RNApolis 0.4.10__py3-none-any.whl → 0.4.12__py3-none-any.whl

{RNApolis-0.4.10.dist-info → RNApolis-0.4.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: RNApolis
-Version: 0.4.10
+Version: 0.4.12
 Summary: A Python library containing RNA-related bioinformatics functions and classes
 Home-page: https://github.com/tzok/rnapolis-py
 Author: Tomasz Zok

{RNApolis-0.4.10.dist-info → RNApolis-0.4.12.dist-info}/RECORD

@@ -2,16 +2,16 @@ rnapolis/annotator.py,sha256=_hsSX2VHFvIQ47l_EA7lwGFXLiVLbhFPEsOQzBKbjRk,22100
 rnapolis/clashfinder.py,sha256=i95kp0o6OWNqmJDBr-PbsZd7RY2iJtBDr7QqolJSuAQ,8513
 rnapolis/common.py,sha256=LY6Uz96Br8ki_gA8LpfatgtvVbt9jOTkwgagayqTgf8,31251
 rnapolis/metareader.py,sha256=I1-cXc2YNBPwa3zihAnMTjEsAo79tEKzSmWu5yvN1Pk,2071
-rnapolis/molecule_filter.py,sha256=hB6-nXgjmw7FAsQ3bj0cZ2FvuW2I1PXunEfcdwEUB1o,7389
+rnapolis/molecule_filter.py,sha256=F_xkAe7q2NZAaDpRaeikv-twUvbNflWdlLte7oFn2Ms,9130
 rnapolis/motif_extractor.py,sha256=Lfn1iEkhkP9eZD3GPEWNAfy00QO7QPCc8wM_XS1ory8,1147
-rnapolis/parser.py,sha256=2pQYy0sh8TCpeluMmmSJ7C5dudK_bsfstTWCdpwwpNU,15193
+rnapolis/parser.py,sha256=lHI6LyFbEEPdHOzbged1-Ov0tl6MpSungIPacip0Py0,15838
 rnapolis/rfam_folder.py,sha256=SjiiyML_T1__saruFwSMJEoQ7Y55GIU8ktS8ZUn5-fw,11111
 rnapolis/tertiary.py,sha256=6t9ZB4w33-5n_M3sns1RoFXCOTgVAgGH4WDNG5OG9Kg,23426
-rnapolis/transformer.py,sha256=V9nOQvdq4-p7yUWo0vQg0CDQMpmyxz9t4TMSRVEKHnw,1817
+rnapolis/transformer.py,sha256=aC0nBmHHJf5TyLvBIV57Jj3tlwpvHbPo347opfAOlQA,3844
 rnapolis/util.py,sha256=IdquFO3PV1_KDqodjupzm0Rqvgy0CeSzxGHaGEHYXVU,543
-RNApolis-0.4.10.dist-info/LICENSE,sha256=ZGRu12MzCgbYA-Lt8MyBlmjvPZh7xfiD5u5wBx0enq4,1066
-RNApolis-0.4.10.dist-info/METADATA,sha256=AiTwfWTRaaJ_Zd_E1UIYMu54Hi0vu9WN8dYA67x3SLk,54323
-RNApolis-0.4.10.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-RNApolis-0.4.10.dist-info/entry_points.txt,sha256=foN2Pn5e-OzEz0fFmNoX6PnFSZFQntOlY8LbognP5F0,308
-RNApolis-0.4.10.dist-info/top_level.txt,sha256=LcO18koxZcWoJ21KDRRRo_tyIbmXL5z61dPitZpy8yc,9
-RNApolis-0.4.10.dist-info/RECORD,,
+RNApolis-0.4.12.dist-info/LICENSE,sha256=ZGRu12MzCgbYA-Lt8MyBlmjvPZh7xfiD5u5wBx0enq4,1066
+RNApolis-0.4.12.dist-info/METADATA,sha256=fPrlpVrM83UYwPYwaeymBP7SeVLMv7XftCZOl7hUnes,54323
+RNApolis-0.4.12.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+RNApolis-0.4.12.dist-info/entry_points.txt,sha256=foN2Pn5e-OzEz0fFmNoX6PnFSZFQntOlY8LbognP5F0,308
+RNApolis-0.4.12.dist-info/top_level.txt,sha256=LcO18koxZcWoJ21KDRRRo_tyIbmXL5z61dPitZpy8yc,9
+RNApolis-0.4.12.dist-info/RECORD,,

rnapolis/molecule_filter.py

@@ -1,10 +1,11 @@
 #! /usr/bin/env python
 import argparse
 import tempfile
-from typing import List, Set, Tuple
+from typing import Iterable, 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
@@ -153,38 +154,63 @@ def select_category_by_id(
     return attributes, rows
 
 
-def main():
-    parser = argparse.ArgumentParser()
-    parser.add_argument(
-        "--type",
-        help="a type of molecule to select, you can provide this argument multiple times (default: polyribonucleotide)",
-        action="append",
-        default=["polyribonucleotide"],
-        choices=ENTITY_POLY_TYPES,
+def filter_by_poly_types(
+    file_content: str, entity_poly_types: Iterable[str] = ["polyribonucleotide"]
+) -> str:
+    adapter = IoAdapterPy()
+
+    with tempfile.NamedTemporaryFile("rt+") as f:
+        f.write(file_content)
+        f.seek(0)
+        data = adapter.readFile(f.name)
+
+    entity_ids = select_ids(
+        data, "entity_poly", "type", "entity_id", set(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=[],
+    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
     )
-    parser.add_argument("path", help="path to a PDBx/mmCIF file")
-    args = parser.parse_args()
 
-    file = handle_input_file(args.path)
-    adapter = IoAdapterPy()
-    data = adapter.readFile(file.name)
     output = DataContainer("rnapolis")
 
-    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)
+    for table, ids in (
+        (CATEGORIES_WITH_ENTITY_ID, entity_ids),
+        (CATEGORIES_WITH_ASYM_ID, asym_ids),
+        (CATEGORIES_WITH_AUTH_ASYM_ID, auth_asym_ids),
+    ):
+        for category, field_name in table:
+            attributes, rows = select_category_by_id(data, category, field_name, ids)
 
+            if attributes and rows:
+                obj = DataCategory(category, attributes, rows)
+                output.append(obj)
+
+    with tempfile.NamedTemporaryFile("rt+") as tmp:
+        adapter.writeFile(tmp.name, [output])
+        tmp.seek(0)
+        return tmp.read()
+
+
+def filter_by_chains(file_content: str, chains: Iterable[str]) -> str:
+    """
+    Filter a PDBx/mmCIF file by chain IDs. The function returns a new PDBx/mmCIF file.
+
+    Warning! The new file might contain more chains than provided in the `chains` argument.
+    This is because the function filters by entity, so if you ask for chain "A",
+    which is part of entity 1 having chains "A", "B" and "C", then you will get all three chains.
+    """
+    adapter = IoAdapterPy()
+
+    with tempfile.NamedTemporaryFile("rt+") as f:
+        f.write(file_content)
+        f.seek(0)
+        data = adapter.readFile(f.name)
+
+    output = DataContainer("rnapolis")
+
+    entity_ids = select_ids(data, "struct_asym", "id", "entity_id", set(chains))
+    asym_ids = set(chains)
     auth_asym_ids = select_ids(
         data, "atom_site", "label_asym_id", "auth_asym_id", asym_ids
     )
@@ -201,9 +227,38 @@ def main():
                 obj = DataCategory(category, attributes, rows)
                 output.append(obj)
 
-    with tempfile.NamedTemporaryFile() as tmp:
+    with tempfile.NamedTemporaryFile("rt+") as tmp:
         adapter.writeFile(tmp.name, [output])
-        print(tmp.read().decode())
+        tmp.seek(0)
+        return tmp.read()
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--type",
+        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()
+
+    file = handle_input_file(args.path)
+
+    if args.chain:
+        print(filter_by_chains(file.read(), args.chain))
+    elif args.type:
+        print(filter_by_poly_types(file.read(), args.type))
+    else:
+        parser.print_help()
 
 
 if __name__ == "__main__":

rnapolis/parser.py

@@ -65,6 +65,7 @@ def parse_cif(
         atom_site = data[0].getObj("atom_site")
         mod_residue = data[0].getObj("pdbx_struct_mod_residue")
         entity_poly = data[0].getObj("entity_poly")
+        entity = data[0].getObj("entity")
 
         if atom_site:
             for row in atom_site.getRowList():
@@ -219,6 +220,23 @@ def parse_cif(
                 if entity_id and pdbx_seq_one_letter_code_can:
                     sequence_by_entity[entity_id] = pdbx_seq_one_letter_code_can
 
+        if entity:
+            for row in entity.getRowList():
+                row_dict = dict(zip(entity.getAttributeList(), row))
+
+                entity_id = row_dict.get("id", None)
+                type_ = row_dict.get("type", None)
+
+                if entity_id:
+                    sequence_by_entity[entity_id] = sequence_by_entity.get(
+                        entity_id, ""
+                    )
+
+                    if type_:
+                        is_nucleic_acid_by_entity[entity_id] = (
+                            is_nucleic_acid_by_entity.get(entity_id, type_)
+                        )
+
     atoms = filter_clashing_atoms(atoms_to_process)
     return atoms, modified, sequence_by_entity, is_nucleic_acid_by_entity
 

rnapolis/transformer.py

@@ -1,64 +1,133 @@
 #! /usr/bin/env python
 import argparse
-import sys
+import string
+import tempfile
+from typing import Dict, Tuple
 
 from mmcif.io.IoAdapterPy import IoAdapterPy
 from mmcif.io.PdbxReader import DataCategory
 
 
-def main():
-    parser = argparse.ArgumentParser()
-    parser.add_argument("input", help="path to input mmCIF file")
-    parser.add_argument("output", help="path to output mmCIF file")
-    parser.add_argument(
-        "--category", help="name of the category to work on, e.g., atom_site"
-    )
-    parser.add_argument(
-        "--copy-from", help="name of a data item to copy from, e.g., label_asym_id"
-    )
-    parser.add_argument(
-        "--copy-to", help="name of a data item to copy to, e.g., auth_asym_id"
-    )
-    args = parser.parse_args()
-
+def copy_from_to(
+    file_content: str,
+    category: str = "atom_site",
+    copy_from: str = "label_asym_id",
+    copy_to: str = "auth_asym_id",
+) -> str:
     adapter = IoAdapterPy()
-    data = adapter.readFile(args.input)
 
-    if len(data) == 0:
-        print("Empty mmCIF file", file=sys.stderr)
-        sys.exit(1)
+    with tempfile.NamedTemporaryFile(mode="wt") as f:
+        f.write(file_content)
+        f.seek(0)
+        data = adapter.readFile(f.name)
 
-    if args.category not in data[0].getObjNameList():
-        print(f"Failed to find {args.category} in the mmCIF file", file=sys.stderr)
-        sys.exit(1)
+    if len(data) == 0 or category not in data[0].getObjNameList():
+        return file_content
 
-    category = data[0].getObj(args.category)
-    attributes = category.getAttributeList()
+    category_obj = data[0].getObj(category)
+    attributes = category_obj.getAttributeList()
 
-    if args.copy_from not in attributes:
-        print(
-            f"Failed to find data item {args.copy_from} in {args.category}",
-            file=sys.stderr,
-        )
-        sys.exit(1)
+    if copy_from not in attributes:
+        return file_content
 
     transformed = []
 
-    if args.copy_to not in attributes:
-        attributes.append(args.copy_to)
+    if copy_to not in attributes:
+        attributes.append(copy_to)
 
-    for row in category.getRowList():
-        i = attributes.index(args.copy_from)
-        j = attributes.index(args.copy_to)
+    for row in category_obj.getRowList():
+        i = attributes.index(copy_from)
+        j = attributes.index(copy_to)
         if j >= len(row):
             row.append(row[i])
         else:
             row[j] = row[i]
         transformed.append(row)
 
-    data[0].replace(DataCategory(args.category, attributes, transformed))
+    data[0].replace(DataCategory(category_obj, attributes, transformed))
+
+    with tempfile.NamedTemporaryFile(mode="rt+") as f:
+        adapter.writeFile(f.name, data)
+        f.seek(0)
+        return f.read()
+
+
+def replace_value(
+    file_content: str,
+    category: str = "atom_site",
+    column: str = "auth_asym_id",
+    values: str = "".join([c for c in string.printable if c not in string.whitespace]),
+) -> Tuple[str, Dict]:
+    adapter = IoAdapterPy()
+    with tempfile.NamedTemporaryFile(mode="wt") as f:
+        f.write(file_content)
+        f.seek(0)
+        data = adapter.readFile(f.name)
+
+    if len(data) == 0 or category not in data[0].getObjNameList():
+        return file_content, {}
+
+    category_obj = data[0].getObj(category)
+    attributes = category_obj.getAttributeList()
+
+    if column not in attributes:
+        return file_content, {}
+
+    transformed = []
+    mapping = {}
+
+    for row in category_obj.getRowList():
+        i = attributes.index(column)
+
+        if row[i] not in mapping:
+            mapping[row[i]] = values[len(mapping)]
+
+        row[i] = mapping[row[i]]
+        transformed.append(row)
+
+    data[0].replace(DataCategory(category_obj, attributes, transformed))
+
+    with tempfile.NamedTemporaryFile(mode="rt+") as f:
+        adapter.writeFile(f.name, data)
+        f.seek(0)
+        return f.read(), mapping
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("input", help="path to input mmCIF file")
+    parser.add_argument("output", help="path to output mmCIF file")
+    parser.add_argument(
+        "--category", help="name of the category to work on, e.g., atom_site"
+    )
+    parser.add_argument(
+        "--copy-from",
+        help="name of a data item to copy from, e.g., label_asym_id (exclusive with --replace)",
+    )
+    parser.add_argument(
+        "--copy-to",
+        help="name of a data item to copy to, e.g., auth_asym_id (exclusive with --replace)",
+    )
+    parser.add_argument(
+        "--replace",
+        help="name of a data item to replace values, e.g., auth_asym_id (exclusive with --copy-from and --copy-to)",
+    )
+    parser.add_argument(
+        "--values",
+        help="values to replace with, e.g., ABCDEFGHIJKLMNOPQRSTUVWXYZ (exclusive with --copy-from and --copy-to)",
+    )
+    args = parser.parse_args()
+
+    if args.copy_from and args.copy_to:
+        output = copy_from_to(args.input, args.category, args.copy_from, args.copy_to)
+    elif args.replace and args.values:
+        output = replace_value(args.input, args.category, args.replace, args.values)
+    else:
+        parser.print_help()
+        return
 
-    adapter.writeFile(args.output, data)
+    with open(args.output, "w") as f:
+        f.write(output)
 
 
 if __name__ == "__main__":