RNApolis 0.3.17__py3-none-any.whl → 0.4.0__py3-none-any.whl

{RNApolis-0.3.17.dist-info → RNApolis-0.4.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: RNApolis
-Version: 0.3.17
+Version: 0.4.0
 Summary: A Python library containing RNA-related bioinformatics functions and classes
 Home-page: https://github.com/tzok/rnapolis-py
 Author: Tomasz Zok
@@ -21,6 +21,7 @@ Requires-Dist: mmcif
 Requires-Dist: numpy
 Requires-Dist: ordered-set
 Requires-Dist: orjson
+Requires-Dist: pandas
 Requires-Dist: pulp
 Requires-Dist: requests
 Requires-Dist: scipy

RNApolis-0.4.0.dist-info/RECORD

@@ -0,0 +1,17 @@
+rnapolis/annotator.py,sha256=7U3f0gchKdIGc6FwJx0UAc_95HJI5SgECj-b7-1yBhc,22086
+rnapolis/clashfinder.py,sha256=i95kp0o6OWNqmJDBr-PbsZd7RY2iJtBDr7QqolJSuAQ,8513
+rnapolis/common.py,sha256=PUYF01P2vevhyImhZjGYE0jJlsxWHX6GQmsxI4W7S-E,30255
+rnapolis/metareader.py,sha256=I1-cXc2YNBPwa3zihAnMTjEsAo79tEKzSmWu5yvN1Pk,2071
+rnapolis/molecule_filter.py,sha256=hB6-nXgjmw7FAsQ3bj0cZ2FvuW2I1PXunEfcdwEUB1o,7389
+rnapolis/motif_extractor.py,sha256=duHvpi9Ulcny9K60E6VBpz5RpJZw-KdTB4_Ph0iP478,774
+rnapolis/parser.py,sha256=wCA9rXqt51iLECgeBqOShFpuT8JwanNkHYD5uXYvLzU,13988
+rnapolis/rfam_folder.py,sha256=SjiiyML_T1__saruFwSMJEoQ7Y55GIU8ktS8ZUn5-fw,11111
+rnapolis/tertiary.py,sha256=iA5_ut1_nhwlbYpu2898h5li4pTEOc-iA_uK7vIvQ2o,20269
+rnapolis/transformer.py,sha256=V9nOQvdq4-p7yUWo0vQg0CDQMpmyxz9t4TMSRVEKHnw,1817
+rnapolis/util.py,sha256=IdquFO3PV1_KDqodjupzm0Rqvgy0CeSzxGHaGEHYXVU,543
+RNApolis-0.4.0.dist-info/LICENSE,sha256=ZGRu12MzCgbYA-Lt8MyBlmjvPZh7xfiD5u5wBx0enq4,1066
+RNApolis-0.4.0.dist-info/METADATA,sha256=kz7fPjyFm8j6HMwnDvtwlLkZGPpzw2Ce29XI1pVyIyU,54322
+RNApolis-0.4.0.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
+RNApolis-0.4.0.dist-info/entry_points.txt,sha256=foN2Pn5e-OzEz0fFmNoX6PnFSZFQntOlY8LbognP5F0,308
+RNApolis-0.4.0.dist-info/top_level.txt,sha256=LcO18koxZcWoJ21KDRRRo_tyIbmXL5z61dPitZpy8yc,9
+RNApolis-0.4.0.dist-info/RECORD,,

{RNApolis-0.3.17.dist-info → RNApolis-0.4.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (70.1.1)
+Generator: setuptools (72.2.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

rnapolis/annotator.py

@@ -10,8 +10,6 @@ from typing import Dict, List, Optional, Set, Tuple
 import numpy
 import numpy.typing
 from ordered_set import OrderedSet
-from scipy.spatial import KDTree
-
 from rnapolis.common import (
     BR,
     BaseInteractions,
@@ -43,6 +41,7 @@ from rnapolis.tertiary import (
     torsion_angle,
 )
 from rnapolis.util import handle_input_file
+from scipy.spatial import KDTree
 
 HYDROGEN_BOND_MAX_DISTANCE = 4.0
 HYDROGEN_BOND_ANGLE_RANGE = (50.0, 130.0)  # 90 degrees is ideal, so allow +- 40 degrees
@@ -149,7 +148,7 @@ def detect_bph_br_classification(
 
 
 def merge_and_clean_bph_br(
-    pairs: List[Tuple[Residue3D, Residue3D, int]]
+    pairs: List[Tuple[Residue3D, Residue3D, int]],
 ) -> Dict[Tuple[Residue3D, Residue3D], OrderedSet[int]]:
     bph_br_map: Dict[Tuple[Residue3D, Residue3D], OrderedSet[int]] = defaultdict(
         OrderedSet
@@ -588,7 +587,7 @@ def main():
         "-a",
         "--all-dot-brackets",
         action="store_true",
-        help=")optional) print all dot-brackets, not only optimal one (exclusive with -e/--extended)",
+        help="(optional) print all dot-brackets, not only optimal one (exclusive with -e/--extended)",
     )
     parser.add_argument("-b", "--bpseq", help="(optional) path to output BPSEQ file")
     parser.add_argument("-c", "--csv", help="(optional) path to output CSV file")

rnapolis/clashfinder.py

@@ -8,11 +8,10 @@ from functools import cached_property
 from typing import List, Optional
 
 import numpy as np
-from scipy.spatial import KDTree
-
 from rnapolis.metareader import read_metadata
 from rnapolis.parser import read_3d_structure
 from rnapolis.tertiary import Atom, Residue3D
+from scipy.spatial import KDTree
 
 CARBON_RADIUS = 0.6
 NITROGEN_RADIUS = 0.54

rnapolis/common.py

@@ -8,7 +8,6 @@ from collections.abc import Sequence
 from dataclasses import dataclass
 from enum import Enum
 from functools import cache, cached_property, total_ordering
-from itertools import permutations
 from typing import Dict, List, Optional, Tuple
 
 import graphviz

rnapolis/metareader.py

@@ -6,7 +6,6 @@ import orjson
 import pandas as pd
 from mmcif.io.IoAdapterPy import IoAdapterPy
 from mmcif.io.PdbxReader import DataContainer
-
 from rnapolis.util import handle_input_file
 
 

rnapolis/molecule_filter.py

@@ -5,7 +5,6 @@ from typing import List, Set, Tuple
 
 from mmcif.io.IoAdapterPy import IoAdapterPy
 from mmcif.io.PdbxReader import DataCategory, DataContainer
-
 from rnapolis.util import handle_input_file
 
 # Source: https://mmcif.wwpdb.org/dictionaries/mmcif_pdbx_v50.dic/Items/_entity_poly.type.html
@@ -158,11 +157,17 @@ def main():
     parser = argparse.ArgumentParser()
     parser.add_argument(
         "--type",
-        help="a type of molecule to select (default: polyribonucleotide)",
+        help="a type of molecule to select, you can provide this argument multiple times (default: polyribonucleotide)",
         action="append",
         default=["polyribonucleotide"],
         choices=ENTITY_POLY_TYPES,
     )
+    parser.add_argument(
+        "--chain",
+        help="a chain ID (label_asym_id) to select, you can provide this argument multiple times (if provided, it overrides the --type argument)",
+        action="append",
+        default=[],
+    )
     parser.add_argument("path", help="path to a PDBx/mmCIF file")
     args = parser.parse_args()
 
@@ -171,8 +176,15 @@ def main():
     data = adapter.readFile(file.name)
     output = DataContainer("rnapolis")
 
-    entity_ids = select_ids(data, "entity_poly", "type", "entity_id", set(args.type))
-    asym_ids = select_ids(data, "struct_asym", "entity_id", "id", entity_ids)
+    if args.chain:
+        entity_ids = select_ids(data, "struct_asym", "id", "entity_id", set(args.chain))
+        asym_ids = set(args.chain)
+    else:
+        entity_ids = select_ids(
+            data, "entity_poly", "type", "entity_id", set(args.type)
+        )
+        asym_ids = select_ids(data, "struct_asym", "entity_id", "id", entity_ids)
+
     auth_asym_ids = select_ids(
         data, "atom_site", "label_asym_id", "auth_asym_id", asym_ids
     )

rnapolis/parser.py

@@ -2,7 +2,6 @@ import logging
 from typing import IO, Dict, List, Optional, Tuple, Union
 
 from mmcif.io.IoAdapterPy import IoAdapterPy
-
 from rnapolis.common import ResidueAuth, ResidueLabel
 from rnapolis.tertiary import BASE_ATOMS, Atom, Residue3D, Structure3D
 
@@ -13,7 +12,7 @@ logger = logging.getLogger(__name__)
 def read_3d_structure(
     cif_or_pdb: IO[str], model: Optional[int] = None, nucleic_acid_only: bool = False
 ) -> Structure3D:
-    atoms, modified, sequence = (
+    atoms, modified, sequence_by_entity, is_nucleic_acid_by_entity = (
         parse_cif(cif_or_pdb) if is_cif(cif_or_pdb) else parse_pdb(cif_or_pdb)
     )
     available_models = {atom.model: None for atom in atoms}
@@ -25,7 +24,13 @@ def read_3d_structure(
         atoms = atoms_by_model[model]
     else:
         atoms = atoms_by_model[list(available_models.keys())[0]]
-    return group_atoms(atoms, modified, sequence, nucleic_acid_only)
+    return group_atoms(
+        atoms,
+        modified,
+        sequence_by_entity,
+        is_nucleic_acid_by_entity,
+        nucleic_acid_only,
+    )
 
 
 def is_cif(cif_or_pdb: IO[str]) -> bool:
@@ -41,7 +46,8 @@ def parse_cif(
 ) -> Tuple[
     List[Atom],
     Dict[Union[ResidueLabel, ResidueAuth], str],
-    Dict[Tuple[str, int], str],
+    Dict[str, str],
+    Dict[str, bool],
 ]:
     cif.seek(0)
 
@@ -49,7 +55,8 @@ def parse_cif(
     data = io_adapter.readFile(cif.name)
     atoms: List[Atom] = []
     modified: Dict[Union[ResidueLabel, ResidueAuth], str] = {}
-    sequence = {}
+    sequence_by_entity = {}
+    is_nucleic_acid_by_entity = {}
 
     if data:
         atom_site = data[0].getObj("atom_site")
@@ -60,6 +67,7 @@ def parse_cif(
             for row in atom_site.getRowList():
                 row_dict = dict(zip(atom_site.getAttributeList(), row))
 
+                label_entity_id = row_dict.get("label_entity_id", None)
                 label_chain_name = row_dict.get("label_asym_id", None)
                 label_residue_number = try_parse_int(row_dict.get("label_seq_id", None))
                 label_residue_name = row_dict.get("label_comp_id", None)
@@ -128,7 +136,19 @@ def parse_cif(
                     else None
                 )
 
-                atoms.append(Atom(label, auth, model, atom_name, x, y, z, occupancy))
+                atoms.append(
+                    Atom(
+                        label_entity_id,
+                        label,
+                        auth,
+                        model,
+                        atom_name,
+                        x,
+                        y,
+                        z,
+                        occupancy,
+                    )
+                )
 
         if mod_residue:
             for row in mod_residue.getRowList():
@@ -179,17 +199,24 @@ def parse_cif(
             for row in entity_poly.getRowList():
                 row_dict = dict(zip(entity_poly.getAttributeList(), row))
 
-                pdbx_strand_id = row_dict.get("pdbx_strand_id", None)
+                entity_id = row_dict.get("entity_id", None)
+                type_ = row_dict.get("type", None)
                 pdbx_seq_one_letter_code_can = row_dict.get(
                     "pdbx_seq_one_letter_code_can", None
                 )
 
-                if pdbx_strand_id and pdbx_seq_one_letter_code_can:
-                    for strand in pdbx_strand_id.split(","):
-                        for i, letter in enumerate(pdbx_seq_one_letter_code_can):
-                            sequence[(strand, i + 1)] = letter
+                if entity_id and type_:
+                    is_nucleic_acid_by_entity[entity_id] = type_ in (
+                        "peptide nucleic acid",
+                        "polydeoxyribonucleotide",
+                        "polydeoxyribonucleotide/polyribonucleotide hybrid",
+                        "polyribonucleotide",
+                    )
+
+                if entity_id and pdbx_seq_one_letter_code_can:
+                    sequence_by_entity[entity_id] = pdbx_seq_one_letter_code_can
 
-    return atoms, modified, sequence
+    return atoms, modified, sequence_by_entity, is_nucleic_acid_by_entity
 
 
 def parse_pdb(
@@ -197,7 +224,8 @@ def parse_pdb(
 ) -> Tuple[
     List[Atom],
     Dict[Union[ResidueLabel, ResidueAuth], str],
-    Dict[Tuple[str, int], str],
+    Dict[str, str],
+    Dict[str, bool],
 ]:
     pdb.seek(0)
     atoms: List[Atom] = []
@@ -223,7 +251,7 @@ def parse_pdb(
             auth = ResidueAuth(
                 chain_identifier, residue_number, insertion_code, residue_name
             )
-            atoms.append(Atom(None, auth, model, atom_name, x, y, z, occupancy))
+            atoms.append(Atom(None, None, auth, model, atom_name, x, y, z, occupancy))
         elif line.startswith("MODRES"):
             original_name = line[12:15]
             chain_identifier = line[16]
@@ -235,13 +263,14 @@ def parse_pdb(
             )
             modified[auth] = standard_residue_name
 
-    return atoms, modified, {}
+    return atoms, modified, {}, {}
 
 
 def group_atoms(
     atoms: List[Atom],
     modified: Dict[Union[ResidueLabel, ResidueAuth], str],
-    sequence: Dict[Tuple[str, int], str],
+    sequence_by_entity: Dict[str, str],
+    is_nucleic_acid_by_entity: Dict[str, bool],
     nucleic_acid_only: bool,
 ) -> Structure3D:
     if not atoms:
@@ -259,28 +288,45 @@ def group_atoms(
             label = key_previous[0]
             auth = key_previous[1]
             model = key_previous[2]
+            entity_id = residue_atoms[-1].entity_id
             name = get_residue_name(auth, label, modified)
-            one_letter_name = get_one_letter_name(label, sequence, name)
-            if one_letter_name not in "ACGUT":
+            one_letter_name = get_one_letter_name(
+                entity_id, label, sequence_by_entity, name
+            )
+
+            if one_letter_name not in "ACGUTN":
                 one_letter_name = detect_one_letter_name(residue_atoms)
-            residue = Residue3D(
-                label, auth, model, one_letter_name, tuple(residue_atoms)
+
+            residues.append(
+                Residue3D(label, auth, model, one_letter_name, tuple(residue_atoms))
             )
-            if not nucleic_acid_only or (nucleic_acid_only and residue.is_nucleotide):
-                residues.append(residue)
+
             key_previous = key
             residue_atoms = [atom]
 
     label = key_previous[0]
     auth = key_previous[1]
     model = key_previous[2]
+    entity_id = residue_atoms[-1].entity_id
     name = get_residue_name(auth, label, modified)
-    one_letter_name = get_one_letter_name(label, sequence, name)
-    if one_letter_name not in "ACGUT":
+    one_letter_name = get_one_letter_name(entity_id, label, sequence_by_entity, name)
+
+    if one_letter_name not in "ACGUTN":
         one_letter_name = detect_one_letter_name(residue_atoms)
-    residue = Residue3D(label, auth, model, one_letter_name, tuple(residue_atoms))
-    if not nucleic_acid_only or (nucleic_acid_only and residue.is_nucleotide):
-        residues.append(residue)
+
+    residues.append(
+        Residue3D(label, auth, model, one_letter_name, tuple(residue_atoms))
+    )
+
+    if nucleic_acid_only:
+        if is_nucleic_acid_by_entity:
+            residues = [
+                residue
+                for residue in residues
+                if is_nucleic_acid_by_entity[residue.atoms[0].entity_id]
+            ]
+        else:
+            residues = [residue for residue in residues if residue.is_nucleotide]
 
     return Structure3D(residues)
 
@@ -305,13 +351,14 @@ def get_residue_name(
 
 
 def get_one_letter_name(
-    label: Optional[ResidueLabel], sequence: Dict[Tuple[str, int], str], name: str
+    entity_id: Optional[str],
+    label: Optional[ResidueLabel],
+    sequence_by_entity: Dict[str, str],
+    name: str,
 ) -> str:
     # try getting the value from _entity_poly first
-    if label is not None:
-        key = (label.chain, label.number)
-        if key in sequence:
-            return sequence[key]
+    if entity_id is not None and label is not None and entity_id in sequence_by_entity:
+        return sequence_by_entity[entity_id][label.number - 1]
     # RNA
     if len(name) == 1:
         return name
@@ -335,11 +382,13 @@ def detect_one_letter_name(atoms: List[Atom]) -> str:
         ) / len(atom_names_expected)
         score[candidate] = count
     items = sorted(score.items(), key=lambda kv: kv[1], reverse=True)
+    if items[0][1] == 0:
+        return "?"
     return items[0][0]
 
 
 def try_parse_int(s: str) -> Optional[int]:
     try:
         return int(s)
-    except:
+    except ValueError:
         return None

rnapolis/rfam_folder.py

@@ -14,7 +14,6 @@ from typing import List
 import appdirs
 import requests
 import RNA
-
 from rnapolis.common import BpSeq, DotBracket
 
 COMBINED_CM = "https://ftp.ebi.ac.uk/pub/databases/Rfam/CURRENT/Rfam.cm.gz"

rnapolis/tertiary.py

@@ -7,7 +7,6 @@ from typing import Dict, List, Optional, Set, Tuple, Union
 
 import numpy
 import numpy.typing
-
 from rnapolis.common import (
     BasePair,
     BpSeq,
@@ -97,6 +96,7 @@ AVERAGE_OXYGEN_PHOSPHORUS_DISTANCE_COVALENT = 1.6
 
 @dataclass(frozen=True, order=True)
 class Atom:
+    entity_id: Optional[str]
     label: Optional[ResidueLabel]
     auth: Optional[ResidueAuth]
     model: int
@@ -129,6 +129,29 @@ class Residue3D(Residue):
         "C": set(["N1", "C2", "O2", "N3", "C4", "N4", "C5", "C6"]),
         "U": set(["N1", "C2", "O2", "N3", "C4", "O4", "C5", "C6"]),
     }
+    # Heavy atoms in nucleotide
+    nucleotide_heavy_atoms = (
+        set(
+            [
+                "P",
+                "OP1",
+                "OP2",
+                "O5'",
+                "C5'",
+                "C4'",
+                "O4'",
+                "C3'",
+                "O3'",
+                "C2'",
+                "O2'",
+                "C1'",
+            ]
+        )
+        .union(nucleobase_heavy_atoms["A"])
+        .union(nucleobase_heavy_atoms["G"])
+        .union(nucleobase_heavy_atoms["C"])
+        .union(nucleobase_heavy_atoms["U"])
+    )
 
     def __lt__(self, other):
         return (self.model, self.chain, self.number, self.icode or " ") < (
@@ -177,8 +200,8 @@ class Residue3D(Residue):
 
     @cached_property
     def is_nucleotide(self) -> bool:
-        return len(self.atoms) > 1 and any(
-            [atom for atom in self.atoms if atom.name == "C1'"]
+        return self.nucleotide_heavy_atoms.intersection(
+            set([atom.name for atom in self.atoms])
         )
 
     @cached_property
@@ -269,7 +292,7 @@ class Residue3D(Residue):
         logging.error(
             f"Failed to determine the outermost atom for nucleotide {self}, so an arbitrary atom will be used"
         )
-        yield Atom(self.label, self.auth, self.model, "UNK", 0.0, 0.0, 0.0, None)
+        yield Atom(None, self.label, self.auth, self.model, "UNK", 0.0, 0.0, 0.0, None)
 
     def __inner_generator(self):
         # try to find expected atom name
@@ -297,7 +320,7 @@ class Residue3D(Residue):
         logging.error(
             f"Failed to determine the innermost atom for nucleotide {self}, so an arbitrary atom will be used"
         )
-        yield Atom(self.label, self.auth, self.model, "UNK", 0.0, 0.0, 0.0, None)
+        yield Atom(None, self.label, self.auth, self.model, "UNK", 0.0, 0.0, 0.0, None)
 
 
 @dataclass(frozen=True, order=True)

RNApolis-0.3.17.dist-info/RECORD

@@ -1,17 +0,0 @@
-rnapolis/annotator.py,sha256=XnjFBeu3P_2UMdkD4Ao7m7K6JfeqYa-13xRzghrLvt8,22086
-rnapolis/clashfinder.py,sha256=jD3s_UovygWi01NUbQNeAeRRFkARTSRraLXUV43UbAA,8514
-rnapolis/common.py,sha256=tbmKV64nLClmzNN0HyKnvWA0-5aSyf4x8CGpBjpIJ4M,30290
-rnapolis/metareader.py,sha256=9HZIrpPsmmWkEUeSeKAeG1sstfqbBDKUw5QPsn5cshw,2072
-rnapolis/molecule_filter.py,sha256=NhjuqdCRnXgPefWZPeTq77tifmnAzamQtA0ODqPPG9k,6918
-rnapolis/motif_extractor.py,sha256=duHvpi9Ulcny9K60E6VBpz5RpJZw-KdTB4_Ph0iP478,774
-rnapolis/parser.py,sha256=nHRXcoKbzfMJuDMJO-8MSPkzfmD-788ZzgcfjLQpgFs,12666
-rnapolis/rfam_folder.py,sha256=3rgXEJR16uPFy_BOo8qkdClOAOQDVOkidnLE-yoRbeI,11112
-rnapolis/tertiary.py,sha256=VuATTN2SD7lBL9iUgT-doDwuEYsLodgV2u-SwQsyQcU,19658
-rnapolis/transformer.py,sha256=V9nOQvdq4-p7yUWo0vQg0CDQMpmyxz9t4TMSRVEKHnw,1817
-rnapolis/util.py,sha256=IdquFO3PV1_KDqodjupzm0Rqvgy0CeSzxGHaGEHYXVU,543
-RNApolis-0.3.17.dist-info/LICENSE,sha256=ZGRu12MzCgbYA-Lt8MyBlmjvPZh7xfiD5u5wBx0enq4,1066
-RNApolis-0.3.17.dist-info/METADATA,sha256=2h_8NfBq0uKpgXC-CYsvB1O1hglxTGyZHfGfJmsKrmI,54301
-RNApolis-0.3.17.dist-info/WHEEL,sha256=mguMlWGMX-VHnMpKOjjQidIo1ssRlCFu4a4mBpz1s2M,91
-RNApolis-0.3.17.dist-info/entry_points.txt,sha256=foN2Pn5e-OzEz0fFmNoX6PnFSZFQntOlY8LbognP5F0,308
-RNApolis-0.3.17.dist-info/top_level.txt,sha256=LcO18koxZcWoJ21KDRRRo_tyIbmXL5z61dPitZpy8yc,9
-RNApolis-0.3.17.dist-info/RECORD,,