increased the maximum number of matches from an rdkit smarts query

package/CHANGELOG

@@ -13,7 +13,8 @@ The rules for this file:
   * release numbers follow "Semantic Versioning" http://semver.org
 
 ------------------------------------------------------------------------------
-??/??/?? IAlibay, melomcr, mdd31, ianmkenney, richardjgowers, hmacdope, orbeckst, scal444
+??/??/?? IAlibay, melomcr, mdd31, ianmkenney, richardjgowers, hmacdope,
+         orbeckst, scal444, orioncohen
  * 2.1.0
 
 Fixes
@@ -29,6 +30,8 @@ Fixes
 Enhancements
   * Add option for custom compiler flags for C/C++ on build and remove march
     option from setup.cfg (Issue #3428, PR #3429).
+  * increase smarts atom selection limit from 1000 -> n_atoms. Add
+    maxMatches and useChirality to rdkit_kwargs. (Issue #3469, PR #3470)
 
 Changes
   * Dropped python 3.6 support and raised minimum numpy version to 1.18.0

package/MDAnalysis/core/groups.py

@@ -2826,7 +2826,7 @@ def ts(self):
 
     def select_atoms(self, sel, *othersel, periodic=True, rtol=1e-05,
                      atol=1e-08, updating=False, sorted=True,
-                     rdkit_kwargs=None, **selgroups):
+                     rdkit_kwargs=None, smarts_kwargs=None, **selgroups):
         """Select atoms from within this Group using a selection string.
 
         Returns an :class:`AtomGroup` sorted according to their index in the
@@ -2977,7 +2977,15 @@ def select_atoms(self, sel, *othersel, periodic=True, rtol=1e-05,
             smarts *SMARTS-query*
                 select atoms using Daylight's SMARTS queries, e.g. ``smarts
                 [#7;R]`` to find nitrogen atoms in rings. Requires RDKit.
-                All matches (max 1000) are combined as a unique match
+                All matches are combined as a unique match. Uses two sets of
+                kwargs: rdkit_kwargs is passed to `RDKitConverter.convert()`
+                and smarts_kwargs is passed to RDKit's [GetSubstructMatches](
+                https://www.rdkit.org/docs/source/
+                rdkit.Chem.rdchem.html#rdkit.Chem.rdchem.Mol.GetSubstructMatches).
+                The useChirality kwarg is True by default.
+
+                >>> universe.select_atoms("C", smarts_kwargs={"maxMatches": 100})
+                <AtomGroup with 100 atoms>
 
         **Boolean**
 
@@ -3147,7 +3155,8 @@ def select_atoms(self, sel, *othersel, periodic=True, rtol=1e-05,
                                                    periodic=periodic,
                                                    atol=atol, rtol=rtol,
                                                    sorted=sorted,
-                                                   rdkit_kwargs=rdkit_kwargs)
+                                                   rdkit_kwargs=rdkit_kwargs,
+                                                   smarts_kwargs=smarts_kwargs)
                             for s in sel_strs))
         if updating:
             atomgrp = UpdatingAtomGroup(self, selections, sel_strs)

package/MDAnalysis/core/selection.py

@@ -643,6 +643,7 @@ def __init__(self, parser, tokens):
             pattern.append(val)
         self.pattern = "".join(pattern)
         self.rdkit_kwargs = parser.rdkit_kwargs
+        self.smarts_kwargs = parser.smarts_kwargs
 
     def _apply(self, group):
         try:
@@ -656,7 +657,12 @@ def _apply(self, group):
         if not pattern:
             raise ValueError(f"{self.pattern!r} is not a valid SMARTS query")
         mol = group.convert_to("RDKIT", **self.rdkit_kwargs)
-        matches = mol.GetSubstructMatches(pattern, useChirality=True)
+        # override GetSubstructMatches default values
+        if "useChirality" not in self.smarts_kwargs:
+            self.smarts_kwargs["useChirality"] = True
+        if "maxMatches" not in self.smarts_kwargs:
+            self.smarts_kwargs["useChirality"] = group.n_atoms
+        matches = mol.GetSubstructMatches(pattern, **self.smarts_kwargs)
         # convert rdkit indices to mdanalysis'
         indices = [
             mol.GetAtomWithIdx(idx).GetIntProp("_MDAnalysis_index")
@@ -1388,7 +1394,7 @@ def expect(self, token):
                 "".format(self.tokens[0], token))
 
     def parse(self, selectstr, selgroups, periodic=None, atol=1e-08,
-              rtol=1e-05, sorted=True, rdkit_kwargs=None):
+              rtol=1e-05, sorted=True, rdkit_kwargs=None, smarts_kwargs=None):
         """Create a Selection object from a string.
 
         Parameters
@@ -1433,6 +1439,7 @@ def parse(self, selectstr, selgroups, periodic=None, atol=1e-08,
         self.rtol = rtol
         self.sorted = sorted
         self.rdkit_kwargs = rdkit_kwargs or {}
+        self.smarts_kwargs = smarts_kwargs or {}
 
         self.selectstr = selectstr
         self.selgroups = selgroups

testsuite/MDAnalysisTests/core/test_atomselections.py

@@ -575,11 +575,17 @@ def test_invalid_smarts_sel_raises_error(self, u2):
         with pytest.raises(ValueError, match="not a valid SMARTS"):
             u2.select_atoms("smarts foo")
 
-    def test_passing_args_to_converter(self):
+    def test_passing_rdkit_kwargs_to_converter(self):
         u = mda.Universe.from_smiles("O=C=O")
         sel = u.select_atoms("smarts [$(O=C)]", rdkit_kwargs=dict(force=True))
         assert sel.n_atoms == 2
 
+    def test_passing_smarts_kwargs_to_converter(self, u2):
+        sel = u2.select_atoms("smarts C", smarts_kwargs=dict(maxMatches=2))
+        assert sel.n_atoms == 2
+        sel2 = u2.select_atoms("smarts c")
+        assert sel2.n_atoms == 4
+
 
 class TestSelectionsNucleicAcids(object):
     @pytest.fixture(scope='class')