Update app.py

app.py

@@ -7,10 +7,14 @@ import pandas as pd
 import os
 import re
 import logging
+import numpy as np
 from predictor import GenePredictor
 from tensorflow.keras.models import load_model
 import ml_simplified_tree
 
+# --- Global Variables ---
+MAFFT_PATH = "mafft/mafftdir/bin/mafft"
+
 # --- Logging ---
 logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
 
@@ -37,13 +41,26 @@ if os.path.exists(keras_path) and os.path.exists(kmer_path):
 
 # --- Keras Prediction ---
 def predict_with_keras(sequence):
+    if len(sequence) < 6:
+        return "Sequence too short for k-mer prediction."
     kmers = [sequence[i:i+6] for i in range(len(sequence)-5)]
     indices = [kmer_to_index.get(kmer, 0) for kmer in kmers]
-    input_arr = torch.tensor([indices])
+    input_arr = np.array([indices])  # Changed from torch.tensor to np.array
     prediction = keras_model.predict(input_arr, verbose=0)[0]
     return ''.join(str(round(p, 3)) for p in prediction)
 
+# --- FASTA Reader ---
+def read_fasta_file(f):
+    content = f.read().decode("utf-8") if hasattr(f, "read") else open(f, "r").read()
+    lines = content.strip().split("\n")
+    seq_lines = [line.strip() for line in lines if not line.startswith(">")]
+    return ''.join(seq_lines)
+
 # --- Full Pipeline ---
+def run_pipeline_from_file(fasta_file_obj):
+    dna_input = read_fasta_file(fasta_file_obj)
+    return run_pipeline(dna_input)
+
 def run_pipeline(dna_input):
     dna_input = dna_input.upper()
     if not re.match('^[ACTGN]+$', dna_input):
@@ -67,8 +84,9 @@ def run_pipeline(dna_input):
 
     # Run MAFFT
     aligned_file = "aligned.fasta"
+    mafft_exec = MAFFT_PATH  # Use global variable
     try:
-        subprocess.run(["mafft", "--auto", fasta_file], stdout=open(aligned_file, "w"), check=True)
+        subprocess.run([mafft_exec, "--auto", fasta_file], stdout=open(aligned_file, "w"), check=True)
     except Exception as e:
         aligned_file = None
         logging.error(f"MAFFT failed: {e}")
@@ -90,21 +108,34 @@ def run_pipeline(dna_input):
                 matched_ids, perc = analyzer.find_similar_sequences(analyzer.matching_percentage)
                 analyzer.create_interactive_tree(matched_ids, perc)
                 ml_output = "Tree generated."
+                if os.path.exists(html_file):
+                    with open(html_file, "r") as f:
+                        tree_html_content = f.read()
+                else:
+                    tree_html_content = "Tree HTML file not generated."
             else:
                 ml_output = "Query sequence not found."
+                tree_html_content = "No tree generated."
         else:
             ml_output = "Failed to load CSV."
+            tree_html_content = "No tree generated."
     else:
         ml_output = "CSV file missing."
+        tree_html_content = "No tree generated."
 
-    return step1_out, step2_out, csv_path, ml_output, html_file, aligned_file, phy_file
+    return step1_out, step2_out, csv_path, ml_output, html_file, aligned_file, phy_file, tree_html_content
 
 # --- Gradio UI ---
 with gr.Blocks() as demo:
     gr.Markdown("# Viral Gene Phylogenetic Inference Pipeline")
 
-    inp = gr.Textbox(label="DNA Input")
-    btn = gr.Button("Run Pipeline")
+    with gr.Tab("Paste DNA"):
+        inp = gr.Textbox(label="DNA Input")
+        btn1 = gr.Button("Run Pipeline")
+
+    with gr.Tab("Upload FASTA"):
+        file_input = gr.File(label="FASTA File", file_types=['.fasta', '.fa'])
+        btn2 = gr.Button("Run on FASTA")
 
     out1 = gr.Textbox(label="Boundary Model Output")
     out2 = gr.Textbox(label="Keras Model Output")
@@ -113,8 +144,10 @@ with gr.Blocks() as demo:
     html = gr.File(label="ML Tree (HTML)", file_types=['.html'])
     fasta = gr.File(label="Aligned FASTA", file_types=['.fasta'])
     phy = gr.File(label="IQ-TREE .phy File", file_types=['.phy'])
+    tree_html = gr.HTML(label="Interactive Tree Preview")
 
-    btn.click(fn=run_pipeline, inputs=inp, outputs=[out1, out2, out3, out4, html, fasta, phy])
+    btn1.click(fn=run_pipeline, inputs=inp, outputs=[out1, out2, out3, out4, html, fasta, phy, tree_html])
+    btn2.click(fn=run_pipeline_from_file, inputs=file_input, outputs=[out1, out2, out3, out4, html, fasta, phy, tree_html])
 
 if __name__ == '__main__':
-    demo.launch(server_name="0.0.0.0", server_port=7860)
+    demo.launch(server_name="0.0.0.0", server_port=7860)