Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Implementation of SugarSelection #4790

Open
wants to merge 12 commits into
base: develop
Choose a base branch
from
+14,060 −0
Open

Implementation of SugarSelection #4790

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
62a09ef
Update selection.py
talagayev Nov 14, 2024
95e8ae8
Update selection.py
talagayev Nov 14, 2024
e395524
Update selection.py
talagayev Nov 14, 2024
9b50428
Update selection.py
talagayev Nov 14, 2024
137f69c
Added Test Files for GLYCAM and PDB sugars
talagayev Nov 15, 2024
70b70be
Update datafiles.py
talagayev Nov 15, 2024
a56a95f
Update test_atomselections.py
talagayev Nov 15, 2024
7639858
Update test_atomselections.py
talagayev Nov 15, 2024
4cf52a4
Update datafiles.py
talagayev Nov 15, 2024
7539469
Merge branch 'develop' into sugar_selection
talagayev Jan 11, 2025
a21d40a
Update CHANGELOG
talagayev Jan 11, 2025
cf29e91
Update selection.py
talagayev Jan 11, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions package/CHANGELOG
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@ Fixes
the function to prevent shared state. (Issue #4655)

Enhancements
* Addition of 'sugar' token for GLYCAM, PDB and CHARMM sugar selection (Issue #4790)
* Addition of 'water' token for water selection (Issue #4839)
* Enables parallelization for analysis.density.DensityAnalysis (Issue #4677, PR #4729)
* Enables parallelization for analysis.contacts.Contacts (Issue #4660)
Expand Down
252 changes: 252 additions & 0 deletions package/MDAnalysis/core/selection.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1056,6 +1056,258 @@ def _apply(self, group):
return group[np.isin(nmidx, matches)]


class SugarSelection(Selection):
"""Consists of sugar residues with recognized abbreviations.

Recognized residue names in :attr:`SugarSelection.sugar_res`.

* from glycam.org server::
Abbreviations for PDB, CHARMM and GLYCAM
https://glycam.org/docs/othertoolsservice/2016/06/09/3d-snfg-list-of-residue-names/index.html

* manually added aglycans 'ROH', 'OME', 'TBT'
from GLYCAM-Web generated files.

.. versionadded:: 2.9.0
"""
token = 'sugar'

sugar_res = {
# https://glycam.org/docs/othertoolsservice/2016/06/09/3d-snfg-list-of-residue-names/index.html
# Full PDB Abbreviations Nomenclature
'GLC', 'MAL', 'BGC', 'NAG', '4YS', 'SGN', 'BGLN', 'NDG', 'GCS',
'GCU', 'QUI', 'OLI', 'MAN', 'BMA', 'MAV', 'BEM', 'RAM', 'TYV', 'ARA',
'AHR', 'GAL', 'GLA', 'NGA', 'ADA', 'GUL', 'GUP', 'GL0', 'LGU', 'ALT',
'ALL', 'WOO', 'TAL', 'IDO', 'IDS', 'FUC', 'FUL', 'LYX', 'ABE', 'XYL',
'XYS', 'LXC', 'XYP', 'PAR', 'RIB', 'DIG', 'COL', 'BAC', 'API', 'FRU',
'TAG', 'SOR', 'PSI', 'DHA', 'KDN', 'KDO', 'NEU', 'SIA', 'MUR', 'GMH',
# Full CHARMM Abbreviations Nomenclature
'AGLC', 'BGLC', 'AGLCNA', 'BGLCNA', 'BGLCN0', 'AGLCA', 'BGLCA',
'BGLCA0', 'AMAN', 'BMAN', 'ARHM', 'BRHM', 'AARB', 'BARB', 'AGAL',
'BGAL', 'AGALNA', 'BGALNA', 'AGUL', 'BGUL', 'AALT', 'BALT', 'AALL',
'ATAL', 'BTAL', 'AIDO', 'BIDO', 'AIDOA', 'BIDOA', 'AFUC', 'BFUC',
'ALYF', 'BLYF', 'AXYL', 'BXYL', 'AXYF', 'BXYF', 'ARIB', 'BRIB',
'AFRU', 'BFRU', 'ANE5AC', 'BNE5AC',
# GLYCAM Abbreviations
# Glucose Nomenculature
'0GA', '0GB', '1GA', '1GB', '2GA', '2GB', '3GA', '3GB', '4GA', '4GB',
'6GA', '6GB', 'ZGA', 'ZGB', 'YGA', 'YGB', 'XGA', 'XGB', 'WGA', 'WGB',
'VGA', 'VGB', 'UGA', 'UGB', 'TGA', 'TGB', 'SGA', 'SGB', 'RGA', 'RGB',
'QGA', 'QGB', 'PGA', 'PGB', '0gA', '0gB', '1gA', '1gB', '2gA', '2gB',
'3gA', '3gB', '4gA', '4gB', '6gA', '6gB', 'ZgA', 'ZgB', 'YgA', 'YgB',
'XgA', 'XgB', 'WgA', 'WgB', 'VgA', 'VgB', 'UgA', 'UgB', 'TgA', 'TgB',
'SgA', 'SgB', 'RgA', 'RgB', 'QgA', 'QgB', 'PgA', 'PgB',
# N-Acetyl Glucosamine Nomenculature
'0YA', '0YB', '1YA', '1YB', '3YA', '3YB', '4YA', '4YB', '6YA', '6YB',
'WYA', 'WYB', 'VYA', 'VYB', 'UYA', 'UYB', 'QYA', 'QYB', '0yA', '0yB',
'1yA', '1yB', '3yA', '3yB', '4yA', '4yB', '6yA', '6yB', 'WyA', 'WyB',
'VyA', 'VyB', 'UyA', 'UyB', 'QyA', 'QyB',
# Glucosamine Nomenculature
'0YN', '0Yn', '0YNP', '0YnP', '0YS', '0Ys', '3YS', '3Ys', '4YS',
'4Ys', '6YS', '6Ys', 'QYS', 'QYs', 'UYS', 'UYs', 'VYS', 'VYs',
'WYS', 'WYs', '0yS', '0ys', '3yS', '3ys', '4yS', '4ys',
# Glucuronic Acid Nomenculature
'0ZA', '0ZB', '1ZA', '1ZB', '2ZA', '2ZB', '3ZA', '3ZB', '4ZA',
'4ZB', 'ZZA', 'ZZB', 'YZA', 'YZB', 'WZA', 'WZB', 'TZA', 'TZB',
'0zA', '0zB', '1zA', '1zB', '2zA', '2zB', '3zA', '3zB', '4zA',
'4zB', 'ZzA', 'ZzB', 'YzA', 'YzB', 'WzA', 'WzB', 'TzA',
'TzB', '0ZBP',
# Quinovose Nomenculature
'0QA', '0QB', '1QA', '1QB', '2QA', '2QB', '3QA', '3QB', '4QA',
'4QB', 'ZQA', 'ZQB', 'YQA', 'YQB', 'WQA', 'WQB', 'TQA', 'TQB',
'0qA', '0qB', '1qA', '1qB', '2qA', '2qB', '3qA', '3qB', '4qA',
'4qB', 'ZqA', 'ZqB', 'YqA', 'YqB', 'WqA', 'WqB', 'TqA', 'TqB',
# Mannose Nomenculature
'0MA', '0MB', '1MA', '1MB', '2MA', '2MB', '3MA', '3MB', '4MA',
'4MB', '6MA', '6MB', 'ZMA', 'ZMB', 'YMA', 'YMB', 'XMA', 'XMB',
'WMA', 'WMB', 'VMA', 'VMB', 'UMA', 'UMB', 'TMA', 'TMB', 'SMA',
'SMB', 'RMA', 'RMB', 'QMA', 'QMB', 'PMA', 'PMB', '0mA', '0mB',
'1mA', '1mB', '2mA', '2mB', '3mA', '3mB', '4mA', '4mB', '6mA',
'6mB', 'ZmA', 'ZmB', 'YmA', 'YmB', 'XmA', 'XmB', 'WmA', 'WmB',
'VmA', 'VmB', 'UmA', 'UmB', 'TmA', 'TmB', 'SmA', 'SmB', 'RmA',
'RmB', 'QmA', 'QmB', 'PmA', 'PmB',
# N-Acetyl Mannosamine Nomenculature
'0WA', '0WB', '1WA', '1WB', '3WA', '3WB', '4WA', '4WB', '6WA',
'6WB', 'WWA', 'WWB', 'VWA', 'VWB', 'UWA', 'UWB', 'QWA', 'QWB',
'0wA', '0wB', '1wA', '1wB', '3wA', '3wB', '4wA', '4wB', '6wA',
'6wB', 'WwA', 'WwB', 'VwA', 'VwB', 'UwA', 'UwB', 'QwA', 'QwB',
# Rhamnose Nomenculature
'0HA', '0HB', '1HA', '1HB', '2HA', '2HB', '3HA', '3HB', '4HA',
'4HB', 'ZHA', 'ZHB', 'YHA', 'YHB', 'WHA', 'WHB', 'THA', 'THB',
'0hA', '0hB', '1hA', '1hB', '2hA', '2hB', '3hA', '3hB', '4hA',
'4hB', 'ZhA', 'ZhB', 'YhA', 'YhB', 'WhA', 'WhB', 'ThA', 'ThB',
# Tyvelose Nomenculature
'0TV', '0Tv', '1TV', '1Tv', '2TV', '2Tv', '4TV', '4Tv', 'YTV',
'YTv', '0tV', '0tv', '1tV', '1tv', '2tV', '2tv', '4tV', '4tv',
'YtV', 'Ytv',
# Arabinose Nomenculature
'0AA', '0AB', '1AA', '1AB', '2AA', '2AB', '3AA', '3AB', '4AA',
'4AB', 'ZAA', 'ZAB', 'YAA', 'YAB', 'WAA', 'WAB', 'TAA', 'TAB',
'0AD', '0AU', '1AD', '1AU', '2AD', '2AU', '3AD', '3AU', '5AD',
'5AU', 'ZAD', 'ZAU', '0aA', '0aB', '1aA', '1aB', '2aA', '2aB',
'3aA', '3aB', '4aA', '4aB', 'ZaA', 'ZaB', 'YaA', 'YaB', 'WaA',
'WaB', 'TaA', 'TaB', '0aD', '0aU', '1aD', '1aU', '2aD', '2aU',
'3aD', '3aU', '5aD', '5aU', 'ZaD', 'ZaU',
# Galactose Nomenculature
'0LA', '0LB', '1LA', '1LB', '2LA', '2LB', '3LA', '3LB', '4LA',
'4LB', '6LA', '6LB', 'ZLA', 'ZLB', 'YLA', 'YLB', 'XLA', 'XLB',
'WLA', 'WLB', 'VLA', 'VLB', 'ULA', 'ULB', 'TLA', 'TLB', 'SLA',
'SLB', 'RLA', 'RLB', 'QLA', 'QLB', 'PLA', 'PLB', '0lA', '0lB',
'1lA', '1lB', '2lA', '2lB', '3lA', '3lB', '4lA', '4lB', '6lA',
'6lB', 'ZlA', 'ZlB', 'YlA', 'YlB', 'XlA', 'XlB', 'WlA', 'WlB',
'VlA', 'VlB', 'UlA', 'UlB', 'TlA', 'TlB', 'SlA', 'SlB', 'RlA',
'RlB', 'QlA', 'QlB', 'PlA', 'PlB',
# N-Acetyl Galactosamine Nomenculature
'0VA', '0VB', '1VA', '1VB', '3VA', '3VB', '4VA', '4VB', '6VA',
'6VB', 'WVA', 'WVB', 'VVA', 'VVB', 'UVA', 'UVB', 'QVA', 'QVB',
'0vA', '0vB', '1vA', '1vB', '3vA', '3vB', '4vA', '4vB', '6vA',
'6vB', 'WvA', 'WvB', 'VvA', 'VvB', 'UvA', 'UvB', 'QvA', 'QvB',
# Galacturonic Acid Nomenculature
'0OA', '0OB', '1OA', '1OB', '2OA', '2OB', '3OA', '3OB', '4OA',
'4OB', 'ZOA', 'ZOB', 'YOA', 'YOB', 'WOA', 'WOB', 'TOA', 'TOB',
'0oA', '0oB', '1oA', '1oB', '2oA', '2oB', '3oA', '3oB', '4oA',
'4oB', 'ZoA', 'ZoB', 'YoA', 'YoB', 'WoA', 'WoB', 'ToA', 'ToB',
# Gulose Nomenculature
'0KA', '0KB', '1KA', '1KB', '2KA', '2KB', '3KA', '3KB', '4KA',
'4KB', '6KA', '6KB', 'ZKA', 'ZKB', 'YKA', 'YKB', 'XKA', 'XKB',
'WKA', 'WKB', 'VKA', 'VKB', 'UKA', 'UKB', 'TKA', 'TKB', 'SKA',
'SKB', 'RKA', 'RKB', 'QKA', 'QKB', 'PKA', 'PKB', '0kA', '0kB',
'1kA', '1kB', '2kA', '2kB', '3kA', '3kB', '4kA', '4kB', '6kA',
'6kB', 'ZkA', 'ZkB', 'YkA', 'YkB', 'XkA', 'XkB', 'WkA', 'WkB',
'VkA', 'VkB', 'UkA', 'UkB', 'TkA', 'TkB', 'SkA', 'SkB', 'RkA',
'RkB', 'QkA', 'QkB', 'PkA', 'PkB',
# Altrose Nomenculature
'0EA', '0EB', '1EA', '1EB', '2EA', '2EB', '3EA', '3EB', '4EA',
'4EB', '6EA', '6EB', 'ZEA', 'ZEB', 'YEA', 'YEB', 'XEA', 'XEB',
'WEA', 'WEB', 'VEA', 'VEB', 'UEA', 'UEB', 'TEA', 'TEB', 'SEA',
'SEB', 'REA', 'REB', 'QEA', 'QEB', 'PEA', 'PEB', '0eA', '0eB',
'1eA', '1eB', '2eA', '2eB', '3eA', '3eB', '4eA', '4eB', '6eA',
'6eB', 'ZeA', 'ZeB', 'YeA', 'YeB', 'XeA', 'XeB', 'WeA', 'WeB',
'VeA', 'VeB', 'UeA', 'UeB', 'TeA', 'TeB', 'SeA', 'SeB', 'ReA',
'ReB', 'QeA', 'QeB', 'PeA', 'PeB',
# Allose Nomenculature
'0NA', '0NB', '1NA', '1NB', '2NA', '2NB', '3NA', '3NB', '4NA',
'4NB', '6NA', '6NB', 'ZNA', 'ZNB', 'YNA', 'YNB', 'XNA', 'XNB',
'WNA', 'WNB', 'VNA', 'VNB', 'UNA', 'UNB', 'TNA', 'TNB', 'SNA',
'SNB', 'RNA', 'RNB', 'QNA', 'QNB', 'PNA', 'PNB', '0nA', '0nB',
'1nA', '1nB', '2nA', '2nB', '3nA', '3nB', '4nA', '4nB', '6nA',
'6nB', 'ZnA', 'ZnB', 'YnA', 'YnB', 'XnA', 'XnB', 'WnA', 'WnB',
'VnA', 'VnB', 'UnA', 'UnB', 'TnA', 'TnB', 'SnA', 'SnB', 'RnA',
'RnB', 'QnA', 'QnB', 'PnA', 'PnB',
# Talose Nomenculature
'0TA', '0TB', '1TA', '1TB', '2TA', '2TB', '3TA', '3TB', '4TA',
'4TB', '6TA', '6TB', 'ZTA', 'ZTB', 'YTA', 'YTB', 'XTA', 'XTB',
'WTA', 'WTB', 'VTA', 'VTB', 'UTA', 'UTB', 'TTA', 'TTB', 'STA',
'STB', 'RTA', 'RTB', 'QTA', 'QTB', 'PTA', 'PTB', '0tA', '0tB',
'1tA', '1tB', '2tA', '2tB', '3tA', '3tB', '4tA', '4tB', '6tA',
'6tB', 'ZtA', 'ZtB', 'YtA', 'YtB', 'XtA', 'XtB', 'WtA', 'WtB',
'VtA', 'VtB', 'UtA', 'UtB', 'TtA', 'TtB', 'StA', 'StB', 'RtA',
'RtB', 'QtA', 'QtB', 'PtA', 'PtB',
# Iduronic Acid Nomenculature
'0UA', '0UB', '1UA', '1UB', '2UA', '2UB', '3UA', '3UB', '4UA',
'4UB', 'ZUA', 'ZUB', 'YUA', 'YUB', 'WUA', 'WUB', 'TUA', 'TUB',
'0uA', '0uB', '1uA', '1uB', '2uA', '2uB', '3uA', '3uB', '4uA',
'4uB', 'ZuA', 'ZuB', 'YuA', 'YuB', 'WuA', 'WuB', 'TuA', 'TuB',
'YuAP',
# Fucose Nomenculature
'0FA', '0FB', '1FA', '1FB', '2FA', '2FB', '3FA', '3FB', '4FA',
'4FB', 'ZFA', 'ZFB', 'YFA', 'YFB', 'WFA', 'WFB', 'TFA', 'TFB',
'0fA', '0fB', '1fA', '1fB', '2fA', '2fB', '3fA', '3fB', '4fA',
'4fB', 'ZfA', 'ZfB', 'YfA', 'YfB', 'WfA', 'WfB', 'TfA', 'TfB',
# Lyxose Nomenculature
'0DA', '0DB', '1DA', '1DB', '2DA', '2DB', '3DA', '3DB', '4DA',
'4DB', 'ZDA', 'ZDB', 'YDA', 'YDB', 'WDA', 'WDB', 'TDA', 'TDB',
'0DD', '0DU', '1DD', '1DU', '2DD', '2DU', '3DD', '3DU', '5DD',
'5DU', 'ZDD', 'ZDU', '0dA', '0dB', '1dA', '1dB', '2dA', '2dB',
'3dA', '3dB', '4dA', '4dB', 'ZdA', 'ZdB', 'YdA', 'YdB', 'WdA',
'WdB', 'TdA', 'TdB', '0dD', '0dU', '1dD', '1dU', '2dD', '2dU',
'3dD', '3dU', '5dD', '5dU', 'ZdD', 'ZdU',
# Abequose Nomenculature
'0AE', '2AE', '4AE', 'YGa', '0AF', '2AF', '4AF', 'YAF',
# Xylose Nomenculature
'0XA', '0XB', '1XA', '1XB', '2XA', '2XB', '3XA', '3XB', '4XA',
'4XB', 'ZXA', 'ZXB', 'YXA', 'YXB', 'WXA', 'WXB', 'TXA', 'TXB',
'0XD', '0XU', '1XD', '1XU', '2XD', '2XU', '3XD', '3XU', '5XD',
'5XU', 'ZXD', 'ZXU', '0xA', '0xB', '1xA', '1xB', '2xA', '2xB',
'3xA', '3xB', '4xA', '4xB', 'ZxA', 'ZxB', 'YxA', 'YxB', 'WxA',
'WxB', 'TxA', 'TxB', '0xD', '0xU', '1xD', '1xU', '2xD', '2xU',
'3xD', '3xU', '5xD', '5xU', 'ZxD', 'ZxU',
# Ribose Nomenculature
'0RA', '0RB', '1RA', '1RB', '2RA', '2RB', '3RA', '3RB', '4RA',
'4RB', 'ZRA', 'ZRB', 'YRA', 'YRB', 'WRA', 'WRB', 'TRA', 'TRB',
'0RD', '0RU', '1RD', '1RU', '2RD', '2RU', '3RD', '3RU', '5RD',
'5RU', 'ZRD', 'ZRU', '0rA', '0rB', '1rA', '1rB', '2rA', '2rB',
'3rA', '3rB', '4rA', '4rB', 'ZrA', 'ZrB', 'YrA', 'YrB', 'WrA',
'WrB', 'TrA', 'TrB', '0rD', '0rU', '1rD', '1rU', '2rD', '2rU',
'3rD', '3rU', '5rD', '5rU', 'ZrD', 'ZrU',
# Bacillosamine Nomenculature
'0BC', '3BC', '0bC', '3bC',
# Fructose Nomenculature
'0CA', '0CB', '1CA', '1CB', '2CA', '2CB', '3CA', '3CB', '4CA',
'4CB', '5CA', '5CB', 'WCA', 'WCB', '0CD', '0CU', '1CD', '1CU',
'2CD', '2CU', '3CD', '3CU', '4CD', '4CU', '6CD', '6CU', 'WCD',
'WCU', 'VCD', 'VCU', 'UCD', 'UCU', 'QCD', 'QCU', '0cA', '0cB',
'1cA', '1cB', '2cA', '2cB', '3cA', '3cB', '4cA', '4cB', '5cA',
'5cB', 'WcA', 'WcB', '0cD', '0cU', '1cD', '1cU', '2cD', '2cU',
'3cD', '3cU', '4cD', '4cU', '6cD', '6cU', 'WcD', 'WcU', 'VcD',
'VcU', 'UcD', 'UcU', 'QcD', 'QcU',
# Tagatose Nomenculature
'0JA', '0JB', '1JA', '1JB', '2JA', '2JB', '3JA', '3JB', '4JA',
'4JB', '5JA', '5JB', 'WJA', 'WJB', '0JD', '0JU', '1JD', '1JU',
'2JD', '2JU', '3JD', '3JU', '4JD', '4JU', '6JD', '6JU', 'WJD',
'WJU', 'VJD', 'VJU', 'UJD', 'UJU', 'QJD', 'QJU', '0jA', '0jB',
'1jA', '1jB', '2jA', '2jB', '3jA', '3jB', '4jA', '4jB', '5jA',
'5jB', 'WjA', 'WjB', '0jD', '0jU', '1jD', '1jU', '2jD', '2jU',
'3jD', '3jU', '4jD', '4jU', '6jD', '6jU', 'WjD', 'WjU', 'VjD',
'VjU', 'UjD', 'UjU', 'QjD', 'QjU',
# Sorbose Nomenculature
'0BA', '0BB', '1BA', '1BB', '2BA', '2BB', '3BA', '3BB', '4BA',
'4BB', '5BA', '5BB', 'WBA', 'WBB', '0BD', '0BU', '1BD', '1BU',
'2BD', '2BU', '3BD', '3BU', '4BD', '4BU', '6BD', '6BU', 'WBD',
'WBU', 'VBD', 'VBU', 'UBD', 'UBU', 'QBD', 'QBU', '0bA', '0bB',
'1bA', '1bB', '2bA', '2bB', '3bA', '3bB', '4bA', '4bB', '5bA',
'5bB', 'WbA', 'WbB', '0bD', '0bU', '1bD', '1bU', '2bD', '2bU',
'3bD', '3bU', '4bD', '4bU', '6bD', '6bU', 'WbD', 'WbU', 'VbD',
'VbU', 'UbD', 'UbU', 'QbD', 'QbU',
# Psicose Nomenculature
'0PA', '0PB', '1PA', '1PB', '2PA', '2PB', '3PA', '3PB', '4PA',
'4PB', '5PA', '5PB', 'WPA', 'WPB', '0PD', '0PU', '1PD', '1PU',
'2PD', '2PU', '3PD', '3PU', '4PD', '4PU', '6PD', '6PU', 'WPD',
'WPU', 'VPD', 'VPU', 'UPD', 'UPU', 'QPD', 'QPU', '0pA', '0pB',
'1pA', '1pB', '2pA', '2pB', '3pA', '3pB', '4pA', '4pB', '5pA',
'5pB', 'WpA', 'WpB', '0pD', '0pU', '1pD', '1pU', '2pD', '2pU',
'3pD', '3pU', '4pD', '4pU', '6pD', '6pU', 'WpD', 'WpU', 'VpD',
'VpU', 'UpD', 'UpU', 'QpD', 'QpU',
# N-Acetyl Neuraminic Acid Nomenculature
'0SA', '0SB', '4SA', '4SB', '7SA', '7SB', '8SA', '8SB', '9SA',
'9SB', 'ASA', 'ASB', 'BSA', 'BSB', 'CSA', 'CSB', 'DSA', 'DSB',
'ESA', 'ESB', 'FSA', 'FSB', 'GSA', 'GSB', 'HSA', 'HSB', 'ISA',
'ISB', 'JSA', 'JSB', 'KSA', 'KSB', '0sA', '0sB', '4sA', '4sB',
'7sA', '7sB', '8sA', '8sB', '9sA', '9sB', 'AsA', 'AsB', 'BsA',
'BsB', 'CsA', 'CsB', 'DsA', 'DsB', 'EsA', 'EsB', 'FsA', 'FsB',
'GsA', 'GsB', 'HsA', 'HsB', 'IsA', 'IsB', 'JsA', 'JsB', 'KsA',
'KsB',
# N-Glycolyl Neuraminic Acid Nomenculature
'0GL', '4GL', '7GL', '8GL', '9GL', 'CGL', 'DGL', 'EGL', 'FGL',
'GGL', 'HGL', 'IGL', 'JGL', 'KGL', '0gL', '4gL', '7gL', '8gL',
'9gL', 'AgL', 'BgL', 'CgL', 'DgL', 'EgL', 'FgL', 'GgL', 'HgL',
'IgL', 'JgL', 'KgL',
# Aglycon Nomenculature
'ROH', 'OME', 'TBT',
}

def _apply(self, group):
resname_attr = group.universe._topology.resnames
# which values in resname attr are in sugar_res?
matches = [ix for (nm, ix) in resname_attr.namedict.items()
if nm in self.sugar_res]
# index of each atom's resname
nmidx = resname_attr.nmidx[group.resindices]
# intersect atom's resname index and matches to sugar_res
return group[np.isin(nmidx, matches)]



class NucleicSelection(Selection):
"""All atoms in nucleic acid residues with recognized residue names.

Expand Down
20 changes: 20 additions & 0 deletions testsuite/MDAnalysisTests/core/test_atomselections.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,8 @@
XTC,
NUCLsel,
PDB_charges,
GLYCAM,
SUGAR_PDB,
PDB_elements,
PDB_full,
PDB_helix,
Expand Down Expand Up @@ -1773,3 +1775,21 @@ def test_formal_charge_selection(sel, size, name):

assert len(ag) == size
assert ag.atoms[0].name == name


def test_sugar_glycam_selection():
u = mda.Universe(GLYCAM)

ag_token = u.select_atoms("sugar")
ag_ref = u.select_atoms("resname ROH or resname 3RA or resname 0MB")

assert ag_token == ag_ref


def test_sugar_pdb_selection():
u = mda.Universe(SUGAR_PDB)

ag_token = u.select_atoms("sugar")
ag_ref = u.select_atoms("resname NAG or resname BMA or resname MAN")

assert ag_token == ag_ref
Loading
Loading