biotite 0.41.1__cp310-cp310-win_amd64.whl → 1.0.0__cp310-cp310-win_amd64.whl

biotite/database/uniprot/query.py

@@ -6,10 +6,9 @@ __name__ = "biotite.database.uniprot"
 __author__ = "Maximilian Greil"
 __all__ = ["Query", "SimpleQuery", "CompositeQuery", "search"]
 
-import requests
 import abc
-from .check import assert_valid_response
-
+import requests
+from biotite.database.uniprot.check import assert_valid_response
 
 _base_url = "https://rest.uniprot.org/uniprotkb/search/"
 
@@ -122,22 +121,114 @@ class SimpleQuery(Query):
     # Field identifiers are taken from
     # https://www.uniprot.org/help/query-fields
     _fields = [
-        "accession", "active", "ft_init_met", "ft_signal", "ft_transit", "ft_propep", "ft_chain", "ft_peptide",
-        "ft_topo_dom", "ft_transmem", "ft_intramem", "ft_domain", "ft_repeat", "ft_zn_fing", "ft_dna_bind",
-        "ft_region", "ft_coiled", "ft_motif", "ft_compbias", "ft_act_site", "ft_binding", "ft_site", "ft_non_std",
-        "ft_mod_res", "ft_lipid", "ft_carbohyd", "ft_disulfid", "ft_crosslnk", "ft_var_seq", "ft_variant",
-        "ft_mutagen", "ft_unsure", "ft_conflict", "ft_non_cons", "ft_non_ter", "ft_helix", "ft_turn", "ft_strand",
-        "lit_author", "protein_name", "chebi", "citation", "uniref_cluster_90", "xrefcount_pdb", "date_created",
-        "database", "xref", "ec", "cc_function", "cc_catalytic_activity", "cc_cofactor", "cc_activity_regulation",
-        "cc_biophysicochemical_properties", "cc_subunit", "cc_pathway", "cc_scl_term", "cc_tissue_specificity",
-        "cc_developmental_stage", "cc_induction", "cc_domain", "cc_ptm cc_rna_editing", "cc_mass_spectrometry",
-        "cc_polymorphism", "cc_disease", "cc_disruption_phenotype", "cc_allergen", "cc_toxic_dose", "cc_biotechnology",
-        "cc_pharmaceutical", "cc_miscellaneous", "cc_similarity", "cc_caution", "cc_sequence_caution",
-        "existence", "family", "fragment", "gene", "gene_exact", "go", "virus_host_name", "virus_host_id",
-        "accession_id", "inchikey", "protein_name", "interactor", "keyword", "length", "lineage", "mass",
-        "cc_mass_spectrometry", "date_modified", "protein_name", "organelle", "organism_name", "organism_id",
-        "plasmid", "proteome", "proteomecomponent", "sec_acc", "reviewed", "scope", "sequence",
-        "date_sequence_modified", "strain", "taxonomy_name", "taxonomy_id", "tissue", "cc_webresource"
+        "accession",
+        "active",
+        "ft_init_met",
+        "ft_signal",
+        "ft_transit",
+        "ft_propep",
+        "ft_chain",
+        "ft_peptide",
+        "ft_topo_dom",
+        "ft_transmem",
+        "ft_intramem",
+        "ft_domain",
+        "ft_repeat",
+        "ft_zn_fing",
+        "ft_dna_bind",
+        "ft_region",
+        "ft_coiled",
+        "ft_motif",
+        "ft_compbias",
+        "ft_act_site",
+        "ft_binding",
+        "ft_site",
+        "ft_non_std",
+        "ft_mod_res",
+        "ft_lipid",
+        "ft_carbohyd",
+        "ft_disulfid",
+        "ft_crosslnk",
+        "ft_var_seq",
+        "ft_variant",
+        "ft_mutagen",
+        "ft_unsure",
+        "ft_conflict",
+        "ft_non_cons",
+        "ft_non_ter",
+        "ft_helix",
+        "ft_turn",
+        "ft_strand",
+        "lit_author",
+        "protein_name",
+        "chebi",
+        "citation",
+        "uniref_cluster_90",
+        "xrefcount_pdb",
+        "date_created",
+        "database",
+        "xref",
+        "ec",
+        "cc_function",
+        "cc_catalytic_activity",
+        "cc_cofactor",
+        "cc_activity_regulation",
+        "cc_biophysicochemical_properties",
+        "cc_subunit",
+        "cc_pathway",
+        "cc_scl_term",
+        "cc_tissue_specificity",
+        "cc_developmental_stage",
+        "cc_induction",
+        "cc_domain",
+        "cc_ptm cc_rna_editing",
+        "cc_mass_spectrometry",
+        "cc_polymorphism",
+        "cc_disease",
+        "cc_disruption_phenotype",
+        "cc_allergen",
+        "cc_toxic_dose",
+        "cc_biotechnology",
+        "cc_pharmaceutical",
+        "cc_miscellaneous",
+        "cc_similarity",
+        "cc_caution",
+        "cc_sequence_caution",
+        "existence",
+        "family",
+        "fragment",
+        "gene",
+        "gene_exact",
+        "go",
+        "virus_host_name",
+        "virus_host_id",
+        "accession_id",
+        "inchikey",
+        "protein_name",
+        "interactor",
+        "keyword",
+        "length",
+        "lineage",
+        "mass",
+        "cc_mass_spectrometry",
+        "date_modified",
+        "protein_name",
+        "organelle",
+        "organism_name",
+        "organism_id",
+        "plasmid",
+        "proteome",
+        "proteomecomponent",
+        "sec_acc",
+        "reviewed",
+        "scope",
+        "sequence",
+        "date_sequence_modified",
+        "strain",
+        "taxonomy_name",
+        "taxonomy_id",
+        "tissue",
+        "cc_webresource",
     ]
 
     def __init__(self, field, term):
@@ -146,14 +237,11 @@ class SimpleQuery(Query):
             raise ValueError(f"Unknown field identifier '{field}'")
         if not _check_brackets(term):
             raise ValueError(
-                f"Query term contains illegal number of round brackets ( ) and/or square brackets [ ]"
+                "Query term contains illegal number of round brackets ( ) and/or square brackets [ ]"
             )
-        for invalid_string in \
-                ['"', "AND", "OR", "NOT", "\t", "\n"]:
+        for invalid_string in ['"', "AND", "OR", "NOT", "\t", "\n"]:
             if invalid_string in term:
-                raise ValueError(
-                    f"Query contains illegal term {invalid_string}"
-                )
+                raise ValueError(f"Query contains illegal term {invalid_string}")
         if " " in term:
             term = f'"{term}"'
         self._field = field
@@ -198,12 +286,8 @@ def search(query, number=500):
     ['P12345']
     """
 
-    params = {
-        'query': str(query),
-        'format': 'list',
-        'size': str(number)
-    }
+    params = {"query": str(query), "format": "list", "size": str(number)}
     r = requests.get(_base_url, params=params)
     content = r.text
     assert_valid_response(r.status_code)
-    return content.split('\n')[:-1]
+    return content.split("\n")[:-1]

biotite/file.py

@@ -4,16 +4,19 @@
 
 __name__ = "biotite"
 __author__ = "Patrick Kunzmann"
-__all__ = ["File", "TextFile", "InvalidFileError",
-           "SerializationError", "DeserializationError"]
+__all__ = [
+    "File",
+    "TextFile",
+    "InvalidFileError",
+    "SerializationError",
+    "DeserializationError",
+]
 
 import abc
+import copy
 import io
-import warnings
 from os import PathLike
-
-from .copyable import Copyable
-import copy
+from biotite.copyable import Copyable
 
 
 class File(Copyable, metaclass=abc.ABCMeta):
@@ -27,13 +30,6 @@ class File(Copyable, metaclass=abc.ABCMeta):
     :func:`write()` method is used.
     """
 
-    def __init__(self):
-        # Support for deprecated instance method 'read()':
-        # When creating an instance, the 'read()' class method is
-        # replaced by the instance method, so that subsequent
-        # 'read()' calls are delegated to the instance method
-        self.read = self._deprecated_read
-
     @classmethod
     @abc.abstractmethod
     def read(cls, file):
@@ -54,23 +50,6 @@ class File(Copyable, metaclass=abc.ABCMeta):
         """
         pass
 
-    def _deprecated_read(self, file, *args, **kwargs):
-        """
-        Support for deprecated instance method :func:`read()`.
-
-        Internally this calls the :func:`read()` class method and
-        replaces the data in `self` with the data from the newly created
-        :class:`File` object
-        """
-        warnings.warn(
-            "Instance method 'read()' is deprecated, "
-            "use class method instead",
-            DeprecationWarning
-        )
-        cls = type(self)
-        new_file = cls.read(file, *args, **kwargs)
-        self.__dict__.update(new_file.__dict__)
-
     @abc.abstractmethod
     def write(self, file):
         """
@@ -209,12 +188,14 @@ class InvalidFileError(Exception):
     either because the file does not contain the required data or
     because the file is malformed.
     """
+
     pass
 
 
 class SerializationError(Exception):
     pass
 
+
 class DeserializationError(Exception):
     pass
 
@@ -229,7 +210,7 @@ def wrap_string(text, width):
     """
     lines = []
     for i in range(0, len(text), width):
-        lines.append(text[i : i+width])
+        lines.append(text[i : i + width])
     return lines
 
 

biotite/sequence/__init__.py

@@ -24,7 +24,15 @@ For example, ``'A'``, ``'C'``, ``'G'`` and ``'T'`` would be encoded into
 These integer values are called *symbol code*, the encoding of an entire
 sequence of symbols is called *sequence code*.
 
-The size of the symbol code type in the array is determined by the 
+.. figure:: /static/assets/figures/symbol_encoding.png
+    :alt: Symbol encoding in Biotite
+    :scale: 50%
+
+    Taken from
+    `Kunzmann & Hamacher 2018 <https://doi.org/10.1186/s12859-018-2367-z>`_
+    licensed under `CC BY 4.0 <https://creativecommons.org/licenses/by/4.0/>`_.
+
+The size of the symbol code type in the array is determined by the
 size of the :class:`Alphabet`:
 If the :class:`Alphabet` contains 256 symbols or less, one byte is used
 per array element, between 257 and 65536 symbols, two bytes are used,
@@ -41,6 +49,7 @@ This approach has multiple advantages:
       indifferent to the actual type of sequence.
     - Symbol codes are directly indices for substitution matrices in
       alignments
+    - *k-mers* can be computed fast
 
 The abstract :class:`Sequence` superclass cannot be instantiated
 directly, as it does not define an :class:`Alphabet` by itself.
@@ -55,19 +64,21 @@ The class :class:`GeneralSequence` allows the usage of a custom
 Additionally, this subpackage provides support for sequence features,
 as used in e.g. GenBank or GFF files.
 A :class:`Feature` stores its key name, its qualifiers and locations.
-An :class:`Annotation` is a group of multiple :class:`Feataure` objects
+An :class:`Annotation` is a group of multiple :class:`Feature` objects
 and offers convenient location based indexing.
 An :class:`AnnotatedSequence` combines an :class:`Annotation` and a
 :class:`Sequence`.
+
+Sequence profiles can be created with the :class:`SequenceProfile` class.
 """
 
 __name__ = "biotite.sequence"
 __author__ = "Patrick Kunzmann"
 
 from .alphabet import *
+from .annotation import *
+from .codon import *
+from .profile import *
 from .search import *
 from .seqtypes import *
 from .sequence import *
-from .codon import *
-from .annotation import *
-from .profile import *

biotite/sequence/align/__init__.py

@@ -22,11 +22,165 @@ These objects contain the original sequences and a trace, that describe
 which positions (indices) in the sequences are aligned.
 Optionally they also contain the similarity score.
 
-The aligning functions are usually C-accelerated, reducing the
-computation time substantially.
+The aligning functions :func:`align_optimal()` and
+:func:`align_multiple()` cover most use cases for pairwise and multiple
+sequence alignments respectively.
+
+However, *Biotite* provides also a modular system to build performant
+heuristic alignment search methods, e.g. for finding homologies in a sequence
+database or map reads to a genome.
+The table below summarizes those provided functionalities.
+The typical stages in alignment search, where those functionalities are used,
+are arranged from top to bottom.
+
+.. grid::
+    :gutter: 0
+    :class-container: sd-text-center
+
+    .. grid-item::
+        :padding: 2
+        :outline:
+        :columns: 3
+
+        **Entire k-mer set**
+
+    .. grid-item::
+        :padding: 2
+        :outline:
+        :columns: 9
+
+        .. grid::
+            :margin: 0
+
+            .. grid-item::
+                :padding: 2
+                :columns: 12
+
+                **k-mer subset selection**
+
+            .. grid-item::
+                :padding: 2
+                :columns: 4
+
+                Minimizers
+
+                :class:`MinimizerSelector`
+
+            .. grid-item::
+                :padding: 2
+                :columns: 4
+
+                Syncmers
+
+                :class:`SyncmerSelector`
+
+                :class:`CachedSyncmerSelector`
+
+            .. grid-item::
+                :padding: 2
+                :columns: 4
+
+                Mincode
+
+                :class:`MincodeSelector`
+
+
+    .. grid-item::
+        :padding: 2
+        :outline:
+        :columns: 12
+
+        .. grid::
+            :margin: 0
+
+            .. grid-item::
+                :padding: 2
+                :columns: 12
+
+                **k-mer indexing and matching**
+
+            .. grid-item::
+                :padding: 2
+                :columns: 6
+
+                Perfect hashing
+
+                :class:`KmerTable`
+
+            .. grid-item::
+                :padding: 2
+                :columns: 6
+
+                Space-efficient hashing
+
+                :class:`BucketKmerTable`
+
+                :func:`bucket_number()`
+
+
+    .. grid-item::
+        :padding: 2
+        :outline:
+        :columns: 12
+
+        .. grid::
+            :margin: 0
+
+            .. grid-item::
+                :padding: 2
+                :columns: 12
+
+                **Ungapped seed extension**
+
+                :class:`align_local_ungapped()`
+
+
+    .. grid-item::
+        :padding: 2
+        :outline:
+        :columns: 12
+
+        .. grid::
+            :margin: 0
+
+            .. grid-item::
+                :padding: 2
+                :columns: 12
+
+                **Gapped alignment**
+
+            .. grid-item::
+                :padding: 2
+                :columns: 6
+
+                Banded local/semiglobal alignment
+
+                :class:`align_banded()`
+
+            .. grid-item::
+                :padding: 2
+                :columns: 6
+
+                Local alignment (*X-drop*)
+
+                :class:`align_local_gapped()`
+
+    .. grid-item::
+        :padding: 2
+        :outline:
+        :columns: 12
+
+        .. grid::
+            :margin: 0
+
+            .. grid-item::
+                :padding: 2
+                :columns: 12
+
+                **Significance evaluation**
+
+                :class:`EValueEstimator`
 
-This subpackage also contains functionality for finding *k-mer* matches
-between two sequences, allowing fast heuristic pairwise alignments.
 """
 
 __name__ = "biotite.sequence.align"
@@ -37,8 +191,8 @@ from .banded import *
 from .buckets import *
 from .cigar import *
 from .kmeralphabet import *
-from .kmertable import *
 from .kmersimilarity import *
+from .kmertable import *
 from .localgapped import *
 from .localungapped import *
 from .matrix import *
@@ -46,4 +200,4 @@ from .multiple import *
 from .pairwise import *
 from .permutation import *
 from .selector import *
-from .statistics import *
+from .statistics import *