Update app.py

✅ GenBank and FASTA upload
✅ Full GenBank record fetching from NCBI by accession ID
✅ Dynamic product size slider
✅ Primer binding visualization with pair selector
✅ Plot export as PNG or SVG

app.py

@@ -1,25 +1,27 @@
 import streamlit as st
 import pandas as pd
 import primer3
-from Bio import SeqIO
+from Bio import SeqIO, Entrez
 import matplotlib.pyplot as plt
 from io import StringIO, BytesIO
 import os
 
-st.set_page_config(page_title="PCR Primer Design", page_icon="🧬", layout="wide")
+# Required by NCBI
+Entrez.email = "your.email@example.com"
+
+st.set_page_config(page_title="PCR Primer Designer", layout="wide")
+
 st.sidebar.header("User Guide")
 st.sidebar.info("""
-1. Upload a GenBank or FASTA file.
-2. Select feature (if GenBank).
-3. Set product size range and number of primers.
-4. Design primers.
-5. Select a pair to visualize and download plot.
+1. Upload a GenBank/FASTA file or enter an NCBI accession ID.
+2. For GenBank: select a feature for primer design.
+3. Set PCR product size and number of primers.
+4. View, select, and download primer designs and visualizations.
 """)
 
-uploaded_file = st.file_uploader("Upload GenBank or FASTA file", type=['gb', 'gbk', 'fa', 'fasta'])
-
+# Helper functions
 def extract_features_from_genbank(content):
-    record = SeqIO.read(StringIO(content.decode("utf-8")), "genbank")
+    record = SeqIO.read(StringIO(content.decode("utf-8") if isinstance(content, bytes) else content), "genbank")
     features = {'CDS': [], 'tRNA': [], 'gene': []}
     for f in record.features:
         if f.type in features:
@@ -29,6 +31,10 @@ def extract_features_from_genbank(content):
 def parse_fasta(content):
     return SeqIO.read(StringIO(content.decode("utf-8")), "fasta")
 
+def fetch_genbank_from_ncbi(accession):
+    with Entrez.efetch(db="nucleotide", id=accession, rettype="gb", retmode="text") as handle:
+        return handle.read()
+
 def design_primers(seq, size_range, count):
     min_size, max_size = map(int, size_range.split('-'))
     return primer3.bindings.designPrimers(
@@ -62,67 +68,90 @@ def plot_primer_binding(seq_len, left_start, left_len, right_start, right_len, p
     ax.set_title("Primer Binding Sites and PCR Product", fontsize=14)
     return fig
 
-primer_df = None
-sequence = None
-df_for_plot = None
+# UI: NCBI or file
+st.subheader("Input Sequence")
+col1, col2 = st.columns(2)
+with col1:
+    accession_input = st.text_input("Enter NCBI accession (e.g., NM_000546)")
+    fetch_btn = st.button("Fetch GenBank Record")
 
-if uploaded_file:
+with col2:
+    uploaded_file = st.file_uploader("Or upload GenBank/FASTA", type=["gb", "gbk", "fa", "fasta"])
+
+sequence = None
+record = None
+df = pd.DataFrame()
+
+# Handle input
+if fetch_btn and accession_input:
+    try:
+        gb_text = fetch_genbank_from_ncbi(accession_input.strip())
+        record = SeqIO.read(StringIO(gb_text), "genbank")
+        ext = ".gb"
+        st.success(f"Fetched GenBank record for {accession_input}")
+    except Exception as e:
+        st.error(f"Error fetching GenBank record: {e}")
+
+elif uploaded_file:
     ext = os.path.splitext(uploaded_file.name)[1].lower()
-    if ext in ['.gb', '.gbk']:
-        features, record = extract_features_from_genbank(uploaded_file.getvalue())
-        st.subheader("Feature Selection")
-        ftype = st.selectbox("Select feature type", ['CDS', 'tRNA', 'gene'])
-        options = [
-            f"{f.qualifiers.get('gene', [''])[0]} ({f.location.start}:{f.location.end}) [length: {len(f.location)} bp]"
-            for f in features[ftype]
-        ]
-        selected = st.selectbox("Select feature", range(len(options)), format_func=lambda x: options[x])
-        selected_feature = features[ftype][selected]
-        sequence = selected_feature.extract(record.seq)
-    elif ext in ['.fa', '.fasta']:
+    if ext in ['.fa', '.fasta']:
         record = parse_fasta(uploaded_file.getvalue())
         sequence = record.seq
-        st.success(f"FASTA loaded (length: {len(sequence)} bp)")
+        st.success(f"FASTA file loaded: {len(sequence)} bp")
+    else:
+        features, record = extract_features_from_genbank(uploaded_file.getvalue())
 
+# Feature selection if GenBank
+if record and hasattr(record, "features"):
+    features, record = extract_features_from_genbank(record.format("genbank"))
+    st.subheader("Feature Selection")
+    ftype = st.selectbox("Feature type", ['CDS', 'tRNA', 'gene'])
+    options = [
+        f"{f.qualifiers.get('gene', [''])[0]} ({f.location.start}:{f.location.end}) [length: {len(f.location)} bp]"
+        for f in features[ftype]
+    ]
+    selected = st.selectbox("Select feature", range(len(options)), format_func=lambda x: options[x])
+    selected_feature = features[ftype][selected]
+    sequence = selected_feature.extract(record.seq)
+elif record and hasattr(record, "seq"):
+    sequence = record.seq
+
+# Primer design UI
 if sequence:
     st.code(str(sequence), language="text")
-    st.subheader("Primer Design Parameters")
-    product_range = st.slider("PCR product size range", 100, len(sequence), (100, min(500, len(sequence))), step=10)
-    primer_count = st.number_input("Number of primer pairs", 1, 20, 5)
-
-    if "primers" not in st.session_state:
-        st.session_state.primers = []
-        st.session_state.df = pd.DataFrame()
+    st.subheader("Primer Design Settings")
+    size_range = st.slider("PCR product size (bp)", 100, len(sequence), (100, min(500, len(sequence))), step=10)
+    pair_count = st.number_input("Number of primer pairs", 1, 20, 5)
 
     if st.button("Design Primers"):
         with st.spinner("Designing primers..."):
-            primers = design_primers(sequence, f"{product_range[0]}-{product_range[1]}", primer_count)
+            result = design_primers(sequence, f"{size_range[0]}-{size_range[1]}", pair_count)
             rows = []
-            for i in range(primer_count):
-                if f'PRIMER_LEFT_{i}_SEQUENCE' in primers:
+            for i in range(pair_count):
+                if f'PRIMER_LEFT_{i}_SEQUENCE' in result:
                     rows.append({
                         "Pair": i + 1,
-                        "Left Seq": primers[f'PRIMER_LEFT_{i}_SEQUENCE'],
-                        "Right Seq": primers[f'PRIMER_RIGHT_{i}_SEQUENCE'],
-                        "Left TM": round(primers[f'PRIMER_LEFT_{i}_TM'], 2),
-                        "Right TM": round(primers[f'PRIMER_RIGHT_{i}_TM'], 2),
-                        "Product Size": primers[f'PRIMER_PAIR_{i}_PRODUCT_SIZE'],
-                        "L_Pos": primers[f'PRIMER_LEFT_{i}'][0],
-                        "L_Len": primers[f'PRIMER_LEFT_{i}'][1],
-                        "R_Pos": primers[f'PRIMER_RIGHT_{i}'][0],
-                        "R_Len": primers[f'PRIMER_RIGHT_{i}'][1],
+                        "Left Seq": result[f'PRIMER_LEFT_{i}_SEQUENCE'],
+                        "Right Seq": result[f'PRIMER_RIGHT_{i}_SEQUENCE'],
+                        "Left TM": round(result[f'PRIMER_LEFT_{i}_TM'], 2),
+                        "Right TM": round(result[f'PRIMER_RIGHT_{i}_TM'], 2),
+                        "Product Size": result[f'PRIMER_PAIR_{i}_PRODUCT_SIZE'],
+                        "L_Pos": result[f'PRIMER_LEFT_{i}'][0],
+                        "L_Len": result[f'PRIMER_LEFT_{i}'][1],
+                        "R_Pos": result[f'PRIMER_RIGHT_{i}'][0],
+                        "R_Len": result[f'PRIMER_RIGHT_{i}'][1],
                     })
-            st.session_state.df = pd.DataFrame(rows)
+            df = pd.DataFrame(rows)
 
-    if not st.session_state.df.empty:
-        st.subheader("Designed Primers")
-        st.dataframe(st.session_state.df.drop(columns=["L_Pos", "L_Len", "R_Pos", "R_Len"]))
+    if not df.empty:
+        st.subheader("Designed Primer Pairs")
+        st.dataframe(df.drop(columns=["L_Pos", "L_Len", "R_Pos", "R_Len"]))
 
-        csv = st.session_state.df.drop(columns=["L_Pos", "L_Len", "R_Pos", "R_Len"]).to_csv(index=False).encode("utf-8")
+        csv = df.drop(columns=["L_Pos", "L_Len", "R_Pos", "R_Len"]).to_csv(index=False).encode("utf-8")
         st.download_button("Download Primer Table", csv, "primers.csv", "text/csv")
 
-        selected_pair = st.selectbox("Select Primer Pair to Visualize", st.session_state.df["Pair"])
-        row = st.session_state.df[st.session_state.df["Pair"] == selected_pair].iloc[0]
+        selected_pair = st.selectbox("Select Primer Pair to Visualize", df["Pair"])
+        row = df[df["Pair"] == selected_pair].iloc[0]
 
         fig = plot_primer_binding(
             len(sequence),
@@ -132,11 +161,10 @@ if sequence:
         )
         st.pyplot(fig)
 
-        export_fmt = st.radio("Download format", ["PNG", "SVG"])
+        fmt = st.radio("Export format", ["PNG", "SVG"])
         buf = BytesIO()
-        fmt = "png" if export_fmt == "PNG" else "svg"
-        fig.savefig(buf, format=fmt, dpi=300)
-        st.download_button(f"Download Plot ({export_fmt})", buf.getvalue(), f"primer_plot.{fmt}", f"image/{fmt}")
+        fig.savefig(buf, format=fmt.lower(), dpi=300)
+        st.download_button(f"Download Plot ({fmt})", buf.getvalue(), f"primer_plot.{fmt.lower()}", f"image/{fmt.lower()}")
 
 # Footer
 st.markdown("""