fix

cas9on.py

@@ -205,29 +205,30 @@ def process_gene(gene_symbol, model_path):
 
 def create_bigwig(df, bigwig_path):
     # Ensure the dataframe has the required columns
-    if not all(column in df.columns for column in ["Chr", "Start Pos", "End Pos", "Prediction"]):
-        raise ValueError("DataFrame must contain 'Chr', 'Start Pos', 'End Pos', and 'Prediction' columns.")
+    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 positions to integers and sort the DataFrame
-    df['Start Pos'] = df['Start Pos'].astype(int)
-    df['End Pos'] = df['End Pos'].astype(int)
+    # Ensure all necessary columns are of correct type and sorted
+    df = df.astype({"Chr": str, "Start Pos": int, "End Pos": int, "Prediction": float})
     df = df.sort_values(by=['Chr', 'Start Pos'])
 
     # Prepare the BigWig header
     chr_sizes = df.groupby('Chr')['End Pos'].max().to_dict()
-    header = [(str(chr), size) for chr, size in chr_sizes.items()]
+    header = [(chr, size) for chr, size in chr_sizes.items()]
 
     # Create and write to the BigWig file
     bw = pyBigWig.open(bigwig_path, "w")
     bw.addHeader(header)
 
-    # Group by chromosome and add entries
+    # Add entries for each chromosome separately
     for chr, group in df.groupby('Chr'):
-        starts = group['Start Pos'].tolist()
-        ends = group['End Pos'].tolist()
-        values = group['Prediction'].astype(float).tolist()
-        bw.addEntries([str(chr)] * len(starts), starts, ends=ends, values=values)
+        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)
 
     bw.close()
 
 
+