biointerface 0.3.2__tar.gz → 0.4.0__tar.gz

{biointerface-0.3.2 → biointerface-0.4.0}/CONTRIBUTING.rst

@@ -110,7 +110,7 @@ Before you submit a pull request, check that it meets these guidelines:
 2. If the pull request adds functionality, the docs should be updated. Put
    your new functionality into a function with a docstring, and add the
    feature to the list in README.rst.
-3. The pull request should work for Python 3.10, 3.11, 3.12 and 3.13,
+3. The pull request should work for Python 3.10, 3.11, 3.12 and 3.13
    and for PyPy. Make sure that the tests pass for all supported Python versions.
 
 Tips

{biointerface-0.3.2 → biointerface-0.4.0}/HISTORY.rst

@@ -2,6 +2,13 @@
 History
 =======
 
+
+0.3.2 (2025-03-10)
+------------------
+
+* Fix: for getting bound double-strands, if one DSNA empties during trimming it raised error
+
+
 0.3.1 (2025-03-05)
 ------------------
 

{biointerface-0.3.2 → biointerface-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: biointerface
-Version: 0.3.2
+Version: 0.4.0
 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>
@@ -29,6 +29,7 @@ Requires-Dist: bump-my-version; extra == "dev"
 Requires-Dist: wheel; extra == "dev"
 Requires-Dist: build; extra == "dev"
 Requires-Dist: twine; extra == "dev"
+Dynamic: license-file
 
 ============
 BioInterface
@@ -46,10 +47,6 @@ BioInterface
         :target: https://gitlab.com/MorfeoRenai/biointerface/-/commits/main
         :alt: Coverage Status
 
-.. image:: https://pyup.io/repos/github/MorfeoRenai/biointerface/shield.svg
-     :target: https://pyup.io/repos/github/MorfeoRenai/biointerface/
-     :alt: Updates
-
 
 BioInterface is a `Biopython <https://biopython.org/>`_ based package that extracts Protein-DNA
 interfaces in a PDB structures.

{biointerface-0.3.2 → biointerface-0.4.0}/README.rst

@@ -14,10 +14,6 @@ BioInterface
         :target: https://gitlab.com/MorfeoRenai/biointerface/-/commits/main
         :alt: Coverage Status
 
-.. image:: https://pyup.io/repos/github/MorfeoRenai/biointerface/shield.svg
-     :target: https://pyup.io/repos/github/MorfeoRenai/biointerface/
-     :alt: Updates
-
 
 BioInterface is a `Biopython <https://biopython.org/>`_ based package that extracts Protein-DNA
 interfaces in a PDB structures.

{biointerface-0.3.2 → biointerface-0.4.0}/docs/installation.rst

@@ -32,15 +32,9 @@ You can either clone the public repository:
 
 .. code-block:: console
 
-    $ git clone git://github.com/MorfeoRenai/biointerface
+    $ git clone git@gitlab.com:MorfeoRenai/biointerface.git
 
-Or download the `tarball`_:
-
-.. code-block:: console
-
-    $ curl -OJL https://gitlab.com/MorfeoRenai/biointerface/tarball/main
-
-Once you have a copy of the source, you can install it with:
+Once you have a copy of the source, go into the directory and you can install it with:
 
 .. code-block:: console
 
@@ -48,4 +42,3 @@ Once you have a copy of the source, you can install it with:
 
 
 .. _Gitlab repo: https://gitlab.com/MorfeoRenai/biointerface
-.. _tarball: https://gitlab.com/MorfeoRenai/biointerface/tarball/main

{biointerface-0.3.2 → biointerface-0.4.0}/docs/usage.rst

@@ -158,7 +158,7 @@ You can get all Protein-DNA interface features as a ``pandas`` DataFrame.
 
 .. code-block:: python
 
-    df = face.get_interface_data()
+    df = face.as_dataframe()
     df.columns
 
 .. code-block:: console

{biointerface-0.3.2 → biointerface-0.4.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "biointerface"
-version = "0.3.2"
+version = "0.4.0"
 description = "BioInterface is a Biopython based package that extracts Protein-DNA interfaces in a PDB structures."
 readme = "README.rst"
 authors = [
@@ -144,7 +144,7 @@ description = "Run the tests on Python 3.13"
 # ----
 
 [tool.bumpversion]
-current_version = "0.3.2"
+current_version = "0.4.0"
 parse = "(?P<major>\\d+)\\.(?P<minor>\\d+)\\.(?P<patch>\\d+)"
 serialize = ["{major}.{minor}.{patch}"]
 search = "{current_version}"

{biointerface-0.3.2 → biointerface-0.4.0}/src/biointerface/__init__.py

@@ -4,6 +4,6 @@ from biointerface.core import Interface, build_interfaces
 
 __author__ = """Alessandro Pandolfi"""
 __email__ = "alessandro.pandolfi@protonmail.com"
-__version__ = "0.3.2"
+__version__ = "0.4.0"
 
 __all__ = ["Interface", "build_interfaces"]

{biointerface-0.3.2 → biointerface-0.4.0}/src/biointerface/core.py

@@ -6,18 +6,11 @@ from Bio.PDB.Residue import Residue
 from Bio.PDB.Atom import Atom
 from Bio.PDB.PDBExceptions import PDBConstructionException
 
-# 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,
-    DSNABuilder,
-    DoubleStrandNucleicAcid,
-)
+from PDBNucleicAcids.NucleicAcid import NABuilder
+from PDBNucleicAcids.NucleicAcid import DSNABuilder
+from PDBNucleicAcids.NucleicAcid import DoubleStrandNucleicAcid
 
 import copy
 
@@ -36,11 +29,11 @@ class Interface:
         Chain id of a protein that may interact with DNA.
     search_radius : float | int, optional
         Search radius, measured in Armstrong, within which Protein-DNA
-        interactions are found. Default is 5.0
+        interactions are found. Default is 4.0
 
     """
 
-    def __init__(self, structure, protein_chain_id, search_radius=5.0) -> None:
+    def __init__(self, structure, protein_chain_id, search_radius=4.0) -> None:
         self.structure = structure
         self.protein_chain_id = protein_chain_id
         self.search_radius = search_radius
@@ -210,7 +203,7 @@ chain id: {self.protein_chain_id}"
         """
         return list({atom_pair[0].parent for atom_pair in self.contacts})
 
-    def get_interface_data(self) -> pd.DataFrame:
+    def as_dataframe(self) -> pd.DataFrame:
         """
         Get all data from the interface, as a dataframe.
 
@@ -334,9 +327,9 @@ chain id: {self.protein_chain_id}"
         A visual example of "gaps":
             ``Input full DSNA:            GATATACAAGCCA``
 
-            ``Protein-bound:                ****  **``
+            ``Protein-bound:                ****  **   ``
 
-            ``Output protein-bound DSNA:    TATACAAG``
+            ``Output protein-bound DSNA:    TATACAAG   ``
 
         Returns
         -------
@@ -373,20 +366,80 @@ chain id: {self.protein_chain_id}"
                 # in this case, there is an actual bound DSNA
                 bound_dsna_list.append(bound_dsna)
 
+                unbound_bps = []
                 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}"
-                        )
+                        unbound_bps.append(bp)
+
+                if unbound_bps:
+                    warnings.warn(
+                        f"Warning: There are {len(unbound_bps)} unbound \
+base-pairs inside {bound_dsna} - {unbound_bps}"
+                    )
 
         return bound_dsna_list
 
+    def fixed_protein_atoms_number(self, num_atoms) -> None:
+        """Filter contacts by a fixed number of protein atoms."""
+        # cast list into dataframe, ready to be sorted
+        df = pd.DataFrame(self.contacts, columns=["na_atom", "protein_atom"])
+        df["euclidean_distance"] = df.apply(
+            lambda row: row["na_atom"] - row["protein_atom"], axis=1
+        )
+
+        # aggregate: for each atom, its minimum distance from DSNA
+        agg = df.groupby(["protein_atom"]).min()
+        agg = agg.reset_index()
+        agg = agg.sort_values(by="euclidean_distance", ascending=True)
+
+        # get closest n atoms to DSNA
+        top_protein_atoms = agg.head(num_atoms)["protein_atom"].tolist()
+
+        if len(top_protein_atoms) <= num_atoms:
+            raise Exception("Not enough atoms.")
+
+        # select contacts by top n atoms
+        selected_contacts = [
+            (na_atom, protein_atom)
+            for na_atom, protein_atom in self.contacts
+            if protein_atom in top_protein_atoms
+        ]
+
+        self.contacts = selected_contacts
+
+    def fixed_na_atoms_number(self, num_atoms) -> None:
+        """Filter contacts by a fixed number of nucleic acid atoms."""
+        # cast list into dataframe, ready to be sorted
+        df = pd.DataFrame(self.contacts, columns=["na_atom", "protein_atom"])
+        df["euclidean_distance"] = df.apply(
+            lambda row: row["na_atom"] - row["protein_atom"], axis=1
+        )
+
+        # aggregate: for each atom, its minimum distance from DSNA
+        agg = df.groupby(["na_atom"]).min()
+        agg = agg.reset_index()
+        agg = agg.sort_values(by="euclidean_distance", ascending=True)
+
+        # get closest n atoms to DSNA
+        top_na_atoms = agg.head(num_atoms)["na_atom"].tolist()
+
+        if len(top_na_atoms) <= num_atoms:
+            raise Exception("Not enough atoms.")
+
+        # select contacts by top n atoms
+        selected_contacts = [
+            (na_atom, protein_atom)
+            for na_atom, protein_atom in self.contacts
+            if na_atom in top_na_atoms
+        ]
+
+        self.contacts = selected_contacts
+
 
-def build_interfaces(structure, search_radius=5.0) -> list[Interface]:
+def build_interfaces(structure, search_radius=4.0) -> list[Interface]:
     """
     Extract all Protein-DNA interfaces found in a structure.
 
@@ -396,7 +449,7 @@ def build_interfaces(structure, search_radius=5.0) -> list[Interface]:
         Biopython Structure entity.
     search_radius : float | int, optional
         Search radius, measured in Armstrong, within which Protein-DNA
-        interactions are found. Default is 5.0
+        interactions are found. Default is 4.0
 
     Returns
     -------
@@ -434,57 +487,3 @@ def build_interfaces(structure, search_radius=5.0) -> list[Interface]:
             face_list.append(face)
 
     return face_list
-
-
-# def export_atom_list(structure_id, atom_list, out_filepath):
-#     """Export atom list."""
-#     # not in Path but in string
-#     out_filepath = str(out_filepath)
-
-#     new_structure = Structure.Structure(structure_id)
-#     for atom in atom_list:
-#         _add_atom_to_new_structure(atom, new_structure)
-
-#     # Prepare IO object
-#     io = MMCIFIO()
-#     io.set_structure(new_structure)
-
-#     # Esporta la nuova struttura in un file PDB
-#     # necessita di string type filepath
-#     io.save(out_filepath)
-
-
-# def _add_atom_to_new_structure(atom, new_structure):
-#     model_id = (
-#         atom.get_parent().get_parent().get_parent().id
-#     )  # Ottieni l'ID del modello
-#     chain_id = atom.get_parent().get_parent().id  # Ottieni l'ID della catena
-#     residue_id = atom.get_parent().id  # Ottieni l'ID del residuo
-#     resname = atom.get_parent().resname  # Nome del residuo
-
-#     # Controlla se il modello esiste già nel nuovo modello
-#     if model_id in [model.id for model in new_structure]:
-#         new_model = new_structure[model_id]
-#     else:
-#         new_model = Model.Model(model_id)
-#         new_structure.add(new_model)
-
-#     # Controlla se la catena esiste già nel nuovo modello
-#     if chain_id in [chain.id for chain in new_model]:
-#         new_chain = new_model[chain_id]
-#     else:
-#         new_chain = Chain.Chain(chain_id)
-#         new_model.add(new_chain)
-
-#     # Controlla se il residuo esiste già nella nuova catena
-#     if residue_id in [res.id for res in new_chain]:
-#         new_residue = new_chain[residue_id]
-#     else:
-#         new_residue = Residue.Residue(
-#             residue_id, resname, atom.get_parent().segid
-#         )
-#         new_chain.add(new_residue)
-
-#     # Copia l'atomo e aggiungilo al residuo
-#     new_atom = atom.copy()
-#     new_residue.add(new_atom)

{biointerface-0.3.2 → biointerface-0.4.0}/src/biointerface.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: biointerface
-Version: 0.3.2
+Version: 0.4.0
 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>
@@ -29,6 +29,7 @@ Requires-Dist: bump-my-version; extra == "dev"
 Requires-Dist: wheel; extra == "dev"
 Requires-Dist: build; extra == "dev"
 Requires-Dist: twine; extra == "dev"
+Dynamic: license-file
 
 ============
 BioInterface
@@ -46,10 +47,6 @@ BioInterface
         :target: https://gitlab.com/MorfeoRenai/biointerface/-/commits/main
         :alt: Coverage Status
 
-.. image:: https://pyup.io/repos/github/MorfeoRenai/biointerface/shield.svg
-     :target: https://pyup.io/repos/github/MorfeoRenai/biointerface/
-     :alt: Updates
-
 
 BioInterface is a `Biopython <https://biopython.org/>`_ based package that extracts Protein-DNA
 interfaces in a PDB structures.

{biointerface-0.3.2 → biointerface-0.4.0}/tests/test_core.py

@@ -59,10 +59,10 @@ def test_get_residues():
     )  # Devono avere nomi di residui
 
 
-def test_get_interface_data():
+def test_as_dataframe():
     structure = get_test_structure()
     face = Interface(structure=structure, protein_chain_id="C")
-    df = face.get_interface_data()
+    df = face.as_dataframe()
     assert df is not None
     assert not df.empty
     assert set(