INNER CODE UNIT · Python
gene_borders
hillerlab/TOGA · CESAR_wrapper.py:399
gene_borders = {_all_positions[0], _all_positions[-1]}
# extract sequences
exons_seq = {} # exon number: sequence dict
target_genome = TwoBitFile(get_2bit_path(t_db)) # use 2bitreader library
get_chr = bed_data["chrom"]
try:
chrom_seq = target_genome[get_chr]
except KeyError:
chrom_seq = [] # to suppress PyCharm analyzer
die(f"Error! Cannot find chrom {get_chr} in 2bit file {t_db}")
verbose("\nExons sequences ####\n")
for num, pos in exons_pos.items():
is_first_exon = num == 0
is_last_exon = num == max_exon_num
# for twoBitToFa start must be < end
# determine search start and end
# do not subtract/add SS_SIZE if gene border: no splice sites then