add visualization

app.py

@@ -4,10 +4,10 @@ import cas9on
 import cas9off
 import pandas as pd
 import streamlit as st
-import plotly.express as px
+from pygenomeviz import GenomeViz
 import numpy as np
 from pathlib import Path
-from igv_component import igv_component
+
 
 # title and documentation
 st.markdown(Path('crisprTool.md').read_text(), unsafe_allow_html=True)
@@ -103,38 +103,30 @@ if selected_model == 'Cas9':
         # Process predictions
         if predict_button and gene_symbol:
             predictions = cas9on.process_gene(gene_symbol, cas9on_path)
-            # Sort predictions by the 'Prediction' score in descending order and take the top 10
             sorted_predictions = sorted(predictions, key=lambda x: x[-1], reverse=True)[:10]
             st.session_state['on_target_results'] = sorted_predictions
 
-        # On-target results display
         if 'on_target_results' in st.session_state and st.session_state['on_target_results']:
-            # Convert the results to a pandas DataFrame for better display
             df = pd.DataFrame(st.session_state['on_target_results'],
                               columns=["Gene ID", "Start Pos", "End Pos", "Strand", "gRNA", "Prediction"])
             st.write('Top on-target predictions:')
             st.dataframe(df)
 
-            # Plotting with Plotly
-            fig = px.bar(df, x='gRNA', y='Prediction', color='Prediction',
-                         labels={'gRNA': 'Guide RNA', 'Prediction': 'Prediction Score'},
-                         hover_data=['Start Pos', 'End Pos', 'Strand'])
-            fig.update_layout(title='Top 10 CRISPR Targets by Prediction Score',
-                              xaxis_title='Guide RNA',
-                              yaxis_title='Prediction Score')
-            st.plotly_chart(fig)
-
-            # Download button for full results
-            if 'full_on_target_results' in st.session_state:
-                full_df = pd.DataFrame(st.session_state['full_on_target_results'],
-                                       columns=["Gene ID", "Start Pos", "End Pos", "Strand", "gRNA", "Prediction"])
-                full_predictions_csv = full_df.to_csv(index=False).encode('utf-8')
-                st.download_button(
-                    label='Download all on-target predictions',
-                    data=full_predictions_csv,
-                    file_name='on_target_results.csv',
-                    mime='text/csv'
-                )
+            # Initialize GenomeViz
+            gv = GenomeViz()
+            genome_size = max(
+                df["End Pos"])  # Assuming the max end position approximates the genome size for visualization purposes
+            track = gv.add_feature_track("CRISPR Targets", genome_size)
+
+            for _, row in df.iterrows():
+                start, end, strand = row["Start Pos"], row["End Pos"], row["Strand"]
+                label = row["gRNA"]
+                track.add_feature(start, end, strand, label=label)
+
+            # Save and display the visualization
+            gv_fig_path = "crispr_targets.png"
+            gv.savefig(gv_fig_path)
+            st.image(gv_fig_path, caption="CRISPR Targets Visualization")
 
     elif target_selection == 'off-target':
         ENTRY_METHODS = dict(

requirements.txt

@@ -3,4 +3,5 @@ biopython==1.80
 pandas==1.5.2
 tensorflow==2.11.0
 tensorflow-probability==0.19.0
-plotly==5.18.0
+plotly==5.18.0
+pygenomeviz