diff --git a/.github/actions/setup-deps/action.yaml b/.github/actions/setup-deps/action.yaml
index 7f40ec146ad..a7f4523293e 100644
--- a/.github/actions/setup-deps/action.yaml
+++ b/.github/actions/setup-deps/action.yaml
@@ -21,8 +21,8 @@ inputs:
     default: 'codecov'
   cython:
     default: 'cython'
-  filelock:
-    default: 'filelock'
+  filelock:
+    default: 'filelock'
   griddataformats:
     default: 'griddataformats'
   gsd:
@@ -60,6 +60,8 @@ inputs:
     default: 'dask'
   distopia:
     default: 'distopia>=0.4.0'
+  gemmi:
+    default: 'gemmi'
   h5py:
     default: 'h5py>=2.10'
   hole2:
@@ -140,6 +142,7 @@ runs:
           ${{ inputs.dask }}
           ${{ inputs.distopia }}
           ${{ inputs.gsd }}
+          ${{ inputs.gemmi }}
           ${{ inputs.h5py }}
           ${{ inputs.hole2 }}
           ${{ inputs.imdclient }}
diff --git a/azure-pipelines.yml b/azure-pipelines.yml
index c5e80b9c579..831d943aa12 100644
--- a/azure-pipelines.yml
+++ b/azure-pipelines.yml
@@ -114,6 +114,7 @@ jobs:
       tidynamics>=1.0.0
       imdclient>=0.2.2
       pytng>=0.3.4
+      gemmi>=0.7.3
 
     # remove from azure to avoid test hanging #4707
     # "gsd>3.0.0"
diff --git a/package/CHANGELOG b/package/CHANGELOG
index c043f683f05..1da61797518 100644
--- a/package/CHANGELOG
+++ b/package/CHANGELOG
@@ -23,6 +23,12 @@ The rules for this file:
  * 2.11.0
 
 Fixes
+
+
+Enhancements
+ * Add reading single-frame files from mmCIF, also known as PDBx format, using
+   crystallographic library `gemmi` as a backend (Issue #2367 and extension of
+   #4303, also solves #5089, PR #4712).
  * Added `.gitattributes` to enforce LF (\n) as line endings and renormalized
    existing files to conform (Issue #5315, PR #5446)
  * `AtomGroup.rotate()` and the `rotateby` trajectory transformation now
diff --git a/package/MDAnalysis/coordinates/MMCIF.py b/package/MDAnalysis/coordinates/MMCIF.py
new file mode 100644
index 00000000000..6bf771c5839
--- /dev/null
+++ b/package/MDAnalysis/coordinates/MMCIF.py
@@ -0,0 +1,183 @@
+# -*- Mode: python; tab-width: 4; indent-tabs-mode:nil; coding:utf-8 -*-
+# vim: tabstop=4 expandtab shiftwidth=4 softtabstop=4
+#
+"""
+MMCIF structure files in MDAnalysis --- :mod:`MDAnalysis.coordinates.MMCIF`
+===========================================================================
+
+.. versionadded:: 2.11.0
+
+MDAnalysis reads coordinates from MMCIF (macromolecular Crystallographic
+Information File) files, also known as PDBx/mmCIF format, using the
+`gemmi <https://gemmi.readthedocs.io>`_ library as a backend. MMCIF is a
+more modern and flexible alternative to the PDB format, capable of storing
+detailed structural and experimental data about biological macromolecules.
+
+MMCIF files use a structured, tabular format with key-value pairs to store
+both coordinate and atom information. The format supports multiple
+models/frames, though this implementation currently only reads the first
+model and provides warning messages for multi-model files.
+
+The reader automatically detects if the structure contains placeholder unit
+cell information (usually the case for cryoEM structures, where cell
+parameters are (1, 1, 1, 90, 90, 90)) and sets dimensions to ``None``
+in that case.
+
+Basic usage
+-----------
+
+.. code-block:: python
+
+    import MDAnalysis as mda
+
+    u = mda.Universe("structure.cif")
+
+    # or from a compressed file
+    u = mda.Universe("structure.cif.gz")
+
+See Also
+--------
+* `wwPDB MMCIF Resources <http://mmcif.wwpdb.org>`_
+* `Gemmi library documentation <https://gemmi.readthedocs.io>`_
+
+Classes
+-------
+
+.. autoclass:: MMCIFReader
+   :members:
+   :inherited-members:
+
+"""
+
+import logging
+import warnings
+from pathlib import Path
+from typing import TYPE_CHECKING
+
+import numpy as np
+
+from ..lib import util
+from . import base
+
+if TYPE_CHECKING:
+    from gemmi import Model, Structure
+
+try:
+    import gemmi
+
+    HAS_GEMMI = True
+except ImportError:
+    HAS_GEMMI = False
+
+logger = logging.getLogger("MDAnalysis.coordinates.MMCIF")
+
+
+def _read_gemmi_structure(filename: str | Path) -> "Structure":
+    # This function exists because of some lacking methods in the gemmi Python API.
+    # Within gemmi in C++, one can call `read_structure` and in-memory, string, and filepath
+    # arguments will all be accepted:
+    # https://github.com/project-gemmi/gemmi/blob/4416e298f204b7b57bf5b3051d7efd4fe02957cf/include/gemmi/mmread.hpp#L86
+
+    # However, for MDA to similarly accept common input types like streams (open File-like objs and StringIO objs)
+    # as well as pathlib.Path() objects, we have to use the Python API methods available currently (as of 0.7.3)
+    # with a string as a common target for all input types.
+    # For this, we call gemmi.cif.read_string (https://gemmi.readthedocs.io/en/latest/cif.html#reading) to handle CIF
+    # strings and gemmi.read_pdb_string to handle PDB strings (no one method can handle both formats currently Py-side)
+
+    # openany() is called instead of passing file paths (when available) differently from streams;
+    # even though reading the file into a string is less efficient, this is easier to maintain.
+
+    # If the gemmi Python API is extended, this function can be simplified/removed and replaced with something like
+    # gemmi.read_structure
+    with util.openany(filename) as f:
+        content_as_str = f.read()
+    try:
+        # String -> Doc -> Block -> Structure
+        # making Structure from first Block in Document as is done internally in gemmi:
+        # https://github.com/project-gemmi/gemmi/blob/4416e298f204b7b57bf5b3051d7efd4fe02957cf/include/gemmi/mmcif.hpp#L32
+        return gemmi.make_structure_from_block(
+            gemmi.cif.read_string(content_as_str)[0]
+        )
+    except ValueError as e:
+        try:
+            return gemmi.read_pdb_string(content_as_str)
+        except (ValueError, RuntimeError):
+            # gemmi raises RuntimeError for unparseable PDB content;
+            # re-raise the mmCIF error since that is the primary format here
+            raise e
+
+
+def _get_coordinates(model: "Model") -> np.ndarray:
+    """Get coordinates of all atoms in the `gemmi.Model` object.
+
+    Parameters
+    ----------
+    model
+        input ``gemmi.Model``, e.g. ``gemmi.read_structure('file.cif')[0]``
+
+    Returns
+    -------
+        np.ndarray, shape [n, 3], where ``n`` is the number of atoms in the structure.
+    """
+    return np.array(
+        [[*at.pos.tolist()] for chain in model for res in chain for at in res]
+    )
+
+
+class MMCIFReader(base.SingleFrameReaderBase):
+    """Reads from an MMCIF file using :mod:`gemmi` as a backend.
+
+    Notes
+    -----
+
+    If the structure represents an ensemble, only the first structure in the ensemble
+    is read here (and a warning is thrown). Also, if the structure has a placeholder "CRYST1"
+    record (1, 1, 1, 90, 90, 90), it's set to ``None`` instead.
+
+    .. versionadded:: 2.11.0
+    """
+
+    format = ["cif", "cif.gz", "mmcif", "mmcif.gz"]
+    units = {"time": None, "length": "Angstrom"}
+
+    def __init__(self, filename, **kwargs):
+        if not HAS_GEMMI:
+            errmsg = "MMCIFReader: To read mmCIF files, please install gemmi"
+            raise ImportError(errmsg)
+        super(MMCIFReader, self).__init__(filename, **kwargs)
+
+    def _read_first_frame(self):
+        structure = self._get_structure()
+        cell_dims = np.array(
+            [
+                getattr(structure.cell, name)
+                for name in ("a", "b", "c", "alpha", "beta", "gamma")
+            ]
+        )
+        if len(structure) > 1:
+            wmsg = (
+                f"File {self.filename} has {len(structure)} models, "
+                "but only the first one will be read"
+            )
+            warnings.warn(wmsg)
+            logger.warning(wmsg)
+
+        model = structure[0]
+        coords = _get_coordinates(model)
+        self.n_atoms = len(coords)
+        self.ts = self._Timestep.from_coordinates(coords, **self._ts_kwargs)
+        if np.allclose(cell_dims, np.array([1.0, 1.0, 1.0, 90.0, 90.0, 90.0])):
+            wmsg = (
+                "1 A^3 CRYST1 record,"
+                " this is usually a placeholder."
+                " Unit cell dimensions will be set to None."
+            )
+            warnings.warn(wmsg)
+            logger.warning(wmsg)
+            self.ts.dimensions = None
+        else:
+            self.ts.dimensions = cell_dims
+        self.ts.frame = 0
+
+    def _get_structure(self):
+        return _read_gemmi_structure(self.filename)
diff --git a/package/MDAnalysis/coordinates/__init__.py b/package/MDAnalysis/coordinates/__init__.py
index f81c4915514..3c0ec3ccbc7 100644
--- a/package/MDAnalysis/coordinates/__init__.py
+++ b/package/MDAnalysis/coordinates/__init__.py
@@ -267,6 +267,11 @@ class can choose an appropriate reader automatically.
    | DL_Poly [#a]_ | history   |  r    | DL_Poly ascii history file                           |
    |               |           |       | :mod:`MDAnalysis.coordinates.DLPOLY`                 |
    +---------------+-----------+-------+------------------------------------------------------+
+   | MMCIF [#a]_   | cif,      |  r    | Single frame of coordinates from macromolecular      |
+   |               | mmcif     |       | structures in the PDBx/mmCIF format (requires the    |
+   |               |           |       | gemmi_ package).                                     |
+   |               |           |       | :mod:`MDAnalysis.coordinates.MMCIF`                  |
+   +---------------+-----------+-------+------------------------------------------------------+
    | MMTF [#a]_    | mmtf      |  r    | Macromolecular Transmission Format                   |
    |               |           |       | :mod:`MDAnalysis.coordinates.MMTF`                   |
    +---------------+-----------+-------+------------------------------------------------------+
@@ -297,6 +302,7 @@ class can choose an appropriate reader automatically.
 .. _`netcdf4-python`: https://github.com/Unidata/netcdf4-python
 .. _`H5MD`: https://nongnu.org/h5md/index.html
 .. _`chemfiles`: https://chemfiles.org/
+.. _`gemmi`: https://gemmi.readthedocs.io/
 .. _`list of chemfiles file formats`: https://chemfiles.org/chemfiles/latest/formats.html
 .. _`additional tng block data`: https://www.mdanalysis.org/pytng/documentation_pages/Blocks.html
 .. _`PyTNG package`: https://github.com/MDAnalysis/pytng
@@ -807,3 +813,4 @@ class can choose an appropriate reader automatically.
 from . import NAMDBIN
 from . import FHIAIMS
 from . import TNG
+from . import MMCIF
diff --git a/package/MDAnalysis/topology/MMCIFParser.py b/package/MDAnalysis/topology/MMCIFParser.py
new file mode 100644
index 00000000000..1278f398ae7
--- /dev/null
+++ b/package/MDAnalysis/topology/MMCIFParser.py
@@ -0,0 +1,233 @@
+# -*- Mode: python; tab-width: 4; indent-tabs-mode:nil; coding:utf-8 -*-
+# vim: tabstop=4 expandtab shiftwidth=4 softtabstop=4
+#
+"""
+MMCIF Topology Parser
+=====================
+
+.. versionadded:: 2.11.0
+
+Read topology information from mmCIF/PDBx coordinate files using the
+`Gemmi library <https://gemmi.readthedocs.io>`_.
+
+
+
+mmCIF files contain topology information about the molecules in the
+structure. For each atom the following attributes are read and stored
+in the relevant topology attributes:
+
+    - :class:`MDAnalysis.core.topologyattrs.AtomAttr` subclasses:
+        - :class:`MDAnalysis.core.topologyattrs.AltLocs`
+        - :class:`MDAnalysis.core.topologyattrs.Atomids`
+        - :class:`MDAnalysis.core.topologyattrs.Atomnames`
+        - :class:`MDAnalysis.core.topologyattrs.Atomtypes`
+        - :class:`MDAnalysis.core.topologyattrs.ChainIDs`
+        - :class:`MDAnalysis.core.topologyattrs.Elements`
+        - :class:`MDAnalysis.core.topologyattrs.FormalCharges`
+        - :class:`MDAnalysis.core.topologyattrs.Masses`
+        - :class:`MDAnalysis.core.topologyattrs.Occupancies`
+        - :class:`MDAnalysis.core.topologyattrs.RecordTypes`
+        - :class:`MDAnalysis.core.topologyattrs.Tempfactors`
+    - :class:`MDAnalysis.core.topologyattrs.ResidueAttr` subclasses:
+        - :class:`MDAnalysis.core.topologyattrs.Resnums`
+        - :class:`MDAnalysis.core.topologyattrs.ICodes`
+        - :class:`MDAnalysis.core.topologyattrs.Resids`
+        - :class:`MDAnalysis.core.topologyattrs.Resnames`
+    - :class:`MDAnalysis.core.topologyattrs.SegmentAttr` subclasses:
+        - :class:`MDAnalysis.core.topologyattrs.Segids`
+
+Classes
+-------
+
+.. autoclass:: MMCIFParser
+   :members:
+   :inherited-members:
+
+"""
+
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from gemmi import Structure
+
+import logging
+import warnings
+
+import numpy as np
+
+from ..coordinates.MMCIF import HAS_GEMMI, _read_gemmi_structure
+from ..core.topology import Topology
+from ..core.topologyattrs import (
+    AltLocs,
+    Atomids,
+    Atomnames,
+    Atomtypes,
+    ChainIDs,
+    Elements,
+    FormalCharges,
+    ICodes,
+    Masses,
+    Occupancies,
+    RecordTypes,
+    Resids,
+    Resnames,
+    Resnums,
+    Segids,
+    Tempfactors,
+)
+from .base import TopologyReaderBase, change_squash
+
+logger = logging.getLogger("MDAnalysis.topology.MMCIFParser")
+
+
+class MMCIFParser(TopologyReaderBase):
+    """Parser that obtains a list of atoms from a standard MMCIF/PDBx file using
+    the `gemmi library <https://gemmi.readthedocs.io>`_.
+
+    The *filename* argument accepts a file path, a compressed ``.cif.gz`` file,
+    or a stream/file-like object.
+
+    Creates the following Attributes (if present):
+        - :class:`MDAnalysis.core.topologyattrs.AtomAttr` subclasses:
+            - :class:`MDAnalysis.core.topologyattrs.AltLocs`
+            - :class:`MDAnalysis.core.topologyattrs.Atomids`
+            - :class:`MDAnalysis.core.topologyattrs.Atomnames`
+            - :class:`MDAnalysis.core.topologyattrs.Atomtypes`
+            - :class:`MDAnalysis.core.topologyattrs.ChainIDs`
+            - :class:`MDAnalysis.core.topologyattrs.Elements`
+            - :class:`MDAnalysis.core.topologyattrs.FormalCharges`
+            - :class:`MDAnalysis.core.topologyattrs.Masses`
+            - :class:`MDAnalysis.core.topologyattrs.Occupancies`
+            - :class:`MDAnalysis.core.topologyattrs.RecordTypes`
+            - :class:`MDAnalysis.core.topologyattrs.Tempfactors`
+        - :class:`MDAnalysis.core.topologyattrs.ResidueAttr` subclasses:
+            - :class:`MDAnalysis.core.topologyattrs.Resnums`
+            - :class:`MDAnalysis.core.topologyattrs.ICodes`
+            - :class:`MDAnalysis.core.topologyattrs.Resids`
+            - :class:`MDAnalysis.core.topologyattrs.Resnames`
+        - :class:`MDAnalysis.core.topologyattrs.SegmentAttr` subclasses:
+            - :class:`MDAnalysis.core.topologyattrs.Segids`
+    """
+
+    format = ["cif", "cif.gz", "mmcif", "mmcif.gz"]
+
+    def __init__(self, filename):
+        if not HAS_GEMMI:
+            errmsg = (
+                "MMCIFParser: To read a Topology from an mmCIF file, "
+                "please install gemmi"
+            )
+            raise ImportError(errmsg)
+        super(MMCIFParser, self).__init__(filename)
+
+    def parse(self, **kwargs) -> Topology:
+        """Read the file and return the structure.
+
+        Returns
+        -------
+        MDAnalysis Topology object
+        """
+        structure = self._get_structure()
+
+        if len(structure) > 1:
+            wmsg = (
+                f"MMCIF model {self.filename} contains {len(structure)} different models, "
+                "but only the first one will be used to assign the topology"
+            )
+            warnings.warn(wmsg)
+            logger.warning(wmsg)
+        model = structure[0]
+
+        # TODO: gemmi.FlatStructure provides vectorised column access to all atom
+        # fields and could replace the per-atom Python loop below for a speed-up
+        # on large structures. gemmi API is still not 100% there yes so worth revisiting
+        # later once it matures more
+        altlocs = []
+        serials = []
+        names = []
+        chainids = []
+        elements = []
+        formalcharges = []
+        weights = []
+        occupancies = []
+        record_types = []
+        tempfactors = []
+        icodes = []
+        resids = []
+        resnames = []
+
+        for chain in model:
+            for residue in chain:
+                match residue.het_flag:
+                    case "A":
+                        rec = "ATOM"
+                    case "H":
+                        rec = "HETATM"
+                    case _:
+                        raise ValueError(
+                            "Found an atom that is neither ATOM nor HETATM"
+                        )
+                for atom in residue:
+                    altlocs.append(atom.altloc if atom.has_altloc() else "")
+                    serials.append(atom.serial)
+                    names.append(atom.name)
+                    chainids.append(chain.name)
+                    elements.append(atom.element.name)
+                    formalcharges.append(atom.charge)
+                    weights.append(atom.element.weight)
+                    occupancies.append(atom.occ)
+                    record_types.append(rec)
+                    tempfactors.append(atom.b_iso)
+                    icodes.append(residue.seqid.icode.strip())
+                    resids.append(residue.seqid.num)
+                    resnames.append(residue.name)
+
+        # Atom Attributes
+        attrs = [
+            AltLocs(altlocs),
+            Atomids(serials),
+            Atomnames(names),
+            Atomtypes(names),
+            # ----------------------------
+            ChainIDs(chainids),
+            Elements(elements),
+            FormalCharges(formalcharges),
+            Masses(weights),
+            # ----------------------------
+            Occupancies(occupancies),
+            RecordTypes(record_types),
+            Tempfactors(tempfactors),
+        ]
+        n_atoms = len(altlocs)
+
+        # Residue Attributes
+        resids = np.array(resids)
+        resnames = np.array(resnames)
+        icodes = np.array(icodes)
+        chainids = np.array(chainids)
+        residx, (resids, resnames, icodes, chainids) = change_squash(
+            (resids, resnames, icodes, chainids),
+            (resids, resnames, icodes, chainids),
+        )
+        attrs.append(Resids(resids))
+        attrs.append(Resnames(resnames))
+        attrs.append(Resnums(resids.copy()))
+        attrs.append(ICodes(icodes))
+        n_residues = len(resids)
+
+        # Segment Attributes
+        segidx, (segids,) = change_squash((chainids,), (chainids,))
+        attrs.append(Segids(segids))
+        n_segments = len(segids)
+
+        return Topology(
+            n_atoms,
+            n_residues,
+            n_segments,
+            attrs=attrs,
+            atom_resindex=residx,
+            residue_segindex=segidx,
+        )
+
+    def _get_structure(self) -> "Structure":
+        return _read_gemmi_structure(self.filename)
diff --git a/package/MDAnalysis/topology/PDBParser.py b/package/MDAnalysis/topology/PDBParser.py
index b168b0a67ae..9d62c876722 100644
--- a/package/MDAnalysis/topology/PDBParser.py
+++ b/package/MDAnalysis/topology/PDBParser.py
@@ -50,9 +50,21 @@
    Partial charges are not set. Elements are parsed if they are
    valid. If partially missing or incorrect, empty records are assigned.
 
+.. Note::
+
+   You can also use :mod:`~MDAnalysis.topology.MMCIFParser` to parse PDB files
+   that you're having trouble parsing with the standard PDB parser. For example::
+
+       import MDAnalysis as mda
+       u = mda.Universe("problematic.pdb", topology_format="MMCIF")
+
+   ``MMCIFParser`` uses the `gemmi <https://gemmi.readthedocs.io>`_ library,
+   which is developed together with RCSB and may handle edge cases better.
+
 See Also
 --------
 * :mod:`MDAnalysis.topology.ExtendedPDBParser`
+* :mod:`MDAnalysis.topology.MMCIFParser`
 * :class:`MDAnalysis.coordinates.PDB.PDBReader`
 * :class:`MDAnalysis.core.universe.Universe`
 
@@ -149,16 +161,22 @@ def hy36decode(width, s):
     int
         Base-10 integer corresponding to hybrid36.
     """
-    if (len(s) == width):
+    if len(s) == width:
         f = s[0]
-        if (f == "-" or f == " " or f.isdigit()):
+        if f == "-" or f == " " or f.isdigit():
             return int(s)
-        elif (f in DIGITS_UPPER_VALUES):
-            return decode_pure(digits_values=DIGITS_UPPER_VALUES,
-                               s=s) - 10 * 36 ** (width - 1) + 10 ** width
-        elif (f in DIGITS_LOWER_VALUES):
-            return decode_pure(digits_values=DIGITS_LOWER_VALUES,
-                               s=s) + 16 * 36 ** (width - 1) + 10 ** width
+        elif f in DIGITS_UPPER_VALUES:
+            return (
+                decode_pure(digits_values=DIGITS_UPPER_VALUES, s=s)
+                - 10 * 36 ** (width - 1)
+                + 10**width
+            )
+        elif f in DIGITS_LOWER_VALUES:
+            return (
+                decode_pure(digits_values=DIGITS_LOWER_VALUES, s=s)
+                + 16 * 36 ** (width - 1)
+                + 10**width
+            )
     raise ValueError("invalid number literal.")
 
 
@@ -217,7 +235,8 @@ class PDBParser(TopologyReaderBase):
         be generated if the segids is not present or if the chainids are not
         completely equal to segids.
     """
-    format = ['PDB', 'ENT']
+
+    format = ["PDB", "ENT"]
 
     def parse(self, **kwargs):
         """Parse atom information from PDB file
@@ -231,11 +250,11 @@ def parse(self, **kwargs):
         try:
             bonds = self._parsebonds(top.ids.values)
         except AttributeError:
-            warnings.warn("Invalid atom serials were present, "
-                          "bonds will not be parsed")
+            warnings.warn(
+                "Invalid atom serials were present, " "bonds will not be parsed"
+            )
         except RuntimeError:
-            warnings.warn("CONECT records was corrupt, "
-                          "bonds will not be parsed")
+            warnings.warn("CONECT records was corrupt, " "bonds will not be parsed")
         else:
             # Issue 2832: don't append Bonds if there are no bonds
             if bonds:
@@ -268,9 +287,9 @@ def _parseatoms(self, **kwargs):
                 line = line.strip()  # Remove extra spaces
                 if not line:  # Skip line if empty
                     continue
-                if line.startswith('END'):
+                if line.startswith("END"):
                     break
-                if not line.startswith(('ATOM', 'HETATM')):
+                if not line.startswith(("ATOM", "HETATM")):
                     continue
 
                 record_types.append(line[:6].strip())
@@ -306,8 +325,9 @@ def _parseatoms(self, **kwargs):
                             resid += 10000
                         resid_prev = resid
                 except ValueError:
-                    warnings.warn("PDB file is missing resid information.  "
-                                  "Defaulted to '1'")
+                    warnings.warn(
+                        "PDB file is missing resid information.  " "Defaulted to '1'"
+                    )
                     resid = 1
                 finally:
                     resids.append(resid)
@@ -320,8 +340,9 @@ def _parseatoms(self, **kwargs):
 
         # Warn about wrapped serials
         if self._wrapped_serials:
-            warnings.warn("Serial numbers went over 100,000.  "
-                          "Higher serials have been guessed")
+            warnings.warn(
+                "Serial numbers went over 100,000.  " "Higher serials have been guessed"
+            )
 
         # If segids is not equal to chainids, warn the user
         if any([a != b for a, b in zip(segids, chainids)]):
@@ -329,14 +350,17 @@ def _parseatoms(self, **kwargs):
 
         # If segids not present, try to use chainids
         if not any(segids):
-            logger.info("Setting segids from chainIDs because no segids "
-                        "found in the PDB file.")
+            logger.info(
+                "Setting segids from chainIDs because no segids "
+                "found in the PDB file."
+            )
             segids = chainids
 
         # If force_chainids_to_segids is set, use chainids as segids
         if kwargs.get("force_chainids_to_segids", False):
-            logger.info("force_chainids_to_segids is set. "
-                        "Using chain IDs as segment IDs.")
+            logger.info(
+                "force_chainids_to_segids is set. " "Using chain IDs as segment IDs."
+            )
             segids = chainids
 
         n_atoms = len(serials)
@@ -344,13 +368,13 @@ def _parseatoms(self, **kwargs):
         attrs = []
         # Make Atom TopologyAttrs
         for vals, Attr, dtype in (
-                (names, Atomnames, object),
-                (altlocs, AltLocs, object),
-                (chainids, ChainIDs, object),
-                (record_types, RecordTypes, object),
-                (serials, Atomids, np.int32),
-                (tempfactors, Tempfactors, np.float32),
-                (occupancies, Occupancies, np.float32),
+            (names, Atomnames, object),
+            (altlocs, AltLocs, object),
+            (chainids, ChainIDs, object),
+            (record_types, RecordTypes, object),
+            (serials, Atomids, np.int32),
+            (tempfactors, Tempfactors, np.float32),
+            (occupancies, Occupancies, np.float32),
         ):
             attrs.append(Attr(np.array(vals, dtype=dtype)))
         # OPT: We do this check twice, maybe could refactor to avoid this
@@ -364,41 +388,47 @@ def _parseatoms(self, **kwargs):
                 if elem.capitalize() in SYMB2Z:
                     validated_elements.append(elem.capitalize())
                 else:
-                    wmsg = (f"Unknown element {elem} found for some atoms. "
-                            f"These have been given an empty element record. "
-                            f"If needed they can be guessed using "
-                            f"universe.guess_TopologyAttrs(context='default',"
-                            " to_guess=['elements']).")
+                    wmsg = (
+                        f"Unknown element {elem} found for some atoms. "
+                        f"These have been given an empty element record. "
+                        f"If needed they can be guessed using "
+                        f"universe.guess_TopologyAttrs(context='default',"
+                        " to_guess=['elements'])."
+                    )
                     warnings.warn(wmsg)
-                    validated_elements.append('')
+                    validated_elements.append("")
             attrs.append(Elements(np.array(validated_elements, dtype=object)))
         else:
-            warnings.warn("Element information is missing, elements attribute "
-                          "will not be populated. If needed these can be"
-                          " guessed using universe.guess_TopologyAttrs("
-                          "context='default', to_guess=['elements']).")
+            warnings.warn(
+                "Element information is missing, elements attribute "
+                "will not be populated. If needed these can be"
+                " guessed using universe.guess_TopologyAttrs("
+                "context='default', to_guess=['elements'])."
+            )
 
         if any(formalcharges):
             try:
                 for i, entry in enumerate(formalcharges):
-                    if not entry == '':
-                        if entry == '0':
+                    if not entry == "":
+                        if entry == "0":
                             # Technically a lack of charge shouldn't be in the
                             # PDB but MDA has a few files that specifically
                             # have 0 entries, indicating that some folks
                             # interpret 0 as an allowed entry
                             formalcharges[i] = 0
-                        elif ('+' in entry) or ('-' in entry):
+                        elif ("+" in entry) or ("-" in entry):
                             formalcharges[i] = int(entry[::-1])
                         else:
                             raise ValueError
                     else:
                         formalcharges[i] = 0
             except ValueError:
-                wmsg = (f"Unknown entry {entry} encountered in formal charge "
-                        "field. This likely indicates that the PDB file is "
-                        "not fully standard compliant. The formalcharges "
-                        "attribute will not be populated.")
+                wmsg = (
+                    f"Unknown entry {entry} encountered in formal charge "
+                    "field. This likely indicates that the PDB file is "
+                    "not fully standard compliant. The formalcharges "
+                    "attribute will not be populated."
+                )
                 warnings.warn(wmsg)
             else:
                 attrs.append(FormalCharges(np.array(formalcharges, dtype=int)))
@@ -406,38 +436,45 @@ def _parseatoms(self, **kwargs):
         # Residue level stuff from here
         resids = np.array(resids, dtype=np.int32)
         resnames = np.array(resnames, dtype=object)
-        if self.format == 'XPDB':  # XPDB doesn't have icodes
-            icodes = [''] * n_atoms
+        if self.format == "XPDB":  # XPDB doesn't have icodes
+            icodes = [""] * n_atoms
         icodes = np.array(icodes, dtype=object)
         resnums = resids.copy()
         segids = np.array(segids, dtype=object)
 
         residx, (resids, resnames, icodes, resnums, segids) = change_squash(
-            (resids, resnames, icodes, segids), (resids, resnames, icodes, resnums, segids))
+            (resids, resnames, icodes, segids),
+            (resids, resnames, icodes, resnums, segids),
+        )
         n_residues = len(resids)
         attrs.append(Resnums(resnums))
         attrs.append(Resids(resids))
         attrs.append(ICodes(icodes))
         attrs.append(Resnames(resnames))
 
-        if (
-            kwargs.get("force_chainids_to_segids", False) or
-            (any(segids) and not any(val is None for val in segids))
+        if kwargs.get("force_chainids_to_segids", False) or (
+            any(segids) and not any(val is None for val in segids)
         ):
             segidx, (segids,) = change_squash((segids,), (segids,))
             n_segments = len(segids)
             attrs.append(Segids(segids))
         else:
             n_segments = 1
-            attrs.append(Segids(np.array(['SYSTEM'], dtype=object)))
+            attrs.append(Segids(np.array(["SYSTEM"], dtype=object)))
             segidx = None
-            logger.info("Segment/chain ID is empty, "
-                        "setting segids to default value 'SYSTEM'.")
-
-        top = Topology(n_atoms, n_residues, n_segments,
-                       attrs=attrs,
-                       atom_resindex=residx,
-                       residue_segindex=segidx)
+            logger.info(
+                "Segment/chain ID is empty, "
+                "setting segids to default value 'SYSTEM'."
+            )
+
+        top = Topology(
+            n_atoms,
+            n_residues,
+            n_segments,
+            attrs=attrs,
+            atom_resindex=residx,
+            residue_segindex=segidx,
+        )
 
         return top
 
@@ -450,8 +487,9 @@ def _parsebonds(self, serials):
 
         # If the serials wrapped, this won't work
         if self._wrapped_serials:
-            warnings.warn("Invalid atom serials were present, bonds will not"
-                          " be parsed")
+            warnings.warn(
+                "Invalid atom serials were present, bonds will not" " be parsed"
+            )
             raise AttributeError  # gets caught in parse
 
         # Mapping between the atom array indicies a.index and atom ids
@@ -471,7 +509,8 @@ def _parsebonds(self, serials):
                         # Ignore these as they are not real atoms
                         warnings.warn(
                             "PDB file contained CONECT record to TER entry. "
-                            "These are not included in bonds.")
+                            "These are not included in bonds."
+                        )
                     else:
                         bonds.add(bond)
 
@@ -505,13 +544,14 @@ def _parse_conect(conect):
 
     try:
         if len(conect[11:]) % n_bond_atoms != 0:
-            raise RuntimeError("Bond atoms aren't aligned proberly for CONECT "
-                               "record: {}".format(conect))
+            raise RuntimeError(
+                "Bond atoms aren't aligned proberly for CONECT "
+                "record: {}".format(conect)
+            )
     except ZeroDivisionError:
         # Conect record with only one entry (CONECT A\n)
         warnings.warn("Found CONECT record with single entry, ignoring this")
         return atom_id, []  # return empty list to allow iteration over nothing
 
-    bond_atoms = (int(conect[11 + i * 5: 16 + i * 5]) for i in
-                  range(n_bond_atoms))
+    bond_atoms = (int(conect[11 + i * 5 : 16 + i * 5]) for i in range(n_bond_atoms))
     return atom_id, bond_atoms
diff --git a/package/MDAnalysis/topology/__init__.py b/package/MDAnalysis/topology/__init__.py
index 945deaf4369..e1d419c01ca 100644
--- a/package/MDAnalysis/topology/__init__.py
+++ b/package/MDAnalysis/topology/__init__.py
@@ -156,6 +156,18 @@
                                 bonds, angles,    angles, and dihedrals.
                                 dihedrals         :mod:`MDAnalysis.topology.GSDParser`
 
+   MMCIF [#a]_       cif,       ids, names,       macromolecular structures in the `PDBx/mmCIF`_
+                     mmcif      types, altLocs,   format, as distributed by, e.g., the RCSB PDB
+                                chainids,         (requires the gemmi_ package);
+                                elements, masses, :mod:`MDAnalysis.topology.MMCIFParser`
+                                formalcharges,
+                                occupancies,
+                                tempfactors,
+                                record_types,
+                                resids, resnames,
+                                resnums, icodes,
+                                segids
+
    MMTF [#a]_        mmtf       altLocs,          `Macromolecular Transmission Format (MMTF)`_. An
                                 tempfactors,      efficient compact format for biomolecular
                                 charges, masses,  structures.
@@ -206,6 +218,8 @@
 .. _AutoDock: http://autodock.scripps.edu/
 .. _APBS: https://apbs.readthedocs.io/en/latest/
 .. _Macromolecular Transmission Format (MMTF): https://www.rcsb.org/news/feature/65a1af31c76ca3abcc925d0c
+.. _PDBx/mmCIF: https://mmcif.wwpdb.org/
+.. _gemmi: https://gemmi.readthedocs.io/
 .. _FHI-AIMS: https://aimsclub.fhi-berlin.mpg.de/
 .. _GAMESS: https://www.msg.chem.iastate.edu/gamess/
 
@@ -311,31 +325,56 @@
 
 """
 
-__all__ = ['core', 'PSFParser', 'PDBParser', 'PQRParser', 'GROParser',
-           'CRDParser', 'TOPParser', 'PDBQTParser', 'TPRParser',
-           'LAMMPSParser', 'XYZParser', 'GMSParser', 'DLPolyParser',
-           'HoomdXMLParser','GSDParser', 'ITPParser']
-
-from . import core
-from . import PSFParser
-from . import TOPParser
-from . import PDBParser
-from . import ExtendedPDBParser
-from . import PQRParser
-from . import GROParser
-from . import CRDParser
-from . import PDBQTParser
-from . import DMSParser
-from . import TPRParser
-from . import MOL2Parser
-from . import LAMMPSParser
-from . import XYZParser
-from . import TXYZParser
-from . import GMSParser
-from . import DLPolyParser
-from . import HoomdXMLParser
-from . import MMTFParser
-from . import GSDParser
-from . import MinimalParser
-from . import ITPParser
-from . import FHIAIMSParser
+__all__ = [
+    "CRDParser",
+    "DLPolyParser",
+    "DMSParser",
+    "ExtendedPDBParser",
+    "FHIAIMSParser",
+    "GMSParser",
+    "GROParser",
+    "GSDParser",
+    "HoomdXMLParser",
+    "ITPParser",
+    "LAMMPSParser",
+    "MinimalParser",
+    "MMCIFParser",
+    "MMTFParser",
+    "MOL2Parser",
+    "PDBParser",
+    "PDBQTParser",
+    "PQRParser",
+    "PSFParser",
+    "TOPParser",
+    "TPRParser",
+    "TXYZParser",
+    "XYZParser",
+    "core",
+]
+
+from . import (
+    CRDParser,
+    DLPolyParser,
+    DMSParser,
+    ExtendedPDBParser,
+    FHIAIMSParser,
+    GMSParser,
+    GROParser,
+    GSDParser,
+    HoomdXMLParser,
+    ITPParser,
+    LAMMPSParser,
+    MinimalParser,
+    MMCIFParser,
+    MMTFParser,
+    MOL2Parser,
+    PDBParser,
+    PDBQTParser,
+    PQRParser,
+    PSFParser,
+    TOPParser,
+    TPRParser,
+    TXYZParser,
+    XYZParser,
+    core,
+)
diff --git a/package/doc/sphinx/source/conf.py b/package/doc/sphinx/source/conf.py
index 3309e3115bd..2bf8944d0cd 100644
--- a/package/doc/sphinx/source/conf.py
+++ b/package/doc/sphinx/source/conf.py
@@ -356,5 +356,6 @@ class KeyStyle(UnsrtStyle):
     "imdclient": ("https://imdclient.readthedocs.io/en/stable/", None),
     "pooch": ("https://www.fatiando.org/pooch/latest/", None),
     "requests": ("https://requests.readthedocs.io/en/latest/", None),
+    "gemmi": ("https://gemmi.readthedocs.io/en/latest/", None),
     "filelock": ("https://py-filelock.readthedocs.io/en/latest/", None),
 }
diff --git a/package/doc/sphinx/source/documentation_pages/coordinates/MMCIF.rst b/package/doc/sphinx/source/documentation_pages/coordinates/MMCIF.rst
new file mode 100644
index 00000000000..f769bd846f5
--- /dev/null
+++ b/package/doc/sphinx/source/documentation_pages/coordinates/MMCIF.rst
@@ -0,0 +1,2 @@
+.. automodule:: MDAnalysis.coordinates.MMCIF
+
diff --git a/package/doc/sphinx/source/documentation_pages/coordinates_modules.rst b/package/doc/sphinx/source/documentation_pages/coordinates_modules.rst
index 8a27767f23f..23ea833aa22 100644
--- a/package/doc/sphinx/source/documentation_pages/coordinates_modules.rst
+++ b/package/doc/sphinx/source/documentation_pages/coordinates_modules.rst
@@ -31,6 +31,7 @@ provide the format in the keyword argument *format* to
    coordinates/INPCRD
    coordinates/LAMMPS
    coordinates/MMTF
+   coordinates/MMCIF
    coordinates/MOL2
    coordinates/NAMDBIN
    coordinates/PDB
diff --git a/package/doc/sphinx/source/documentation_pages/topology/MMCIFParser.rst b/package/doc/sphinx/source/documentation_pages/topology/MMCIFParser.rst
new file mode 100644
index 00000000000..6b31bb012a4
--- /dev/null
+++ b/package/doc/sphinx/source/documentation_pages/topology/MMCIFParser.rst
@@ -0,0 +1 @@
+.. automodule:: MDAnalysis.topology.MMCIFParser
diff --git a/package/doc/sphinx/source/documentation_pages/topology_modules.rst b/package/doc/sphinx/source/documentation_pages/topology_modules.rst
index e1f818adabf..03582e4465e 100644
--- a/package/doc/sphinx/source/documentation_pages/topology_modules.rst
+++ b/package/doc/sphinx/source/documentation_pages/topology_modules.rst
@@ -9,7 +9,7 @@ files. MDAnalysis uses topology files to identify atoms and bonds
 between the atoms. It can use topology files from MD packages such as
 CHARMM's and NAMD's PSF format or Amber's PRMTOP files. In addition,
 it can also glean atom information from single frame coordinate files
-such the PDB, CRD, or PQR formats (see the :ref:`Supported topology
+such the PDB, CRD, MMCIF, or PQR formats (see the :ref:`Supported topology
 formats`).
 
 Typically, MDAnalysis recognizes formats by the file extension and
@@ -38,6 +38,7 @@ topology file format in the *topology_format* keyword argument to
    topology/MinimalParser
    topology/MMTFParser
    topology/MOL2Parser
+   topology/MMCIFParser
    topology/PDBParser
    topology/ExtendedPDBParser
    topology/PDBQTParser
diff --git a/package/pyproject.toml b/package/pyproject.toml
index 3ff785f7bd0..36da16ab107 100644
--- a/package/pyproject.toml
+++ b/package/pyproject.toml
@@ -76,6 +76,7 @@ extra_formats = [
     "pyedr>=0.7.0",
     "pytng>=0.2.3",
     "gsd>3.0.0",
+    "gemmi>=0.7.3",     # for mmcif format
     "rdkit>=2022.09.1",
     "imdclient>=0.2.2",
 ]
diff --git a/testsuite/MDAnalysisTests/coordinates/test_mmcif.py b/testsuite/MDAnalysisTests/coordinates/test_mmcif.py
new file mode 100644
index 00000000000..e2f4d7ed749
--- /dev/null
+++ b/testsuite/MDAnalysisTests/coordinates/test_mmcif.py
@@ -0,0 +1,127 @@
+import glob
+from pathlib import Path
+
+import MDAnalysis as mda
+import numpy as np
+import pytest
+from MDAnalysis.coordinates.MMCIF import HAS_GEMMI
+
+from MDAnalysisTests.datafiles import MMCIF as MMCIF_FOLDER
+
+
+@pytest.mark.skipif(not HAS_GEMMI, reason="gemmi not installed")
+@pytest.mark.parametrize(
+    "mmcif_filename",
+    [
+        f
+        for f in glob.glob(f"{MMCIF_FOLDER}/*.cif.gz")
+        if "invalid" not in f
+        and "warning" not in f
+        and Path(f).with_suffix("").with_suffix(".pdb.gz").exists()
+    ],
+)
+@pytest.mark.filterwarnings("ignore::UserWarning")
+def test_legacy_pdb_vs_mmcif(mmcif_filename):
+    u_cif = mda.Universe(mmcif_filename)
+    u_pdb = mda.Universe(
+        Path(mmcif_filename).with_suffix("").with_suffix(".pdb.gz")
+    )
+    assert len(u_cif.residues) == len(u_pdb.residues)
+    assert len(u_cif.atoms) == len(u_pdb.atoms)
+
+
+@pytest.mark.skipif(not HAS_GEMMI, reason="gemmi not installed")
+@pytest.mark.parametrize(
+    "mmcif_filename",
+    [
+        f
+        for f in glob.glob(f"{MMCIF_FOLDER}/*.cif*")
+        if "invalid" not in f and "warning" not in f
+    ],
+)
+@pytest.mark.filterwarnings("ignore::UserWarning")
+def test_works_with_explicit_format(mmcif_filename):
+    u = mda.Universe(mmcif_filename, format="MMCIF")
+    assert u.trajectory.n_atoms > 0
+
+
+@pytest.mark.skipif(not HAS_GEMMI, reason="gemmi not installed")
+@pytest.mark.parametrize(
+    "mmcif_filename",
+    [
+        f
+        for f in glob.glob(f"{MMCIF_FOLDER}/*.cif*")
+        if "invalid" not in f and "warning" not in f
+    ],
+)
+@pytest.mark.filterwarnings("ignore::UserWarning")
+def test_works_without_explicit_format(mmcif_filename):
+    u = mda.Universe(mmcif_filename)
+    assert u.trajectory.n_atoms > 0
+
+
+@pytest.mark.skipif(not HAS_GEMMI, reason="gemmi not installed")
+@pytest.mark.parametrize(
+    "mmcif_filename,natoms_protein,natoms_total",
+    [
+        (f"{MMCIF_FOLDER}/1YJP.cif", 59, 66),
+        (f"{MMCIF_FOLDER}/1YJP.cif.gz", 59, 66),
+        (f"{MMCIF_FOLDER}/7ETN.cif.gz", 150, 150),
+    ],
+)
+def test_n_atoms(mmcif_filename, natoms_protein, natoms_total):
+    u = mda.Universe(mmcif_filename)
+    assert len(u.atoms) == natoms_total
+    assert len(u.select_atoms("protein").atoms) == natoms_protein
+
+
+@pytest.mark.skipif(not HAS_GEMMI, reason="gemmi not installed")
+@pytest.mark.parametrize(
+    "mmcif_filename,cell",
+    [
+        (
+            f"{MMCIF_FOLDER}/1YJP.cif.gz",
+            np.array([21.937, 4.866, 23.477, 90.00, 107.08, 90.00]),
+        ),
+        (
+            f"{MMCIF_FOLDER}/7ETN.cif.gz",
+            np.array([5.264, 24.967, 20.736, 90.00, 94.85, 90.00]),
+        ),
+    ],
+)
+def test_cell(mmcif_filename, cell):
+    assert np.allclose(mda.Universe(mmcif_filename).coord._unitcell, cell)
+
+
+def test_no_gemmi_raises(monkeypatch):
+    monkeypatch.setattr(mda.coordinates.MMCIF, "HAS_GEMMI", False)
+    with pytest.raises(ImportError, match="please install gemmi"):
+        mda.coordinates.MMCIF.MMCIFReader(f"{MMCIF_FOLDER}/1YJP.cif")
+
+
+@pytest.mark.skipif(not HAS_GEMMI, reason="gemmi not installed")
+def test_multimodel_warning_msg():
+    with pytest.warns(
+        UserWarning,
+        match=r"File .+ has .+ models, but only the first one will be read",
+    ):
+        mda.coordinates.MMCIF.MMCIFReader(
+            f"{MMCIF_FOLDER}/multimodel_warning.cif.gz"
+        )
+
+
+@pytest.mark.skipif(not HAS_GEMMI, reason="gemmi not installed")
+def test_cryst1_record_placeholder():
+    with pytest.warns(
+        UserWarning,
+        match=(
+            r"CRYST1 record, this is usually a placeholder. "
+            r"Unit cell dimensions will be set to"
+        ),
+    ):
+        assert (
+            mda.coordinates.MMCIF.MMCIFReader(
+                f"{MMCIF_FOLDER}/custom.cif.gz"
+            ).ts.dimensions
+            is None
+        )
diff --git a/testsuite/MDAnalysisTests/data/mmcif/1BD2.cif.gz b/testsuite/MDAnalysisTests/data/mmcif/1BD2.cif.gz
new file mode 100644
index 00000000000..bc153df52b4
Binary files /dev/null and b/testsuite/MDAnalysisTests/data/mmcif/1BD2.cif.gz differ
diff --git a/testsuite/MDAnalysisTests/data/mmcif/1BD2.pdb.gz b/testsuite/MDAnalysisTests/data/mmcif/1BD2.pdb.gz
new file mode 100644
index 00000000000..3c5409d1c7c
Binary files /dev/null and b/testsuite/MDAnalysisTests/data/mmcif/1BD2.pdb.gz differ
diff --git a/testsuite/MDAnalysisTests/data/mmcif/1BD2_short.cif.gz b/testsuite/MDAnalysisTests/data/mmcif/1BD2_short.cif.gz
new file mode 100644
index 00000000000..9b42f51a25c
Binary files /dev/null and b/testsuite/MDAnalysisTests/data/mmcif/1BD2_short.cif.gz differ
diff --git a/testsuite/MDAnalysisTests/data/mmcif/1BD2_short.pdb.gz b/testsuite/MDAnalysisTests/data/mmcif/1BD2_short.pdb.gz
new file mode 100644
index 00000000000..7159b186506
Binary files /dev/null and b/testsuite/MDAnalysisTests/data/mmcif/1BD2_short.pdb.gz differ
diff --git a/testsuite/MDAnalysisTests/data/mmcif/1YJP.cif b/testsuite/MDAnalysisTests/data/mmcif/1YJP.cif
new file mode 100644
index 00000000000..b0e30c0ddc6
--- /dev/null
+++ b/testsuite/MDAnalysisTests/data/mmcif/1YJP.cif
@@ -0,0 +1,813 @@
+data_1YJP
+# 
+_entry.id   1YJP 
+# 
+_audit.revision_id     1 
+_audit.creation_date   2005-01-14 
+_audit.update_record   'initial release' 
+# 
+_audit_conform.dict_name       mmcif_pdbx.dic 
+_audit_conform.dict_version    5.387 
+_audit_conform.dict_location   http://mmcif.pdb.org/dictionaries/ascii/mmcif_pdbx.dic 
+# 
+loop_
+_database_2.database_id 
+_database_2.database_code 
+_database_2.pdbx_database_accession 
+_database_2.pdbx_DOI 
+PDB   1YJP         pdb_00001yjp 10.2210/pdb1yjp/pdb 
+RCSB  RCSB031590   ?            ?                   
+WWPDB D_1000031590 ?            ?                   
+# 
+loop_
+_pdbx_audit_revision_history.ordinal 
+_pdbx_audit_revision_history.data_content_type 
+_pdbx_audit_revision_history.major_revision 
+_pdbx_audit_revision_history.minor_revision 
+_pdbx_audit_revision_history.revision_date 
+1 'Structure model' 1 0 2005-06-14 
+2 'Structure model' 1 1 2008-04-30 
+3 'Structure model' 1 2 2011-07-13 
+4 'Structure model' 1 3 2017-10-11 
+5 'Structure model' 1 4 2024-02-14 
+# 
+_pdbx_audit_revision_details.ordinal             1 
+_pdbx_audit_revision_details.revision_ordinal    1 
+_pdbx_audit_revision_details.data_content_type   'Structure model' 
+_pdbx_audit_revision_details.provider            repository 
+_pdbx_audit_revision_details.type                'Initial release' 
+_pdbx_audit_revision_details.description         ? 
+_pdbx_audit_revision_details.details             ? 
+# 
+loop_
+_pdbx_audit_revision_group.ordinal 
+_pdbx_audit_revision_group.revision_ordinal 
+_pdbx_audit_revision_group.data_content_type 
+_pdbx_audit_revision_group.group 
+1 2 'Structure model' 'Version format compliance' 
+2 3 'Structure model' 'Version format compliance' 
+3 4 'Structure model' 'Refinement description'    
+4 5 'Structure model' 'Data collection'           
+5 5 'Structure model' 'Database references'       
+# 
+loop_
+_pdbx_audit_revision_category.ordinal 
+_pdbx_audit_revision_category.revision_ordinal 
+_pdbx_audit_revision_category.data_content_type 
+_pdbx_audit_revision_category.category 
+1 4 'Structure model' software       
+2 5 'Structure model' chem_comp_atom 
+3 5 'Structure model' chem_comp_bond 
+4 5 'Structure model' database_2     
+# 
+loop_
+_pdbx_audit_revision_item.ordinal 
+_pdbx_audit_revision_item.revision_ordinal 
+_pdbx_audit_revision_item.data_content_type 
+_pdbx_audit_revision_item.item 
+1 5 'Structure model' '_database_2.pdbx_DOI'                
+2 5 'Structure model' '_database_2.pdbx_database_accession' 
+# 
+_pdbx_database_status.entry_id                        1YJP 
+_pdbx_database_status.deposit_site                    RCSB 
+_pdbx_database_status.process_site                    RCSB 
+_pdbx_database_status.recvd_initial_deposition_date   2005-01-15 
+_pdbx_database_status.status_code                     REL 
+_pdbx_database_status.status_code_sf                  REL 
+_pdbx_database_status.status_code_mr                  ? 
+_pdbx_database_status.SG_entry                        ? 
+_pdbx_database_status.pdb_format_compatible           Y 
+_pdbx_database_status.status_code_cs                  ? 
+_pdbx_database_status.methods_development_category    ? 
+_pdbx_database_status.status_code_nmr_data            ? 
+# 
+_pdbx_database_related.db_name        PDB 
+_pdbx_database_related.db_id          1YJO 
+_pdbx_database_related.details        . 
+_pdbx_database_related.content_type   unspecified 
+# 
+loop_
+_audit_author.name 
+_audit_author.pdbx_ordinal 
+'Nelson, R.'    1 
+'Sawaya, M.R.'  2 
+'Balbirnie, M.' 3 
+'Madsen, A.O.'  4 
+'Riekel, C.'    5 
+'Grothe, R.'    6 
+'Eisenberg, D.' 7 
+# 
+loop_
+_citation.id 
+_citation.title 
+_citation.journal_abbrev 
+_citation.journal_volume 
+_citation.page_first 
+_citation.page_last 
+_citation.year 
+_citation.journal_id_ASTM 
+_citation.country 
+_citation.journal_id_ISSN 
+_citation.journal_id_CSD 
+_citation.book_publisher 
+_citation.pdbx_database_id_PubMed 
+_citation.pdbx_database_id_DOI 
+primary 'Structure of the cross-beta spine of amyloid-like fibrils.'               Nature                     435 773 778 2005 
+NATUAS UK 0028-0836 0006 ? 15944695 10.1038/nature03680 
+1       'Refinement of Macromolecular Structures by the Maximum-Likelihood Method' 'Acta Crystallogr.,Sect.D' 53  240 255 1997 
+ABCRE6 DK 0907-4449 0766 ? ?        ?                   
+# 
+loop_
+_citation_author.citation_id 
+_citation_author.name 
+_citation_author.ordinal 
+_citation_author.identifier_ORCID 
+primary 'Nelson, R.'      1  ? 
+primary 'Sawaya, M.R.'    2  ? 
+primary 'Balbirnie, M.'   3  ? 
+primary 'Madsen, A.O.'    4  ? 
+primary 'Riekel, C.'      5  ? 
+primary 'Grothe, R.'      6  ? 
+primary 'Eisenberg, D.'   7  ? 
+1       'Murshudov, G.N.' 8  ? 
+1       'Vagin, A.A.'     9  ? 
+1       'Dodson, E.J.'    10 ? 
+# 
+loop_
+_entity.id 
+_entity.type 
+_entity.src_method 
+_entity.pdbx_description 
+_entity.formula_weight 
+_entity.pdbx_number_of_molecules 
+_entity.pdbx_ec 
+_entity.pdbx_mutation 
+_entity.pdbx_fragment 
+_entity.details 
+1 polymer syn 'Eukaryotic peptide chain release factor GTP-binding subunit' 836.807 1 ? ? 'prion determining domain of Sup35' ? 
+2 water   nat water                                                         18.015  7 ? ? ?                                   ? 
+# 
+_entity_name_com.entity_id   1 
+_entity_name_com.name        
+'ERF2, Translation release factor 3, ERF3, ERF-3, Omnipotent suppressor protein 2, G1 to S phase transition protein 1' 
+# 
+_entity_poly.entity_id                      1 
+_entity_poly.type                           'polypeptide(L)' 
+_entity_poly.nstd_linkage                   no 
+_entity_poly.nstd_monomer                   no 
+_entity_poly.pdbx_seq_one_letter_code       GNNQQNY 
+_entity_poly.pdbx_seq_one_letter_code_can   GNNQQNY 
+_entity_poly.pdbx_strand_id                 A 
+_entity_poly.pdbx_target_identifier         ? 
+# 
+_pdbx_entity_nonpoly.entity_id   2 
+_pdbx_entity_nonpoly.name        water 
+_pdbx_entity_nonpoly.comp_id     HOH 
+# 
+loop_
+_entity_poly_seq.entity_id 
+_entity_poly_seq.num 
+_entity_poly_seq.mon_id 
+_entity_poly_seq.hetero 
+1 1 GLY n 
+1 2 ASN n 
+1 3 ASN n 
+1 4 GLN n 
+1 5 GLN n 
+1 6 ASN n 
+1 7 TYR n 
+# 
+_pdbx_entity_src_syn.entity_id              1 
+_pdbx_entity_src_syn.pdbx_src_id            1 
+_pdbx_entity_src_syn.pdbx_alt_source_flag   sample 
+_pdbx_entity_src_syn.pdbx_beg_seq_num       ? 
+_pdbx_entity_src_syn.pdbx_end_seq_num       ? 
+_pdbx_entity_src_syn.organism_scientific    ? 
+_pdbx_entity_src_syn.organism_common_name   ? 
+_pdbx_entity_src_syn.ncbi_taxonomy_id       ? 
+_pdbx_entity_src_syn.details                'This sequence is from the prion determining domain of Saccharomyces cerevisiae Sup35' 
+# 
+loop_
+_chem_comp.id 
+_chem_comp.type 
+_chem_comp.mon_nstd_flag 
+_chem_comp.name 
+_chem_comp.pdbx_synonyms 
+_chem_comp.formula 
+_chem_comp.formula_weight 
+ASN 'L-peptide linking' y ASPARAGINE ? 'C4 H8 N2 O3'  132.118 
+GLN 'L-peptide linking' y GLUTAMINE  ? 'C5 H10 N2 O3' 146.144 
+GLY 'peptide linking'   y GLYCINE    ? 'C2 H5 N O2'   75.067  
+HOH non-polymer         . WATER      ? 'H2 O'         18.015  
+TYR 'L-peptide linking' y TYROSINE   ? 'C9 H11 N O3'  181.189 
+# 
+loop_
+_pdbx_poly_seq_scheme.asym_id 
+_pdbx_poly_seq_scheme.entity_id 
+_pdbx_poly_seq_scheme.seq_id 
+_pdbx_poly_seq_scheme.mon_id 
+_pdbx_poly_seq_scheme.ndb_seq_num 
+_pdbx_poly_seq_scheme.pdb_seq_num 
+_pdbx_poly_seq_scheme.auth_seq_num 
+_pdbx_poly_seq_scheme.pdb_mon_id 
+_pdbx_poly_seq_scheme.auth_mon_id 
+_pdbx_poly_seq_scheme.pdb_strand_id 
+_pdbx_poly_seq_scheme.pdb_ins_code 
+_pdbx_poly_seq_scheme.hetero 
+A 1 1 GLY 1 1 1 GLY GLY A . n 
+A 1 2 ASN 2 2 2 ASN ASN A . n 
+A 1 3 ASN 3 3 3 ASN ASN A . n 
+A 1 4 GLN 4 4 4 GLN GLN A . n 
+A 1 5 GLN 5 5 5 GLN GLN A . n 
+A 1 6 ASN 6 6 6 ASN ASN A . n 
+A 1 7 TYR 7 7 7 TYR TYR A . n 
+# 
+loop_
+_pdbx_nonpoly_scheme.asym_id 
+_pdbx_nonpoly_scheme.entity_id 
+_pdbx_nonpoly_scheme.mon_id 
+_pdbx_nonpoly_scheme.ndb_seq_num 
+_pdbx_nonpoly_scheme.pdb_seq_num 
+_pdbx_nonpoly_scheme.auth_seq_num 
+_pdbx_nonpoly_scheme.pdb_mon_id 
+_pdbx_nonpoly_scheme.auth_mon_id 
+_pdbx_nonpoly_scheme.pdb_strand_id 
+_pdbx_nonpoly_scheme.pdb_ins_code 
+B 2 HOH 1 8  8  HOH HOH A . 
+B 2 HOH 2 9  9  HOH HOH A . 
+B 2 HOH 3 10 10 HOH HOH A . 
+B 2 HOH 4 11 11 HOH HOH A . 
+B 2 HOH 5 12 12 HOH HOH A . 
+B 2 HOH 6 13 13 HOH HOH A . 
+B 2 HOH 7 14 14 HOH HOH A . 
+# 
+loop_
+_software.name 
+_software.version 
+_software.date 
+_software.type 
+_software.contact_author 
+_software.contact_author_email 
+_software.classification 
+_software.location 
+_software.language 
+_software.citation_id 
+_software.pdbx_ordinal 
+REFMAC    . ? program 'Murshudov, G.N.' ccp4@dl.ac.uk refinement       http://www.ccp4.ac.uk/main.html Fortran ? 1 
+DENZO     . ? ?       ?                 ?             'data reduction' ?                               ?       ? 2 
+SCALEPACK . ? ?       ?                 ?             'data scaling'   ?                               ?       ? 3 
+# 
+_cell.entry_id           1YJP 
+_cell.length_a           21.937 
+_cell.length_b           4.866 
+_cell.length_c           23.477 
+_cell.angle_alpha        90.00 
+_cell.angle_beta         107.08 
+_cell.angle_gamma        90.00 
+_cell.Z_PDB              2 
+_cell.pdbx_unique_axis   ? 
+# 
+_symmetry.entry_id                         1YJP 
+_symmetry.space_group_name_H-M             'P 1 21 1' 
+_symmetry.pdbx_full_space_group_name_H-M   ? 
+_symmetry.cell_setting                     ? 
+_symmetry.Int_Tables_number                4 
+_symmetry.space_group_name_Hall            ? 
+# 
+_exptl.method            'X-RAY DIFFRACTION' 
+_exptl.entry_id          1YJP 
+_exptl.crystals_number   1 
+# 
+_exptl_crystal.id                    1 
+_exptl_crystal.density_meas          ? 
+_exptl_crystal.density_percent_sol   14.03 
+_exptl_crystal.density_Matthews      1.43 
+_exptl_crystal.description           ? 
+_exptl_crystal.F_000                 ? 
+_exptl_crystal.preparation           ? 
+# 
+_exptl_crystal_grow.crystal_id      1 
+_exptl_crystal_grow.method          'VAPOR DIFFUSION, HANGING DROP' 
+_exptl_crystal_grow.pH              7 
+_exptl_crystal_grow.temp            298 
+_exptl_crystal_grow.temp_details    ? 
+_exptl_crystal_grow.pdbx_details    'water, pH 7, VAPOR DIFFUSION, HANGING DROP, temperature 298K' 
+_exptl_crystal_grow.pdbx_pH_range   . 
+# 
+_diffrn.id                     1 
+_diffrn.ambient_temp           100 
+_diffrn.ambient_temp_details   ? 
+_diffrn.crystal_id             1 
+# 
+_diffrn_detector.diffrn_id              1 
+_diffrn_detector.detector               CCD 
+_diffrn_detector.type                   MARRESEARCH 
+_diffrn_detector.pdbx_collection_date   2004-06-12 
+_diffrn_detector.details                'Ellipsoidal Mirror' 
+# 
+_diffrn_radiation.diffrn_id                        1 
+_diffrn_radiation.wavelength_id                    1 
+_diffrn_radiation.pdbx_diffrn_protocol             'SINGLE WAVELENGTH' 
+_diffrn_radiation.monochromator                    'channel-cut Si-111 monochromator' 
+_diffrn_radiation.pdbx_monochromatic_or_laue_m_l   M 
+_diffrn_radiation.pdbx_scattering_type             x-ray 
+# 
+_diffrn_radiation_wavelength.id           1 
+_diffrn_radiation_wavelength.wavelength   0.975 
+_diffrn_radiation_wavelength.wt           1.0 
+# 
+_diffrn_source.diffrn_id                   1 
+_diffrn_source.source                      SYNCHROTRON 
+_diffrn_source.type                        'ESRF BEAMLINE ID13' 
+_diffrn_source.pdbx_wavelength             0.975 
+_diffrn_source.pdbx_wavelength_list        0.975 
+_diffrn_source.pdbx_synchrotron_site       ESRF 
+_diffrn_source.pdbx_synchrotron_beamline   ID13 
+# 
+_reflns.d_resolution_low             80.00 
+_reflns.d_resolution_high            1.80 
+_reflns.number_obs                   509 
+_reflns.percent_possible_obs         89.5 
+_reflns.pdbx_Rmerge_I_obs            0.204 
+_reflns.pdbx_chi_squared             1.057 
+_reflns.entry_id                     1YJP 
+_reflns.observed_criterion_sigma_F   0 
+_reflns.observed_criterion_sigma_I   0 
+_reflns.number_all                   509 
+_reflns.pdbx_Rsym_value              ? 
+_reflns.pdbx_netI_over_sigmaI        3.75 
+_reflns.B_iso_Wilson_estimate        45.6 
+_reflns.pdbx_redundancy              2.0 
+_reflns.R_free_details               ? 
+_reflns.limit_h_max                  ? 
+_reflns.limit_h_min                  ? 
+_reflns.limit_k_max                  ? 
+_reflns.limit_k_min                  ? 
+_reflns.limit_l_max                  ? 
+_reflns.limit_l_min                  ? 
+_reflns.observed_criterion_F_max     ? 
+_reflns.observed_criterion_F_min     ? 
+_reflns.pdbx_scaling_rejects         ? 
+_reflns.pdbx_diffrn_id               1 
+_reflns.pdbx_ordinal                 1 
+# 
+_reflns_shell.d_res_low              1.94 
+_reflns_shell.d_res_high             1.80 
+_reflns_shell.number_unique_all      85 
+_reflns_shell.percent_possible_all   84.2 
+_reflns_shell.Rmerge_I_obs           0.491 
+_reflns_shell.pdbx_redundancy        ? 
+_reflns_shell.pdbx_chi_squared       1.092 
+_reflns_shell.number_unique_obs      ? 
+_reflns_shell.meanI_over_sigI_obs    1.5 
+_reflns_shell.pdbx_Rsym_value        ? 
+_reflns_shell.percent_possible_obs   ? 
+_reflns_shell.number_measured_all    ? 
+_reflns_shell.number_measured_obs    ? 
+_reflns_shell.pdbx_diffrn_id         ? 
+_reflns_shell.pdbx_ordinal           1 
+# 
+_refine.entry_id                                 1YJP 
+_refine.ls_d_res_high                            1.80 
+_refine.ls_d_res_low                             22.44 
+_refine.pdbx_ls_sigma_F                          0 
+_refine.pdbx_ls_sigma_I                          0 
+_refine.ls_number_reflns_all                     474 
+_refine.ls_number_reflns_obs                     474 
+_refine.ls_number_reflns_R_free                  20 
+_refine.ls_percent_reflns_obs                    ? 
+_refine.ls_R_factor_all                          0.18139 
+_refine.ls_R_factor_obs                          0.18139 
+_refine.ls_R_factor_R_work                       0.18086 
+_refine.ls_R_factor_R_free                       0.19014 
+_refine.ls_redundancy_reflns_obs                 ? 
+_refine.pdbx_data_cutoff_high_absF               ? 
+_refine.pdbx_data_cutoff_low_absF                ? 
+_refine.ls_number_parameters                     ? 
+_refine.ls_number_restraints                     ? 
+_refine.ls_percent_reflns_R_free                 ? 
+_refine.ls_R_factor_R_free_error                 ? 
+_refine.ls_R_factor_R_free_error_details         ? 
+_refine.pdbx_method_to_determine_struct          'FOURIER SYNTHESIS' 
+_refine.pdbx_starting_model                      ? 
+_refine.pdbx_ls_cross_valid_method               THROUGHOUT 
+_refine.pdbx_R_Free_selection_details            RANDOM 
+_refine.pdbx_stereochem_target_val_spec_case     ? 
+_refine.pdbx_stereochemistry_target_values       'Engh & Huber' 
+_refine.solvent_model_details                    ? 
+_refine.solvent_model_param_bsol                 ? 
+_refine.solvent_model_param_ksol                 ? 
+_refine.occupancy_max                            ? 
+_refine.occupancy_min                            ? 
+_refine.pdbx_isotropic_thermal_model             ? 
+_refine.B_iso_mean                               ? 
+_refine.aniso_B[1][1]                            ? 
+_refine.aniso_B[1][2]                            ? 
+_refine.aniso_B[1][3]                            ? 
+_refine.aniso_B[2][2]                            ? 
+_refine.aniso_B[2][3]                            ? 
+_refine.aniso_B[3][3]                            ? 
+_refine.details                                  ? 
+_refine.B_iso_min                                ? 
+_refine.B_iso_max                                ? 
+_refine.correlation_coeff_Fo_to_Fc               ? 
+_refine.correlation_coeff_Fo_to_Fc_free          ? 
+_refine.pdbx_solvent_vdw_probe_radii             ? 
+_refine.pdbx_solvent_ion_probe_radii             ? 
+_refine.pdbx_solvent_shrinkage_radii             ? 
+_refine.overall_SU_R_Cruickshank_DPI             ? 
+_refine.overall_SU_R_free                        ? 
+_refine.overall_SU_B                             ? 
+_refine.overall_SU_ML                            ? 
+_refine.pdbx_overall_ESU_R                       ? 
+_refine.pdbx_overall_ESU_R_Free                  ? 
+_refine.pdbx_data_cutoff_high_rms_absF           ? 
+_refine.ls_wR_factor_R_free                      ? 
+_refine.ls_wR_factor_R_work                      ? 
+_refine.overall_FOM_free_R_set                   ? 
+_refine.overall_FOM_work_R_set                   ? 
+_refine.pdbx_refine_id                           'X-RAY DIFFRACTION' 
+_refine.pdbx_diffrn_id                           1 
+_refine.pdbx_TLS_residual_ADP_flag               ? 
+_refine.pdbx_overall_phase_error                 ? 
+_refine.pdbx_overall_SU_R_free_Cruickshank_DPI   ? 
+_refine.pdbx_overall_SU_R_Blow_DPI               ? 
+_refine.pdbx_overall_SU_R_free_Blow_DPI          ? 
+# 
+_refine_hist.pdbx_refine_id                   'X-RAY DIFFRACTION' 
+_refine_hist.cycle_id                         LAST 
+_refine_hist.pdbx_number_atoms_protein        59 
+_refine_hist.pdbx_number_atoms_nucleic_acid   0 
+_refine_hist.pdbx_number_atoms_ligand         0 
+_refine_hist.number_atoms_solvent             7 
+_refine_hist.number_atoms_total               66 
+_refine_hist.d_res_high                       1.80 
+_refine_hist.d_res_low                        22.44 
+# 
+loop_
+_refine_ls_restr.type 
+_refine_ls_restr.dev_ideal 
+_refine_ls_restr.dev_ideal_target 
+_refine_ls_restr.number 
+_refine_ls_restr.weight 
+_refine_ls_restr.pdbx_refine_id 
+_refine_ls_restr.pdbx_restraint_function 
+r_angle_refined_deg 1.228 ? ? ? 'X-RAY DIFFRACTION' ? 
+r_bond_refined_d    0.014 ? ? ? 'X-RAY DIFFRACTION' ? 
+# 
+_struct.entry_id                  1YJP 
+_struct.title                     'Structure of GNNQQNY from yeast prion Sup35' 
+_struct.pdbx_model_details        ? 
+_struct.pdbx_CASP_flag            ? 
+_struct.pdbx_model_type_details   ? 
+# 
+_struct_keywords.entry_id        1YJP 
+_struct_keywords.pdbx_keywords   'PROTEIN BINDING' 
+_struct_keywords.text            'beta sheet, steric zipper, glutamine zipper, asparagine zipper, PROTEIN BINDING' 
+# 
+loop_
+_struct_asym.id 
+_struct_asym.pdbx_blank_PDB_chainid_flag 
+_struct_asym.pdbx_modified 
+_struct_asym.entity_id 
+_struct_asym.details 
+A N N 1 ? 
+B N N 2 ? 
+# 
+_struct_ref.id                         1 
+_struct_ref.db_name                    UNP 
+_struct_ref.db_code                    ERF2_YEAST 
+_struct_ref.pdbx_db_accession          P05453 
+_struct_ref.entity_id                  1 
+_struct_ref.pdbx_seq_one_letter_code   GNNQQNY 
+_struct_ref.pdbx_align_begin           7 
+_struct_ref.pdbx_db_isoform            ? 
+# 
+_struct_ref_seq.align_id                      1 
+_struct_ref_seq.ref_id                        1 
+_struct_ref_seq.pdbx_PDB_id_code              1YJP 
+_struct_ref_seq.pdbx_strand_id                A 
+_struct_ref_seq.seq_align_beg                 1 
+_struct_ref_seq.pdbx_seq_align_beg_ins_code   ? 
+_struct_ref_seq.seq_align_end                 7 
+_struct_ref_seq.pdbx_seq_align_end_ins_code   ? 
+_struct_ref_seq.pdbx_db_accession             P05453 
+_struct_ref_seq.db_align_beg                  7 
+_struct_ref_seq.pdbx_db_align_beg_ins_code    ? 
+_struct_ref_seq.db_align_end                  13 
+_struct_ref_seq.pdbx_db_align_end_ins_code    ? 
+_struct_ref_seq.pdbx_auth_seq_align_beg       1 
+_struct_ref_seq.pdbx_auth_seq_align_end       7 
+# 
+_pdbx_struct_assembly.id                   1 
+_pdbx_struct_assembly.details              author_defined_assembly 
+_pdbx_struct_assembly.method_details       ? 
+_pdbx_struct_assembly.oligomeric_details   dimeric 
+_pdbx_struct_assembly.oligomeric_count     2 
+# 
+_pdbx_struct_assembly_gen.assembly_id       1 
+_pdbx_struct_assembly_gen.oper_expression   1,2 
+_pdbx_struct_assembly_gen.asym_id_list      A,B 
+# 
+loop_
+_pdbx_struct_oper_list.id 
+_pdbx_struct_oper_list.type 
+_pdbx_struct_oper_list.name 
+_pdbx_struct_oper_list.symmetry_operation 
+_pdbx_struct_oper_list.matrix[1][1] 
+_pdbx_struct_oper_list.matrix[1][2] 
+_pdbx_struct_oper_list.matrix[1][3] 
+_pdbx_struct_oper_list.vector[1] 
+_pdbx_struct_oper_list.matrix[2][1] 
+_pdbx_struct_oper_list.matrix[2][2] 
+_pdbx_struct_oper_list.matrix[2][3] 
+_pdbx_struct_oper_list.vector[2] 
+_pdbx_struct_oper_list.matrix[3][1] 
+_pdbx_struct_oper_list.matrix[3][2] 
+_pdbx_struct_oper_list.matrix[3][3] 
+_pdbx_struct_oper_list.vector[3] 
+1 'identity operation'         1_555 x,y,z       1.0000000000  0.0000000000 0.0000000000 0.0000000000 0.0000000000 1.0000000000 
+0.0000000000 0.0000000000 0.0000000000 0.0000000000 1.0000000000  0.0000000000 
+2 'crystal symmetry operation' 2_555 -x,y+1/2,-z -1.0000000000 0.0000000000 0.0000000000 0.0000000000 0.0000000000 1.0000000000 
+0.0000000000 2.4330000000 0.0000000000 0.0000000000 -1.0000000000 0.0000000000 
+# 
+_pdbx_database_remark.id     300 
+_pdbx_database_remark.text   
+;BIOMOLECULE: 1
+THIS ENTRY CONTAINS THE CRYSTALLOGRAPHIC ASYMMETRIC UNIT
+WHICH CONSISTS OF 1 CHAIN(S).  The second beta strand of
+the beta sandwich is generated as described in remark 350.
+Beta sheets are generated from unit cell translations
+along the unit cell b dimension: x,y+1,z.
+;
+# 
+loop_
+_chem_comp_atom.comp_id 
+_chem_comp_atom.atom_id 
+_chem_comp_atom.type_symbol 
+_chem_comp_atom.pdbx_aromatic_flag 
+_chem_comp_atom.pdbx_stereo_config 
+_chem_comp_atom.pdbx_ordinal 
+ASN N    N N N 1  
+ASN CA   C N S 2  
+ASN C    C N N 3  
+ASN O    O N N 4  
+ASN CB   C N N 5  
+ASN CG   C N N 6  
+ASN OD1  O N N 7  
+ASN ND2  N N N 8  
+ASN OXT  O N N 9  
+ASN H    H N N 10 
+ASN H2   H N N 11 
+ASN HA   H N N 12 
+ASN HB2  H N N 13 
+ASN HB3  H N N 14 
+ASN HD21 H N N 15 
+ASN HD22 H N N 16 
+ASN HXT  H N N 17 
+GLN N    N N N 18 
+GLN CA   C N S 19 
+GLN C    C N N 20 
+GLN O    O N N 21 
+GLN CB   C N N 22 
+GLN CG   C N N 23 
+GLN CD   C N N 24 
+GLN OE1  O N N 25 
+GLN NE2  N N N 26 
+GLN OXT  O N N 27 
+GLN H    H N N 28 
+GLN H2   H N N 29 
+GLN HA   H N N 30 
+GLN HB2  H N N 31 
+GLN HB3  H N N 32 
+GLN HG2  H N N 33 
+GLN HG3  H N N 34 
+GLN HE21 H N N 35 
+GLN HE22 H N N 36 
+GLN HXT  H N N 37 
+GLY N    N N N 38 
+GLY CA   C N N 39 
+GLY C    C N N 40 
+GLY O    O N N 41 
+GLY OXT  O N N 42 
+GLY H    H N N 43 
+GLY H2   H N N 44 
+GLY HA2  H N N 45 
+GLY HA3  H N N 46 
+GLY HXT  H N N 47 
+HOH O    O N N 48 
+HOH H1   H N N 49 
+HOH H2   H N N 50 
+TYR N    N N N 51 
+TYR CA   C N S 52 
+TYR C    C N N 53 
+TYR O    O N N 54 
+TYR CB   C N N 55 
+TYR CG   C Y N 56 
+TYR CD1  C Y N 57 
+TYR CD2  C Y N 58 
+TYR CE1  C Y N 59 
+TYR CE2  C Y N 60 
+TYR CZ   C Y N 61 
+TYR OH   O N N 62 
+TYR OXT  O N N 63 
+TYR H    H N N 64 
+TYR H2   H N N 65 
+TYR HA   H N N 66 
+TYR HB2  H N N 67 
+TYR HB3  H N N 68 
+TYR HD1  H N N 69 
+TYR HD2  H N N 70 
+TYR HE1  H N N 71 
+TYR HE2  H N N 72 
+TYR HH   H N N 73 
+TYR HXT  H N N 74 
+# 
+loop_
+_chem_comp_bond.comp_id 
+_chem_comp_bond.atom_id_1 
+_chem_comp_bond.atom_id_2 
+_chem_comp_bond.value_order 
+_chem_comp_bond.pdbx_aromatic_flag 
+_chem_comp_bond.pdbx_stereo_config 
+_chem_comp_bond.pdbx_ordinal 
+ASN N   CA   sing N N 1  
+ASN N   H    sing N N 2  
+ASN N   H2   sing N N 3  
+ASN CA  C    sing N N 4  
+ASN CA  CB   sing N N 5  
+ASN CA  HA   sing N N 6  
+ASN C   O    doub N N 7  
+ASN C   OXT  sing N N 8  
+ASN CB  CG   sing N N 9  
+ASN CB  HB2  sing N N 10 
+ASN CB  HB3  sing N N 11 
+ASN CG  OD1  doub N N 12 
+ASN CG  ND2  sing N N 13 
+ASN ND2 HD21 sing N N 14 
+ASN ND2 HD22 sing N N 15 
+ASN OXT HXT  sing N N 16 
+GLN N   CA   sing N N 17 
+GLN N   H    sing N N 18 
+GLN N   H2   sing N N 19 
+GLN CA  C    sing N N 20 
+GLN CA  CB   sing N N 21 
+GLN CA  HA   sing N N 22 
+GLN C   O    doub N N 23 
+GLN C   OXT  sing N N 24 
+GLN CB  CG   sing N N 25 
+GLN CB  HB2  sing N N 26 
+GLN CB  HB3  sing N N 27 
+GLN CG  CD   sing N N 28 
+GLN CG  HG2  sing N N 29 
+GLN CG  HG3  sing N N 30 
+GLN CD  OE1  doub N N 31 
+GLN CD  NE2  sing N N 32 
+GLN NE2 HE21 sing N N 33 
+GLN NE2 HE22 sing N N 34 
+GLN OXT HXT  sing N N 35 
+GLY N   CA   sing N N 36 
+GLY N   H    sing N N 37 
+GLY N   H2   sing N N 38 
+GLY CA  C    sing N N 39 
+GLY CA  HA2  sing N N 40 
+GLY CA  HA3  sing N N 41 
+GLY C   O    doub N N 42 
+GLY C   OXT  sing N N 43 
+GLY OXT HXT  sing N N 44 
+HOH O   H1   sing N N 45 
+HOH O   H2   sing N N 46 
+TYR N   CA   sing N N 47 
+TYR N   H    sing N N 48 
+TYR N   H2   sing N N 49 
+TYR CA  C    sing N N 50 
+TYR CA  CB   sing N N 51 
+TYR CA  HA   sing N N 52 
+TYR C   O    doub N N 53 
+TYR C   OXT  sing N N 54 
+TYR CB  CG   sing N N 55 
+TYR CB  HB2  sing N N 56 
+TYR CB  HB3  sing N N 57 
+TYR CG  CD1  doub Y N 58 
+TYR CG  CD2  sing Y N 59 
+TYR CD1 CE1  sing Y N 60 
+TYR CD1 HD1  sing N N 61 
+TYR CD2 CE2  doub Y N 62 
+TYR CD2 HD2  sing N N 63 
+TYR CE1 CZ   doub Y N 64 
+TYR CE1 HE1  sing N N 65 
+TYR CE2 CZ   sing Y N 66 
+TYR CE2 HE2  sing N N 67 
+TYR CZ  OH   sing N N 68 
+TYR OH  HH   sing N N 69 
+TYR OXT HXT  sing N N 70 
+# 
+_atom_sites.entry_id                    1YJP 
+_atom_sites.fract_transf_matrix[1][1]   0.045585 
+_atom_sites.fract_transf_matrix[1][2]   0.000000 
+_atom_sites.fract_transf_matrix[1][3]   0.014006 
+_atom_sites.fract_transf_matrix[2][1]   0.000000 
+_atom_sites.fract_transf_matrix[2][2]   0.205508 
+_atom_sites.fract_transf_matrix[2][3]   0.000000 
+_atom_sites.fract_transf_matrix[3][1]   0.000000 
+_atom_sites.fract_transf_matrix[3][2]   0.000000 
+_atom_sites.fract_transf_matrix[3][3]   0.044560 
+_atom_sites.fract_transf_vector[1]      0.00000 
+_atom_sites.fract_transf_vector[2]      0.00000 
+_atom_sites.fract_transf_vector[3]      0.00000 
+# 
+loop_
+_atom_type.symbol 
+C 
+N 
+O 
+# 
+loop_
+_atom_site.group_PDB 
+_atom_site.id 
+_atom_site.type_symbol 
+_atom_site.label_atom_id 
+_atom_site.label_alt_id 
+_atom_site.label_comp_id 
+_atom_site.label_asym_id 
+_atom_site.label_entity_id 
+_atom_site.label_seq_id 
+_atom_site.pdbx_PDB_ins_code 
+_atom_site.Cartn_x 
+_atom_site.Cartn_y 
+_atom_site.Cartn_z 
+_atom_site.occupancy 
+_atom_site.B_iso_or_equiv 
+_atom_site.pdbx_formal_charge 
+_atom_site.auth_seq_id 
+_atom_site.auth_comp_id 
+_atom_site.auth_asym_id 
+_atom_site.auth_atom_id 
+_atom_site.pdbx_PDB_model_num 
+ATOM   1  N N   . GLY A 1 1 ? -9.009  4.612  6.102  1.00 16.77 ? 1  GLY A N   1 
+ATOM   2  C CA  . GLY A 1 1 ? -9.052  4.207  4.651  1.00 16.57 ? 1  GLY A CA  1 
+ATOM   3  C C   . GLY A 1 1 ? -8.015  3.140  4.419  1.00 16.16 ? 1  GLY A C   1 
+ATOM   4  O O   . GLY A 1 1 ? -7.523  2.521  5.381  1.00 16.78 ? 1  GLY A O   1 
+ATOM   5  N N   . ASN A 1 2 ? -7.656  2.923  3.155  1.00 15.02 ? 2  ASN A N   1 
+ATOM   6  C CA  . ASN A 1 2 ? -6.522  2.038  2.831  1.00 14.10 ? 2  ASN A CA  1 
+ATOM   7  C C   . ASN A 1 2 ? -5.241  2.537  3.427  1.00 13.13 ? 2  ASN A C   1 
+ATOM   8  O O   . ASN A 1 2 ? -4.978  3.742  3.426  1.00 11.91 ? 2  ASN A O   1 
+ATOM   9  C CB  . ASN A 1 2 ? -6.346  1.881  1.341  1.00 15.38 ? 2  ASN A CB  1 
+ATOM   10 C CG  . ASN A 1 2 ? -7.584  1.342  0.692  1.00 14.08 ? 2  ASN A CG  1 
+ATOM   11 O OD1 . ASN A 1 2 ? -8.025  0.227  1.016  1.00 17.46 ? 2  ASN A OD1 1 
+ATOM   12 N ND2 . ASN A 1 2 ? -8.204  2.155  -0.169 1.00 11.72 ? 2  ASN A ND2 1 
+ATOM   13 N N   . ASN A 1 3 ? -4.438  1.590  3.905  1.00 12.26 ? 3  ASN A N   1 
+ATOM   14 C CA  . ASN A 1 3 ? -3.193  1.904  4.589  1.00 11.74 ? 3  ASN A CA  1 
+ATOM   15 C C   . ASN A 1 3 ? -1.955  1.332  3.895  1.00 11.10 ? 3  ASN A C   1 
+ATOM   16 O O   . ASN A 1 3 ? -1.872  0.119  3.648  1.00 10.42 ? 3  ASN A O   1 
+ATOM   17 C CB  . ASN A 1 3 ? -3.259  1.378  6.042  1.00 12.15 ? 3  ASN A CB  1 
+ATOM   18 C CG  . ASN A 1 3 ? -2.006  1.739  6.861  1.00 12.82 ? 3  ASN A CG  1 
+ATOM   19 O OD1 . ASN A 1 3 ? -1.702  2.925  7.072  1.00 15.05 ? 3  ASN A OD1 1 
+ATOM   20 N ND2 . ASN A 1 3 ? -1.271  0.715  7.306  1.00 13.48 ? 3  ASN A ND2 1 
+ATOM   21 N N   . GLN A 1 4 ? -1.005  2.228  3.598  1.00 10.29 ? 4  GLN A N   1 
+ATOM   22 C CA  . GLN A 1 4 ? 0.384   1.888  3.199  1.00 10.53 ? 4  GLN A CA  1 
+ATOM   23 C C   . GLN A 1 4 ? 1.435   2.606  4.088  1.00 10.24 ? 4  GLN A C   1 
+ATOM   24 O O   . GLN A 1 4 ? 1.547   3.843  4.115  1.00 8.86  ? 4  GLN A O   1 
+ATOM   25 C CB  . GLN A 1 4 ? 0.656   2.148  1.711  1.00 9.80  ? 4  GLN A CB  1 
+ATOM   26 C CG  . GLN A 1 4 ? 1.944   1.458  1.213  1.00 10.25 ? 4  GLN A CG  1 
+ATOM   27 C CD  . GLN A 1 4 ? 2.504   2.044  -0.089 1.00 12.43 ? 4  GLN A CD  1 
+ATOM   28 O OE1 . GLN A 1 4 ? 2.744   3.268  -0.190 1.00 14.62 ? 4  GLN A OE1 1 
+ATOM   29 N NE2 . GLN A 1 4 ? 2.750   1.161  -1.091 1.00 9.05  ? 4  GLN A NE2 1 
+ATOM   30 N N   . GLN A 1 5 ? 2.154   1.821  4.871  1.00 10.38 ? 5  GLN A N   1 
+ATOM   31 C CA  . GLN A 1 5 ? 3.270   2.361  5.640  1.00 11.39 ? 5  GLN A CA  1 
+ATOM   32 C C   . GLN A 1 5 ? 4.594   1.768  5.172  1.00 11.52 ? 5  GLN A C   1 
+ATOM   33 O O   . GLN A 1 5 ? 4.768   0.546  5.054  1.00 12.05 ? 5  GLN A O   1 
+ATOM   34 C CB  . GLN A 1 5 ? 3.056   2.183  7.147  1.00 11.96 ? 5  GLN A CB  1 
+ATOM   35 C CG  . GLN A 1 5 ? 1.829   2.950  7.647  1.00 10.81 ? 5  GLN A CG  1 
+ATOM   36 C CD  . GLN A 1 5 ? 1.344   2.414  8.954  1.00 13.10 ? 5  GLN A CD  1 
+ATOM   37 O OE1 . GLN A 1 5 ? 0.774   1.325  9.002  1.00 10.65 ? 5  GLN A OE1 1 
+ATOM   38 N NE2 . GLN A 1 5 ? 1.549   3.187  10.039 1.00 12.30 ? 5  GLN A NE2 1 
+ATOM   39 N N   . ASN A 1 6 ? 5.514   2.664  4.856  1.00 11.99 ? 6  ASN A N   1 
+ATOM   40 C CA  . ASN A 1 6 ? 6.831   2.310  4.318  1.00 12.30 ? 6  ASN A CA  1 
+ATOM   41 C C   . ASN A 1 6 ? 7.854   2.761  5.324  1.00 13.40 ? 6  ASN A C   1 
+ATOM   42 O O   . ASN A 1 6 ? 8.219   3.943  5.374  1.00 13.92 ? 6  ASN A O   1 
+ATOM   43 C CB  . ASN A 1 6 ? 7.065   3.016  2.993  1.00 12.13 ? 6  ASN A CB  1 
+ATOM   44 C CG  . ASN A 1 6 ? 5.961   2.735  2.003  1.00 12.77 ? 6  ASN A CG  1 
+ATOM   45 O OD1 . ASN A 1 6 ? 5.798   1.604  1.551  1.00 14.27 ? 6  ASN A OD1 1 
+ATOM   46 N ND2 . ASN A 1 6 ? 5.195   3.747  1.679  1.00 10.07 ? 6  ASN A ND2 1 
+ATOM   47 N N   . TYR A 1 7 ? 8.292   1.817  6.147  1.00 14.70 ? 7  TYR A N   1 
+ATOM   48 C CA  . TYR A 1 7 ? 9.159   2.144  7.299  1.00 15.18 ? 7  TYR A CA  1 
+ATOM   49 C C   . TYR A 1 7 ? 10.603  2.331  6.885  1.00 15.91 ? 7  TYR A C   1 
+ATOM   50 O O   . TYR A 1 7 ? 11.041  1.811  5.855  1.00 15.76 ? 7  TYR A O   1 
+ATOM   51 C CB  . TYR A 1 7 ? 9.061   1.065  8.369  1.00 15.35 ? 7  TYR A CB  1 
+ATOM   52 C CG  . TYR A 1 7 ? 7.665   0.929  8.902  1.00 14.45 ? 7  TYR A CG  1 
+ATOM   53 C CD1 . TYR A 1 7 ? 6.771   0.021  8.327  1.00 15.68 ? 7  TYR A CD1 1 
+ATOM   54 C CD2 . TYR A 1 7 ? 7.210   1.756  9.920  1.00 14.80 ? 7  TYR A CD2 1 
+ATOM   55 C CE1 . TYR A 1 7 ? 5.480   -0.094 8.796  1.00 13.46 ? 7  TYR A CE1 1 
+ATOM   56 C CE2 . TYR A 1 7 ? 5.904   1.649  10.416 1.00 14.33 ? 7  TYR A CE2 1 
+ATOM   57 C CZ  . TYR A 1 7 ? 5.047   0.729  9.831  1.00 15.09 ? 7  TYR A CZ  1 
+ATOM   58 O OH  . TYR A 1 7 ? 3.766   0.589  10.291 1.00 14.39 ? 7  TYR A OH  1 
+ATOM   59 O OXT . TYR A 1 7 ? 11.358  2.999  7.612  1.00 17.49 ? 7  TYR A OXT 1 
+HETATM 60 O O   . HOH B 2 . ? -6.471  5.227  7.124  1.00 22.62 ? 8  HOH A O   1 
+HETATM 61 O O   . HOH B 2 . ? 10.431  1.858  3.216  1.00 19.71 ? 9  HOH A O   1 
+HETATM 62 O O   . HOH B 2 . ? -11.286 1.756  -1.468 1.00 17.08 ? 10 HOH A O   1 
+HETATM 63 O O   . HOH B 2 . ? 11.808  4.179  9.970  1.00 23.99 ? 11 HOH A O   1 
+HETATM 64 O O   . HOH B 2 . ? 13.605  1.327  9.198  1.00 26.17 ? 12 HOH A O   1 
+HETATM 65 O O   . HOH B 2 . ? -2.749  3.429  10.024 1.00 39.15 ? 13 HOH A O   1 
+HETATM 66 O O   . HOH B 2 . ? -1.500  0.682  10.967 1.00 43.49 ? 14 HOH A O   1 
+# 
diff --git a/testsuite/MDAnalysisTests/data/mmcif/1YJP.cif.gz b/testsuite/MDAnalysisTests/data/mmcif/1YJP.cif.gz
new file mode 100644
index 00000000000..5bb72507515
Binary files /dev/null and b/testsuite/MDAnalysisTests/data/mmcif/1YJP.cif.gz differ
diff --git a/testsuite/MDAnalysisTests/data/mmcif/1YJP_invalid.cif.gz b/testsuite/MDAnalysisTests/data/mmcif/1YJP_invalid.cif.gz
new file mode 100644
index 00000000000..34874b14845
Binary files /dev/null and b/testsuite/MDAnalysisTests/data/mmcif/1YJP_invalid.cif.gz differ
diff --git a/testsuite/MDAnalysisTests/data/mmcif/3KPR.cif.gz b/testsuite/MDAnalysisTests/data/mmcif/3KPR.cif.gz
new file mode 100644
index 00000000000..2b95b252040
Binary files /dev/null and b/testsuite/MDAnalysisTests/data/mmcif/3KPR.cif.gz differ
diff --git a/testsuite/MDAnalysisTests/data/mmcif/3KPR.pdb.gz b/testsuite/MDAnalysisTests/data/mmcif/3KPR.pdb.gz
new file mode 100644
index 00000000000..44e115cfac0
Binary files /dev/null and b/testsuite/MDAnalysisTests/data/mmcif/3KPR.pdb.gz differ
diff --git a/testsuite/MDAnalysisTests/data/mmcif/3PWP.cif.gz b/testsuite/MDAnalysisTests/data/mmcif/3PWP.cif.gz
new file mode 100644
index 00000000000..58134d71b16
Binary files /dev/null and b/testsuite/MDAnalysisTests/data/mmcif/3PWP.cif.gz differ
diff --git a/testsuite/MDAnalysisTests/data/mmcif/3PWP.pdb.gz b/testsuite/MDAnalysisTests/data/mmcif/3PWP.pdb.gz
new file mode 100644
index 00000000000..78295e18b77
Binary files /dev/null and b/testsuite/MDAnalysisTests/data/mmcif/3PWP.pdb.gz differ
diff --git a/testsuite/MDAnalysisTests/data/mmcif/7ETN.cif.gz b/testsuite/MDAnalysisTests/data/mmcif/7ETN.cif.gz
new file mode 100644
index 00000000000..c5d77f66adc
Binary files /dev/null and b/testsuite/MDAnalysisTests/data/mmcif/7ETN.cif.gz differ
diff --git a/testsuite/MDAnalysisTests/data/mmcif/custom.cif.gz b/testsuite/MDAnalysisTests/data/mmcif/custom.cif.gz
new file mode 100644
index 00000000000..a08985c3ea8
Binary files /dev/null and b/testsuite/MDAnalysisTests/data/mmcif/custom.cif.gz differ
diff --git a/testsuite/MDAnalysisTests/data/mmcif/multimodel_warning.cif.gz b/testsuite/MDAnalysisTests/data/mmcif/multimodel_warning.cif.gz
new file mode 100644
index 00000000000..53c76bb6319
Binary files /dev/null and b/testsuite/MDAnalysisTests/data/mmcif/multimodel_warning.cif.gz differ
diff --git a/testsuite/MDAnalysisTests/datafiles.py b/testsuite/MDAnalysisTests/datafiles.py
index 0289d64aed9..c83d27892e5 100644
--- a/testsuite/MDAnalysisTests/datafiles.py
+++ b/testsuite/MDAnalysisTests/datafiles.py
@@ -398,10 +398,10 @@
     "SURFACE_PDB",  # 111 FCC lattice topology for NSGrid bug #2345
     "SURFACE_TRR",  # full precision coordinates for NSGrid bug #2345
     "DSSP",  # DSSP test suite
+    "MMCIF",  # MMCIF test suite
 ]
 
 from importlib import resources
-import MDAnalysisTests.data
 
 _data_ref = resources.files("MDAnalysisTests.data")
 
@@ -932,5 +932,8 @@
 # DSSP testing: from https://github.com/ShintaroMinami/PyDSSP
 DSSP = (_data_ref / "dssp").as_posix()
 
+# MMCIF data: valid structures from RCSB and generated by Biopython
+MMCIF = (_data_ref / "mmcif").as_posix()
+
 # This should be the last line: clean up namespace
 del resources
diff --git a/testsuite/MDAnalysisTests/topology/test_mmcif.py b/testsuite/MDAnalysisTests/topology/test_mmcif.py
new file mode 100644
index 00000000000..7eb816aa144
--- /dev/null
+++ b/testsuite/MDAnalysisTests/topology/test_mmcif.py
@@ -0,0 +1,186 @@
+import MDAnalysis as mda
+import pytest
+from pathlib import Path
+from io import StringIO
+import gzip
+from MDAnalysis.lib import util
+from MDAnalysis.coordinates.MMCIF import HAS_GEMMI
+
+from MDAnalysisTests.datafiles import MMCIF as MMCIF_FOLDER
+
+
+@pytest.mark.skipif(not HAS_GEMMI, reason="gemmi not installed")
+@pytest.mark.parametrize(
+    "basename",
+    [
+        f"{MMCIF_FOLDER}/1BD2_short",
+        f"{MMCIF_FOLDER}/1BD2",
+        f"{MMCIF_FOLDER}/3PWP",
+        f"{MMCIF_FOLDER}/3KPR",
+    ],
+)
+@pytest.mark.filterwarnings("ignore::UserWarning")
+def test_legacy_pdb_vs_mmcif(basename):
+    u_cif = mda.Universe(f"{basename}.cif.gz")
+    u_pdb = mda.Universe(f"{basename}.pdb.gz")
+    assert len(u_pdb.atoms) == len(u_cif.atoms)
+    assert len(u_pdb.select_atoms("segid *")) == len(
+        u_cif.select_atoms("segid *")
+    )
+
+    assert len(u_pdb.select_atoms("protein")) == len(
+        u_cif.select_atoms("protein")
+    )
+
+    assert len(u_pdb.select_atoms("name CA and segid D")) == len(
+        u_cif.select_atoms("name CA and segid D")
+    )
+    for segment in "ABCDE":
+        for resid in [1, 10, 54, 72]:
+            assert len(u_pdb.select_atoms(f"segid {segment}")) == len(
+                u_cif.select_atoms(f"segid {segment}")
+            )
+            assert len(
+                u_pdb.select_atoms(f"segid {segment} and resid {resid}")
+            ) == len(u_cif.select_atoms(f"segid {segment} and resid {resid}"))
+            assert len(
+                u_pdb.select_atoms(
+                    f"segid {segment} and resid {resid} and name CA"
+                )
+            ) == len(
+                u_cif.select_atoms(
+                    f"segid {segment} and resid {resid} and name CA"
+                )
+            )
+
+
+@pytest.mark.skipif(not HAS_GEMMI, reason="gemmi not installed")
+@pytest.mark.parametrize(
+    "mmcif_filename,n_chains",
+    [
+        (f"{MMCIF_FOLDER}/1YJP.cif", 1),
+        (f"{MMCIF_FOLDER}/1YJP.cif.gz", 1),
+        (f"{MMCIF_FOLDER}/7ETN.cif.gz", 2),
+    ],
+)
+def test_chains(mmcif_filename, n_chains):
+    u = mda.Universe(mmcif_filename)
+    assert len(u.segments) == n_chains
+
+
+@pytest.mark.skipif(not HAS_GEMMI, reason="gemmi not installed")
+@pytest.mark.parametrize(
+    "mmcif_filename,sequence",
+    [
+        (
+            f"{MMCIF_FOLDER}/1YJP.cif",
+            ["GLY", "ASN", "ASN", "GLN", "GLN", "ASN", "TYR"],
+        ),
+        (
+            f"{MMCIF_FOLDER}/1YJP.cif.gz",
+            ["GLY", "ASN", "ASN", "GLN", "GLN", "ASN", "TYR"],
+        ),
+        (f"{MMCIF_FOLDER}/7ETN.cif.gz", ["PRO", "PHE", "LEU", "ILE"]),
+    ],
+)
+def test_sequence(mmcif_filename, sequence):
+    u = mda.Universe(mmcif_filename)
+    in_structure = [
+        str(res.resname)
+        for res in u.select_atoms("protein and chainid A").residues
+    ]
+    assert in_structure == sequence, ":".join(in_structure)
+
+
+@pytest.mark.skipif(not HAS_GEMMI, reason="gemmi not installed")
+def test_altlocs():
+    # gemmi stores absent altlocs as "\0", which must not leak into the
+    # topology (it ends up in written PDB files otherwise)
+    u = mda.Universe(f"{MMCIF_FOLDER}/3PWP.cif.gz")
+    assert not any("\x00" in altloc for altloc in u.atoms.altLocs)
+    with_altloc = u.atoms[[altloc != "" for altloc in u.atoms.altLocs]]
+    assert len(with_altloc) == 12
+    assert set(with_altloc.altLocs) == {"A", "B"}
+    assert set(with_altloc.resnames) == {"GLN"}
+
+
+def test_no_gemmi_raises(monkeypatch):
+    monkeypatch.setattr(mda.topology.MMCIFParser, "HAS_GEMMI", False)
+    with pytest.raises(ImportError, match="please install gemmi"):
+        mda.topology.MMCIFParser.MMCIFParser(f"{MMCIF_FOLDER}/1YJP.cif")
+
+
+@pytest.mark.skipif(not HAS_GEMMI, reason="gemmi not installed")
+def test_wrong_format():
+    with pytest.raises(ValueError):
+        mda.Universe(f"{MMCIF_FOLDER}/1YJP_invalid.cif.gz")
+
+
+@pytest.mark.skipif(not HAS_GEMMI, reason="gemmi not installed")
+def test_unparseable_content():
+    # content that fails both CIF and PDB parsing in gemmi must re-raise
+    # the original CIF error
+    garbage = util.NamedStream(
+        StringIO("data_\n_nonsense.field ??? ][\n"), "garbage.cif"
+    )
+    with pytest.raises(ValueError, match="parse error"):
+        mda.Universe(garbage)
+
+
+@pytest.mark.skipif(not HAS_GEMMI, reason="gemmi not installed")
+def test_multimodel_warning_msg():
+    with pytest.warns(
+        UserWarning,
+        match=(
+            r"MMCIF model .+ contains .+ different models, but only the "
+            r"first one will be used to assign the topology"
+        ),
+    ):
+        mda.topology.MMCIFParser.MMCIFParser(
+            f"{MMCIF_FOLDER}/multimodel_warning.cif.gz"
+        ).parse()
+
+
+@pytest.mark.skipif(not HAS_GEMMI, reason="gemmi not installed")
+@pytest.mark.parametrize(
+    "filename,fmt",
+    [
+        (f"{MMCIF_FOLDER}/1BD2_short.cif.gz", None),
+        (Path(f"{MMCIF_FOLDER}/1BD2_short.cif.gz"), None),
+        (
+            StringIO(util.anyopen(f"{MMCIF_FOLDER}/1BD2_short.cif.gz").read()),
+            "CIF",
+        ),
+        (gzip.open(f"{MMCIF_FOLDER}/1BD2_short.cif.gz"), "CIF"),
+        (
+            util.NamedStream(
+                StringIO(
+                    util.anyopen(f"{MMCIF_FOLDER}/1BD2_short.cif.gz").read()
+                ),
+                "some_name.cif",
+            ),
+            "CIF",
+        ),
+        (f"{MMCIF_FOLDER}/1BD2_short.pdb.gz", None),
+        (Path(f"{MMCIF_FOLDER}/1BD2_short.pdb.gz"), None),
+        (
+            StringIO(util.anyopen(f"{MMCIF_FOLDER}/1BD2_short.pdb.gz").read()),
+            "CIF",
+        ),
+        (
+            util.anyopen(f"{MMCIF_FOLDER}/1BD2_short.pdb.gz"),
+            "CIF",
+        ),
+        (
+            util.NamedStream(
+                StringIO(
+                    util.anyopen(f"{MMCIF_FOLDER}/1BD2_short.pdb.gz").read()
+                ),
+                "some_name.pdb",
+            ),
+            "CIF",
+        ),
+    ],
+)
+def test_input_methods(filename, fmt):
+    mda.Universe(filename, topology_format=fmt)
diff --git a/testsuite/pyproject.toml b/testsuite/pyproject.toml
index bc0b236535a..83b8e9ef466 100644
--- a/testsuite/pyproject.toml
+++ b/testsuite/pyproject.toml
@@ -161,8 +161,6 @@ extend-exclude = '''
 (
 testsuite/MDAnalysisTests/datafiles\.py
 | testsuite/MDAnalysisTests/analysis/conftest\.py
-| testsuite/MDAnalysisTests/coordinates/test_mmcif\.py
-| testsuite/MDAnalysisTests/topology/test_mmcif\.py
 )
 '''
 required-version = '24'