metavar="fasta_file",
type=argparse.FileType('r'),
help="FASTA file of the genome.")
parser.add_argument('scaffold_gff3',
metavar="gff3_file",
type=argparse.FileType('r'),
help="corresponding gff3 file of the genome.")
args = parser.parse_args()
# read genome details into memory
genome_fasta = parse_fasta.get_all_sequences(args.genome_fasta, 'fasta')
scaffold_gff3 = parse_gff3.parse_gff3(args.scaffold_gff3, 'exon')
# pick longest transcript in the gff3 file
scaffold_gff3 = parse_gff3.pick_longest_mRNA(scaffold_gff3)
# read the positions from the cov file
for scaf in scaffold_gff3:
for gene in scaffold_gff3[scaf]:
gene_coords = scaffold_gff3[scaf][gene].coords
gene_on_crick = gene_coords[0] > gene_coords[1]
tx = list(scaffold_gff3[scaf][gene].mRNAs.keys())[0]
mrna_coords = scaffold_gff3[scaf][gene].mRNAs[tx].details['exon']
exon_seq = ''
for i in mrna_coords:
temp = genome_fasta[scaf][min(i):max(i)]
if gene_on_crick: temp = reverse_complement(temp)
def generate_relative_locations(n):
'''
Evenly split the range {0..1} depending on n (number of divisions), and
returns the midpoint of the sub-ranges.
i.e. if n == 5, return [0.1, 0.3, 0.5, 0.7, 0.9]
'''
return [(x + 0.5) / n for x in range(n)]
# read sequences
genome_sequences = parse_fasta.get_all_sequences(args.genome_fasta, 'fasta')
# read coordinates of genes and exons from .gff3 file
scaffold_gff3 = parse_gff3.pick_longest_mRNA(
parse_gff3.parse_gff3(args.genome_gff3, 'exon'))
# create dictionary to map genes to their respective scaffold (this is needed
# to obtain gene coords based solely on gene names)
gene_to_scaffold = {}
for s in scaffold_gff3:
for g in scaffold_gff3[s]:
gene_to_scaffold[g] = s
# print header row for results
print('Gene',
'Intron relative location',
'Scaffold',
'Desired region',
'Outer region',
'Outer amplicon length',