Create app.py

app.py

@@ -0,0 +1,80 @@
+# Import libraries
+import streamlit as st
+import pandas as pd
+from Bio import SeqIO
+import altair as alt
+import numpy as np
+
+# Function to parse GenBank file
+def parse_genbank(file):
+    record = SeqIO.read(file, "genbank")
+    organism = record.annotations['organism']
+    features = record.features
+    genes, cds = [], []
+    for feature in features:
+        if feature.type == "gene":
+            genes.append(feature)
+        elif feature.type == "CDS":
+            cds.append(feature)
+    gc_content = (record.seq.count('G') + record.seq.count('C')) / len(record.seq) * 100
+    gene_info = [{
+        'Gene': gene.qualifiers.get('gene', ['N/A'])[0],
+        'Length': len(gene),
+        'Location': str(gene.location)} for gene in genes]
+    cds_info = [{
+        'Gene': cds.qualifiers.get('gene', ['N/A'])[0],
+        'Protein': cds.qualifiers.get('translation', ['N/A'])[0],
+        'Length': len(cds),
+        'Location': str(cds.location)} for cds in cds]
+    return organism, gene_info, cds_info, gc_content, len(record.seq)
+
+# Page setup
+st.set_page_config(page_title="Genomic Data Dashboard", page_icon="🧬", layout="wide")
+
+# Upload GenBank file
+uploaded_file = st.file_uploader("Upload a GenBank file", type=['gb', 'gbk'])
+if uploaded_file is not None:
+    organism, gene_info, cds_info, gc_content, sequence_length = parse_genbank(uploaded_file)
+    gene_df = pd.DataFrame(gene_info)
+    cds_df = pd.DataFrame(cds_info)
+else:
+    st.warning("Please upload a GenBank file.")
+    st.stop()
+
+# Sidebar information
+with st.sidebar:
+    st.title('Genomic Data Dashboard')
+    st.write(f'Organism: {organism}')
+    # You can add more interactive widgets here as needed
+
+# Main content
+col1, col2 = st.columns(2)
+
+with col1:
+    st.markdown('### General Information')
+    st.write(f'**Organism:** {organism}')
+    st.write(f'**Sequence Length:** {sequence_length} bp')
+    st.write(f'**GC Content:** {gc_content:.2f}%')
+    st.write(f'**Number of Genes:** {len(gene_df)}')
+    st.write(f'**Number of Coding Sequences (CDS):** {len(cds_df)}')
+
+with col2:
+    st.markdown('### Genes and Proteins')
+    gene_selected = st.selectbox('Select a gene to view details:', options=gene_df['Gene'])
+    if gene_selected:
+        selected_gene = gene_df[gene_df['Gene'] == gene_selected]
+        if not selected_gene.empty:
+            st.write(f"**Gene Details:** {selected_gene.to_dict('records')[0]}")
+        selected_cds = cds_df[cds_df['Gene'] == gene_selected]
+        if not selected_cds.empty:
+            st.write(f"**CDS Details:** {selected_cds.to_dict('records')[0]}")
+
+# Display data tables (optional)
+with st.expander("View All Genes"):
+    st.dataframe(gene_df)
+with st.expander("View All Coding Sequences"):
+    st.dataframe(cds_df)
+
+# You can extend the app with more functionalities like visualizations, 
+# k-mer analysis, or other genomic metrics based on your requirements.
+