fix

cas9on.py

@@ -203,37 +203,45 @@ def process_gene(gene_symbol, model_path):
 #     df.to_csv(output_path, index=False)
 
 
+import pyBigWig
+
+
 def create_bigwig(df, bigwig_path):
-    # Ensure the dataframe has the required columns
+    # Check for required columns in the DataFrame
     required_columns = ["Chr", "Start Pos", "End Pos", "Prediction"]
     if not all(column in df.columns for column in required_columns):
         raise ValueError(f"DataFrame must contain {required_columns} columns.")
 
-    # Convert columns to appropriate types and sort
+    # Convert columns to the correct types
     df['Start Pos'] = df['Start Pos'].astype(int)
     df['End Pos'] = df['End Pos'].astype(int)
     df['Prediction'] = df['Prediction'].astype(float)
+
+    # Sort the DataFrame by chromosome and start position to ensure order
     df = df.sort_values(by=['Chr', 'Start Pos'])
 
-    # Prepare the BigWig header with chromosome sizes
+    # Calculate chromosome sizes for the BigWig header
     chr_sizes = df.groupby('Chr')['End Pos'].max().to_dict()
     header = [(chr, size) for chr, size in chr_sizes.items()]
 
-    # Initialize the BigWig file
+    # Create the BigWig file and add the header
     bw = pyBigWig.open(bigwig_path, "w")
     bw.addHeader(header)
 
-    # Iterate over each chromosome and add entries in sorted order
-    for chr in sorted(df['Chr'].unique()):
-        chrom_df = df[df['Chr'] == chr]
-        starts = chrom_df['Start Pos'].tolist()
-        ends = chrom_df['End Pos'].tolist()
-        values = chrom_df['Prediction'].tolist()
-        bw.addEntries([chr] * len(starts), starts, ends=ends, values=values)
+    # Add entries for each chromosome
+    for chr, group in df.groupby('Chr'):
+        starts = group['Start Pos'].tolist()
+        ends = group['End Pos'].tolist()
+        values = group['Prediction'].tolist()
+        bw.addEntries(chr, starts, ends=ends, values=values)
 
+    # Close the BigWig file
     bw.close()
 
 
 
 
 
+
+
+