RNApolis 0.0.16__tar.gz → 0.1.1__tar.gz

{RNApolis-0.0.16 → RNApolis-0.1.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: RNApolis
-Version: 0.0.16
+Version: 0.1.1
 Summary: A Python library containing RNA-related bioinformatics functions and classes
 Home-page: https://github.com/tzok/rnapolis-py
 Author: Tomasz Zok

{RNApolis-0.0.16 → RNApolis-0.1.1}/setup.py

@@ -5,7 +5,7 @@ with open("README.md") as f:
 
 setup(
     name="RNApolis",
-    version="0.0.16",
+    version="0.1.1",
     packages=["rnapolis"],
     package_dir={"": "src"},
     author="Tomasz Zok",

{RNApolis-0.0.16 → RNApolis-0.1.1}/src/RNApolis.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: RNApolis
-Version: 0.0.16
+Version: 0.1.1
 Summary: A Python library containing RNA-related bioinformatics functions and classes
 Home-page: https://github.com/tzok/rnapolis-py
 Author: Tomasz Zok

{RNApolis-0.0.16 → RNApolis-0.1.1}/src/rnapolis/annotator.py

@@ -19,6 +19,7 @@ from rnapolis.common import (
     BasePhosphate,
     BaseRibose,
     BPh,
+    BpSeq,
     LeontisWesthof,
     Residue,
     Saenger,
@@ -471,11 +472,26 @@ def find_stackings(structure: Structure3D, model: int = 1) -> List[Stacking]:
 
 
 def extract_secondary_structure(
-    tertiary_structure: Structure3D, model: int = 1
+    tertiary_structure: Structure3D, model: int = 1, find_gaps: bool = False
 ) -> Structure2D:
     base_pairs, base_phosphate, base_ribose = find_pairs(tertiary_structure, model)
     stackings = find_stackings(tertiary_structure, model)
-    return Structure2D(base_pairs, stackings, base_ribose, base_phosphate, [])
+    mapping = Mapping2D3D(tertiary_structure, base_pairs, stackings, find_gaps)
+    stems, single_strands, hairpins, loops = mapping.bpseq.elements
+    return Structure2D(
+        base_pairs,
+        stackings,
+        base_ribose,
+        base_phosphate,
+        [],
+        str(mapping.bpseq),
+        mapping.dot_bracket,
+        mapping.extended_dot_bracket,
+        stems,
+        single_strands,
+        hairpins,
+        loops,
+    )
 
 
 def write_json(path: str, structure2d: Structure2D):
@@ -541,9 +557,9 @@ def write_csv(path: str, structure2d: Structure2D):
             )
 
 
-def write_bpseq(path: str, mapping: Mapping2D3D):
+def write_bpseq(path: str, bpseq: BpSeq):
     with open(path, "w") as f:
-        f.write(str(mapping.bpseq))
+        f.write(str(bpseq))
 
 
 def main():
@@ -563,14 +579,14 @@ def main():
     parser.add_argument(
         "--find-gaps",
         action="store_true",
-        help=f"(optional) if set, the program will detect gaps and break the PDB chain into two or more strands; "
-        "the gap is defined as O3'-P distance greater then {1.5 * AVERAGE_OXYGEN_PHOSPHORUS_DISTANCE_COVALENT}",
+        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}",
     )
     args = parser.parse_args()
 
     file = handle_input_file(args.input)
     structure3d = read_3d_structure(file, 1)
-    structure2d = extract_secondary_structure(structure3d)
+    structure2d = extract_secondary_structure(structure3d, 1, args.find_gaps)
 
     if args.csv:
         write_csv(args.csv, structure2d)
@@ -578,15 +594,13 @@ def main():
     if args.json:
         write_json(args.json, structure2d)
 
-    mapping = Mapping2D3D(structure3d, structure2d, args.find_gaps)
-
     if args.bpseq:
-        write_bpseq(args.bpseq, mapping)
+        write_bpseq(args.bpseq, structure2d.bpseq)
 
     if args.extended:
-        print(mapping.extended_dot_bracket)
+        print(structure2d.extendedDotBracket)
     else:
-        print(mapping.dot_bracket)
+        print(structure2d.dotBracket)
 
 
 if __name__ == "__main__":

{RNApolis-0.0.16 → RNApolis-0.1.1}/src/rnapolis/common.py

@@ -321,15 +321,6 @@ class OtherInteraction(Interaction):
     pass
 
 
-@dataclass(frozen=True, order=True)
-class Structure2D:
-    basePairs: List[BasePair]
-    stackings: List[Stacking]
-    baseRiboseInteractions: List[BaseRibose]
-    basePhosphateInteractions: List[BasePhosphate]
-    otherInteractions: List[OtherInteraction]
-
-
 @dataclass
 class Entry(Sequence):
     index_: int
@@ -380,12 +371,15 @@ class Strand:
         return f"{self.first}-{self.sequence}-{self.last}"
 
 
-@dataclass(frozen=True)
+@dataclass
 class SingleStrand:
     strand: Strand
     is5p: bool
     is3p: bool
 
+    def __post_init__(self):
+        self.description = str(self)
+
     def __str__(self):
         if self.is5p:
             return f"SingleStrand5p {self.strand.first} {self.strand.last} {self.strand.sequence} {self.strand.structure}"
@@ -394,7 +388,7 @@ class SingleStrand:
         return f"SingleStrand {self.strand.first} {self.strand.last} {self.strand.sequence} {self.strand.structure}"
 
 
-@dataclass(frozen=True)
+@dataclass
 class Stem:
     strand5p: Strand
     strand3p: Strand
@@ -410,22 +404,31 @@ class Stem:
             Strand.from_bpseq_entries(strand3p_entries, dotbracket),
         )
 
+    def __post_init__(self):
+        self.description = str(self)
+
     def __str__(self):
         return f"Stem {self.strand5p.first} {self.strand5p.last} {self.strand5p.sequence} {self.strand5p.structure} {self.strand3p.first} {self.strand3p.last} {self.strand3p.sequence} {self.strand3p.structure}"
 
 
-@dataclass(frozen=True)
+@dataclass
 class Hairpin:
     strand: Strand
 
+    def __post_init__(self):
+        self.description = str(self)
+
     def __str__(self):
         return f"Hairpin {self.strand.first} {self.strand.last} {self.strand.sequence} {self.strand.structure}"
 
 
-@dataclass(frozen=True)
+@dataclass
 class Loop:
     strands: List[Strand]
 
+    def __post_init__(self):
+        self.description = str(self)
+
     def __str__(self):
         desc = " ".join(
             [
@@ -516,30 +519,32 @@ class BpSeq:
         return stems
 
     @cached_property
-    def elements(self):
+    def elements(
+        self,
+    ) -> Tuple[List[Stem], List[SingleStrand], List[Hairpin], List[Loop]]:
         if not self.__stems_entries:
-            return []
+            return [], [], [], []
 
-        elements = []
-        stops = set()
+        stems, single_strands, hairpins, loops = [], [], [], []
+        stopset = set()
 
         # stems
         for stem_entries in self.__stems_entries:
             stem = Stem.from_bpseq_entries(
                 stem_entries, self.entries, self.to_dot_bracket.structure
             )
-            elements.append(stem)
-            stops.add(stem.strand5p.first - 1)
-            stops.add(stem.strand5p.last - 1)
-            stops.add(stem.strand3p.first - 1)
-            stops.add(stem.strand3p.last - 1)
+            stems.append(stem)
+            stopset.add(stem.strand5p.first - 1)
+            stopset.add(stem.strand5p.last - 1)
+            stopset.add(stem.strand3p.first - 1)
+            stopset.add(stem.strand3p.last - 1)
 
-        stops = sorted(stops)
+        stops = sorted(stopset)
         loop_candidates = []
 
         # 5' single strand
         if stops[0] > 0:
-            elements.append(
+            single_strands.append(
                 SingleStrand(
                     Strand.from_bpseq_entries(
                         self.entries[: stops[0] + 1],
@@ -555,7 +560,7 @@ class BpSeq:
             candidate = self.entries[stops[i - 1] : stops[i] + 1]
             if all([entry.pair == 0 for entry in candidate[1:-1]]):
                 if candidate[0].pair == candidate[-1].index_:
-                    elements.append(
+                    hairpins.append(
                         Hairpin(
                             Strand.from_bpseq_entries(
                                 candidate, self.to_dot_bracket.structure
@@ -571,7 +576,7 @@ class BpSeq:
 
         # 3' single strand
         if stops[-1] < len(self.entries) - 1:
-            elements.append(
+            single_strands.append(
                 SingleStrand(
                     Strand.from_bpseq_entries(
                         self.entries[stops[-1] :], self.to_dot_bracket.structure
@@ -613,13 +618,13 @@ 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]):
-                    elements.append(Loop(loop))
+                    loops.append(Loop(loop))
 
         for i in range(len(loop_candidates)):
             if i not in used:
-                elements.append(SingleStrand(loop_candidates[i]))
+                single_strands.append(SingleStrand(loop_candidates[i], False, False))
 
-        return elements
+        return stems, single_strands, hairpins, loops
 
     @cached_property
     def __regions(self) -> List[Tuple[int, int, int]]:
@@ -675,14 +680,14 @@ class BpSeq:
                 vars_by_region[i].append(variable)
                 vars_by_order[j].append(variable)
                 var_by_region_order[(i, j)] = variable
-                region_by_var[variable] = i
+                region_by_var[variable] = regions[i]
 
         # define objective function terms
         terms = []
 
         for order, vars in vars_by_order.items():
             for var in vars:
-                length = len(regions[region_by_var[var]])
+                length = region_by_var[var][2]
                 if order == 0:
                     terms.append(var * length)
                 else:
@@ -707,6 +712,7 @@ class BpSeq:
 
         # solve the problem
         try:
+            logging.debug(f"POA: problem formulation\n{problem}")
             problem.solve(solver)
         except pulp.PulpSolverError:
             logging.warning(
@@ -720,7 +726,7 @@ class BpSeq:
             return self.fcfs()
 
         # log solver time statistics
-        logging.info(
+        logging.debug(
             f"POA: solver {solver.name} took {round(problem.solutionTime, 2)} seconds"
         )
 
@@ -833,3 +839,19 @@ class DotBracket:
 
     def __str__(self):
         return f"{self.sequence}\n{self.structure}"
+
+
+@dataclass(frozen=True, order=True)
+class Structure2D:
+    basePairs: List[BasePair]
+    stackings: List[Stacking]
+    baseRiboseInteractions: List[BaseRibose]
+    basePhosphateInteractions: List[BasePhosphate]
+    otherInteractions: List[OtherInteraction]
+    bpseq: str
+    dotBracket: str
+    extendedDotBracket: str
+    stems: List[Stem]
+    singleStrands: List[SingleStrand]
+    hairpins: List[Hairpin]
+    loops: List[Loop]

{RNApolis-0.0.16 → RNApolis-0.1.1}/src/rnapolis/motif_extractor.py

@@ -1,5 +1,6 @@
 #! /usr/bin/env python
 import argparse
+import itertools
 from typing import IO, Dict, List
 
 import orjson
@@ -24,7 +25,10 @@ def main():
         parser.print_help()
         return
 
-    for element in bpseq.elements:
+    print(f"Full dot-bracket:\n{bpseq.to_dot_bracket}")
+    stems, single_strands, hairpins, loops = bpseq.elements
+
+    for element in itertools.chain(stems, single_strands, hairpins, loops):
         print(element)
 
 

{RNApolis-0.0.16 → RNApolis-0.1.1}/src/rnapolis/tertiary.py

@@ -388,14 +388,15 @@ class Structure3D:
 @dataclass
 class Mapping2D3D:
     structure3d: Structure3D
-    structure2d: Structure2D
+    base_pairs2d: List[BasePair]
+    stackings2d: List[Stacking]
     find_gaps: bool
 
     @cached_property
     def base_pairs(self) -> List[BasePair3D]:
         result = []
         used = set()
-        for base_pair in self.structure2d.basePairs:
+        for base_pair in self.base_pairs2d:
             nt1 = self.structure3d.find_residue(base_pair.nt1.label, base_pair.nt1.auth)
             nt2 = self.structure3d.find_residue(base_pair.nt2.label, base_pair.nt2.auth)
             if nt1 is not None and nt2 is not None:
@@ -439,7 +440,7 @@ class Mapping2D3D:
     def stackings(self) -> List[Stacking3D]:
         result = []
         used = set()
-        for stacking in self.structure2d.stackings:
+        for stacking in self.stackings2d:
             nt1 = self.structure3d.find_residue(stacking.nt1.label, stacking.nt1.auth)
             nt2 = self.structure3d.find_residue(stacking.nt2.label, stacking.nt2.auth)
             if nt1 is not None and nt2 is not None:

{RNApolis-0.0.16 → RNApolis-0.1.1}/tests/test_bugfixes.py

@@ -9,7 +9,9 @@ def test_1E7K():
     with open("tests/1E7K_1_C.cif") as f:
         structure3d = read_3d_structure(f, 1)
     structure2d = extract_secondary_structure(structure3d)
-    mapping = Mapping2D3D(structure3d, structure2d, True)
+    mapping = Mapping2D3D(
+        structure3d, structure2d.basePairs, structure2d.stackings, True
+    )
     assert len(mapping.strands_sequences) == 2
 
 
@@ -25,7 +27,9 @@ def test_1DFU():
     assert b2g is not None
 
     structure2d = extract_secondary_structure(structure3d)
-    mapping = Mapping2D3D(structure3d, structure2d, True)
+    mapping = Mapping2D3D(
+        structure3d, structure2d.basePairs, structure2d.stackings, True
+    )
     assert b2g not in mapping.base_pair_graph[b1u]
     assert b1u not in mapping.base_pair_graph[b2g]
 
@@ -35,7 +39,9 @@ def test_4WTI():
     with open("tests/4WTI_1_T-P.cif") as f:
         structure3d = read_3d_structure(f, 1)
     structure2d = extract_secondary_structure(structure3d)
-    mapping = Mapping2D3D(structure3d, structure2d, True)
+    mapping = Mapping2D3D(
+        structure3d, structure2d.basePairs, structure2d.stackings, True
+    )
     assert mapping.dot_bracket == ">strand_T\nCGG\n.((\n>strand_P\nCC\n))"
 
 
@@ -44,7 +50,9 @@ def test_1HMH():
     with open("tests/1HMH_1_E.cif") as f:
         structure3d = read_3d_structure(f, 1)
     structure2d = extract_secondary_structure(structure3d)
-    mapping = Mapping2D3D(structure3d, structure2d, True)
+    mapping = Mapping2D3D(
+        structure3d, structure2d.basePairs, structure2d.stackings, True
+    )
     assert mapping.dot_bracket == ">strand_E\nUG\n.."
 
 

{RNApolis-0.0.16 → RNApolis-0.1.1}/tests/test_common.py

@@ -85,7 +85,7 @@ def test_rnapdbee_adapters_api_compliance_other(obj):
 @given(st.from_type(Structure2D))
 @settings(max_examples=10)
 def test_rnapdbee_adapters_api_compliance_structure2d(obj):
-    assert obj.__dict__.keys() == {
+    assert obj.__dict__.keys() >= {
         "basePairs",
         "stackings",
         "baseRiboseInteractions",
@@ -102,13 +102,7 @@ def test_bpseq_from_dotbracket():
 
 def test_elements():
     bpseq = BpSeq.from_dotbracket(DotBracket.from_file("tests/1EHZ.dbn"))
-    stems = [element for element in bpseq.elements if isinstance(element, Stem)]
-    single_strands = [
-        element for element in bpseq.elements if isinstance(element, SingleStrand)
-    ]
-    hairpins = [element for element in bpseq.elements if isinstance(element, Hairpin)]
-    loops = [element for element in bpseq.elements if isinstance(element, Loop)]
-
+    stems, single_strands, hairpins, loops = bpseq.elements
     assert len(stems) == 5
     assert len(single_strands) == 1
     assert len(hairpins) == 1
@@ -121,10 +115,10 @@ def test_pseudoknot_order_assignment():
 
     counter = Counter(dot_bracket.structure)
     assert counter["."] == 1185
-    assert counter["("] == 1296
-    assert counter["["] == 45
+    assert counter["("] == 1298
+    assert counter["["] == 44
     assert counter["{"] == 17
-    assert counter["<"] == 8
+    assert counter["<"] == 7
     assert counter["A"] == 4
     assert counter["B"] == 1
     assert counter["C"] == 1

{RNApolis-0.0.16 → RNApolis-0.1.1}/tests/test_quadruplexes.py

@@ -9,7 +9,9 @@ def test_2HY9():
     with open("tests/2HY9.cif") as f:
         structure3d = read_3d_structure(f, 1)
     structure2d = extract_secondary_structure(structure3d)
-    mapping = Mapping2D3D(structure3d, structure2d, True)
+    mapping = Mapping2D3D(
+        structure3d, structure2d.basePairs, structure2d.stackings, True
+    )
 
     # tract 1
     g4 = structure3d.find_residue(ResidueLabel("A", 4, "DG"), None)
@@ -60,7 +62,9 @@ def test_6RS3():
     with open("tests/6RS3.cif") as f:
         structure3d = read_3d_structure(f, 1)
     structure2d = extract_secondary_structure(structure3d)
-    mapping = Mapping2D3D(structure3d, structure2d, True)
+    mapping = Mapping2D3D(
+        structure3d, structure2d.basePairs, structure2d.stackings, True
+    )
 
     g1 = structure3d.find_residue(ResidueLabel("A", 1, "DG"), None)
     g2 = structure3d.find_residue(ResidueLabel("A", 2, "DG"), None)
@@ -103,7 +107,9 @@ def test_1JJP():
     with open("tests/1JJP.cif") as f:
         structure3d = read_3d_structure(f, 1)
     structure2d = extract_secondary_structure(structure3d)
-    mapping = Mapping2D3D(structure3d, structure2d, True)
+    mapping = Mapping2D3D(
+        structure3d, structure2d.basePairs, structure2d.stackings, True
+    )
 
     ag1 = structure3d.find_residue(ResidueLabel("A", 1, "DG"), None)
     ag2 = structure3d.find_residue(ResidueLabel("A", 2, "DG"), None)
@@ -175,7 +181,9 @@ def test_6FC9():
     with open("tests/6FC9.cif") as f:
         structure3d = read_3d_structure(f, 1)
     structure2d = extract_secondary_structure(structure3d)
-    mapping = Mapping2D3D(structure3d, structure2d, True)
+    mapping = Mapping2D3D(
+        structure3d, structure2d.basePairs, structure2d.stackings, True
+    )
 
     g1 = structure3d.find_residue(ResidueLabel("A", 1, "DG"), None)
     g2 = structure3d.find_residue(ResidueLabel("A", 2, "DG"), None)
@@ -249,7 +257,9 @@ def test_UGG_md():
     with open("tests/q-ugg-5k-salt_400-500ns_frame1065.pdb") as f:
         structure3d = read_3d_structure(f, 1)
     structure2d = extract_secondary_structure(structure3d)
-    mapping = Mapping2D3D(structure3d, structure2d, True)
+    mapping = Mapping2D3D(
+        structure3d, structure2d.basePairs, structure2d.stackings, True
+    )
 
     u1 = structure3d.find_residue(None, ResidueAuth(" ", 1, None, "U5"))
     g2 = structure3d.find_residue(None, ResidueAuth(" ", 2, None, "G"))