Last active
May 19, 2020 11:34
-
-
Save DenisVerkhoturov/31792f8e8e4b8e7dae3c7e8b0ecb4e20 to your computer and use it in GitHub Desktop.
PCRE (Perl Compatible Regular Expression) for protein level alteration notation. Based on http://www.hgmd.cf.ac.uk/docs/mut_nom.html#protein
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
(?x) | |
^ | |
(?<prefix>p.)? | |
(?<alteration> | |
(?: | |
(?<substitution> | |
(?<substitution_old>A|R|N|D|B|C|E|Q|Z|G|H|I|L|K|M|F|P|S|T|W|Y|V|X) | |
(?<substitution_position>\d+) | |
(?<substitution_new>A|R|N|D|B|C|E|Q|Z|G|H|I|L|K|M|F|P|S|T|W|Y|V|X) | |
) | |
| | |
(?<deletion> | |
(?: | |
(?<single_deletion> | |
(?<deletion_nucleotide>A|R|N|D|B|C|E|Q|Z|G|H|I|L|K|M|F|P|S|T|W|Y|V|X) | |
(?<deletion_position>\d+) | |
) | |
| | |
(?<range_deletion> | |
(?<deletion_start_nucleotide>A|R|N|D|B|C|E|Q|Z|G|H|I|L|K|M|F|P|S|T|W|Y|V|X) | |
(?<deletion_start_position>\d+) | |
(?:_) | |
(?<deletion_end_nucleotide>A|R|N|D|B|C|E|Q|Z|G|H|I|L|K|M|F|P|S|T|W|Y|V|X) | |
(?<deletion_end_position>\d+) | |
) | |
) | |
(?:del) | |
) | |
| | |
(?<insersion> | |
(?<insersion_start_nucleotide>A|R|N|D|B|C|E|Q|Z|G|H|I|L|K|M|F|P|S|T|W|Y|V|X) | |
(?<insersion_start_position>\d+) | |
(?:_) | |
(?<insersion_end_nucleotide>A|R|N|D|B|C|E|Q|Z|G|H|I|L|K|M|F|P|S|T|W|Y|V|X) | |
(?<insersion_end_position>\d+) | |
(?:ins) | |
(?<insersion_sequence>(?:A|R|N|D|B|C|E|Q|Z|G|H|I|L|K|M|F|P|S|T|W|Y|V|X)+) | |
) | |
| | |
(?<indels> | |
(?: | |
(?<single_indels> | |
(?<indels_nucleotide>A|R|N|D|B|C|E|Q|Z|G|H|I|L|K|M|F|P|S|T|W|Y|V|X) | |
(?<indels_position>\d+) | |
) | |
| | |
(?<range_indels> | |
(?<indels_start_nucleotide>A|R|N|D|B|C|E|Q|Z|G|H|I|L|K|M|F|P|S|T|W|Y|V|X) | |
(?<indels_start_position>\d+) | |
(?:_) | |
(?<indels_end_nucleotide>A|R|N|D|B|C|E|Q|Z|G|H|I|L|K|M|F|P|S|T|W|Y|V|X) | |
(?<indels_end_position>\d+) | |
) | |
) | |
(?:delins) | |
(?<indels_sequence>(?:A|R|N|D|B|C|E|Q|Z|G|H|I|L|K|M|F|P|S|T|W|Y|V|X)+) | |
) | |
| | |
(?<duplications> | |
(?<duplications_start_nucleotide>A|R|N|D|B|C|E|Q|Z|G|H|I|L|K|M|F|P|S|T|W|Y|V|X) | |
(?<duplications_start_position>\d+) | |
(?:_) | |
(?<duplications_end_nucleotide>A|R|N|D|B|C|E|Q|Z|G|H|I|L|K|M|F|P|S|T|W|Y|V|X) | |
(?<duplications_end_position>\d+) | |
(?:dup) | |
) | |
| | |
(?<frame_shifting> | |
(?<frame_shifting_start_nucleotide>A|R|N|D|B|C|E|Q|Z|G|H|I|L|K|M|F|P|S|T|W|Y|V|X) | |
(?<frame_shifting_start_position>\d+) | |
(?:fs) | |
(?<frame_shifting_end_nucleotide>A|R|N|D|B|C|E|Q|Z|G|H|I|L|K|M|F|P|S|T|W|Y|V|X) | |
(?<frame_shifting_end_position>\d+) | |
) | |
)+ | |
) | |
$ |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment