}}
         );
 
         // Create a new model for high-scoring residues and apply red sticks style
@@ -434,12 +463,12 @@ with gr.Blocks() as demo:
 
     molecule_output = gr.HTML(label="Protein Structure")
     explanation_vis = gr.Markdown("""
-    Residues with a score > 0.5 are represented as sticks with a score dependent colorcoding:
-    - 0.5-0.6: blue  
-    - 0.6–0.7: light blue  
-    - 0.7–0.8: white
-    - 0.8–0.9: orange
-    - 0.9–1.0: red
+    Score dependent colorcoding:
+    - 0.0-0.2: white  
+    - 0.2–0.4: light orange  
+    - 0.4–0.6: orange
+    - 0.6–0.8: orangered
+    - 0.8–1.0: red
     """)
     predictions_output = gr.Textbox(label="Visualize Prediction with PyMol")
     gr.Markdown("### Download:\n- List of predicted binding site residues\n- PDB with score in beta factor column")

app.py

@@ -208,18 +208,39 @@ def process_pdb(pdb_id_or_file, segment):
     residue_scores = [(resi, score) for resi, score in zip(sequence_id, normalized_scores)]
 
     
-    # Identify high scoring residues (> 0.5)
-    high_score_residues = [resi for resi, score in residue_scores if score > 0.5]
+    # Define the score brackets
+    score_brackets = {
+        "0.0-0.2": (0.0, 0.2),
+        "0.2-0.4": (0.2, 0.4),
+        "0.4-0.6": (0.4, 0.6),
+        "0.6-0.8": (0.6, 0.8),
+        "0.8-1.0": (0.8, 1.0)
+    }
     
-    # Preparing the result: only print high scoring residues
+    # Initialize a dictionary to store residues by bracket
+    residues_by_bracket = {bracket: [] for bracket in score_brackets}
+    
+    # Categorize residues into brackets
+    for resi, score in residue_scores:
+        for bracket, (lower, upper) in score_brackets.items():
+            if lower <= score < upper:
+                residues_by_bracket[bracket].append(resi)
+                break
+    
+    # Preparing the result string
     current_time = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
     result_str = f"Prediction for PDB: {pdb_id}, Chain: {segment}\nDate: {current_time}\n\n"
-    result_str += "High-scoring Residues (Score > 0.5):\n"
-    result_str += "Columns: Residue Name, Residue Number, One-letter Code, Normalized Score\n\n"
-    result_str += "\n".join([
-        f"{res.resname} {res.id[1]} {sequence[i]} {normalized_scores[i]:.2f}" 
-        for i, res in enumerate(protein_residues) if res.id[1] in high_score_residues
-    ])
+    result_str += "Residues by Score Brackets:\n\n"
+    
+    # Add residues for each bracket
+    for bracket, residues in residues_by_bracket.items():
+        result_str += f"Bracket {bracket}:\n"
+        result_str += "Columns: Residue Name, Residue Number, One-letter Code, Normalized Score\n"
+        result_str += "\n".join([
+            f"{res.resname} {res.id[1]} {sequence[i]} {normalized_scores[i]:.2f}" 
+            for i, res in enumerate(protein_residues) if res.id[1] in residues
+        ])
+        result_str += "\n\n"
 
     # Create chain-specific PDB with scores in B-factor
     scored_pdb = create_chain_specific_pdb(pdb_path, segment, residue_scores, protein_residues)
@@ -232,24 +253,32 @@ def process_pdb(pdb_id_or_file, segment):
     pymol_commands = f"Prediction for PDB: {pdb_id}, Chain: {segment}\nDate: {current_time}\n\n"
     
     pymol_commands += f"""
-# PyMOL Visualization Commands
-load {os.path.abspath(pdb_path)}, protein
-hide everything, all
-show cartoon, chain {segment}
-color white, chain {segment}
-"""
+    # PyMOL Visualization Commands
+    load {os.path.abspath(pdb_path)}, protein
+    hide everything, all
+    show cartoon, chain {segment}
+    color white, chain {segment}
+    """
+    
+    # Define colors for each score bracket
+    bracket_colors = {
+        "0.0-0.2": "white",
+        "0.2-0.4": "lightorange",
+        "0.4-0.6": "orange",
+        "0.6-0.8": "orangered",
+        "0.8-1.0": "red"
+    }
     
-    # Color specific residues
-    for score_range, color in [
-        (high_score_residues, "red")
-    ]:
-        if score_range:
-            resi_list = '+'.join(map(str, score_range))
+    # Add PyMOL commands for each score bracket
+    for bracket, residues in residues_by_bracket.items():
+        if residues:  # Only add commands if there are residues in this bracket
+            color = bracket_colors[bracket]
+            resi_list = '+'.join(map(str, residues))
             pymol_commands += f"""
-select high_score_residues, resi {resi_list} and chain {segment}
-show sticks, high_score_residues
-color {color}, high_score_residues
-"""
+    select bracket_{bracket.replace('.', '').replace('-', '_')}, resi {resi_list} and chain {segment}
+    show sticks, bracket_{bracket.replace('.', '').replace('-', '_')}
+    color {color}, bracket_{bracket.replace('.', '').replace('-', '_')}
+    """
     # Create prediction and scored PDB files
     prediction_file = f"{pdb_id}_binding_site_residues.txt"
     with open(prediction_file, "w") as f:
@@ -294,7 +323,7 @@ def molecule(input_pdb, residue_scores=None, segment='A'):
         class2Model.setStyle({}, {});
         class2Model.setStyle(
             {"chain": "%s", "resi": [%s]}, 
-            {"stick": {"color": "0xFFD580", "opacity": 0.5}}
+            {"stick": {"color": "0xFFD580", "opacity": 0.7}}
         );
 
         // Create a new model for high-scoring residues and apply red sticks style
@@ -434,12 +463,12 @@ with gr.Blocks() as demo:
 
     molecule_output = gr.HTML(label="Protein Structure")
     explanation_vis = gr.Markdown("""
-    Residues with a score > 0.5 are represented as sticks with a score dependent colorcoding:
-    - 0.5-0.6: blue  
-    - 0.6–0.7: light blue  
-    - 0.7–0.8: white
-    - 0.8–0.9: orange
-    - 0.9–1.0: red
+    Score dependent colorcoding:
+    - 0.0-0.2: white  
+    - 0.2–0.4: light orange  
+    - 0.4–0.6: orange
+    - 0.6–0.8: orangered
+    - 0.8–1.0: red
     """)
     predictions_output = gr.Textbox(label="Visualize Prediction with PyMol")
     gr.Markdown("### Download:\n- List of predicted binding site residues\n- PDB with score in beta factor column")