seqClass.py

#Import modules
import sys, re
from argparse import ArgumentParser

#Set up command line 
parser = ArgumentParser(description = 'Classify a sequence as DNA or RNA')
parser.add_argument("-s", "--seq", type = str, required = True, help = "Input sequence")
parser.add_argument("-m", "--motif", type = str, required = False, help = "Motif")

#Show help if no arguments provided

if len(sys.argv) == 1:
    parser.print_help()
    sys.exit(1)

args = parser.parse_args()

#Convert sequence to uppercase for consisten comparison
args.seq = args.seq.upper()

#Check if sequence contains only valid nucleotides (A,T,C,G,U)

if re.search('^[ACGTU]+$', args.seq):
    if re.search('T', args.seq) and re.search('U', args.seq):
        print ('The sequence is not DNA nor RNA')
    elif re.search('T', args.seq):
        print ('The sequence is DNA')
    elif re.search('U', args.seq):
        print ('The sequence is RNA')
    else:
        print ('The sequence can be DNA or RNA')
else:
    print ('The sequence is not DNA nor RNA')

#Optional motif search feature
#Contribution by aguillaumet: Fixed missing FOUND print statement
if args.motif:
    args.motif = args.motif.upper()
    print(f'Motif search enabled: looking for motif "{args.motif}" in sequence "{args.seq}"... ', end = '')
    if re.search(args.motif, args.seq):
        print("FOUND")
    else:
        print("NOT FOUND")