Update DNA sequence analyzer with Plotly visuals

Refactored DNA analysis app with updated input handling and enhanced visualizations.

Author: Siddharth-lab-cmd

app.py

@@ -1,29 +1,52 @@
-import streamlit as str
+import streamlit as st
+import plotly.express as px
+import pandas as pd
 
-str.set_page_config(page_title="Bioinformatics Aligner", page_icon="🧬")
+st.set_page_config(page_title="Bioinformatics Aligner", page_icon="🧬")
 
-str.title("🧬 Advanced DNA Sequence Checker")
-str.write("Built by Siddharth-lab-cmd")
+st.title("🧬 Advanced DNA Analyzer & Visualizer")
+st.write("Built with tactical precision by Siddharth-lab-cmd")
 
-seq1 = str.text_input("Enter DNA Sequence 1:", "ATCGATCG").upper()
-seq2 = str.text_input("Enter DNA Sequence 2:", "ATGGATCG").upper()
+# Input field for DNA
+seq = st.text_input("Enter DNA Sequence to Analyze:", "ATCGATCGATGGATCGATCG").upper()
 
-if str.button("Analyze Match"):
-    if len(seq1) != len(seq2):
-        str.error("For a simple match check, both sequences must be the same length!")
+# Core calculation logic
+if st.button("Run Analytics"):
+    # 1. Calculate length and counts
+    total_length = len(seq)
+    a_count = seq.count("A")
+    t_count = seq.count("T")
+    c_count = seq.count("C")
+    g_count = seq.count("G")
+    
+    # 2. Check for empty or invalid inputs
+    if total_length == 0:
+        st.error("Please enter a valid DNA sequence!")
     else:
-        matches = 0
-        visual_line = ""
-        for i in range(len(seq1)):
-            if seq1[i] == seq2[i]:
-                matches += 1
-                visual_line += "|"
-            else:
-                visual_line += "."
-                
-        identity = (matches / len(seq1)) * 100
+        gc_total = g_count + c_count
+        gc_percentage = (gc_total / total_length) * 100
 
-        str.success(f"Analysis Complete! Identity Score: {identity:.2f}%")
-        str.text(f"Seq 1: {seq1}")
-        str.text(f"Match: {visual_line}")
-        str.text(f"Seq 2: {seq2}")
+        # Display text matrix scores
+        st.success("Analysis Complete!")
+        st.write(f"**Total Base Pairs:** {total_length}")
+        st.write(f"**GC Content Percentage:** {gc_percentage:.2f}%")
+        
+        # 3. Create the Plotly Data Frame Table
+        data = {
+            'Nucleotide': ['Adenine (A)', 'Thymine (T)', 'Cytosine (C)', 'Guanine (G)'],
+            'Count': [a_count, t_count, c_count, g_count]
+        }
+        df = pd.DataFrame(data)
+        
+        # 4. Generate Interactive Plotly Bar Chart
+        fig = px.bar(
+            df, 
+            x='Nucleotide', 
+            y='Count', 
+            title="DNA Base Distribution Frequency",
+            color='Nucleotide',
+            labels={'Count': 'Number of Bases'}
+        )
+        
+        # Render the interactive chart on our Streamlit site
+        st.plotly_chart(fig)