fixed bugs

app.py

@@ -125,8 +125,9 @@ if selected_model == 'Cas9':
             st.session_state['on_target_results'] = sorted_predictions
 
             if 'on_target_results' in st.session_state and st.session_state['on_target_results']:
+                # Include "Target" in the DataFrame's columns
                 df = pd.DataFrame(st.session_state['on_target_results'],
-                                  columns=["Gene ID", "Start Pos", "End Pos", "Strand", "gRNA", "Prediction"])
+                                  columns=["Gene ID", "Start Pos", "End Pos", "Strand", "Target", "gRNA", "Prediction"])
 
                 # Now create a Plotly plot with the sorted_predictions
                 fig = go.Figure()
@@ -134,8 +135,7 @@ if selected_model == 'Cas9':
                 # 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, gRNA, pred_score = prediction
-                    # Strand is not used in this plot, but you could use it to determine marker symbol, for example
+                    chrom, start, end, strand, target, gRNA, pred_score = prediction  # Adjusted to include the target sequence
                     fig.add_trace(go.Scatter(
                         x=[start, end],
                         y=[i, i],  # Y-values are just the rank of the prediction
@@ -144,7 +144,7 @@ if selected_model == 'Cas9':
                         text=[f"Rank: {i}", ""],  # Text at the start position only
                         hoverinfo='text',
                         hovertext=[
-                            f"Rank: {i}<br>Target: {gRNA}<br>Cutsite: {start}<br>On Target Score: {pred_score}",
+                            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}",
                             ""
                         ],
                     ))
@@ -155,7 +155,7 @@ if selected_model == 'Cas9':
                     xaxis_title='Genomic Position',
                     yaxis_title='Rank',
                     yaxis=dict(showticklabels=False)
-                    # We hide the y-axis labels since the rank is indicated in the hovertext
+                    # Hide the y-axis labels since the rank is indicated in the hovertext
                 )
 
                 # Display the plot
@@ -364,10 +364,10 @@ elif selected_model == 'Cas12':
                 bed_file_path = f"{gene_symbol}_crispr_targets.bed"
 
                 # Generate GenBank file
-                cas12.generate_genbank_file_from_df(df, gene_sequence, gene_symbol, genbank_file_path)
+                cas12.generate_genbank_file_from_data(df, gene_sequence, gene_symbol, genbank_file_path)
 
                 # Generate BED file
-                cas12.create_bed_file_from_df(df, bed_file_path)
+                cas12.generate_bed_file_from_data(df, bed_file_path)
 
                 st.write('Top on-target predictions:')
                 st.dataframe(df)

cas9on.py

@@ -98,7 +98,8 @@ def find_crispr_targets(sequence, chr, start, strand, pam="NGG", target_length=2
                 target_seq = sequence[i - target_length:i + 3]
                 tar_start = start + i - target_length
                 tar_end = start + i + 3
-                targets.append([target_seq, chr, tar_start, tar_end, strand])
+                gRNA = sequence[i - target_length:i]
+                targets.append([target_seq, gRNA, chr, str(tar_start), str(tar_end), str(strand)])
 
     return targets
 
@@ -125,13 +126,16 @@ def process_gene(gene_symbol, model_path):
     # Return both the data and the fetched sequence
     return all_data, gene_sequence
 
-def create_genbank_features(gRNAs, predictions):
+def create_genbank_features(formatted_data):
     features = []
-    for gRNA, prediction in zip(gRNAs, predictions):
-        location = FeatureLocation(start=gRNA[2], end=gRNA[3], strand=gRNA[4])
+    for data in formatted_data:
+        # Strand conversion to Biopython's convention
+        strand = 1 if data[3] == '+' else -1
+        location = FeatureLocation(start=int(data[1]), end=int(data[2]), strand=strand)
         feature = SeqFeature(location=location, type="misc_feature", qualifiers={
-            'label': gRNA[0],  # Target sequence as label
-            'note': f"Prediction: {prediction}"  # Prediction score in note
+            'label': data[5],  # Use gRNA as the label
+            'target': data[4],  # Include the target sequence
+            'note': f"Prediction: {data[6]}"  # Include the prediction score
         })
         features.append(feature)
     return features
@@ -162,7 +166,7 @@ def create_bed_file_from_df(df, output_path):
             chrom = row["Gene ID"]
             start = int(row["Start Pos"])
             end = int(row["End Pos"])
-            strand = '+' if int(row["Strand"]) > 0 else '-'
+            strand = '+' if row["Strand"] == '+' else '-'
             gRNA = row["gRNA"]
-            score = row["Prediction"]
+            score = str(row["Prediction"])  # Ensure score is converted to string if not already
             bed_file.write(f"{chrom}\t{start}\t{end}\t{gRNA}\t{score}\t{strand}\n")