Merge branch 'develop' into rdkit-converter-inferring

.github/workflows/gh-ci.yaml

@@ -127,7 +127,7 @@ jobs:
       with:
         token: ${{ secrets.CODECOV_TOKEN }}
         file: coverage.xml
-        fail_ci_if_error: True
+        fail_ci_if_error: False
         verbose: True
 
 
@@ -259,22 +259,22 @@ jobs:
 
     - name: check_package_build
       run: |
-        DISTRIBUTION=$(ls -t1 dist/MDAnalysis-*.tar.gz | head -n1)
+        DISTRIBUTION=$(ls -t1 dist/mdanalysis-*.tar.gz | head -n1)
         test -n "${DISTRIBUTION}" || { echo "no distribution dist/MDAnalysis-*.tar.gz found"; exit 1; }
         twine check $DISTRIBUTION
 
     - name: check_testsuite_build
       run: |
-        DISTRIBUTION=$(ls -t1 dist/MDAnalysisTests-*.tar.gz | head -n1)
+        DISTRIBUTION=$(ls -t1 dist/mdanalysistests-*.tar.gz | head -n1)
         test -n "${DISTRIBUTION}" || { echo "no distribution dist/MDAnalysisTests-*.tar.gz found"; exit 1; }
         twine check $DISTRIBUTION
 
     - name: install sdist
       working-directory: ./dist
       run: |
         ls -a .
-        python -m pip install MDAnalysis-*.tar.gz
-        python -m pip install MDAnalysisTests-*.tar.gz
+        python -m pip install mdanalysis-*.tar.gz
+        python -m pip install mdanalysistests-*.tar.gz
 
     - name: run tests
       working-directory: ./dist

.github/workflows/linters.yaml

@@ -146,6 +146,7 @@ jobs:
           micromamba: true
           full-deps: true
           numpy: numpy=1.23.2
+          rdkit: rdkit=2023.09.3
 
       - name: install
         run: |

README.rst

@@ -102,19 +102,18 @@ Citation
 When using MDAnalysis in published work, please cite the following
 two papers:
 
-*   R. J. Gowers, M. Linke, J. Barnoud, T. J. E. Reddy,
-    M. N. Melo, S. L. Seyler, D. L. Dotson, J. Domanski,
-    S. Buchoux, I. M. Kenney, and O. Beckstein. MDAnalysis:
+*   R\. J. Gowers, M. Linke, J. Barnoud, T. J. E. Reddy,
+    M\. N. Melo, S. L. Seyler, D. L. Dotson, J. Domanski,
+    S\. Buchoux, I. M. Kenney, and O. Beckstein. MDAnalysis:
     A Python package for the rapid analysis of molecular
     dynamics simulations. In S. Benthall and S. Rostrup,
     editors, Proceedings of the 15th Python in Science
     Conference, pages 102-109, Austin, TX, 2016. SciPy.
-    doi:`10.25080/Majora-629e541a-00e`_    
-
+    doi: `10.25080/Majora-629e541a-00e`_    
 *   N. Michaud-Agrawal, E. J. Denning, T. B. Woolf,
     and O. Beckstein. MDAnalysis: A Toolkit for the Analysis of Molecular
     Dynamics Simulations. *J. Comput. Chem.* **32** (2011), 2319--2327.
-    doi:`10.1002/jcc.21787`_
+    doi: `10.1002/jcc.21787`_
 
 For citations of included algorithms and sub-modules please see the references_.
 
@@ -194,4 +193,4 @@ For citations of included algorithms and sub-modules please see the references_.
 
 .. |discussions| image:: https://img.shields.io/github/discussions/MDAnalysis/MDAnalysis
    :alt: GitHub Discussions
-   :target: https://github.com/MDAnalysis/mdanalysis/discussions
+   :target: https://github.com/MDAnalysis/mdanalysis/discussions

package/CHANGELOG

@@ -16,11 +16,17 @@ The rules for this file:
 -------------------------------------------------------------------------------
 ??/??/?? IAlibay, HeetVekariya, marinegor, lilyminium, RMeli,
          ljwoods2, aditya292002, pstaerk, PicoCentauri, BFedder,
-         tyler.je.reddy, SampurnaM, leonwehrhan, kainszs, orionarcher, cbouy
-
+         tyler.je.reddy, SampurnaM, leonwehrhan, kainszs, orionarcher,
+         yuxuanzhuang, cbouy
+
  * 2.8.0
 
 Fixes
+ * Fix PSFParser error when encoutering string-like resids
+ * (Issue #2053, Issue #4189 PR #4582)
+ * Fix `MDAnalysis.analysis.align.AlignTraj` not accepting writer kwargs
+   (Issue #4564, PR #4565)
+ * Fix #4259 via removing argument `parallelizable` of `NoJump` transformation.
  * Fix doctest errors of analysis/pca.py related to rounding issues 
    (Issue #3925, PR #4377)
  * Convert openmm Quantity to raw value for KE and PE in OpenMMSimulationReader.

package/MDAnalysis/analysis/align.py

@@ -681,6 +681,7 @@ class AlignTraj(AnalysisBase):
     def __init__(self, mobile, reference, select='all', filename=None,
                  prefix='rmsfit_', weights=None,
                  tol_mass=0.1, match_atoms=True, strict=False, force=True, in_memory=False,
+                 writer_kwargs=None,
                  **kwargs):
         """Parameters
         ----------
@@ -720,6 +721,8 @@ def __init__(self, mobile, reference, select='all', filename=None,
         verbose : bool (optional)
              Set logger to show more information and show detailed progress of
              the calculation if set to ``True``; the default is ``False``.
+        writer_kwargs : dict (optional)
+            kwarg dict to be passed to the constructed writer
 
 
         Attributes
@@ -780,6 +783,9 @@ def __init__(self, mobile, reference, select='all', filename=None,
            :attr:`rmsd` results are now stored in a
            :class:`MDAnalysis.analysis.base.Results` instance.
 
+        .. versionchanged:: 2.8.0
+           Added ``writer_kwargs`` kwarg dict to pass to the writer
+
         """
         select = rms.process_selection(select)
         self.ref_atoms = reference.select_atoms(*select['reference'])
@@ -816,10 +822,12 @@ def __init__(self, mobile, reference, select='all', filename=None,
             self.ref_atoms, self.mobile_atoms, tol_mass=tol_mass,
             strict=strict, match_atoms=match_atoms)
 
+        if writer_kwargs is None:
+            writer_kwargs = {}
         # with self.filename == None (in_memory), the NullWriter is chosen
         # (which just ignores input) and so only the in_memory trajectory is
         # retained
-        self._writer = mda.Writer(self.filename, natoms)
+        self._writer = mda.Writer(self.filename, natoms, **writer_kwargs)
 
         self._weights = get_weights(self.ref_atoms, weights)
 
@@ -1661,4 +1669,4 @@ def get_atoms_byres(g, match_mask=np.logical_not(mismatch_mask)):
                 logger.error(errmsg)
                 raise SelectionError(errmsg)
 
-    return ag1, ag2
+    return ag1, ag2

package/MDAnalysis/analysis/helix_analysis.py

@@ -121,7 +121,7 @@ def vector_of_best_fit(coordinates):
     """
     centered = coordinates - coordinates.mean(axis=0)
     Mt_M = np.matmul(centered.T, centered)
-    u, s, vh = np.linalg.linalg.svd(Mt_M)
+    u, s, vh = np.linalg.svd(Mt_M)
     vector = vh[0]
 
     # does vector face first local helix origin?

package/MDAnalysis/analysis/rdf.py

@@ -32,7 +32,7 @@
 
 .. math::
 
-   g_{ab}(r) = (N_{a} N_{b})^{-1} \sum_{i=1}^{N_a} \sum_{j=1}^{N_b}
+   g_{ab}(r) = \frac{1}{N_{a}} \frac{1}{N_{b}/V} \sum_{i=1}^{N_a} \sum_{j=1}^{N_b}
                \langle \delta(|\mathbf{r}_i - \mathbf{r}_j| - r) \rangle
 
 which is normalized so that the RDF becomes 1 for large separations in a

package/MDAnalysis/coordinates/LAMMPS.py

@@ -66,22 +66,33 @@
 :class:`~MDAnalysis.topology.LAMMPSParser.DATAParser`) together with a
 LAMMPS DCD with "*real*" provide the keyword *format="LAMMPS*"::
 
-    >>> u = MDAnalysis.Universe("lammps.data", "lammps_real.dcd", format="LAMMPS")
+    >>> import MDAnalysis
+    >>> from MDAnalysis.tests.datafiles import LAMMPSdata2, LAMMPSdcd2
+    >>> u = MDAnalysis.Universe(LAMMPSdata2, LAMMPSdcd2, format="LAMMPS")
 
-If the trajectory uses *units nano* then use ::
+If the trajectory uses *units nano* then use
 
-    >>> u = MDAnalysis.Universe("lammps.data", "lammps_nano.dcd", format="LAMMPS",
+    >>> import MDAnalysis
+    >>> from MDAnalysis.tests.datafiles import LAMMPSdata2, LAMMPSdcd2
+    >>> u = MDAnalysis.Universe(LAMMPSdata2, LAMMPSdcd2, format="LAMMPS",
     ...                          lengthunit="nm", timeunit="ns")
 
 To scan through a trajectory to find a desirable frame and write to a LAMMPS
 data file,
 
->>> for ts in u.trajectory:
-...     # analyze frame
-...     if take_this_frame == True:
-...         with mda.Writer('frame.data') as W:
-...             W.write(u.atoms)
-...         break
+   >>> import MDAnalysis
+   >>> from MDAnalysis.tests.datafiles import LAMMPSdata2, LAMMPSdcd2 
+   >>> u = MDAnalysis.Universe(LAMMPSdata2, LAMMPSdcd2, format="LAMMPS",
+   ...                          lengthunit="nm", timeunit="ns")
+   >>> take_this_frame = False
+   >>> for ts in u.trajectory:
+   ...     # analyze frame
+   ...     if ts.frame == 4:
+   ...         take_this_frame = True
+   ...     if take_this_frame == True:
+   ...         with MDAnalysis.Writer('frame.data') as W:
+   ...             W.write(u.atoms)
+   ...         break
 
 Note
 ----

package/MDAnalysis/lib/formats/cython_util.pyx

@@ -26,6 +26,8 @@ cimport numpy as cnp
 from libc.stdlib cimport free
 from cpython cimport PyObject, Py_INCREF
 
+from MDAnalysis.lib.util import no_copy_shim
+
 cnp.import_array()
 
 
@@ -71,7 +73,7 @@ cdef class ArrayWrapper:
         self.data_type = data_type
         self.ndim = ndim
 
-    def __array__(self):
+    def __array__(self, dtype=None, copy=None):
         """ Here we use the __array__ method, that is called when numpy
             tries to get an array from the object."""
         ndarray = cnp.PyArray_SimpleNewFromData(self.ndim,
@@ -110,7 +112,7 @@ cdef cnp.ndarray ptr_to_ndarray(void* data_ptr, cnp.int64_t[:] dim, int data_typ
     array_wrapper = ArrayWrapper()
     array_wrapper.set_data(<void*> data_ptr, <int*> &dim[0], dim.size, data_type)
 
-    cdef cnp.ndarray ndarray = np.array(array_wrapper, copy=False)
+    cdef cnp.ndarray ndarray = np.array(array_wrapper, copy=no_copy_shim)
     # Assign our object to the 'base' of the ndarray object
     ndarray[:] = array_wrapper.__array__()
     # Increment the reference count, as the above assignement was done in

package/MDAnalysis/lib/transformations.py

@@ -170,6 +170,7 @@
 from numpy.linalg import norm
 
 from .mdamath import angle as vecangle
+from MDAnalysis.lib.util import no_copy_shim
 
 def identity_matrix():
     """Return 4x4 identity/unit matrix.
@@ -326,7 +327,7 @@ def rotation_matrix(angle, direction, point=None):
     M[:3, :3] = R
     if point is not None:
         # rotation not around origin
-        point = np.array(point[:3], dtype=np.float64, copy=False)
+        point = np.array(point[:3], dtype=np.float64, copy=no_copy_shim)
         M[:3, 3] = point - np.dot(R, point)
     return M
 
@@ -497,7 +498,7 @@ def projection_matrix(point, normal, direction=None,
 
     """
     M = np.identity(4)
-    point = np.array(point[:3], dtype=np.float64, copy=False)
+    point = np.array(point[:3], dtype=np.float64, copy=no_copy_shim)
     normal = unit_vector(normal[:3])
     if perspective is not None:
         # perspective projection
@@ -515,7 +516,7 @@ def projection_matrix(point, normal, direction=None,
         M[3, 3] = np.dot(perspective, normal)
     elif direction is not None:
         # parallel projection
-        direction = np.array(direction[:3], dtype=np.float64, copy=False)
+        direction = np.array(direction[:3], dtype=np.float64, copy=no_copy_shim)
         scale = np.dot(direction, normal)
         M[:3, :3] -= np.outer(direction, normal) / scale
         M[:3, 3] = direction * (np.dot(point, normal) / scale)
@@ -970,8 +971,8 @@ def superimposition_matrix(v0, v1, scaling=False, usesvd=True):
     True
 
     """
-    v0 = np.array(v0, dtype=np.float64, copy=False)[:3]
-    v1 = np.array(v1, dtype=np.float64, copy=False)[:3]
+    v0 = np.array(v0, dtype=np.float64, copy=no_copy_shim)[:3]
+    v1 = np.array(v1, dtype=np.float64, copy=no_copy_shim)[:3]
 
     if v0.shape != v1.shape or v0.shape[1] < 3:
         raise ValueError("vector sets are of wrong shape or type")
@@ -1314,7 +1315,7 @@ def quaternion_from_matrix(matrix, isprecise=False):
     True
 
     """
-    M = np.array(matrix, dtype=np.float64, copy=False)[:4, :4]
+    M = np.array(matrix, dtype=np.float64, copy=no_copy_shim)[:4, :4]
     if isprecise:
         q = np.empty((4, ), dtype=np.float64)
         t = np.trace(M)

package/MDAnalysis/lib/util.py

@@ -205,6 +205,7 @@
 from functools import wraps
 import textwrap
 import weakref
+import itertools
 
 import mmtf
 import numpy as np
@@ -2552,3 +2553,42 @@ def wrapper(self, *args, **kwargs):
                         self._kwargs[key] = arg
         return func(self, *args, **kwargs)
     return wrapper
+
+
+def no_copy_shim():
+    if np.lib.NumpyVersion >= "2.0.0rc1":
+        copy = None
+    else:
+        copy = False
+    return copy
+
+
+def atoi(s: str) -> int:
+    """Convert the leading number part of a string to an integer.
+
+    Parameters
+    ----------
+    s : str
+        The string to convert to an integer.
+
+    Returns
+    -------
+    number : int
+        The first numeric part of the string converted to an integer.
+        If the string does not start with a number, 0 is returned.
+
+    Examples
+    --------
+    >>> from MDAnalysis.lib.util import atoi
+    >>> atoi('34f4')
+    34
+    >>> atoi('foo')
+    0
+ 
+
+    .. versionadded:: 2.8.0
+    """
+    try:
+        return int(''.join(itertools.takewhile(str.isdigit, s.strip())))
+    except ValueError:
+        return 0

package/MDAnalysis/topology/PSFParser.py

@@ -48,7 +48,7 @@
 from math import ceil
 import numpy as np
 
-from ..lib.util import openany
+from ..lib.util import openany, atoi
 from . import guessers
 from .base import TopologyReaderBase, squash_by, change_squash
 from ..core.topologyattrs import (
@@ -89,6 +89,10 @@ class PSFParser(TopologyReaderBase):
     - impropers
 
     .. _PSF: http://www.charmm.org/documentation/c35b1/struct.html
+
+
+    .. versionchanged:: 2.8.0
+       PSFParser now reads string resids and converts them to integers.
     """
     format = 'PSF'
 
@@ -248,7 +252,8 @@ def _parseatoms(self, lines, atoms_per, numlines):
         }
         atom_parser = atom_parsers[self._format]
         # once partitioned, assigned each component the correct type
-        set_type = lambda x: (int(x[0]) - 1, x[1] or "SYSTEM", int(x[2]), x[3],
+        set_type = lambda x: (int(x[0]) - 1, x[1] or "SYSTEM",
+                              atoi(x[2]), x[3],
                               x[4], x[5], float(x[6]), float(x[7]))
 
         # Oli: I don't think that this is the correct OUTPUT format:

package/MDAnalysis/transformations/nojump.py

@@ -99,11 +99,10 @@ def __init__(
         self,
         check_continuity=True,
         max_threads=None,
+    ):
         # NoJump transforms are inherently unparallelizable, since
         # it depends on the previous frame's unwrapped coordinates
-        parallelizable=False,
-    ):
-        super().__init__(max_threads=max_threads, parallelizable=parallelizable)
+        super().__init__(max_threads=max_threads, parallelizable=False)
         self.prev = None
         self.old_frame = 0
         self.older_frame = "A"

package/doc/sphinx/source/documentation_pages/analysis/hole2.rst

@@ -24,6 +24,8 @@ under the Apache v2.0 license.)
    `mdahole2 <https://www.mdanalysis.org/mdahole2/>`_ and
    will be removed in MDAnalysis 3.0.0.
 
+.. _HOLE: http://www.holeprogram.org/
+
 
 See Also
 --------