fix

cas9on.py

@@ -213,25 +213,31 @@ def create_bigwig(df, bigwig_path):
     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'])
+    # Get the list of all chromosomes present in the DataFrame
+    all_chromosomes = df['Chr'].unique().tolist()
 
     # 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()]
+    chr_sizes = []
+    for chr in all_chromosomes:
+        chr_group = df[df['Chr'] == chr]
+        max_end_pos = chr_group['End Pos'].max()
+        chr_sizes.append((chr, max_end_pos))
 
     # Create the BigWig file and add the header
     bw = pyBigWig.open(bigwig_path, "w")
-    bw.addHeader(header)
-
-    # Create separate lists for chromosomes, starts, ends, and values
-    chromosomes = df['Chr'].tolist()
-    starts = df['Start Pos'].tolist()
-    ends = df['End Pos'].tolist()
-    values = df['Prediction'].astype(float).tolist()
-
-    # Add entries to the BigWig file
-    bw.addEntries(chromosomes, starts, ends=ends, values=values)
+    bw.addHeader(chr_sizes)
+
+    # Add entries for each chromosome
+    for chr in all_chromosomes:
+        chr_group = df[df['Chr'] == chr]
+        if not chr_group.empty:
+            starts = chr_group['Start Pos'].tolist()
+            ends = chr_group['End Pos'].tolist()
+            values = chr_group['Prediction'].astype(float).tolist()
+            bw.addEntries([chr] * len(starts), starts, ends=ends, values=values)
+        else:
+            # Add empty entries for the missing chromosome
+            bw.addEntries([chr], [0], ends=[1], values=[0.0])
 
     # Close the BigWig file
     bw.close()