biointerface 0.1.0__py3-none-any.whl

biointerface/__init__.py

@@ -0,0 +1,5 @@
+"""Top-level package for BioInterface."""
+
+__author__ = """Alessandro Pandolfi"""
+__email__ = 'alessandro.pandolfi@protonmail.com'
+__version__ = '0.1.0'

biointerface/biointerface.py

@@ -0,0 +1,138 @@
+"""Extract interface."""
+
+from Bio.PDB.Polypeptide import PPBuilder
+from Bio.PDB.NeighborSearch import NeighborSearch
+from Bio.PDB import Structure, Model, Chain, Residue
+from Bio.PDB import MMCIFIO
+
+import pandas as pd
+
+from PDBNucleicAcids.NucleicAcid import NABuilder
+
+
+def get_interface(structure, protein_chain_id, search_radius, n_atoms):
+    """Extract interface."""
+    # get all the atoms from the nucleic acids, in most cases DNA
+    na_builder = NABuilder()
+    na_list = na_builder.build_nucleic_acids(structure)
+    na_atoms = []
+    for na in na_list:
+        na_atoms.extend(na.get_atoms())
+    na_atoms = list(set(na_atoms))
+
+    # get all the atoms from the protein chain
+    protein_chain = structure[0][protein_chain_id]
+    pp_builder = PPBuilder()
+    pp = pp_builder.build_peptides(protein_chain)[0]
+    pp_atoms = []
+    for pp in pp_builder.build_peptides(protein_chain):
+        for res in pp:
+            pp_atoms.extend(res.get_atoms())
+    pp_atoms = list(set(pp_atoms))
+
+    # Crea una lista con tutti gli atomi di DNA e proteina
+    all_atoms = na_atoms + pp_atoms
+
+    # Usa NeighborSearch per trovare gli atomi vicini entro una certa
+    # distanza
+    ns = NeighborSearch(all_atoms)
+
+    # Cerca gli atomi vicini entro un raggio di 4 Å tra DNA e proteina
+    all_contacts = ns.search_all(search_radius)
+
+    # Filtra solo i contatti, ovvero le coppied di atomi,
+    # che hanno un atomo di DNA
+    temp = [
+        (atom1, atom2)
+        for atom1, atom2 in all_contacts
+        if (atom1 in na_atoms or atom2 in na_atoms)
+    ]
+
+    # Filtra solo i contatti tra DNA e proteina
+    contacts = [
+        (atom1, atom2)
+        for atom1, atom2 in temp
+        if (atom1 in na_atoms and atom2 in pp_atoms)
+    ] + [
+        (atom2, atom1)
+        for atom1, atom2 in temp
+        if (atom1 in pp_atoms and atom2 in na_atoms)
+    ]
+    # temp è utile per greedyness, prima prendi il DNA, che ha meno
+    # atomi, escludendo quelli intra-proteina
+    # poi escludi anche quelli intra-DNA
+    # inoltre ci assicuriamo che la col 0 contenga gli atomi di DNA e
+    # che col 1 contenga gli atomi di proteine
+    # Ce ne assicuriamo invertendo atom1 e atom2 nella seconda lista
+
+    # dataframe
+    contacts_df = pd.DataFrame(contacts, columns=["na_atoms", "pp_atoms"])
+
+    # distance column
+    # Atom - Atom = distance in armstrong
+    contacts_df["dist"] = contacts_df.apply(
+        lambda row: row["na_atoms"] - row["pp_atoms"], axis=1
+    )
+
+    # grouping: minimum distance for every protein atom, then sorted
+    dist = contacts_df.groupby(by="pp_atoms")["dist"].min().sort_values()
+
+    # take the n top smallest distances
+    # atoms as indexes
+    dist = dist.head(n_atoms)  # Series of floats
+    interface_atoms = dist.index.tolist()  # index of Atom objects, to list
+
+    return interface_atoms
+
+
+def export_atom_list(structure_id, atom_list, out_filepath):
+    # 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-0.1.0.dist-info/AUTHORS.rst

@@ -0,0 +1,13 @@
+=======
+Credits
+=======
+
+Development Lead
+----------------
+
+* Alessandro Pandolfi <alessandro.pandolfi@protonmail.com>
+
+Contributors
+------------
+
+None yet. Why not be the first?

biointerface-0.1.0.dist-info/LICENSE

@@ -0,0 +1,22 @@
+MIT License
+
+Copyright (c) 2025, Alessandro Pandolfi
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+

biointerface-0.1.0.dist-info/METADATA

@@ -0,0 +1,64 @@
+Metadata-Version: 2.2
+Name: biointerface
+Version: 0.1.0
+Summary: BioInterface is a python package capable of extracting Protein-DNA interfaces from PDB/mmCif structures.
+Author-email: Alessandro Pandolfi <alessandro.pandolfi@protonmail.com>
+Maintainer-email: Alessandro Pandolfi <alessandro.pandolfi@protonmail.com>
+License: MIT license
+Project-URL: bugs, https://gitlab.com/MorfeoRenai/biointerface/-/issues
+Project-URL: changelog, https://gitlab.com/MorfeoRenai/biointerface/-/blob/main/HISTORY.rst
+Project-URL: homepage, https://gitlab.com/MorfeoRenai/biointerface
+Classifier: Programming Language :: Python :: 3
+Description-Content-Type: text/x-rst
+License-File: LICENSE
+License-File: AUTHORS.rst
+Requires-Dist: pandas
+Requires-Dist: biopython
+Requires-Dist: pdbnucleicacids>=0.2.0
+Provides-Extra: dev
+Requires-Dist: coverage; extra == "dev"
+Requires-Dist: mypy; extra == "dev"
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: ruff; extra == "dev"
+
+============
+BioInterface
+============
+
+
+.. image:: https://img.shields.io/pypi/v/biointerface.svg
+        :target: https://pypi.python.org/pypi/biointerface
+
+.. image:: https://img.shields.io/travis/MorfeoRenai/biointerface.svg
+        :target: https://travis-ci.com/MorfeoRenai/biointerface
+
+.. image:: https://readthedocs.org/projects/biointerface/badge/?version=latest
+        :target: https://biointerface.readthedocs.io/en/latest/?version=latest
+        :alt: Documentation Status
+
+
+.. image:: https://pyup.io/repos/github/MorfeoRenai/biointerface/shield.svg
+     :target: https://pyup.io/repos/github/MorfeoRenai/biointerface/
+     :alt: Updates
+
+
+
+BioInterface is a python package capable of extracting Protein-DNA interfaces from PDB/mmCif structures.
+
+
+* Free software: MIT license
+* Documentation: https://biointerface.readthedocs.io.
+
+
+Features
+--------
+
+* TODO
+
+Credits
+-------
+
+This package was created with Cookiecutter_ and the `audreyr/cookiecutter-pypackage`_ project template.
+
+.. _Cookiecutter: https://github.com/audreyr/cookiecutter
+.. _`audreyr/cookiecutter-pypackage`: https://github.com/audreyr/cookiecutter-pypackage

biointerface-0.1.0.dist-info/RECORD

@@ -0,0 +1,8 @@
+biointerface/__init__.py,sha256=jFvgoMrByp0YlveTOAzv2gyphtN70LdEyTodTKn0y3I,153
+biointerface/biointerface.py,sha256=IXkJv0P5pwKXSSCI_sug6dUi2ToHZDB5RVbf2ZRvup8,4569
+biointerface-0.1.0.dist-info/AUTHORS.rst,sha256=PlS91A-GkfHib1OMvyWWkRdgjalaZgkJ5_abeMyqhQk,179
+biointerface-0.1.0.dist-info/LICENSE,sha256=jkfdeLRHl54F0J5pRsgqRV_s6drHgL7dRyhV5ujqx10,1078
+biointerface-0.1.0.dist-info/METADATA,sha256=5y-1Zu_1V-Dq2Z9E63Vd3b9lzvwZwopl_eNnXGRcuOU,2100
+biointerface-0.1.0.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+biointerface-0.1.0.dist-info/top_level.txt,sha256=rvrViMtBwoeIEjKJGFooCoreOc0KWUSQLJSwCvUPVuI,13
+biointerface-0.1.0.dist-info/RECORD,,

biointerface-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (75.8.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

biointerface-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+biointerface