biointerface 0.2.2__tar.gz → 0.3.0__tar.gz

biointerface-0.3.0/HISTORY.rst

@@ -0,0 +1,47 @@
+=======
+History
+=======
+
+0.1.0 (2025-02-08)
+------------------
+
+* First release on PyPI.
+
+
+0.2.0 (2025-02-28)
+------------------
+
+* Features: Interface class, with getter methods for atoms, dataframes etc
+
+
+0.2.1 (2025-03-1)
+------------------
+
+* Gitlab CI
+
+
+0.2.2 (2025-03-04)
+------------------
+
+* Interface methods to get residues
+
+* Interface raise error condition in case of no protein in the structure
+
+* Coverage badge on README
+
+* Full documentation
+
+
+0.2.3 (2025-03-05)
+------------------
+
+* fix: bump-my-version was updating pdbnucleicacids version too
+
+* fix: import classes instead of modules
+
+* chore: remove old tox environments
+
+
+0.3.0 (2025-03-05)
+
+* Feature: get all continous protein-bound double-strand nucleic acids;

{biointerface-0.2.2 → biointerface-0.3.0}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.2
 Name: biointerface
-Version: 0.2.2
-Summary: BioInterface is a python package capable of extracting Protein-DNA interfaces from PDB/mmCif structures.
+Version: 0.3.0
+Summary: BioInterface is a Biopython based package that extracts Protein-DNA interfaces in a PDB structures.
 Author-email: Alessandro Pandolfi <alessandro.pandolfi@protonmail.com>
 Maintainer-email: Alessandro Pandolfi <alessandro.pandolfi@protonmail.com>
 License: MIT license
@@ -14,7 +14,7 @@ License-File: LICENSE
 License-File: AUTHORS.rst
 Requires-Dist: pandas
 Requires-Dist: biopython
-Requires-Dist: pdbnucleicacids>=0.2
+Requires-Dist: pdbnucleicacids>=0.2.1
 Provides-Extra: dev
 Requires-Dist: coverage; extra == "dev"
 Requires-Dist: mypy; extra == "dev"
@@ -101,12 +101,12 @@ Feaures
 
 * Interface data as ``pandas`` DataFrame;
 
+* Get all continous protein-bound double-strand nucleic acids;
+
 
 TODO
 --------
 
-* Extract continous bound DNA sequence
-
 * Proper tests (WIP)
 
 

{biointerface-0.2.2 → biointerface-0.3.0}/README.rst

@@ -78,12 +78,12 @@ Feaures
 
 * Interface data as ``pandas`` DataFrame;
 
+* Get all continous protein-bound double-strand nucleic acids;
+
 
 TODO
 --------
 
-* Extract continous bound DNA sequence
-
 * Proper tests (WIP)
 
 

{biointerface-0.2.2 → biointerface-0.3.0}/docs/usage.rst

@@ -35,7 +35,7 @@ You can extract a single Protein-DNA interface from a single protein chain.
     # extract interface from a specific protein chain
     face = Interface(
         structure=structure,
-        protein_chain_id="A",
+        protein_chain_id="F",
         search_radius=5.0
     )
     face
@@ -119,7 +119,7 @@ First of all you can get all interacting atoms as atom pairs.
 
 .. code-block:: python
 
-    contacts = face.get_get_atomic_contacts()
+    contacts = face.get_atomic_contacts()
     contacts[:5]
 
 .. code-block:: console
@@ -192,3 +192,34 @@ You can get all Protein-DNA interface features as a ``pandas`` DataFrame.
     257                F                                157  ...           4.299844
 
     [258 rows x 23 columns]
+
+
+Protein-Bound Nucleic Acids
+---------------------------
+
+BioInterface can extract all double-strand nucleic acids bound by
+the input protein, as a ``DoubleStrandNucleicAcid`` class from the package
+PDBNucleicAcids_.
+
+.. code-block:: python
+
+    bound_dsna_list = face.get_bound_double_strands()
+    bound_dsna = dsna_list[0]
+    bound_dsna
+
+.. code-block:: console
+
+    <DoubleStrandNucleicAcid type='dsDNA' i-th strand='A' j-th strand='B'
+     length=9>
+
+The ``DoubleStrandNucleicAcid`` class has other useful methods.
+
+.. code-block:: python
+
+    bound_dsna.get_i_strand().get_seq()
+
+.. code-block:: console
+
+    Seq('GTTTCATAG')
+
+.. _PDBNucleicAcids: https://gitlab.com/MorfeoRenai/pdbnucleicacids

{biointerface-0.2.2 → biointerface-0.3.0}/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "biointerface"
-version = "0.2.2"
-description = "BioInterface is a python package capable of extracting Protein-DNA interfaces from PDB/mmCif structures."
+version = "0.3.0"
+description = "BioInterface is a Biopython based package that extracts Protein-DNA interfaces in a PDB structures."
 readme = "README.rst"
 authors = [
   {name = "Alessandro Pandolfi", email = "alessandro.pandolfi@protonmail.com"}
@@ -20,7 +20,7 @@ license = {text = "MIT license"}
 dependencies = [
     "pandas",
     "biopython",
-    "pdbnucleicacids >= 0.2",
+    "pdbnucleicacids >= 0.2.1",
 ]
 
 [project.optional-dependencies]
@@ -32,7 +32,6 @@ dev = [
 ]
 
 [project.urls]
-
 bugs = "https://gitlab.com/MorfeoRenai/biointerface/-/issues"
 changelog = "https://gitlab.com/MorfeoRenai/biointerface/-/blob/main/HISTORY.rst"
 homepage = "https://gitlab.com/MorfeoRenai/biointerface"
@@ -44,8 +43,6 @@ package-dir = {"" = "src"}
 "*" = ["*.*"]
 
 
-
-
 # Mypy
 # ----
 
@@ -64,8 +61,6 @@ allow_untyped_defs = true
 disable_error_code = "attr-defined"
 
 
-
-
 # pytest
 # ----
 
@@ -77,13 +72,11 @@ testpaths = [
 ]
 
 
-
-
 # bump-my-version
 # ----
 
 [tool.bumpversion]
-current_version = "0.2.2"
+current_version = "0.3.0"
 parse = "(?P<major>\\d+)\\.(?P<minor>\\d+)\\.(?P<patch>\\d+)"
 serialize = ["{major}.{minor}.{patch}"]
 search = "{current_version}"
@@ -91,7 +84,7 @@ replace = "{new_version}"
 regex = false
 ignore_missing_version = false
 ignore_missing_files = false
-tag = false
+tag = true
 sign_tags = false
 tag_name = "v{new_version}"
 tag_message = "Bump version: {current_version} → {new_version}"
@@ -110,10 +103,8 @@ replace = "{new_version}"
 
 [[tool.bumpversion.files]]
 filename = "pyproject.toml"
-search = "{current_version}"
-replace = "{new_version}"
-
-
+search = 'version = "{current_version}"'
+replace = 'version = "{new_version}"'
 
 
 # ruff
@@ -131,8 +122,6 @@ show-fixes = true
 extend-select = ["E501"]
 
 
-
-
 # tox
 # ----
 
@@ -140,7 +129,7 @@ extend-select = ["E501"]
 #requires = ["tox>=4.19"]
 requires = ["tox"]
 # Elenco delle versioni di Python con cui testare
-envlist = ["py38", "py39", "py310", "py311", "py312", "py313"]
+envlist = ["py310", "py311", "py312", "py313"]
 
 [tool.tox.env_run_base]  # Configurazione generale per tutti gli ambienti di test
 description = "Run the tests with pytest"
@@ -172,3 +161,4 @@ description = "Run the tests on Python 3.13"
 #description = "Run linting"
 #deps = ["flake8"]
 #commands = ["flake8 src tests"]
+

{biointerface-0.2.2 → biointerface-0.3.0}/src/biointerface/__init__.py

@@ -4,6 +4,6 @@ from biointerface.core import Interface, build_interfaces
 
 __author__ = """Alessandro Pandolfi"""
 __email__ = "alessandro.pandolfi@protonmail.com"
-__version__ = "0.2.2"
+__version__ = "0.3.0"
 
 __all__ = ["Interface", "build_interfaces"]

{biointerface-0.2.2 → biointerface-0.3.0}/src/biointerface/core.py

@@ -2,15 +2,26 @@
 
 from Bio.PDB.Polypeptide import PPBuilder
 from Bio.PDB.NeighborSearch import NeighborSearch
-from Bio.PDB import Atom, Residue
+from Bio.PDB.Residue import Residue
+from Bio.PDB.Atom import Atom
 from Bio.PDB.PDBExceptions import PDBConstructionException
 
-# from Bio.PDB import Structure, Model, Chain
+# from Bio.PDB.Structure import Structure
+# from Bio.PDB.Model import Model
+# from Bio.PDB.Chain import Chain
 # from Bio.PDB import MMCIFIO
 
 import pandas as pd
 
-from PDBNucleicAcids.NucleicAcid import NABuilder
+from PDBNucleicAcids.NucleicAcid import (
+    NABuilder,
+    DSNABuilder,
+    DoubleStrandNucleicAcid,
+)
+
+import copy
+
+import warnings
 
 
 def build_interfaces(structure, search_radius=5.0) -> list:
@@ -95,7 +106,7 @@ class Interface:
 
     def _extract_contacts(self) -> list[tuple[Atom]]:
         """
-        Extract interface contacts.
+        Extract interface contacts (PRIVATE).
 
         Raises
         ------
@@ -355,6 +366,70 @@ chain id: {self.protein_chain_id}"
 
         return df
 
+    def get_bound_double_strands(self) -> list[DoubleStrandNucleicAcid]:
+        """
+        Get all double-strand nucleic acids bound by the protein.
+
+        The output double stranded nucleic acids (DSNAs) are subsequences
+        of the full DSNAs found in the structure,
+        since proteins usually do not bind the whole DSNA.
+
+        This method allows for "gaps" of unbound base-pairs inside the
+        DSNA, only the base pairs at the ends are trimmed accourding
+        to being protein-bound or not.
+
+        A visual example of "gaps":
+            ```
+            Input full DSNA:            GATATACAAGCCA
+            Protein-bound:                ****  **
+            Output protein-bound DSNA:    TATACAAG
+            ```
+
+        Returns
+        -------
+        bound_dsna_list : list[DoubleStrandNucleicAcid]
+            List of double-strand nucleic acids bound by the protein.
+
+        """
+        bound_nucleotides = self.get_nucleotides()
+
+        builder = DSNABuilder()
+        dsna_list = builder.build_double_strands(self.structure)
+        bound_dsna_list = []
+        for dsna in dsna_list:
+            bound_dsna = copy.copy(dsna)
+            while (
+                bound_dsna[0].i_res not in bound_nucleotides
+                and bound_dsna[0].j_res not in bound_nucleotides
+            ):
+                # if the FIRST base pair isn't bound by protein
+                # then discard it and check the next FIRST base pair
+                bound_dsna.pop(0)
+
+            while (
+                bound_dsna[-1].i_res not in bound_nucleotides
+                and bound_dsna[-1].j_res not in bound_nucleotides
+            ):
+                # if the LAST base pair isn't bound by protein
+                # then discard it and check the next LAST base pair
+                bound_dsna.pop(-1)
+
+            if len(bound_dsna) > 0:
+                # in this case, there is an actual bound DSNA
+                bound_dsna_list.append(bound_dsna)
+
+                for bp in bound_dsna:
+                    if (
+                        bp.i_res not in bound_nucleotides
+                        and bp.j_res not in bound_nucleotides
+                    ):
+                        warnings.warn(
+                            f"Warning: there are unbound base-pairs \
+inside the resulting DoubleStrandNucleicAcid - {bp}"
+                        )
+
+        return bound_dsna_list
+
 
 # def export_atom_list(structure_id, atom_list, out_filepath):
 #     """Export atom list."""

{biointerface-0.2.2 → biointerface-0.3.0}/src/biointerface.egg-info/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.2
 Name: biointerface
-Version: 0.2.2
-Summary: BioInterface is a python package capable of extracting Protein-DNA interfaces from PDB/mmCif structures.
+Version: 0.3.0
+Summary: BioInterface is a Biopython based package that extracts Protein-DNA interfaces in a PDB structures.
 Author-email: Alessandro Pandolfi <alessandro.pandolfi@protonmail.com>
 Maintainer-email: Alessandro Pandolfi <alessandro.pandolfi@protonmail.com>
 License: MIT license
@@ -14,7 +14,7 @@ License-File: LICENSE
 License-File: AUTHORS.rst
 Requires-Dist: pandas
 Requires-Dist: biopython
-Requires-Dist: pdbnucleicacids>=0.2
+Requires-Dist: pdbnucleicacids>=0.2.1
 Provides-Extra: dev
 Requires-Dist: coverage; extra == "dev"
 Requires-Dist: mypy; extra == "dev"
@@ -101,12 +101,12 @@ Feaures
 
 * Interface data as ``pandas`` DataFrame;
 
+* Get all continous protein-bound double-strand nucleic acids;
+
 
 TODO
 --------
 
-* Extract continous bound DNA sequence
-
 * Proper tests (WIP)
 
 

{biointerface-0.2.2 → biointerface-0.3.0}/src/biointerface.egg-info/requires.txt

@@ -1,6 +1,6 @@
 pandas
 biopython
-pdbnucleicacids>=0.2
+pdbnucleicacids>=0.2.1
 
 [dev]
 coverage

biointerface-0.2.2/HISTORY.rst

@@ -1,14 +0,0 @@
-=======
-History
-=======
-
-0.1.0 (2025-02-08)
-------------------
-
-* First release on PyPI.
-
-
-0.2.0 (2025-02-28)
-------------------
-
-* Feature: Interface class, with getter methods for atoms, dataframes etc