import re
regex = re.compile(r"(?P<reference_sequence>(NM|NR|XM|XR)_[0-9]{4,12}|ENST[0-9]{1,11})(\.(?P<version>([0-9]?[0-9])))?(:(?P<prefix>c|n)\.(?P<start>-?[1-9][0-9]{0,7})(?P<start_offset>[+-][1-9][0-9]{0,7})?_(?P<end>-?[1-9][0-9]{0,7})(?P<end_offset>[+-][1-9][0-9]{0,7})?)del$", flags=re.MULTILINE)
test_str = "NM_12345.4:c.19999+500_20000+400del"
matches = regex.finditer(test_str)
for match_num, match in enumerate(matches, start=1):
print(f"Match {match_num} was found at {match.start()}-{match.end()}: {match.group()}")
for group_num, group in enumerate(match.groups(), start=1):
print(f"Group {group_num} found at {match.start(group_num)}-{match.end(group_num)}: {group}")
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Python, please visit: https://docs.python.org/3/library/re.html