RNApolis 0.3.9__tar.gz → 0.3.11__tar.gz

{RNApolis-0.3.9/src/RNApolis.egg-info → rnapolis-0.3.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: RNApolis
-Version: 0.3.9
+Version: 0.3.11
 Summary: A Python library containing RNA-related bioinformatics functions and classes
 Home-page: https://github.com/tzok/rnapolis-py
 Author: Tomasz Zok

{RNApolis-0.3.9 → rnapolis-0.3.11}/setup.py

@@ -5,7 +5,7 @@ with open("README.md") as f:
 
 setup(
     name="RNApolis",
-    version="0.3.9",
+    version="0.3.11",
     packages=["rnapolis"],
     package_dir={"": "src"},
     author="Tomasz Zok",

{RNApolis-0.3.9 → rnapolis-0.3.11/src/RNApolis.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: RNApolis
-Version: 0.3.9
+Version: 0.3.11
 Summary: A Python library containing RNA-related bioinformatics functions and classes
 Home-page: https://github.com/tzok/rnapolis-py
 Author: Tomasz Zok

{RNApolis-0.3.9 → rnapolis-0.3.11}/src/rnapolis/annotator.py

@@ -486,7 +486,7 @@ def extract_secondary_structure(
     tertiary_structure: Structure3D,
     model: Optional[int] = None,
     find_gaps: bool = False,
-) -> BaseInteractions:
+) -> Structure2D:
     base_interactions = extract_base_interactions(tertiary_structure, model)
     mapping = Mapping2D3D(
         tertiary_structure,

{RNApolis-0.3.9 → rnapolis-0.3.11}/src/rnapolis/common.py

@@ -1,6 +1,7 @@
 import itertools
 import logging
 import os
+import re
 import string
 from collections import defaultdict
 from collections.abc import Sequence
@@ -896,6 +897,37 @@ class DotBracket:
         return f"{self.sequence}\n{self.structure}"
 
 
+@dataclass
+class MultiStrandDotBracket(DotBracket):
+    strands: List[Strand]
+
+    @staticmethod
+    def from_string(input: str):
+        strands = []
+        first = 1
+
+        for match in re.finditer(
+            r"((>.*?\n)?([ACGUNacgun]+)\n([.()\[\]{}<>A-Za-z]+))", input
+        ):
+            sequence = match.group(3)
+            structure = match.group(4)
+            assert len(sequence) == len(structure)
+            last = first + len(sequence) - 1
+            strands.append(Strand(first, last, sequence, structure))
+            first = last + 1
+
+        return MultiStrandDotBracket(
+            "".join(strand.sequence for strand in strands),
+            "".join(strand.structure for strand in strands),
+            strands,
+        )
+
+    @staticmethod
+    def from_file(path: str):
+        with open(path) as f:
+            return MultiStrandDotBracket.from_string(f.read())
+
+
 @dataclass(frozen=True, order=True)
 class BaseInteractions:
     basePairs: List[BasePair]

{RNApolis-0.3.9 → rnapolis-0.3.11}/src/rnapolis/parser.py

@@ -12,8 +12,15 @@ def read_3d_structure(
     atoms, modified, sequence = (
         parse_cif(cif_or_pdb) if is_cif(cif_or_pdb) else parse_pdb(cif_or_pdb)
     )
-    if model is not None:
-        atoms = list(filter(lambda atom: atom.model == model, atoms))
+    available_models = {atom.model: None for atom in atoms}
+    atoms_by_model = {
+        model: list(filter(lambda atom: atom.model == model, atoms))
+        for model in available_models
+    }
+    if model is not None and model in available_models:
+        atoms = atoms_by_model[model]
+    else:
+        atoms = atoms_by_model[list(available_models.keys())[0]]
     return group_atoms(atoms, modified, sequence, nucleic_acid_only)
 
 

{RNApolis-0.3.9 → rnapolis-0.3.11}/tests/test_common.py

@@ -11,6 +11,7 @@ from rnapolis.common import (
     BpSeq,
     DotBracket,
     Interaction,
+    MultiStrandDotBracket,
     OtherInteraction,
     Residue,
     ResidueAuth,
@@ -122,3 +123,17 @@ def test_pseudoknot_order_assignment():
 
     bpseq_again = BpSeq.from_dotbracket(dot_bracket)
     assert bpseq == bpseq_again
+
+
+def test_multi_strand_dot_bracket():
+    input = ">strand_A\nAGCGCCUGGACUUAAAGCCAU\n..((((.((((((((((((..\n>strand_B\nGGCUUUAAGUUGACGAGGGCAGGGUUUAUCGAGACAUCGGCGGGUGCCCUGCGGUCUUCCUGCGACCGUUAGAGGACUGGUAAAACCACAGGCGACUGUGGCAUAGAGCAGUCCGGGCAGGAA\n)))))))))))..(((...[[[[[[...)))......)))))...]]]]]][[[[[.((((((]]]]].....((((((......((((((....)))))).......))))))..))))))."
+    dot_bracket = MultiStrandDotBracket.from_string(input)
+    assert len(dot_bracket.strands) == 2
+    assert dot_bracket.strands[0].sequence == "AGCGCCUGGACUUAAAGCCAU"
+    assert dot_bracket.strands[1].sequence == (
+        "GGCUUUAAGUUGACGAGGGCAGGGUUUAUCGAGACAUCGGCGGGUGCCCUGCGGUCUUCCUGCGACCGUUAGAGGACUGGUAAAACCACAGGCGACUGUGGCAUAGAGCAGUCCGGGCAGGAA"
+    )
+    assert dot_bracket.strands[0].structure == ("..((((.((((((((((((..")
+    assert dot_bracket.strands[1].structure == (
+        ")))))))))))..(((...[[[[[[...)))......)))))...]]]]]][[[[[.((((((]]]]].....((((((......((((((....)))))).......))))))..))))))."
+    )