RNApolis 0.3.16__tar.gz → 0.3.18__tar.gz

{rnapolis-0.3.16/src/RNApolis.egg-info → rnapolis-0.3.18}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: RNApolis
-Version: 0.3.16
+Version: 0.3.18
 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-0.3.16 → rnapolis-0.3.18}/setup.py

@@ -5,7 +5,7 @@ with open("README.md") as f:
 
 setup(
     name="RNApolis",
-    version="0.3.16",
+    version="0.3.18",
     packages=["rnapolis"],
     package_dir={"": "src"},
     author="Tomasz Zok",
@@ -42,6 +42,7 @@ setup(
         "numpy",
         "ordered-set",
         "orjson",
+        "pandas",
         "pulp",
         "requests",
         "scipy",

{rnapolis-0.3.16 → rnapolis-0.3.18/src/RNApolis.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: RNApolis
-Version: 0.3.16
+Version: 0.3.18
 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-0.3.16 → rnapolis-0.3.18}/src/RNApolis.egg-info/requires.txt

@@ -4,6 +4,7 @@ mmcif
 numpy
 ordered-set
 orjson
+pandas
 pulp
 requests
 scipy

{rnapolis-0.3.16 → rnapolis-0.3.18}/src/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-0.3.16 → rnapolis-0.3.18}/src/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-0.3.16 → rnapolis-0.3.18}/src/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-0.3.16 → rnapolis-0.3.18}/src/rnapolis/metareader.py

@@ -3,9 +3,9 @@ import argparse
 from typing import IO, Dict, List
 
 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
 
 
@@ -46,6 +46,10 @@ def main():
         help="read the mmCIF file and list categories available inside",
         action="store_true",
     )
+    parser.add_argument(
+        "--csv-directory",
+        help="directory where to output CSV per each category",
+    )
     args = parser.parse_args()
 
     file = handle_input_file(args.path)
@@ -57,6 +61,12 @@ def main():
         result = read_metadata(file, args.category)
         print(orjson.dumps(result).decode("utf-8"))
 
+        if args.csv_directory:
+            for category in result:
+                with open(f"{args.csv_directory}/{category}.csv", "w") as f:
+                    df = pd.DataFrame(result[category])
+                    df.to_csv(f, index=False)
+
 
 if __name__ == "__main__":
     main()

{rnapolis-0.3.16 → rnapolis-0.3.18}/src/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-0.3.16 → rnapolis-0.3.18}/src/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
 
@@ -212,7 +211,7 @@ def parse_pdb(
             if alternate_location != " ":
                 continue
             atom_name = line[12:16].strip()
-            residue_name = line[18:20].strip()
+            residue_name = line[17:20].strip()
             chain_identifier = line[21]
             residue_number = int(line[22:26].strip())
             insertion_code = line[26] if line[26] != " " else None

{rnapolis-0.3.16 → rnapolis-0.3.18}/src/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-0.3.16 → rnapolis-0.3.18}/src/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,

{rnapolis-0.3.16 → rnapolis-0.3.18}/tests/test_parser.py

@@ -9,3 +9,10 @@ def test_nucleic_acid_only():
     with open("tests/184D.cif") as f:
         structure3d = read_3d_structure(f, 1, nucleic_acid_only=True)
     assert len(structure3d.residues) == 14
+
+
+def test_1ato():
+    with open("tests/1ATO.pdb") as f:
+        structure3d = read_3d_structure(f)
+    sequence = "".join([residue.one_letter_name for residue in structure3d.residues])
+    assert sequence == "GGCACCUCCUCGCGGUGCC"