fixed bug

app.py

@@ -107,10 +107,10 @@ if selected_model == 'Cas9':
         def clean_up_old_files(gene_symbol):
             genbank_file_path = f"{gene_symbol}_crispr_targets.gb"
             bed_file_path = f"{gene_symbol}_crispr_targets.bed"
-            if os.path.exists(genbank_file_path):
-                os.remove(genbank_file_path)
-            if os.path.exists(bed_file_path):
-                os.remove(bed_file_path)
+            csv_file_path = f"{gene_symbol}_crispr_predictions.csv"
+            for path in [genbank_file_path, bed_file_path, csv_file_path]:
+                if os.path.exists(path):
+                    os.remove(path)
 
         if st.session_state['current_gene_symbol'] and gene_symbol != st.session_state['current_gene_symbol']:
             clean_up_old_files(st.session_state['current_gene_symbol'])
@@ -136,44 +136,47 @@ if selected_model == 'Cas9':
                 # Now create a Plotly plot with the sorted_predictions
                 fig = go.Figure()
 
-                # Variables to help spread gRNAs on the y-axis based on their strand
-                y_positive_strand = 10
-                y_negative_strand = -10
-                strand_offset = 1  # This will space out each subsequent guide on the same strand
+                # Variables to initialize the y position for the positive and negative strands
+                positive_strand_y = 1
+                negative_strand_y = -1
 
                 # Iterate over the sorted predictions to create the plot
                 for i, prediction in enumerate(sorted_predictions, start=1):
                     # Extract data for plotting
                     chrom, start, end, strand, target, gRNA, pred_score = prediction
-                    y_value = y_positive_strand if strand == 1 else y_negative_strand
+                    # Set the y-value and arrow symbol based on the strand
+                    if strand == 1:
+                        y_value = positive_strand_y
+                        arrow_symbol = 'triangle-right'
+                        positive_strand_y += 0.1  # Increment the y-value for the next positive strand gRNA
+                    else:
+                        y_value = negative_strand_y
+                        arrow_symbol = 'triangle-left'
+                        negative_strand_y -= 0.1  # Decrement the y-value for the next negative strand gRNA
+
                     fig.add_trace(go.Scatter(
                         x=[start, end],
-                        y=[y_value, y_value],  # Assign all points the same y value based on strand
+                        y=[y_value, y_value],  # Use the y_value set above for the strand
                         mode='lines+markers+text',
+                        marker=dict(symbol=arrow_symbol, size=10),
                         name=f"gRNA: {gRNA}",
-                        text=[f"Rank: {i}", ""],  # Text at the start position only
+                        text=[f"Rank: {i}", ""],  # Text at the first point
                         hoverinfo='text',
-                        hovertext=[
-                            f"Rank: {i}<br>Target: {target}<br>gRNA: {gRNA}<br>Cutsite: {start}<br>On Target Score: {pred_score:.4f}",
-                            ""
-                        ],
+                        hovertext=f"Rank: {i}<br>Chromosome: {chrom}<br>Target Sequence: {target}<br>gRNA: {gRNA}<br>Start: {start}<br>End: {end}<br>Strand: {'+' if strand == 1 else '-'}<br>Prediction Score: {pred_score:.4f}",
                     ))
-                    # Update the y-value for the next guide on the same strand
-                    if strand == 1:
-                        y_positive_strand += strand_offset
-                    else:
-                        y_negative_strand -= strand_offset
 
                 # Update the layout of the plot
                 fig.update_layout(
                     title='Top 10 gRNA Sequences by Prediction Score',
                     xaxis_title='Genomic Position',
-                    yaxis_title='Strand',
                     yaxis=dict(
+                        title='Strand',
                         showgrid=True,  # Show horizontal gridlines for clarity
-                        zeroline=True,  # Show a line at y=0
+                        zeroline=True,  # Show a line at y=0 to represent the axis
                         zerolinecolor='Black',
                         zerolinewidth=2,
+                        tickvals=[positive_strand_y, negative_strand_y],
+                        ticktext=['+ Strand', '- Strand']
                     ),
                     showlegend=False  # Hide the legend if it's not necessary
                 )
@@ -181,7 +184,7 @@ if selected_model == 'Cas9':
                 # Display the plot
                 st.plotly_chart(fig)
 
-                if gene_sequence:  # Ensure gene_sequence is not empty
+                if gene_sequence:
                     # Define file paths
                     genbank_file_path = f"{gene_symbol}_crispr_targets.gb"
                     bed_file_path = f"{gene_symbol}_crispr_targets.bed"
@@ -192,26 +195,27 @@ if selected_model == 'Cas9':
                     cas9on.create_bed_file_from_df(df, bed_file_path)
                     cas9on.create_csv_from_df(df, csv_file_path)
 
-                    # File download selection
-                    file_type = st.selectbox('Select file type to download:', ('GenBank', 'BED', 'CSV'))
-
-                    if file_type == 'GenBank':
+                    # Layout for download buttons
+                    col1, col2, col3 = st.columns(3)
+                    with col1:
                         with open(genbank_file_path, "rb") as file:
                             st.download_button(label="Download GenBank File", data=file, file_name=genbank_file_path,
                                                mime="text/x-genbank")
-                        st.markdown(
-                            "GenBank files can be visualized using [PyGenomeViz](https://pygenomeviz.streamlit.app/)")
-                    elif file_type == 'BED':
+                    with col2:
                         with open(bed_file_path, "rb") as file:
                             st.download_button(label="Download BED File", data=file, file_name=bed_file_path,
                                                mime="text/plain")
-                        st.markdown(
-                            "BED files can be used with the [UCSC Genome Browser](https://genome.ucsc.edu/cgi-bin/hgCustom)")
-                    elif file_type == 'CSV':
+                    with col3:
                         with open(csv_file_path, "rb") as file:
                             st.download_button(label="Download CSV File", data=file, file_name=csv_file_path,
                                                mime="text/csv")
 
+                    # Links for user guidance on using the downloaded files
+                    st.markdown(
+                        "GenBank files can be visualized using [PyGenomeViz](https://pygenomeviz.streamlit.app/). "
+                        "BED files can be used with the [UCSC Genome Browser](https://genome.ucsc.edu/cgi-bin/hgCustom)."
+                    )
+
                     # # Visualize the GenBank file using pyGenomeViz
                     # gv = GenomeViz(
                     #     feature_track_ratio=0.3,
@@ -333,10 +337,10 @@ elif selected_model == 'Cas12':
     def clean_up_old_files(gene_symbol):
         genbank_file_path = f"{gene_symbol}_crispr_targets.gb"
         bed_file_path = f"{gene_symbol}_crispr_targets.bed"
-        if os.path.exists(genbank_file_path):
-            os.remove(genbank_file_path)
-        if os.path.exists(bed_file_path):
-            os.remove(bed_file_path)
+        csv_file_path = f"{gene_symbol}_crispr_predictions.csv"
+        for path in [genbank_file_path, bed_file_path, csv_file_path]:
+            if os.path.exists(path):
+                os.remove(path)
 
     # Clean up files if a new gene symbol is entered
     if st.session_state['current_gene_symbol'] and gene_symbol != st.session_state['current_gene_symbol']:
@@ -362,44 +366,47 @@ elif selected_model == 'Cas12':
             # Now create a Plotly plot with the sorted_predictions
             fig = go.Figure()
 
-            # Variables to help spread gRNAs on the y-axis based on their strand
-            y_positive_strand = 10
-            y_negative_strand = -10
-            strand_offset = 1  # This will space out each subsequent guide on the same strand
+            # Variables to initialize the y position for the positive and negative strands
+            positive_strand_y = 1
+            negative_strand_y = -1
 
             # Iterate over the sorted predictions to create the plot
             for i, prediction in enumerate(sorted_predictions, start=1):
                 # Extract data for plotting
                 chrom, start, end, strand, target, gRNA, pred_score = prediction
-                y_value = y_positive_strand if strand == 1 else y_negative_strand
+                # Set the y-value and arrow symbol based on the strand
+                if strand == 1:
+                    y_value = positive_strand_y
+                    arrow_symbol = 'triangle-right'
+                    positive_strand_y += 0.1  # Increment the y-value for the next positive strand gRNA
+                else:
+                    y_value = negative_strand_y
+                    arrow_symbol = 'triangle-left'
+                    negative_strand_y -= 0.1  # Decrement the y-value for the next negative strand gRNA
+
                 fig.add_trace(go.Scatter(
                     x=[start, end],
-                    y=[y_value, y_value],  # Assign all points the same y value based on strand
+                    y=[y_value, y_value],  # Use the y_value set above for the strand
                     mode='lines+markers+text',
+                    marker=dict(symbol=arrow_symbol, size=10),
                     name=f"gRNA: {gRNA}",
-                    text=[f"Rank: {i}", ""],  # Text at the start position only
+                    text=[f"Rank: {i}", ""],  # Text at the first point
                     hoverinfo='text',
-                    hovertext=[
-                        f"Rank: {i}<br>Target: {target}<br>gRNA: {gRNA}<br>Cutsite: {start}<br>On Target Score: {pred_score:.4f}",
-                        ""
-                    ],
+                    hovertext=f"Rank: {i}<br>Chromosome: {chrom}<br>Target Sequence: {target}<br>gRNA: {gRNA}<br>Start: {start}<br>End: {end}<br>Strand: {'+' if strand == 1 else '-'}<br>Prediction Score: {pred_score:.4f}",
                 ))
-                # Update the y-value for the next guide on the same strand
-                if strand == 1:
-                    y_positive_strand += strand_offset
-                else:
-                    y_negative_strand -= strand_offset
 
             # Update the layout of the plot
             fig.update_layout(
                 title='Top 10 gRNA Sequences by Prediction Score',
                 xaxis_title='Genomic Position',
-                yaxis_title='Strand',
                 yaxis=dict(
+                    title='Strand',
                     showgrid=True,  # Show horizontal gridlines for clarity
-                    zeroline=True,  # Show a line at y=0
+                    zeroline=True,  # Show a line at y=0 to represent the axis
                     zerolinecolor='Black',
                     zerolinewidth=2,
+                    tickvals=[positive_strand_y, negative_strand_y],
+                    ticktext=['+ Strand', '- Strand']
                 ),
                 showlegend=False  # Hide the legend if it's not necessary
             )
@@ -419,26 +426,27 @@ elif selected_model == 'Cas12':
                 cas9on.create_bed_file_from_df(df, bed_file_path)
                 cas9on.create_csv_from_df(df, csv_file_path)
 
-                # File download selection
-                file_type = st.selectbox('Select file type to download:', ('GenBank', 'BED', 'CSV'))
-
-                if file_type == 'GenBank':
+                # Layout for download buttons
+                col1, col2, col3 = st.columns(3)
+                with col1:
                     with open(genbank_file_path, "rb") as file:
                         st.download_button(label="Download GenBank File", data=file, file_name=genbank_file_path,
                                            mime="text/x-genbank")
-                    st.markdown(
-                        "GenBank files can be visualized using [PyGenomeViz](https://pygenomeviz.streamlit.app/)")
-                elif file_type == 'BED':
+                with col2:
                     with open(bed_file_path, "rb") as file:
                         st.download_button(label="Download BED File", data=file, file_name=bed_file_path,
                                            mime="text/plain")
-                    st.markdown(
-                        "BED files can be used with the [UCSC Genome Browser](https://genome.ucsc.edu/cgi-bin/hgCustom)")
-                elif file_type == 'CSV':
+                with col3:
                     with open(csv_file_path, "rb") as file:
                         st.download_button(label="Download CSV File", data=file, file_name=csv_file_path,
                                            mime="text/csv")
 
+                # Links for user guidance on using the downloaded files
+                st.markdown(
+                    "GenBank files can be visualized using [PyGenomeViz](https://pygenomeviz.streamlit.app/). "
+                    "BED files can be used with the [UCSC Genome Browser](https://genome.ucsc.edu/cgi-bin/hgCustom)."
+                )
+
 
 
 elif selected_model == 'Cas13d':