Find MoClo-YTK overhangs in input sequence

find_moclo_ytk_overhangs

#!/usr/bin/env python
"""Find MoClo-YTK overhangs in input sequence

@author: Arvind R. Subramaniam
@date: 15 Aug 2019

These overhangs can be used for BsmBI-mediated
cloning into the pYTK001 part entry vector
to mutate or to combine fragments.
"""

import sys
from Bio.Seq import Seq

if len(sys.argv) != 2:
    sys.exit("You need to give exactly one input sequence.")

seq = sys.argv[1]

seq = seq.upper()

# see Table S4 in 
# https://pubs.acs.org/doi/suppl/10.1021/acssynbio.8b00333/suppl_file/sb8b00333_si_001.pdf
# for these overhangs.
# Overhangs differing by <1nt from TCGG and GACC or their 
# reverse complements were manually removed.
sites = ['GGAG',
	 'ATCA',
	 'GATA',
	 'TCTT',
	 'GGCA',
	 'AGGT',
	 'CAAA',
	 'AAGC',
	 'GAGG',
	 'GCAC',
	 'CAGT',
	 'CAAC',
	 'GTAA',
	 'AACG',
	 'TCCA',
	 'CGAA',
	 'CACA',
	 'GTCT',
	 'GAAT',
	 'ATAG',
	 'CCAT',
	 'AGTA'
]

sites_rc = [str(Seq(x).reverse_complement()) for x in sites]

for x in sites:
    if seq.find(x) != -1:
        print(f'{x} at pos {seq.find(x) + 1}.')
for x in sites_rc:
    if seq.find(x) != -1:
        print(f'{x} at pos {seq.find(x) + 1}.')