Added transformation return to orient_principal_components

doc/apidoc.json

@@ -465,11 +465,13 @@
     "biotite.structure.alphabet" : {
         "Structural alphabets": [
             "I3DSequence",
-            "ProteinBlocksSequence"
+            "ProteinBlocksSequence",
+            "ClepapsSequence"
         ],
         "Conversion Function": [
             "to_3di",
-            "to_protein_blocks"
+            "to_protein_blocks",
+            "to_clepaps"
         ]
     }
 }

doc/examples/scripts/structure/modeling/docking.py

@@ -65,7 +65,8 @@
 # of the original ligand position
 app = autodock.VinaApp(ligand, receptor, ref_ligand_center, [20, 20, 20])
 # For reproducibility
-app.set_seed(0)
+# (Vina interprets seed 0 as a request for a random seed, so use a non-zero one)
+app.set_seed(42)
 app.set_cpu(1)
 # This is the maximum number:
 # Vina may find less interesting binding modes

doc/references.bib

@@ -917,6 +917,21 @@ @article{Varadi2024
   doi = {10.1093/nar/gkad1011}
 }
 
+@article{Wang2008,
+  title = {{{CLePAPS}}: {{FAST PAIR ALIGNMENT OF PROTEIN STRUCTURES BASED ON CONFORMATIONAL LETTERS}}},
+  shorttitle = {{{CLePAPS}}},
+  author = {Wang, Sheng and Zheng, Wei-Mou},
+  year = {2008},
+  month = apr,
+  journal = {Journal of Bioinformatics and Computational Biology},
+  volume = {06},
+  number = {02},
+  pages = {347--366},
+  publisher = {World Scientific Publishing Co.},
+  issn = {0219-7200},
+  doi = {10.1142/S0219720008003461}
+}
+
 @article{Westbrook2015,
   title = {The Chemical Component Dictionary: Complete Descriptions of Constituent Molecules in Experimentally Determined {{3D}} Macromolecules in the {{Protein Data Bank}}},
   shorttitle = {The Chemical Component Dictionary},

src/biotite/application/sra/app.py

@@ -14,7 +14,6 @@
 from os.path import join
 from subprocess import PIPE, Popen, SubprocessError, TimeoutExpired
 from tempfile import TemporaryDirectory
-from typing import Literal, TypeAlias
 import numpy as np
 from biotite.application.application import (
     Application,
@@ -28,10 +27,6 @@
 from biotite.sequence.io.fastq.file import FastqFile
 from biotite.sequence.seqtypes import NucleotideSequence
 
-_OffsetFormat: TypeAlias = Literal[
-    "Sanger", "Solexa", "Illumina-1.3", "Illumina-1.5", "Illumina-1.8"
-]
-
 
 # Do not use LocalApp, as two programs are executed
 class _DumpApp(Application, metaclass=abc.ABCMeta):
@@ -237,11 +232,11 @@ class FastqDumpApp(_DumpApp):
     prefetch_path, fasterq_dump_path : str, optional
         Path to the ``prefetch_path`` and ``fasterq-dump`` binary,
         respectively.
-    offset : int or {'Sanger', 'Solexa', 'Illumina-1.3', 'Illumina-1.5', 'Illumina-1.8'}, optional
+    offset : int or FastqFile.Offset, optional
         This value is subtracted from the FASTQ ASCII code to obtain the
         quality score.
-        Can either be directly the value, or a string that indicates
-        the score format.
+        Can be provided directly as integer or as a member of
+        :class:`FastqFile.Offset`.
     """
 
     def __init__(
@@ -250,10 +245,10 @@ def __init__(
         output_path_prefix: PathLike[str] | str | None = None,
         prefetch_path: PathLike[str] | str = "prefetch",
         fasterq_dump_path: PathLike[str] | str = "fasterq-dump",
-        offset: int | _OffsetFormat = "Sanger",
+        offset: int | FastqFile.Offset = FastqFile.Offset.SANGER,
     ) -> None:
         super().__init__(uid, output_path_prefix, prefetch_path, fasterq_dump_path)
-        self._offset: int | _OffsetFormat = offset
+        self._offset: int | FastqFile.Offset = offset
         self._fastq_files: list[FastqFile] | None = None
 
     @requires_state(AppState.JOINED)
@@ -312,7 +307,7 @@ def fetch(
         output_path_prefix: PathLike[str] | str | None = None,
         prefetch_path: PathLike[str] | str = "prefetch",
         fasterq_dump_path: PathLike[str] | str = "fasterq-dump",
-        offset: int | _OffsetFormat = "Sanger",
+        offset: int | FastqFile.Offset = FastqFile.Offset.SANGER,
     ) -> list[dict[str, NucleotideSequence]]:
         """
         Get the sequences belonging to the UID from the
@@ -333,11 +328,11 @@ def fetch(
         prefetch_path, fasterq_dump_path : str, optional
             Path to the ``prefetch_path`` and ``fasterq-dump`` binary,
             respectively.
-        offset : int or {'Sanger', 'Solexa', 'Illumina-1.3', 'Illumina-1.5', 'Illumina-1.8'}, optional
+        offset : int or FastqFile.Offset, optional
             This value is subtracted from the FASTQ ASCII code to obtain the
             quality score.
-            Can either be directly the value, or a string that indicates
-            the score format.
+            Can be provided directly as integer or as a member of
+            :class:`FastqFile.Offset`.
 
         Returns
         -------

src/biotite/database/entrez/query.py

@@ -2,6 +2,8 @@
 # under the 3-Clause BSD License. Please see 'LICENSE.rst' for further
 # information.
 
+from __future__ import annotations
+
 __name__ = "biotite.database.entrez"
 __author__ = "Patrick Kunzmann"
 __all__ = ["Query", "SimpleQuery", "CompositeQuery", "search"]
@@ -31,17 +33,17 @@ def __init__(self) -> None:
     def __str__(self) -> str:
         pass
 
-    def __or__(self, operand: "Query | str") -> "CompositeQuery":
+    def __or__(self, operand: Query | str) -> CompositeQuery:
         if not isinstance(operand, Query):
             operand = SimpleQuery(operand)
         return CompositeQuery("OR", self, operand)
 
-    def __and__(self, operand: "Query | str") -> "CompositeQuery":
+    def __and__(self, operand: Query | str) -> CompositeQuery:
         if not isinstance(operand, Query):
             operand = SimpleQuery(operand)
         return CompositeQuery("AND", self, operand)
 
-    def __xor__(self, operand: "Query | str") -> "CompositeQuery":
+    def __xor__(self, operand: Query | str) -> CompositeQuery:
         if not isinstance(operand, Query):
             operand = SimpleQuery(operand)
         return CompositeQuery("NOT", self, operand)

src/biotite/database/pubchem/query.py

@@ -2,6 +2,8 @@
 # under the 3-Clause BSD License. Please see 'LICENSE.rst' for further
 # information.
 
+from __future__ import annotations
+
 __name__ = "biotite.database.pubchem"
 __author__ = "Patrick Kunzmann"
 __all__ = [
@@ -236,7 +238,7 @@ def from_atoms(
         atoms: AtomArray[N],
         allow_other_elements: bool = False,
         number: int | None = None,
-    ) -> "FormulaQuery":
+    ) -> FormulaQuery:
         """
         Create the query from an the given structure by using its
         molecular formula.
@@ -385,7 +387,7 @@ def from_atoms(
         atoms: AtomArray[N],
         *args: Any,
         **kwargs: Any,
-    ) -> "StructureQuery":
+    ) -> StructureQuery:
         """
         Create a query using the given query structure.
 

src/biotite/database/pubchem/throttle.py

@@ -2,6 +2,8 @@
 # under the 3-Clause BSD License. Please see 'LICENSE.rst' for further
 # information.
 
+from __future__ import annotations
+
 __name__ = "biotite.database.pubchem"
 __author__ = "Patrick Kunzmann"
 __all__ = ["ThrottleStatus"]
@@ -52,7 +54,7 @@ class ThrottleStatus:
     service: float
 
     @staticmethod
-    def from_response(response: requests.Response) -> "ThrottleStatus":
+    def from_response(response: requests.Response) -> ThrottleStatus:
         """
         Extract the throttle status from a *Pubchem* server response.
 

src/biotite/database/rcsb/query.py

@@ -2,6 +2,8 @@
 # under the 3-Clause BSD License. Please see 'LICENSE.rst' for further
 # information.
 
+from __future__ import annotations
+
 __name__ = "biotite.database.rcsb"
 __author__ = "Patrick Kunzmann, Maximilian Dombrowsky"
 __all__ = [
@@ -71,10 +73,10 @@ def get_content(self) -> dict[str, Any]:
         """
         pass
 
-    def __and__(self, query: "Query") -> "CompositeQuery":
+    def __and__(self, query: Query) -> CompositeQuery:
         return CompositeQuery([self, query], "and")
 
-    def __or__(self, query: "Query") -> "CompositeQuery":
+    def __or__(self, query: Query) -> CompositeQuery:
         return CompositeQuery([self, query], "or")
 
 
@@ -433,7 +435,7 @@ def get_content(self) -> dict[str, Any]:
             content["parameters"]["value"] = self._value
         return content
 
-    def __invert__(self) -> "FieldQuery":
+    def __invert__(self) -> FieldQuery:
         clone = copy.deepcopy(self)
         clone._negation = not clone._negation
         return clone
@@ -831,7 +833,7 @@ def is_compatible_return_type(self, return_type: str) -> bool:
 def count(
     query: Query,
     return_type: _ReturnType = "entry",
-    group_by: "Grouping | None" = None,
+    group_by: Grouping | None = None,
     content_types: Iterable[_ContentType] = ("experimental",),
 ) -> int:
     """

src/biotite/database/uniprot/query.py

@@ -2,6 +2,8 @@
 # under the 3-Clause BSD License. Please see 'LICENSE.rst' for further
 # information.
 
+from __future__ import annotations
+
 __name__ = "biotite.database.uniprot"
 __author__ = "Maximilian Greil"
 __all__ = ["Query", "SimpleQuery", "CompositeQuery", "search"]
@@ -27,13 +29,13 @@ def __init__(self) -> None:
     def __str__(self) -> str:
         pass
 
-    def __or__(self, operand: "Query") -> "CompositeQuery":
+    def __or__(self, operand: Query) -> CompositeQuery:
         return CompositeQuery("OR", self, operand)
 
-    def __and__(self, operand: "Query") -> "CompositeQuery":
+    def __and__(self, operand: Query) -> CompositeQuery:
         return CompositeQuery("AND", self, operand)
 
-    def __xor__(self, operand: "Query") -> "CompositeQuery":
+    def __xor__(self, operand: Query) -> CompositeQuery:
         return CompositeQuery("NOT", self, operand)
 
 

src/biotite/sequence/align/matrix.py

@@ -76,6 +76,7 @@ class SubstitutionMatrix(Generic[S1, S2]):
 
             - **3Di** - For 3Di alphabet from ``foldseek`` :footcite:`VanKempen2024`
             - **PB** - For Protein Blocks alphabet from *PBexplore* :footcite:`Barnoud2017`
+            - **CLESUM** - For CLePAPS alphabet :footcite:`Wang2008`
 
     A list of all available matrix names is returned by
     :meth:`list_db()`.
@@ -630,6 +631,50 @@ def std_protein_blocks_matrix(
             matrix_dict,
         )
 
+    @staticmethod
+    @functools.cache
+    def std_clepaps_matrix(
+        unknown_match: int = 200, unknown_mismatch: int = -200
+    ) -> SubstitutionMatrix[str, str]:
+        """
+        Get the *CLESUM* substitution matrix for *CLePAPS* sequence.
+        :footcite:`Wang2008`
+
+        Parameters
+        ----------
+        unknown_match, unknown_mismatch : int, optional
+            The match and mismatch score for the unknown symbol.
+            The default values were chosen arbitrarily, but are in the order of
+            magnitude of the other score values.
+
+        Returns
+        -------
+        matrix : SubstitutionMatrix
+            Default matrix.
+
+        References
+        ----------
+
+        .. footbibliography::
+        """
+        from biotite.structure.alphabet.clepaps import ClepapsSequence
+
+        alphabet = ClepapsSequence.alphabet
+        unknown_symbol = ClepapsSequence.unknown_symbol
+        matrix_dict = SubstitutionMatrix.dict_from_db("CLESUM")
+        # Add match/mismatch scores for the unknown symbol
+        for symbol in alphabet:
+            if symbol == unknown_symbol:
+                continue
+            matrix_dict[symbol, unknown_symbol] = unknown_mismatch
+            matrix_dict[unknown_symbol, symbol] = unknown_mismatch
+        matrix_dict[unknown_symbol, unknown_symbol] = unknown_match
+        return SubstitutionMatrix(
+            alphabet,
+            alphabet,
+            matrix_dict,
+        )
+
     def _fill_with_matrix_dict(self, matrix_dict: dict[tuple[Any, Any], int]) -> None:
         self._matrix = np.zeros((len(self._alph1), len(self._alph2)), dtype=np.int32)
         for i in range(len(self._alph1)):

src/biotite/sequence/align/matrix_data/CLESUM.mat

@@ -0,0 +1,19 @@
+# CLESUM: The conformation letter substitution matrix from the CLePAPS paper
+      A    B    C    D    E    F    G    H    I    J    K    L    M    N    O    P    Q
+A    73   20   13  -17  -25  -20   -6  -45  -31  -23  -19  -11   -2   10   25   35   16
+B    20   51    7   13   15    7   13  -96  -74  -57  -50  -12  -13  -11  -12   42   12
+C    13    7   53   21    3   20   -4  -77  -56  -43  -33    0  -12   -5    3    4   29
+D   -17   13   21   52   22   21  -31 -124 -105  -88  -81  -22  -49  -44  -42  -10   14
+E   -25   15    3   22   36   26  -22 -127 -108  -93  -84  -21  -47  -43  -48   -5   -6
+F   -20    7   20   21   26   50   -5 -107  -88  -73  -69  -16  -33  -32  -30    0    3
+G    -6   13   -4  -31  -22   -5   69  -51  -34  -21  -13   29   21   -8   -1    5    8
+H   -45  -96  -77 -124 -127 -107  -51   23   18   13    5  -62   -4  -34  -55  -60  -87
+I   -31  -74  -56 -105 -108  -88  -34   18   23   16   21  -41    1  -11  -34  -49  -62
+J   -23  -57  -43  -88  -93  -73  -21   13   16   37   13  -32   16   -2  -24  -34  -44
+K   -19  -50  -33  -81  -84  -69  -13    5   21   13   49   -1   12   28    5  -36  -24
+L   -11  -12    0  -22  -21  -16   29  -62  -41  -32   -1   74    5    8   -4  -12   26
+M    -2  -13  -12  -49  -47  -33   21   -4    1   16   12    5   61    7    5    8   -7
+N    10  -11   -5  -44  -43  -32   -8  -34  -11   -2   28    8    7   90   15   -3   32
+O    25  -12    3  -42  -48  -30   -1  -55  -34  -24    5   -4    5   15  104    4  -13
+P    35   42    4  -10   -5    0    5  -60  -49  -34  -36  -12    8   -3    4   66    7
+Q    16   12   29   14   -6    3    8  -87  -62  -44  -24   26   -7   32  -13    7   90

src/biotite/sequence/align/multiple.pyx

@@ -373,8 +373,8 @@ def _get_distance_matrix(CodeType[:] _T, sequences, matrix,
             for code1 in range(alphabet_size):
                 for code2 in range(alphabet_size):
                     score_rand += score_matrix[code1,code2] \
-                                  * code_count[i,code1] \
-                                  * code_count[j,code2]
+                                  * code_count_v[i,code1] \
+                                  * code_count_v[j,code2]
             score_rand /= alignments[i,j].trace.shape[0]
             gap_open_count, gap_ext_count = _count_gaps(
                 alignments[i,j].trace.astype(np.int64, copy=False),

src/biotite/sequence/graphics/plasmid.py

@@ -412,7 +412,7 @@ def __init__(
             else:
                 self._arrow_head = None
 
-            self._label: "CurvedText | None"
+            self._label: CurvedText | None
             if label is not None:
                 label_properties["color"] = label_color
                 self._label = CurvedText(