RNApolis 0.1.4__py3-none-any.whl → 0.2.0__py3-none-any.whl

{RNApolis-0.1.4.dist-info → RNApolis-0.2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: RNApolis
-Version: 0.1.4
+Version: 0.2.0
 Summary: A Python library containing RNA-related bioinformatics functions and classes
 Home-page: https://github.com/tzok/rnapolis-py
 Author: Tomasz Zok
@@ -15,6 +15,7 @@ Classifier: Programming Language :: Python :: 3
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Requires-Dist: graphviz
 Requires-Dist: mmcif
 Requires-Dist: numpy
 Requires-Dist: ordered-set

RNApolis-0.2.0.dist-info/RECORD

@@ -0,0 +1,15 @@
+rnapolis/annotator.py,sha256=XtEJrog8c3zZ-pLlGBytJExGahPstGd-nbPLKQLa58A,21228
+rnapolis/clashfinder.py,sha256=jD3s_UovygWi01NUbQNeAeRRFkARTSRraLXUV43UbAA,8514
+rnapolis/common.py,sha256=DPmRpNkMaxuIai3vfLzSlP6IN0zpj6kmT3LoRjnJUWE,26440
+rnapolis/metareader.py,sha256=4qtMKRvww2sUStLeV8WVrLEt-ScydHUv4Gxx96tnf-M,1683
+rnapolis/motif_extractor.py,sha256=duHvpi9Ulcny9K60E6VBpz5RpJZw-KdTB4_Ph0iP478,774
+rnapolis/parser.py,sha256=Z3Zd_IuRyOP45x5BStgu7UgoyHthhw55fT3udHUhAE4,11905
+rnapolis/tertiary.py,sha256=iWMPD9c21rjMPpEdBd7mPCQgds65IbOr4_Fy06s0NoU,18957
+rnapolis/transformer.py,sha256=V9nOQvdq4-p7yUWo0vQg0CDQMpmyxz9t4TMSRVEKHnw,1817
+rnapolis/util.py,sha256=IdquFO3PV1_KDqodjupzm0Rqvgy0CeSzxGHaGEHYXVU,543
+RNApolis-0.2.0.dist-info/LICENSE,sha256=ZGRu12MzCgbYA-Lt8MyBlmjvPZh7xfiD5u5wBx0enq4,1066
+RNApolis-0.2.0.dist-info/METADATA,sha256=-ApE3-kETFzu512tLPAQa7MJjY7tuT-qyHLkPMBhI7A,1148
+RNApolis-0.2.0.dist-info/WHEEL,sha256=Xo9-1PvkuimrydujYJAjF7pCkriuXBpUPEjma1nZyJ0,92
+RNApolis-0.2.0.dist-info/entry_points.txt,sha256=113HwzaWSIoCvcPxkg_j2TIbnezP4_7akpTNr5n3Zjg,220
+RNApolis-0.2.0.dist-info/top_level.txt,sha256=LcO18koxZcWoJ21KDRRRo_tyIbmXL5z61dPitZpy8yc,9
+RNApolis-0.2.0.dist-info/RECORD,,

{RNApolis-0.1.4.dist-info → RNApolis-0.2.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.41.1)
+Generator: bdist_wheel (0.41.3)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

rnapolis/annotator.py

@@ -5,7 +5,7 @@ import logging
 import math
 import os
 from collections import Counter, defaultdict
-from typing import IO, Dict, List, Optional, Set, Tuple
+from typing import Dict, List, Optional, Set, Tuple
 
 import numpy
 import numpy.typing
@@ -15,6 +15,7 @@ from scipy.spatial import KDTree
 
 from rnapolis.common import (
     BR,
+    BaseInteractions,
     BasePair,
     BasePhosphate,
     BaseRibose,
@@ -471,19 +472,27 @@ def find_stackings(structure: Structure3D, model: int = 1) -> List[Stacking]:
     return stackings
 
 
-def extract_secondary_structure(
-    tertiary_structure: Structure3D, model: int = 1, find_gaps: bool = False
-) -> Structure2D:
+def extract_base_interactions(
+    tertiary_structure: Structure3D, model: int = 1
+) -> BaseInteractions:
     base_pairs, base_phosphate, base_ribose = find_pairs(tertiary_structure, model)
     stackings = find_stackings(tertiary_structure, model)
-    mapping = Mapping2D3D(tertiary_structure, base_pairs, stackings, find_gaps)
+    return BaseInteractions(base_pairs, stackings, base_ribose, base_phosphate, [])
+
+
+def extract_secondary_structure(
+    tertiary_structure: Structure3D, model: int = 1, find_gaps: bool = False
+) -> BaseInteractions:
+    base_interactions = extract_base_interactions(tertiary_structure, model)
+    mapping = Mapping2D3D(
+        tertiary_structure,
+        base_interactions.basePairs,
+        base_interactions.stackings,
+        find_gaps,
+    )
     stems, single_strands, hairpins, loops = mapping.bpseq.elements
     return Structure2D(
-        base_pairs,
-        stackings,
-        base_ribose,
-        base_phosphate,
-        [],
+        base_interactions,
         str(mapping.bpseq),
         mapping.dot_bracket,
         mapping.extended_dot_bracket,
@@ -494,12 +503,12 @@ def extract_secondary_structure(
     )
 
 
-def write_json(path: str, structure2d: Structure2D):
+def write_json(path: str, structure2d: BaseInteractions):
     with open(path, "wb") as f:
         f.write(orjson.dumps(structure2d))
 
 
-def write_csv(path: str, structure2d: Structure2D):
+def write_csv(path: str, structure2d: BaseInteractions):
     with open(path, "w") as f:
         writer = csv.writer(f)
         writer.writerow(["nt1", "nt2", "type", "classification-1", "classification-2"])
@@ -582,6 +591,7 @@ def main():
         help="(optional) if set, the program will detect gaps and break the PDB chain into two or more strands; "
         f"the gap is defined as O3'-P distance greater then {1.5 * AVERAGE_OXYGEN_PHOSPHORUS_DISTANCE_COVALENT}",
     )
+    parser.add_argument("--dot", help="(optional) path to output DOT file")
     args = parser.parse_args()
 
     file = handle_input_file(args.input)
@@ -602,6 +612,9 @@ def main():
     else:
         print(structure2d.dotBracket)
 
+    if args.dot:
+        print(BpSeq.from_string(structure2d.bpseq).graphviz)
+
 
 if __name__ == "__main__":
     main()

rnapolis/common.py

@@ -9,6 +9,7 @@ from enum import Enum
 from functools import cache, cached_property, total_ordering
 from typing import Dict, List, Optional, Tuple
 
+import graphviz
 import pulp
 
 LOGLEVEL = os.environ.get("LOGLEVEL", "INFO").upper()
@@ -609,13 +610,14 @@ class BpSeq:
                 continue
 
             loop = [loop_candidates[i]]
-            used.add(i)
 
             while True:
                 for j in graph[i]:
-                    if j not in used:
+                    if (
+                        loop_candidates[j] not in used
+                        and loop_candidates[j] not in loop
+                    ):
                         loop.append(loop_candidates[j])
-                        used.add(j)
                         i = j
                         break
                 else:
@@ -624,13 +626,71 @@ class BpSeq:
             if self.entries[loop[0].first - 1].pair == loop[-1].last:
                 if not all([strand.last - strand.first <= 1 for strand in loop]):
                     loops.append(Loop(loop))
+                    used.update(loop)
 
-        for i in range(len(loop_candidates)):
-            if i not in used:
-                single_strands.append(SingleStrand(loop_candidates[i], False, False))
+        for loop_candidate in loop_candidates:
+            if loop_candidate not in used:
+                single_strands.append(SingleStrand(loop_candidate, False, False))
 
         return stems, single_strands, hairpins, loops
 
+    @cached_property
+    def graphviz(self):
+        stems, single_strands, hairpins, loops = self.elements
+        graph = defaultdict(set)
+        dot = graphviz.Graph()
+
+        for single_strand in single_strands:
+            graph[str(single_strand)].update(
+                [
+                    single_strand.strand.first,
+                    single_strand.strand.last,
+                ]
+            )
+
+        for stem in stems:
+            if stem.strand5p.first == stem.strand5p.last:
+                continue
+            graph[str(stem)].update(
+                [
+                    stem.strand5p.first,
+                    stem.strand5p.last,
+                    stem.strand3p.first,
+                    stem.strand3p.last,
+                ]
+            )
+
+        for hairpin in hairpins:
+            graph[str(hairpin)].update(
+                [
+                    hairpin.strand.first,
+                    hairpin.strand.last,
+                ]
+            )
+
+        for loop in loops:
+            stops = set()
+            for strand in loop.strands:
+                stops.update(
+                    [
+                        strand.first,
+                        strand.last,
+                    ]
+                )
+            graph[str(loop)].update(stops)
+
+        for i, element in enumerate(graph.keys()):
+            dot.node(f"E{i}", str(element))
+
+        keys = list(graph.keys())
+
+        for i in range(len(keys)):
+            for j in range(i + 1, len(keys)):
+                if graph[keys[i]].intersection(graph[keys[j]]):
+                    dot.edge(f"E{i}", f"E{j}")
+
+        return dot.render()
+
     @cached_property
     def __regions(self) -> List[Tuple[int, int, int]]:
         return [
@@ -749,18 +809,8 @@ class BpSeq:
         # build dot-bracket
         sequence = self.sequence
         structure = ["." for _ in range(len(sequence))]
-        brackets = [
-            "()",
-            "[]",
-            "{}",
-            "<>",
-            "Aa",
-            "Bb",
-            "Cc",
-            "Dd",
-            "Ee",
-            "Ff",
-            "Gg",
+        brackets = ["()", "[]", "{}", "<>"] + [
+            "".join(p) for p in zip(string.ascii_uppercase, string.ascii_lowercase)
         ]
 
         for i, stem in enumerate(regions):
@@ -829,8 +879,8 @@ class DotBracket:
     def __post_init__(self):
         self.pairs = []
 
-        opening = "([{<ABC"
-        closing = ")]}>abc"
+        opening = "([{<" + string.ascii_uppercase
+        closing = ")]}>" + string.ascii_lowercase
         begins = {bracket: list() for bracket in opening}
         matches = {end: begin for begin, end in zip(opening, closing)}
 
@@ -847,12 +897,17 @@ class DotBracket:
 
 
 @dataclass(frozen=True, order=True)
-class Structure2D:
+class BaseInteractions:
     basePairs: List[BasePair]
     stackings: List[Stacking]
     baseRiboseInteractions: List[BaseRibose]
     basePhosphateInteractions: List[BasePhosphate]
     otherInteractions: List[OtherInteraction]
+
+
+@dataclass(frozen=True, order=True)
+class Structure2D:
+    baseInteractions: BaseInteractions
     bpseq: str
     dotBracket: str
     extendedDotBracket: str

rnapolis/motif_extractor.py

@@ -1,14 +1,8 @@
 #! /usr/bin/env python
 import argparse
 import itertools
-from typing import IO, Dict, List
-
-import orjson
-from mmcif.io.IoAdapterPy import IoAdapterPy
-from mmcif.io.PdbxReader import DataContainer
 
 from rnapolis.common import BpSeq, DotBracket
-from rnapolis.util import handle_input_file
 
 
 def main():

rnapolis/tertiary.py

@@ -1,7 +1,5 @@
-import itertools
 import logging
 import math
-import string
 from collections import defaultdict
 from dataclasses import dataclass, field
 from functools import cached_property, total_ordering
@@ -20,7 +18,6 @@ from rnapolis.common import (
     ResidueAuth,
     ResidueLabel,
     Stacking,
-    Structure2D,
 )
 
 BASE_ATOMS = {

RNApolis-0.1.4.dist-info/RECORD

@@ -1,15 +0,0 @@
-rnapolis/annotator.py,sha256=CLdwuq0Y42unPd3W-NKIqy4JMCSanzUj6GmP9VnfRb4,20766
-rnapolis/clashfinder.py,sha256=jD3s_UovygWi01NUbQNeAeRRFkARTSRraLXUV43UbAA,8514
-rnapolis/common.py,sha256=PRCIuHp7H6Gq38yoLZSaRcR8XvObSo_RYc9C5TsD7uA,24620
-rnapolis/metareader.py,sha256=4qtMKRvww2sUStLeV8WVrLEt-ScydHUv4Gxx96tnf-M,1683
-rnapolis/motif_extractor.py,sha256=VJV1jUPschb_YZTwIatoqF3JQ_jc8uygQZGBao8k9wo,958
-rnapolis/parser.py,sha256=Z3Zd_IuRyOP45x5BStgu7UgoyHthhw55fT3udHUhAE4,11905
-rnapolis/tertiary.py,sha256=PuW2TZJuXzrDvYpR4fnFzsvyOvZlRv2b97N9sUPH1vQ,19005
-rnapolis/transformer.py,sha256=V9nOQvdq4-p7yUWo0vQg0CDQMpmyxz9t4TMSRVEKHnw,1817
-rnapolis/util.py,sha256=IdquFO3PV1_KDqodjupzm0Rqvgy0CeSzxGHaGEHYXVU,543
-RNApolis-0.1.4.dist-info/LICENSE,sha256=ZGRu12MzCgbYA-Lt8MyBlmjvPZh7xfiD5u5wBx0enq4,1066
-RNApolis-0.1.4.dist-info/METADATA,sha256=mQbEA9rXCrbmgwParYgzB4HK9BAWnSJvHpzqieUf0Vs,1124
-RNApolis-0.1.4.dist-info/WHEEL,sha256=5sUXSg9e4bi7lTLOHcm6QEYwO5TIF1TNbTSVFVjcJcc,92
-RNApolis-0.1.4.dist-info/entry_points.txt,sha256=113HwzaWSIoCvcPxkg_j2TIbnezP4_7akpTNr5n3Zjg,220
-RNApolis-0.1.4.dist-info/top_level.txt,sha256=LcO18koxZcWoJ21KDRRRo_tyIbmXL5z61dPitZpy8yc,9
-RNApolis-0.1.4.dist-info/RECORD,,