fix bigwig

cas9on.py

@@ -204,22 +204,21 @@ def process_gene(gene_symbol, model_path):
 
 
 def create_bigwig(df, bigwig_path):
-    if isinstance(df, list):
-        df = pd.DataFrame(df, columns=["Chr", "Start Pos", "End Pos", "Strand", "Transcript", "Exon", "Target", "gRNA", "Prediction"])
+    # 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.")
 
-    # Calculate chromosome sizes as the maximum end position per chromosome
-    chrom_sizes = df.groupby('Chr')['End Pos'].max().astype(int).to_dict()
+    # Prepare the BigWig header using unique chromosomes and their max position
+    chr_sizes = df.groupby('Chr')['End Pos'].max().to_dict()
+    header = [(chr, size) for chr, size in chr_sizes.items()]
 
-    with pyBigWig.open(bigwig_path, "w") as bw:
-        # Add chromosome sizes to the header
-        bw.addHeader([(chr, size) for chr, size in chrom_sizes.items()])
+    # Create a BigWig file
+    bw = pyBigWig.open(bigwig_path, "w")
+    bw.addHeader(header)
 
-        # Iterate over the DataFrame and add entries for each chromosome
-        for chrom in df['Chr'].unique():
-            chrom_df = df[df['Chr'] == chrom]
-            starts = chrom_df['Start Pos'].astype(int).tolist()
-            ends = chrom_df['End Pos'].astype(int).tolist()
-            values = chrom_df['Prediction'].astype(float).tolist()
+    # Add entries to the BigWig file
+    for _, row in df.iterrows():
+        bw.addEntries([row['Chr']], [int(row['Start Pos'])], ends=[int(row['End Pos'])], values=[float(row['Prediction'])])
 
-            if starts and ends and values:
-                bw.addEntries(chrom, starts, ends=ends, values=values)
+    # Close the BigWig file
+    bw.close()