Replace mdtraj with biotraj

.github/workflows/test_and_deploy.yml

@@ -124,6 +124,9 @@ jobs:
         with:
           mamba-version: "*"
           environment-file: environment.yml
+      # TODO: Re-enable DSSP tests as soon as issues with libboost in CI are resolved
+      - name: "TEMP: Remove DSSP from environment"
+        run: mamba remove dssp -y
       - name: Build distribution
         run: pip wheel --no-deps -w dist .
       - name: Install distribution

README.rst

@@ -21,7 +21,7 @@ This package bundles popular tasks in computational molecular biology
 into a uniform *Python* library.
 It can handle a major part of the typical workflow
 for sequence and biomolecular structure data:
-   
+
    - Searching and fetching data from biological databases
    - Reading and writing popular sequence/structure file formats
    - Analyzing and editing sequence/structure data
@@ -57,7 +57,6 @@ Installation
 
 Some functions require some extra packages:
 
-   - **mdtraj** - Required for trajetory file I/O operations.
    - **matplotlib** - Required for plotting purposes.
 
 *Biotite* can be installed via *Conda*...

doc/contribution/development.rst

@@ -79,9 +79,8 @@ The import statement for the dependency should be located directly inside the
 function or class, rather than module level, to ensure that the package is not
 required for any other functionality or for building the API documentation.
 
-An example for this approach is the support for trajectory files in
-:mod:`biotite.structure.io`, that require `MDTraj <http://mdtraj.org/>`_.
-The usage of these packages is not only allowed but even encouraged.
+An example for this approach are the plotting functions in
+:mod:`biotite.sequence.graphics`, that require *Matplotlib*.
 
 Code efficiency
 ---------------

doc/install.rst

@@ -20,7 +20,6 @@ dependencies if not already present.
 
 Some functionalities require extra packages:
 
-   - ``mdtraj`` - Required for trajectory file I/O operations.
    - ``matplotlib`` - Required for plotting purposes.
 
 

doc/tutorial/structure/trajectories.rst

@@ -10,11 +10,6 @@ If you like, you can even use the
 seamless interaction between *Biotite* and the
 `OpenMM <https://openmm.org/>`_ MD simulation toolkit.
 
-.. note::
-
-    Reading/writing trajectory files currently requires the
-    `MDtraj <https://www.mdtraj.org>`_ package.
-
 Reading trajectory files
 ------------------------
 

environment.yml

@@ -10,19 +10,19 @@ channels:
   - bioconda
 
 dependencies:
-  - python =3.10
+  - python =3.12
   # Package building
   - cython >=3.0
   - pip >=10.0
   - setuptools >=30.0
   - wheel >=0.30
   # Biotite dependencies
+  # - biotraj >=1.0,<2.0
   - msgpack-python >=0.5.6
   - networkx >=2.0
-  - numpy >=1.25
+  - numpy >=2.0
   - requests >=2.12
   # Testing
-  # - mdtraj >=1.9.3, <1.10  # tempoarily disabled due to incompatibility with numpy 2.0
   - pytest >=7.0
   # Code style
   - ruff =0.5.2

pyproject.toml

@@ -23,6 +23,8 @@ dependencies = [
   # Wheels compiled with NumPy 2.0 are backward compatible with NumPy 1.x
   # https://numpy.org/devdocs/dev/depending_on_numpy.html#numpy-2-0-specific-advice
   "numpy >= 1.25",
+  "biotraj >= 1.0, < 2.0",
+  "requests >= 2.12",
   "msgpack >= 0.5.6",
   "networkx >= 2.0",
   "requests >= 2.12",
@@ -75,6 +77,13 @@ no-lines-before = [
 order-by-type = true
 known-first-party = ["biotite"]
 
+[tool.pytest.ini_options]
+filterwarnings = [
+  # Appears in loading NetCDF trajectory files
+  "ignore:The 'netCDF4' Python package is not installed.",
+  "ignore:Input structure has no associated 'BondList'",
+]
+
 [tool.hatch.build.targets.sdist]
 exclude = [
   "tests",

src/biotite/application/localapp.py

@@ -301,5 +301,8 @@ def cleanup_tempfile(temp_file):
         The temporary file to be closed and deleted.
     """
     temp_file.close()
-    if not temp_file.delete:
+    try:
         remove(temp_file.name)
+    except FileNotFoundError:
+        # File was already deleted, e.g. due to `TemporaryFile(delete=True)`
+        pass

src/biotite/sequence/align/cigar.py

@@ -294,10 +294,10 @@ def write_alignment_to_cigar(
 
     >>> op_tuples = write_alignment_to_cigar(semiglobal_alignment, as_string=False)
     >>> for op, length in op_tuples:
-    ...     print(CigarOp(op), length)
-    CigarOp.MATCH 9
-    CigarOp.DELETION 2
-    CigarOp.MATCH 12
+    ...     print(CigarOp(op).name, length)
+    MATCH 9
+    DELETION 2
+    MATCH 12
     """
     if not include_terminal_gaps:
         alignment = _remove_terminal_segment_gaps(alignment, segment_index)

src/biotite/sequence/annotation.py

@@ -342,7 +342,7 @@ class Annotation(Copyable):
     ...     gene = f.qual["gene"]
     ...     loc_str = "".join([f"{loc}    {loc.defect}" for loc in f.locs])
     ...     print(gene, loc_str)
-    test5 40-149 >    Defect.MISS_RIGHT|MISS_LEFT
+    test5 40-149 >    Defect.MISS_LEFT|MISS_RIGHT
     test2 40-50 >    Defect.MISS_LEFT
     test3 100-130 >    Defect.NONE
     """

src/biotite/sequence/io/genbank/file.py

@@ -80,7 +80,7 @@ class GenBankFile(TextFile):
     >>> print(content)
     ['One line', 'A second line']
     >>> print(subfields)
-    OrderedDict([('SUBFIELD1', ['Single Line']), ('SUBFIELD2', ['Two', 'lines'])])
+    OrderedDict({'SUBFIELD1': ['Single Line'], 'SUBFIELD2': ['Two', 'lines']})
 
     Adding an additional field:
 

src/biotite/structure/basepairs.py

@@ -379,19 +379,19 @@ def base_pairs_edge(atom_array, base_pairs):
     The resulting integers can be interpreted as :class:`Edge` ``Enum``:
 
     >>> for interaction in interacting_edges:
-    ...     print(Edge(interaction[0]), Edge(interaction[1]))
-    Edge.WATSON_CRICK Edge.WATSON_CRICK
-    Edge.WATSON_CRICK Edge.WATSON_CRICK
-    Edge.WATSON_CRICK Edge.WATSON_CRICK
-    Edge.WATSON_CRICK Edge.WATSON_CRICK
-    Edge.WATSON_CRICK Edge.WATSON_CRICK
-    Edge.WATSON_CRICK Edge.WATSON_CRICK
-    Edge.WATSON_CRICK Edge.WATSON_CRICK
-    Edge.WATSON_CRICK Edge.WATSON_CRICK
-    Edge.WATSON_CRICK Edge.WATSON_CRICK
-    Edge.WATSON_CRICK Edge.WATSON_CRICK
-    Edge.WATSON_CRICK Edge.WATSON_CRICK
-    Edge.WATSON_CRICK Edge.WATSON_CRICK
+    ...     print(f"{Edge(interaction[0]).name} to {Edge(interaction[1]).name}")
+    WATSON_CRICK to WATSON_CRICK
+    WATSON_CRICK to WATSON_CRICK
+    WATSON_CRICK to WATSON_CRICK
+    WATSON_CRICK to WATSON_CRICK
+    WATSON_CRICK to WATSON_CRICK
+    WATSON_CRICK to WATSON_CRICK
+    WATSON_CRICK to WATSON_CRICK
+    WATSON_CRICK to WATSON_CRICK
+    WATSON_CRICK to WATSON_CRICK
+    WATSON_CRICK to WATSON_CRICK
+    WATSON_CRICK to WATSON_CRICK
+    WATSON_CRICK to WATSON_CRICK
 
     References
     ----------
@@ -531,19 +531,19 @@ def base_pairs_glycosidic_bond(atom_array, base_pairs):
     ``Enum``:
 
     >>> for orientation in orientations:
-    ...     print(GlycosidicBond(orientation))
-    GlycosidicBond.CIS
-    GlycosidicBond.CIS
-    GlycosidicBond.CIS
-    GlycosidicBond.CIS
-    GlycosidicBond.CIS
-    GlycosidicBond.CIS
-    GlycosidicBond.CIS
-    GlycosidicBond.CIS
-    GlycosidicBond.CIS
-    GlycosidicBond.CIS
-    GlycosidicBond.CIS
-    GlycosidicBond.CIS
+    ...     print(GlycosidicBond(orientation).name)
+    CIS
+    CIS
+    CIS
+    CIS
+    CIS
+    CIS
+    CIS
+    CIS
+    CIS
+    CIS
+    CIS
+    CIS
 
     References
     ----------

src/biotite/structure/bonds.pyx

@@ -85,8 +85,8 @@ class BondType(IntEnum):
         Examples
         --------
 
-        >>> print(BondType.AROMATIC_DOUBLE.without_aromaticity())
-        BondType.DOUBLE
+        >>> print(BondType.AROMATIC_DOUBLE.without_aromaticity().name)
+        DOUBLE
         """
         difference = BondType.AROMATIC_SINGLE - BondType.SINGLE
         if self >= BondType.AROMATIC_SINGLE:
@@ -212,21 +212,21 @@ class BondList(Copyable):
     ... )
     >>> for i, j, bond_type in benzene.bonds.as_array():
     ...     print(
-    ...         f"{str(BondType(bond_type))} bond between "
+    ...         f"{BondType(bond_type).name} bond between "
     ...         f"{benzene.atom_name[i]} and {benzene.atom_name[j]}"
     ...     )
-    BondType.AROMATIC_SINGLE bond between C1 and C2
-    BondType.AROMATIC_DOUBLE bond between C2 and C3
-    BondType.AROMATIC_SINGLE bond between C3 and C4
-    BondType.AROMATIC_DOUBLE bond between C4 and C5
-    BondType.AROMATIC_SINGLE bond between C5 and C6
-    BondType.AROMATIC_DOUBLE bond between C1 and C6
-    BondType.SINGLE bond between C1 and H1
-    BondType.SINGLE bond between C2 and H2
-    BondType.SINGLE bond between C3 and H3
-    BondType.SINGLE bond between C4 and H4
-    BondType.SINGLE bond between C5 and H5
-    BondType.SINGLE bond between C6 and H6
+    AROMATIC_SINGLE bond between C1 and C2
+    AROMATIC_DOUBLE bond between C2 and C3
+    AROMATIC_SINGLE bond between C3 and C4
+    AROMATIC_DOUBLE bond between C4 and C5
+    AROMATIC_SINGLE bond between C5 and C6
+    AROMATIC_DOUBLE bond between C1 and C6
+    SINGLE bond between C1 and H1
+    SINGLE bond between C2 and H2
+    SINGLE bond between C3 and H3
+    SINGLE bond between C4 and H4
+    SINGLE bond between C5 and H5
+    SINGLE bond between C6 and H6
 
     Obtain the bonded atoms for the :math:`C_1`:
 
@@ -248,14 +248,14 @@ class BondList(Copyable):
     ... ]
     >>> for i, j, bond_type in half_benzene.bonds.as_array():
     ...     print(
-    ...         f"{str(BondType(bond_type))} bond between "
+    ...         f"{BondType(bond_type).name} bond between "
     ...         f"{half_benzene.atom_name[i]} and {half_benzene.atom_name[j]}"
     ...     )
-    BondType.AROMATIC_DOUBLE bond between C4 and C5
-    BondType.AROMATIC_SINGLE bond between C5 and C6
-    BondType.SINGLE bond between C4 and H4
-    BondType.SINGLE bond between C5 and H5
-    BondType.SINGLE bond between C6 and H6
+    AROMATIC_DOUBLE bond between C4 and C5
+    AROMATIC_SINGLE bond between C5 and C6
+    SINGLE bond between C4 and H4
+    SINGLE bond between C5 and H5
+    SINGLE bond between C6 and H6
     """
 
     def __init__(self, uint32 atom_count, np.ndarray bonds=None):
@@ -449,9 +449,9 @@ class BondList(Copyable):
         >>> bond_list.add_bond(1, 2, BondType.AROMATIC_DOUBLE)
         >>> bond_list.remove_aromaticity()
         >>> for i, j, bond_type in bond_list.as_array():
-        ...     print(i, j, BondType(bond_type))
-        0 1 BondType.SINGLE
-        1 2 BondType.DOUBLE
+        ...     print(i, j, BondType(bond_type).name)
+        0 1 SINGLE
+        1 2 DOUBLE
         """
         bonds = self._bonds
         difference = BondType.AROMATIC_SINGLE - BondType.SINGLE

src/biotite/structure/info/bonds.py

@@ -47,13 +47,13 @@ def bond_type(res_name, atom_name1, atom_name2):
     Examples
     --------
 
-    >>> print(bond_type("PHE", "CA", "CB"))
-    BondType.SINGLE
-    >>> print(bond_type("PHE", "CG", "CD1"))
-    BondType.AROMATIC_DOUBLE
-    >>> print(bond_type("PHE", "CA", "CG"))
+    >>> print(repr(bond_type("PHE", "CA", "CB")))
+    <BondType.SINGLE: 1>
+    >>> print(repr(bond_type("PHE", "CG", "CD1")))
+    <BondType.AROMATIC_DOUBLE: 6>
+    >>> print(repr(bond_type("PHE", "CA", "CG")))
     None
-    >>> print(bond_type("PHE", "FOO", "BAR"))
+    >>> print(repr(bond_type("PHE", "FOO", "BAR")))
     None
     """
     bonds_for_residue = bonds_in_residue(res_name)
@@ -99,30 +99,30 @@ def bonds_in_residue(res_name):
     >>> bonds = bonds_in_residue("PHE")
     >>> for atoms, bond_type_int in sorted(bonds.items()):
     ...     atom1, atom2 = sorted(atoms)
-    ...     print(f"{atom1:3} + {atom2:3} -> {str(BondType(bond_type_int))}")
-    C   + O   -> BondType.DOUBLE
-    C   + OXT -> BondType.SINGLE
-    C   + CA  -> BondType.SINGLE
-    CA  + CB  -> BondType.SINGLE
-    CA  + HA  -> BondType.SINGLE
-    CB  + CG  -> BondType.SINGLE
-    CB  + HB2 -> BondType.SINGLE
-    CB  + HB3 -> BondType.SINGLE
-    CD1 + CE1 -> BondType.AROMATIC_SINGLE
-    CD1 + HD1 -> BondType.SINGLE
-    CD2 + CE2 -> BondType.AROMATIC_DOUBLE
-    CD2 + HD2 -> BondType.SINGLE
-    CE1 + CZ  -> BondType.AROMATIC_DOUBLE
-    CE1 + HE1 -> BondType.SINGLE
-    CE2 + CZ  -> BondType.AROMATIC_SINGLE
-    CE2 + HE2 -> BondType.SINGLE
-    CD1 + CG  -> BondType.AROMATIC_DOUBLE
-    CD2 + CG  -> BondType.AROMATIC_SINGLE
-    CZ  + HZ  -> BondType.SINGLE
-    CA  + N   -> BondType.SINGLE
-    H   + N   -> BondType.SINGLE
-    H2  + N   -> BondType.SINGLE
-    HXT + OXT -> BondType.SINGLE
+    ...     print(f"{atom1:3} + {atom2:3} -> {BondType(bond_type_int).name}")
+    C   + O   -> DOUBLE
+    C   + OXT -> SINGLE
+    C   + CA  -> SINGLE
+    CA  + CB  -> SINGLE
+    CA  + HA  -> SINGLE
+    CB  + CG  -> SINGLE
+    CB  + HB2 -> SINGLE
+    CB  + HB3 -> SINGLE
+    CD1 + CE1 -> AROMATIC_SINGLE
+    CD1 + HD1 -> SINGLE
+    CD2 + CE2 -> AROMATIC_DOUBLE
+    CD2 + HD2 -> SINGLE
+    CE1 + CZ  -> AROMATIC_DOUBLE
+    CE1 + HE1 -> SINGLE
+    CE2 + CZ  -> AROMATIC_SINGLE
+    CE2 + HE2 -> SINGLE
+    CD1 + CG  -> AROMATIC_DOUBLE
+    CD2 + CG  -> AROMATIC_SINGLE
+    CZ  + HZ  -> SINGLE
+    CA  + N   -> SINGLE
+    H   + N   -> SINGLE
+    H2  + N   -> SINGLE
+    HXT + OXT -> SINGLE
     """
     global _intra_bonds
     if res_name not in _intra_bonds:

src/biotite/structure/io/__init__.py

@@ -18,8 +18,8 @@
 The recommended format for reading structure files is *BinaryCIF*.
 It has by far the shortest parsing time and file size.
 
-Besides the mentioned structure formats, Gromacs trajectory files can be
-loaded, if `mdtraj` is installed.
+Besides the mentioned structure formats, common trajectory formats can be
+loaded as well.
 """
 
 __name__ = "biotite.structure.io"

src/biotite/structure/io/dcd/file.py

@@ -6,6 +6,7 @@
 __author__ = "Patrick Kunzmann"
 __all__ = ["DCDFile"]
 
+import biotraj
 import numpy as np
 from biotite.structure.box import unitcell_from_vectors, vectors_from_unitcell
 from biotite.structure.io.trajfile import TrajectoryFile
@@ -18,9 +19,7 @@ class DCDFile(TrajectoryFile):
 
     @classmethod
     def traj_type(cls):
-        import mdtraj.formats as traj
-
-        return traj.DCDTrajectoryFile
+        return biotraj.DCDTrajectoryFile
 
     @classmethod
     def process_read_values(cls, read_values):