merge conflicts

Author: jberg5

.github/workflows/gh-ci.yaml

@@ -55,6 +55,12 @@ jobs:
               full-deps: false
               codecov: true
               cython: "cython<3.1"
+            - name: ubuntu_arm
+              os: ubuntu-24.04-arm
+              python-version: "3.13"
+              full-deps: false
+              codecov: false
+              cython: "cython>3.1"
             - name: numpy_min
               os: ubuntu-latest
               python-version: "3.11"

.github/workflows/greetings.yaml

@@ -195,6 +195,17 @@ def time_wrap_compound(self, num_atoms):
         """
         self.ag.wrap(compound="residues")
 
+    def time_asunique_no_sorted(self, num_atoms):
+        """Benchmark asunique() operation on
+        atomgroup without sorting"""
+        self.ag.asunique(sorted=False)
+
+    def time_asunique_sorted(self, num_atoms):
+        """Benchmark asunique() operation on
+        atomgroup with sorting"""
+        self.ag.asunique(sorted=True)
+
+
 class AtomGroupAttrsBench(object):
     """Benchmarks for the various MDAnalysis
     atomgroup attributes.

.github/workflows/rtd.yaml

@@ -0,0 +1,62 @@
+import MDAnalysis as mda
+from MDAnalysis.analysis import contacts
+from MDAnalysisTests.datafiles import PSF, DCD
+
+
+class ContactsBench(object):
+    """
+    Benchmarks for MDAnalysis.analysis.contacts.Contacts
+    """
+
+    # Parameter combinations tested in the benchmark.
+    # radius : cutoff distance used to define a contact
+    # method : algorithm used to compute contacts
+    # pbc    : whether periodic boundary conditions are applied
+    params = [
+        [4.5, 6.0],
+        ["hard_cut", "soft_cut", "radius_cut"],
+        [True, False],
+    ]
+
+    # Names corresponding to the parameters above
+    param_names = ["radius", "method", "pbc"]
+
+    def setup(self, radius, method, pbc):
+        """
+        Prepare the Universe and contact analysis object
+        for benchmarking.
+        """
+
+        # Load test trajectory
+        self.u = mda.Universe(PSF, DCD)
+
+        # Define atom selections
+        self.sel1 = "protein"
+        self.sel2 = "name CA"
+
+        # Create atom groups from the selections
+        g1 = self.u.select_atoms(self.sel1)
+        g2 = self.u.select_atoms(self.sel2)
+
+        # Initialize the Contacts analysis
+        # select   : atom selection strings
+        # refgroup : reference atom groups used for contacts
+        # radius   : contact cutoff distance
+        # method   : contact calculation method
+        # pbc      : periodic boundary conditions flag
+        self.analysis = contacts.Contacts(
+            self.u,
+            select=(self.sel1, self.sel2),
+            refgroup=(g1, g2),
+            radius=radius,
+            method=method,
+            pbc=pbc,
+        )
+
+    def time_contacts_run(self, radius, method, pbc):
+        """
+        Benchmark execution of Contacts.run()
+        over the full trajectory.
+        """
+
+        self.analysis.run()

benchmarks/benchmarks/ag_methods.py

@@ -0,0 +1,48 @@
+import MDAnalysis as mda
+
+try:
+    from MDAnalysisTests.datafiles import TPR, XTC, PDB_janin
+except:
+    pass
+
+try:
+    from MDAnalysis.analysis.dssp import DSSP
+    from MDAnalysis.analysis.dssp.pydssp_numpy import assign
+except:
+    pass
+
+
+class DsspBench(object):
+    """Benchmarks for MDAnalysis.analysis.dssp.DSSP over a trajectory."""
+
+    params = ([1, 5, 10], [True, False])
+    param_names = ["n_frames", "guess_hydrogens"]
+
+    def setup(self, n_frames, guess_hydrogens):
+        self.u = mda.Universe(TPR, XTC)
+        self.dssp = DSSP(self.u, guess_hydrogens=guess_hydrogens)
+        self.n_frames = n_frames
+
+    def time_dssp_run(self, n_frames, guess_hydrogens):
+        """Benchmark DSSP.run() over n_frames of a trajectory."""
+        self.dssp.run(stop=self.n_frames)
+
+
+class DsspAssignBench(object):
+    """Benchmarks for the core DSSP assign() function on a single frame.
+
+    Uses PDB_janin as a large test system for number of residues
+    """
+
+    params = [50, 100, 214, 500]
+    param_names = ["n_residues"]
+
+    def setup(self, n_residues):
+        self.u = mda.Universe(PDB_janin)
+        dssp = DSSP(self.u)
+        coords = dssp._get_coords()
+        self.coords = coords[:n_residues]
+
+    def time_assign(self, n_residues):
+        """Benchmark single-frame assign() call."""
+        assign(self.coords)

benchmarks/benchmarks/analysis/contacts.py

@@ -0,0 +1,31 @@
+"""
+Benchmark for HydrogenBondAnalysis
+"""
+
+try:
+    from MDAnalysis.analysis.hydrogenbonds.hbond_analysis import HydrogenBondAnalysis as HBA
+    from MDAnalysisTests.datafiles import waterPSF , waterDCD
+except ImportError:
+    pass
+
+import MDAnalysis
+
+class HydrogenBondAnalysisBenchmark:
+    """
+    It tests performance of hbond.run() across different
+    number of frames using waterPSF/waterDCD test files.
+    """
+
+    unit = "ms"
+    timeout = 60.0
+    params = [2, 5, 10]
+    param_names = ["n_frames"]
+
+
+    def setup(self, n_frames):
+        u = MDAnalysis.Universe(waterPSF, waterDCD)
+        self.hbonds = HBA(universe= u)
+    
+    def time_run(self, n_frames):
+        self.hbonds.run(stop = n_frames)
+        

benchmarks/benchmarks/analysis/dssp.py

@@ -192,7 +192,7 @@ Chronological list of authors
   - Mingyi Xue
   - Meghan Osato
   - Anirvinya G
-  - Rishabh Shukla  
+  - Rishabh Shukla
   - Manish Kumar
   - Aditi Tripathi
   - Sukeerti T
@@ -247,22 +247,22 @@ Chronological list of authors
   - Jia-Xin Zhu
   - Tanish Yelgoe
 2025
-  - Joshua Raphael Uy 
+  - Joshua Raphael Uy
   - Namir Oues
-  - Pavel Buslaev  
+  - Pavel Buslaev
   - Lexi Xu
-  - BHM-Bob G  
+  - BHM-Bob G
   - Yu-Yuan (Stuart) Yang
   - James Rowe
-  - Debasish Mohanty  
+  - Debasish Mohanty
   - Abdulrahman Elbanna
   - Tulga-Erdene Sodjargal
   - Gareth Elliott
   - Marc Schuh
   - Sirsha Ganguly
   - Amruthesh Thirumalaiswamy
   - Ch Zhang
-  - Raúl Lois-Cuns  
+  - Raúl Lois-Cuns
   - Pranay Pelapkar
   - Shreejan Dolai
   - Tanisha Dubey
@@ -277,6 +277,9 @@ Chronological list of authors
   - Ayush Agarwal
   - Parth Uppal
   - Olivier Languin--Cattoën
+  - Amarendra Mohan
+  - Shubham Mittal  
+  - Charity Grey
   - Jonathan Berg
 
 External code
@@ -325,4 +328,4 @@ Logo
 
 The MDAnalysis 'Atom' logo was designed by Christian Beckstein; it is
 Copyright (c) 2011 Christian Beckstein and made available under a
-Creative Commons Attribution-NoDerivs 3.0 Unported License.
+Creative Commons Attribution-NoDerivs 3.0 Unported License.

benchmarks/benchmarks/analysis/hbond_analysis.py

@@ -17,11 +17,26 @@ The rules for this file:
 ??/??/?? IAlibay, orbeckst, marinegor, tylerjereddy, ljwoods2, marinegor,
          spyke7, talagayev, tanii1125, BradyAJohnston, hejamu, jeremyleung521,
          harshitgajjela-droid, kunjsinha, aygarwal, jauy123, Dreamstick9,
-         ollyfutur, jberg
+         ollyfutur, Amarendra22, charity-g, ParthUppal523, jberg5
 
  * 2.11.0
 
 Fixes
+ * `MDAnalysis.analysis.nucleicacids.WatsonCrickDist`, `MinorPairDist`,
+   and `MajorPairDist` now match residue names against the full resname
+   instead of only the first character, fixing incorrect behaviour with
+   multi-character names such as CHARMM ``DG``/``DA`` or ``GUA``/``ADE``
+   (Issue #5360). Note: users relying on the previous truncation
+   behaviour must now pass explicit residue names via the ``g_name``,
+   ``a_name``, etc. keyword arguments.
+ * `MDAnalysis.analysis.atomicdistances.AtomicDistances` results are now
+   consistent with expected `analysis` documentation data type = Results
+   (Issue #4819, PR #5347)
+   Note: This fix is backwards-incompatible.
+ * DSSP now correctly handles periodic boundary conditions in hydrogen bond
+   detection; previously, hydrogen bonds across periodic boundaries were
+   missed (PR #5182)
+ * Fix mixed-case atom types in guess_bonds (Issue #5342, PR #5343)
  * Fixes msd for non-linear frames, when non_linear is not explicitly
    provided (Issue #5100, PR #5254)
  * Fixes TypeError with np.int64 indexing in GSD Reader (Issue #5224)
@@ -45,13 +60,25 @@ Fixes
    DSSP by porting upstream PyDSSP 0.9.1 fix (Issue #4913)
 
 Enhancements
+ * Enables parallelization for analysis.atomicdistances.AtomicDistances
+   (Issue #4662, PR #4822)
+ * DSSP uses ``capped_distance`` and ``calc_bonds`` for faster distance
+   calculations and supports ``backend`` selection (e.g. ``"distopia"``)
+   (PR #5182)
+ * Added ASV benchmark for `MDAnalysis.analysis.contacts` (PR #5291)
+ * Improved performance of inverse index mapping in AtomGroup using an optimized
+   Cython implementation in lib._cutils.inverse_int_index()
+   (Issue #3387, PR #5252)
+ * Added documentation for all keyword in select_atoms() and
+   selections.rst (Issue #5317, PR #5325)
+ * Added HydrogenBondAnalysis benchmark for performance tracking (PR #5309)
  * Added `select=None` in `analysis.rms.RMSD` to perform no selection on
    the input `atomgroup` and `reference` (Issue #5300, PR #5296)
  * MOL2Parser now reads unit cell dimensions from @<TRIPOS>CRYSIN records (Issue #3341)
  * Reduces duplication of code in _apply() function (Issue #5247, PR #5294)
  * Added new top-level `MDAnalysis.fetch` module (PR #4943)
  * Added new function `MDAnalysis.fetch.from_PDB` to download structure files from wwPDB
-   using `pooch` as optional dependency (Issue #4907, PR #4943) 
+   using `pooch` as optional dependency (Issue #4907, PR #4943)
  * Added benchmarks for package.MDAnalysis.analysis.msd.EinsteinMSD (PR #5277)
  * Improved PCA performance by computing covariance matrix via batched BLAS matrix
    multiply instead of per-frame outer product accumulation, and using