fix

cas9on.py

@@ -209,26 +209,31 @@ def create_bigwig(df, bigwig_path):
     if not all(column in df.columns for column in required_columns):
         raise ValueError(f"DataFrame must contain {required_columns} columns.")
 
-    # Ensure all necessary columns are of correct type and sorted
-    df = df.astype({"Chr": str, "Start Pos": int, "End Pos": int, "Prediction": float})
+    # Convert columns to appropriate types and sort
+    df['Start Pos'] = df['Start Pos'].astype(int)
+    df['End Pos'] = df['End Pos'].astype(int)
+    df['Prediction'] = df['Prediction'].astype(float)
     df = df.sort_values(by=['Chr', 'Start Pos'])
 
-    # Prepare the BigWig header
+    # Prepare the BigWig header with chromosome sizes
     chr_sizes = df.groupby('Chr')['End Pos'].max().to_dict()
     header = [(chr, size) for chr, size in chr_sizes.items()]
 
-    # Create and write to the BigWig file
+    # Initialize the BigWig file
     bw = pyBigWig.open(bigwig_path, "w")
     bw.addHeader(header)
 
-    # Add entries for each chromosome separately
-    for chr, group in df.groupby('Chr'):
-        starts = group['Start Pos'].values.tolist()
-        ends = group['End Pos'].values.tolist()
-        values = group['Prediction'].values.tolist()
-        bw.addEntries(chr, starts, ends=ends, values=values)
+    # 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)
 
     bw.close()
 
 
 
+
+