utr_regions.py

import pandas as pd

df_utr_regions = pd.read_csv(snakemake.input[0])

info = list(df_utr_regions["info"])
chrms = list(df_utr_regions["chr"])
start = list(df_utr_regions["start"])
stop = list(df_utr_regions["stop"])

output = []
for ann in range(len(info)):        
    if "gene_name" in info[ann]:
        line = info[ann].split(";")
        transID = line[1].split(" ")[-1][1:-1].split(".")[0]
        gene = line[3].split(" ")[-1][1:-1]
        
        
        if (gene == snakemake.params[0].upper()):
            bedline = chrms[ann] + "\t" + str(start[ann]) + "\t" + str(stop[ann]) + "\t" + transID
            output.append(bedline)
                  
output_file = open(snakemake.output[0],"w+")
output_file.write("\n".join(output))
output_file.close()