Update app.py

app.py

@@ -44,7 +44,31 @@ def parse_genbank(uploaded_file):
 
     return organism, gene_info, cds_info, gc_content, len(record.seq), feature_types, str(record.seq)
 
-# Additional functions (calculate_gc_content, calculate_kmers, add_protein_features) as before
+# Additional functions (calculate_gc_content, calculate_kmers, add_protein_features) 
+# Function to calculate GC content over genome
+def calculate_gc_content(sequence, window_size=1000):
+    gc_content = [
+        (sequence[i:i+window_size].count('G') + sequence[i:i+window_size].count('C')) / window_size * 100
+        for i in range(0, len(sequence) - window_size + 1, window_size)
+    ]
+    return gc_content
+
+# Function to calculate k-mers
+def calculate_kmers(sequence, k):
+    kmers = Counter([sequence[i:i+k] for i in range(len(sequence) - k + 1)])
+    return kmers
+
+# Function to add molecular weight and isoelectric point to CDS information
+def add_protein_features(cds_info):
+    for cds in cds_info:
+        if cds['Protein'] != 'N/A':
+            prot_analysis = ProteinAnalysis(cds['Protein'])
+            cds['Molecular Weight'] = prot_analysis.molecular_weight()
+            cds['Isoelectric Point'] = prot_analysis.isoelectric_point()
+        else:
+            cds['Molecular Weight'] = 'N/A'
+            cds['Isoelectric Point'] = 'N/A'
+    return cds_info
 
 # Function to generate genome diagram
 def create_genome_diagram(genbank_content, output_file_path):