diff --git a/actions/ost-compare-structures b/actions/ost-compare-structures
index 2e4c324792a614591a2aa6ae73e882b5cd5c2750..75972640de0c7dd4869470593ab00628962beb97 100644
--- a/actions/ost-compare-structures
+++ b/actions/ost-compare-structures
@@ -457,11 +457,15 @@ def _ParseArgs():
"--n-max-naive",
dest="n_max_naive",
required=False,
- default=12,
+ default=40320,
type=int,
- help=("If number of chains in model and reference are below or equal "
- "that number, the chain mapping will naively enumerate all "
- "possible mappings. A heuristic is used otherwise."))
+ help=("Parameter for chain mapping. If the number of possible "
+ "mappings is <= *n_max_naive*, the full "
+ "mapping solution space is enumerated to find the "
+ "the mapping with optimal QS-score. A heuristic is used "
+ "otherwise. The default of 40320 corresponds to an octamer "
+ "(8! = 40320). A structure with stoichiometry A6B2 would be "
+ "6!*2! = 1440 etc."))
parser.add_argument(
"--dump-aligned-residues",
diff --git a/modules/doc/actions.rst b/modules/doc/actions.rst
index bd5785bfd23431642f627bed679680e21fa74402..eee1181a1275a8615c6893dded821d314114bc68 100644
--- a/modules/doc/actions.rst
+++ b/modules/doc/actions.rst
@@ -333,12 +333,24 @@ Details on the usage (output of ``ost compare-structures --help``):
--lddt-no-stereochecks
Disable stereochecks for lDDT computation
--n-max-naive N_MAX_NAIVE
- If number of chains in model and reference are below
- or equal that number, the chain mapping will naively
- enumerate all possible mappings. A heuristic is used
- otherwise.
-
-
+ Parameter for chain mapping. If the number of possible
+ mappings is <= *n_max_naive*, the full mapping
+ solution space is enumerated to find the the mapping
+ with optimal QS-score. A heuristic is used otherwise.
+ The default of 40320 corresponds to an octamer (8! =
+ 40320). A structure with stoichiometry A6B2 would be
+ 6!*2! = 1440 etc.
+ --dump-aligned-residues
+ Dump additional info on aligned model and reference
+ residues.
+ --dump-pepnuc-alns Dump alignments of mapped chains but with sequences
+ that did not undergo Molck preprocessing in the
+ scorer. Sequences are extracted from model/target
+ after undergoing selection for peptide and nucleotide
+ residues.
+ --dump-pepnuc-aligned-residues
+ Dump additional info on model and reference residues
+ that occur in pepnuc alignments.
.. _ost compare ligand structures:
diff --git a/modules/mol/alg/pymod/chain_mapping.py b/modules/mol/alg/pymod/chain_mapping.py
index 7b8d2f645f9d23b9bd0a15ab8c60e38e45136512..417cfa58d59b55c1e67be4e3d3b40dd1251f53de 100644
--- a/modules/mol/alg/pymod/chain_mapping.py
+++ b/modules/mol/alg/pymod/chain_mapping.py
@@ -1228,24 +1228,24 @@ class ChainMapper:
return MappingResult(self.target, mdl, self.chem_groups, chem_mapping,
final_mapping, alns)
- def GetMapping(self, model, n_max_naive = 12):
+ def GetMapping(self, model, n_max_naive = 40320):
""" Convenience function to get mapping with currently preferred method
- If number of chains in model and target are <= *n_max_naive*, a naive
- QS-score mapping is performed. For anything else, a QS-score mapping
- with the greedy_full strategy is performed
- (greedy_prune_contact_map = True).
+ If number of possible chain mappings is <= *n_max_naive*, a naive
+ QS-score mapping is performed and optimal QS-score is guaranteed.
+ For anything else, a QS-score mapping with the greedy_full strategy is
+ performed (greedy_prune_contact_map = True). The default for
+ *n_max_naive* of 40320 corresponds to an octamer (8!=40320). A
+ structure with stoichiometry A6B2 would be 6!*2!=1440 etc.
"""
- n_trg_chains = len(self.target.chains)
- res = self.GetChemMapping(model)
- n_mdl_chains = len(res[2].chains)
- if n_trg_chains <= n_max_naive and n_mdl_chains <= n_max_naive:
+ chem_mapping_res = self.GetChemMapping(model)
+ if _NMappingsWithin(self.chem_groups, chem_mapping_res[0], n_max_naive):
return self.GetQSScoreMapping(model, strategy="naive",
- chem_mapping_result=res)
+ chem_mapping_result=chem_mapping_res)
else:
return self.GetQSScoreMapping(model, strategy="greedy_full",
greedy_prune_contact_map=True,
- chem_mapping_result=res)
+ chem_mapping_result=chem_mapping_res)
def GetRepr(self, substructure, model, topn=1, inclusion_radius=15.0,
thresholds=[0.5, 1.0, 2.0, 4.0], bb_only=False,
diff --git a/modules/mol/alg/pymod/scoring.py b/modules/mol/alg/pymod/scoring.py
index af70aca279de11ec5a615d6bfa92a794a17bf665..530a881bea6121795047225984484367a784d858 100644
--- a/modules/mol/alg/pymod/scoring.py
+++ b/modules/mol/alg/pymod/scoring.py
@@ -129,10 +129,13 @@ class Scorer:
:param lddt_no_stereochecks: Whether to compute lDDT without stereochemistry
checks
:type lddt_no_stereochecks: :class:`bool`
- :param n_max_naive: Parameter for chain mapping. If *model* and *target*
- have less or equal that number of chains, the full
+ :param n_max_naive: Parameter for chain mapping. If the number of possible
+ mappings is <= *n_max_naive*, the full
mapping solution space is enumerated to find the
- the optimum. A heuristic is used otherwise.
+ the optimum. A heuristic is used otherwise. The default
+ of 40320 corresponds to an octamer (8! = 40320).
+ A structure with stoichiometry A6B2 would be
+ 6!*2! = 1440 etc.
:type n_max_naive: :class:`int`
:param oum: Override USalign Mapping. Inject mapping of :class:`Scorer`
object into USalign to compute TM-score. Experimental feature
@@ -144,7 +147,7 @@ class Scorer:
def __init__(self, model, target, resnum_alignments=False,
molck_settings = None, cad_score_exec = None,
custom_mapping=None, usalign_exec = None,
- lddt_no_stereochecks=False, n_max_naive=12,
+ lddt_no_stereochecks=False, n_max_naive=40320,
oum=False):
self._target_orig = target
diff --git a/modules/mol/alg/tests/test_chain_mapping.py b/modules/mol/alg/tests/test_chain_mapping.py
index 3d4ccbde250a3f9e2f4b39e7b4b9a5010a18645f..e26ad858d36432ff8b170701b719f6760e43cc1e 100644
--- a/modules/mol/alg/tests/test_chain_mapping.py
+++ b/modules/mol/alg/tests/test_chain_mapping.py
@@ -289,17 +289,20 @@ class TestChainMapper(unittest.TestCase):
greedy_rigid_res = mapper.GetRigidMapping(mdl, strategy="greedy_iterative_rmsd")
self.assertEqual(greedy_rigid_res.mapping, [['X', 'Y'],[None],['Z']])
+ # the default chain mapping
+ default_res = mapper.GetMapping(mdl)
+
# test flat mapping functionality of MappingResult
- flat_map = greedy_rigid_res.GetFlatMapping()
+ flat_map = default_res.GetFlatMapping()
self.assertEqual(len(flat_map), 3)
- self.assertEqual(flat_map[greedy_rigid_res.chem_groups[0][0]], 'X')
- self.assertEqual(flat_map[greedy_rigid_res.chem_groups[0][1]], 'Y')
- self.assertEqual(flat_map[greedy_rigid_res.chem_groups[2][0]], 'Z')
- flat_map = greedy_rigid_res.GetFlatMapping(mdl_as_key=True)
+ self.assertEqual(flat_map[default_res.chem_groups[0][0]], 'X')
+ self.assertEqual(flat_map[default_res.chem_groups[0][1]], 'Y')
+ self.assertEqual(flat_map[default_res.chem_groups[2][0]], 'Z')
+ flat_map = default_res.GetFlatMapping(mdl_as_key=True)
self.assertEqual(len(flat_map), 3)
- self.assertEqual(greedy_rigid_res.chem_groups[0][0], flat_map['X'])
- self.assertEqual(greedy_rigid_res.chem_groups[0][1], flat_map['Y'])
- self.assertEqual(greedy_rigid_res.chem_groups[2][0], flat_map['Z'])
+ self.assertEqual(default_res.chem_groups[0][0], flat_map['X'])
+ self.assertEqual(default_res.chem_groups[0][1], flat_map['Y'])
+ self.assertEqual(default_res.chem_groups[2][0], flat_map['Z'])
# test Align function of ChainMapper
_, mdl_polypep_seqs, mdl_polynuc_seqs = mapper.ProcessStructure(mdl)