modified guess_atom_element for more accurate guess (#4168)

* modified guess_atom_element for more accurate guess Co-authored-by: Rocco Meli <[email protected]> Co-authored-by: pillose <[email protected]>
MDAnalysis · Aug 16, 2023 · acfd122 · acfd122
1 parent a14e98d
commit acfd122
Show file tree

Hide file tree

Showing 4 changed files with 15 additions and 3 deletions.
diff --git a/package/AUTHORS b/package/AUTHORS
@@ -220,6 +220,7 @@ Chronological list of authors
   - Mohit Kumar
   - Shubham Kumar
   - Zaheer Timol
+  - Geongi Moon
 
 External code
 -------------

diff --git a/package/CHANGELOG b/package/CHANGELOG
@@ -13,11 +13,12 @@ The rules for this file:
   * release numbers follow "Semantic Versioning" http://semver.org
 
 ------------------------------------------------------------------------------
-??/??/?? IAlibay, hmacdope
+??/??/?? IAlibay, hmacdope, pillose
 
  * 2.7.0
 
 Fixes
+  * Fix Atom type guessing error (PR #4168, Issue #4167)
 
 Enhancements
 

diff --git a/package/MDAnalysis/topology/guessers.py b/package/MDAnalysis/topology/guessers.py
@@ -202,9 +202,14 @@ def guess_atom_element(atomname):
     try:
         return tables.atomelements[atomname.upper()]
     except KeyError:
-        # strip symbols and numbers
+        # strip symbols
         no_symbols = re.sub(SYMBOLS, '', atomname)
-        name = re.sub(NUMBERS, '', no_symbols).upper()
+
+        # split name by numbers
+        no_numbers = re.split(NUMBERS, no_symbols)
+        no_numbers = list(filter(None, no_numbers)) #remove ''
+        # if no_numbers is not empty, use the first element of no_numbers
+        name = no_numbers[0].upper() if no_numbers else ''
 
         # just in case
         if name in tables.atomelements:

diff --git a/testsuite/MDAnalysisTests/topology/test_guessers.py b/testsuite/MDAnalysisTests/topology/test_guessers.py
@@ -104,6 +104,11 @@ def test_guess_atom_element_1H(self):
         ('zn', 'ZN'),
         ('Ca2+', 'CA'),
         ('CA', 'C'),
+        ('N0A', 'N'),
+        ('C0U', 'C'),
+        ('C0S', 'C'),
+        ('Na+', 'NA'),
+        ('Cu2+', 'CU')
     ))
     def test_guess_element_from_name(self, name, element):
         assert guessers.guess_atom_element(name) == element