RNApolis 0.4.14__tar.gz → 0.4.16__tar.gz

{rnapolis-0.4.14/src/RNApolis.egg-info → rnapolis-0.4.16}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: RNApolis
-Version: 0.4.14
+Version: 0.4.16
 Summary: A Python library containing RNA-related bioinformatics functions and classes
 Home-page: https://github.com/tzok/rnapolis-py
 Author: Tomasz Zok
@@ -26,6 +26,15 @@ Requires-Dist: pulp
 Requires-Dist: requests
 Requires-Dist: scipy
 Requires-Dist: viennarna
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: project-url
+Dynamic: requires-dist
+Dynamic: summary
 
 # RNApolis
 

{rnapolis-0.4.14 → rnapolis-0.4.16}/setup.py

@@ -5,7 +5,7 @@ with open("README.md") as f:
 
 setup(
     name="RNApolis",
-    version="0.4.14",
+    version="0.4.16",
     packages=["rnapolis"],
     package_dir={"": "src"},
     author="Tomasz Zok",

{rnapolis-0.4.14 → rnapolis-0.4.16/src/RNApolis.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: RNApolis
-Version: 0.4.14
+Version: 0.4.16
 Summary: A Python library containing RNA-related bioinformatics functions and classes
 Home-page: https://github.com/tzok/rnapolis-py
 Author: Tomasz Zok
@@ -26,6 +26,15 @@ Requires-Dist: pulp
 Requires-Dist: requests
 Requires-Dist: scipy
 Requires-Dist: viennarna
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: project-url
+Dynamic: requires-dist
+Dynamic: summary
 
 # RNApolis
 

{rnapolis-0.4.14 → rnapolis-0.4.16}/src/rnapolis/annotator.py

@@ -11,6 +11,8 @@ import numpy
 import numpy.typing
 import orjson
 from ordered_set import OrderedSet
+from scipy.spatial import KDTree
+
 from rnapolis.common import (
     BR,
     BaseInteractions,
@@ -42,7 +44,6 @@ 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

rnapolis-0.4.16/src/rnapolis/molecule_filter.py

@@ -0,0 +1,229 @@
+#! /usr/bin/env python
+import argparse
+import os
+import tempfile
+from collections import defaultdict, namedtuple
+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
+ENTITY_POLY_TYPES = [
+    "cyclic-pseudo-peptide",
+    "other",
+    "peptide nucleic acid",
+    "polydeoxyribonucleotide",
+    "polydeoxyribonucleotide/polyribonucleotide hybrid",
+    "polypeptide(D)",
+    "polypeptide(L)",
+    "polyribonucleotide",
+]
+
+Link = namedtuple(
+    "Link", ["parent_category_id", "parent_name", "child_category_id", "child_name"]
+)
+
+
+def load_pdbx_item_linked_group_list():
+    dictionary = os.path.join(
+        os.path.abspath(os.path.dirname(__file__)), "mmcif_pdbx_v50.dic"
+    )
+    adapter = IoAdapterPy()
+    data = adapter.readFile(dictionary)
+    obj = data[0].getObj("pdbx_item_linked_group_list")
+    links = defaultdict(set)
+
+    if obj:
+        for row in obj.getRowList():
+            row_dict = dict(zip(obj.getAttributeList(), row))
+            child_category_id = row_dict["child_category_id"]
+            child_name = row_dict["child_name"].split(".")[1]
+            parent_name = row_dict["parent_name"].split(".")[1]
+            parent_category_id = row_dict["parent_category_id"]
+            links[parent_category_id].add(
+                Link(parent_category_id, parent_name, child_category_id, child_name)
+            )
+
+    return links
+
+
+def select_ids(
+    data: List[DataContainer],
+    category: str,
+    field_name_to_extract: str,
+    field_name_to_check: str,
+    accepted_values: Iterable[str],
+) -> Set[str]:
+    obj = data[0].getObj(category)
+    if not obj:
+        return set()
+    attributes = obj.getAttributeList()
+    if field_name_to_check not in attributes or field_name_to_extract not in attributes:
+        return set()
+    index_to_check = attributes.index(field_name_to_check)
+    index_to_extract = attributes.index(field_name_to_extract)
+    return {
+        row[index_to_extract]
+        for row in obj.getRowList()
+        if row[index_to_check] in accepted_values
+    }
+
+
+def select_category_by_id(
+    data: List[DataContainer],
+    category: str,
+    field_name: str,
+    ids: Iterable[str],
+) -> Tuple[List[str], List[List[str]]]:
+    obj = data[0].getObj(category)
+    if not obj:
+        return [], []
+    attributes = obj.getAttributeList()
+    if field_name not in attributes:
+        return attributes, []
+    index = attributes.index(field_name)
+    return attributes, [row for row in obj.getRowList() if row[index] in ids]
+
+
+def read_cif(file_content: str) -> DataContainer:
+    with tempfile.NamedTemporaryFile("rt+") as f:
+        adapter = IoAdapterPy()
+        f.write(file_content)
+        f.seek(0)
+        return adapter.readFile(f.name)
+
+
+def filter_cif(data, entity_ids, asym_ids, auth_asym_ids, retain_categories):
+    links = load_pdbx_item_linked_group_list()
+    categories_with_entity_id = [("entity", "id")] + [
+        (link.child_category_id, link.child_name)
+        for link in links["entity"]
+        if link.parent_name == "id"
+    ]
+    categories_with_asym_id = [("struct_asym", "id")] + [
+        (link.child_category_id, link.child_name)
+        for link in links["struct_asym"]
+        if link.parent_name == "id"
+    ]
+    categories_with_auth_asym_id = [("atom_site", "auth_asym_id")] + [
+        (link.child_category_id, link.child_name)
+        for link in links["atom_site"]
+        if link.parent_name == "auth_asym_id"
+    ]
+
+    output = DataContainer("rnapolis")
+
+    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)
+
+    for category in retain_categories:
+        obj = data[0].getObj(category)
+        if obj:
+            output.append(obj)
+
+    with tempfile.NamedTemporaryFile("rt+") as tmp:
+        adapter = IoAdapterPy()
+        adapter.writeFile(tmp.name, [output])
+        tmp.seek(0)
+        return tmp.read()
+
+
+def filter_by_poly_types(
+    file_content: str,
+    entity_poly_types: Iterable[str] = [
+        "polyribonucleotide",
+        "polydeoxyribonucleotide",
+        "polydeoxyribonucleotide/polyribonucleotide hybrid",
+    ],
+    retain_categories: Iterable[str] = ["chem_comp"],
+) -> str:
+    data = read_cif(file_content)
+    entity_ids = select_ids(
+        data, "entity_poly", "entity_id", "type", set(entity_poly_types)
+    )
+    asym_ids = select_ids(data, "struct_asym", "id", "entity_id", entity_ids)
+    auth_asym_ids = select_ids(
+        data, "atom_site", "auth_asym_id", "label_asym_id", asym_ids
+    )
+    return filter_cif(data, entity_ids, asym_ids, auth_asym_ids, retain_categories)
+
+
+def filter_by_chains(
+    file_content: str,
+    chains: Iterable[str],
+    retain_categories: Iterable[str] = ["chem_comp"],
+) -> 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.
+    """
+    data = read_cif(file_content)
+    asym_ids = set(chains)
+    entity_ids = select_ids(data, "struct_asym", "entity_id", "id", asym_ids)
+    auth_asym_ids = select_ids(
+        data, "atom_site", "auth_asym_id", "label_asym_id", asym_ids
+    )
+    return filter_cif(data, entity_ids, asym_ids, auth_asym_ids, retain_categories)
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--filter-by-poly-types",
+        help=f"filter by entity poly types, possible values: {', '.join(ENTITY_POLY_TYPES)}",
+        action="append",
+        default=[],
+    )
+    parser.add_argument(
+        "--filter-by-chains",
+        help="filter by chain IDs (label_asym_id), e.g. A, B, C",
+        action="append",
+        default=[],
+    )
+    parser.add_argument(
+        "--retain-categories",
+        help="categories to retain in the output file default: chem_comp",
+        action="append",
+        default=["chem_comp"],
+    )
+    parser.add_argument("path", help="path to a PDBx/mmCIF file")
+    args = parser.parse_args()
+
+    file = handle_input_file(args.path)
+    if args.filter_by_poly_types:
+        print(
+            filter_by_poly_types(
+                file.read(),
+                entity_poly_types=args.filter_by_poly_types,
+                retain_categories=args.retain_categories,
+            )
+        )
+    elif args.filter_by_chains:
+        print(
+            filter_by_chains(
+                file.read(),
+                chains=args.filter_by_chains,
+                retain_categories=args.retain_categories,
+            )
+        )
+    else:
+        parser.print_help()
+
+
+if __name__ == "__main__":
+    main()

{rnapolis-0.4.14 → rnapolis-0.4.16}/src/rnapolis/parser.py

@@ -218,7 +218,9 @@ def parse_cif(
                     )
 
                 if entity_id and pdbx_seq_one_letter_code_can:
-                    sequence_by_entity[entity_id] = pdbx_seq_one_letter_code_can
+                    sequence_by_entity[entity_id] = (
+                        pdbx_seq_one_letter_code_can.replace("\n", "")
+                    )
 
         if entity:
             for row in entity.getRowList():
@@ -234,7 +236,16 @@ def parse_cif(
 
                     if type_:
                         is_nucleic_acid_by_entity[entity_id] = (
-                            is_nucleic_acid_by_entity.get(entity_id, type_)
+                            is_nucleic_acid_by_entity.get(
+                                entity_id,
+                                type_
+                                in (
+                                    "peptide nucleic acid",
+                                    "polydeoxyribonucleotide",
+                                    "polydeoxyribonucleotide/polyribonucleotide hybrid",
+                                    "polyribonucleotide",
+                                ),
+                            )
                         )
 
     atoms = filter_clashing_atoms(atoms_to_process)

{rnapolis-0.4.14 → rnapolis-0.4.16}/tests/test_parser.py

@@ -1,3 +1,5 @@
+import gzip
+
 from rnapolis.parser import read_3d_structure
 
 
@@ -31,3 +33,20 @@ def test_4qln_no_duplicate_atoms():
             assert len(atom_names) == len(
                 set(atom_names)
             ), f"Duplicate atoms found in residue {residue.auth}"
+
+
+def test_1gid():
+    expected_sequence = "GAAUUGCGGGAAAGGGGUCAACAGCCGUUCAGUACCAAGUCUCAGGGGAAACUUUGAGAUGGCCUUGCAAAGGGUAUGGUAAUAAGCUGACGGACAUGGUCCUAACCACGCAGCCAAGUCCUAAGUCAACAGAUCUUCUGUUGAUAUGGAUGCAGUUC"
+
+    with gzip.open("tests/1gid.cif.gz", "rt") as f:
+        structure3d = read_3d_structure(f, nucleic_acid_only=True)
+
+    residues_a = [r for r in structure3d.residues if r.auth.chain == "A"]
+    residues_b = [r for r in structure3d.residues if r.auth.chain == "B"]
+    assert len(residues_a) == len(expected_sequence)
+    assert len(residues_b) == len(expected_sequence)
+
+    actual_sequence_a = "".join([residue.one_letter_name for residue in residues_a])
+    actual_sequence_b = "".join([residue.one_letter_name for residue in residues_b])
+    assert actual_sequence_a == expected_sequence
+    assert actual_sequence_b == expected_sequence

rnapolis-0.4.14/src/rnapolis/molecule_filter.py

@@ -1,280 +0,0 @@
-#! /usr/bin/env python
-import argparse
-import tempfile
-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
-ENTITY_POLY_TYPES = [
-    "cyclic-pseudo-peptide",
-    "other",
-    "peptide nucleic acid",
-    "polydeoxyribonucleotide",
-    "polydeoxyribonucleotide/polyribonucleotide hybrid",
-    "polypeptide(D)",
-    "polypeptide(L)",
-    "polyribonucleotide",
-]
-
-CATEGORIES_WITH_ENTITY_ID = [
-    ("entity", "id"),
-    ("atom_site", "label_entity_id"),
-    ("entity_keywords", "entity_id"),
-    ("entity_name_com", "entity_id"),
-    ("entity_name_sys", "entity_id"),
-    ("entity_poly", "entity_id"),
-    ("entity_src_gen", "entity_id"),
-    ("entity_src_nat", "entity_id"),
-    ("pdbx_branch_scheme", "entity_id"),
-    ("pdbx_chain_remapping", "entity_id"),
-    ("pdbx_construct", "entity_id"),
-    ("pdbx_entity_assembly", "entity_id"),
-    ("pdbx_entity_branch", "entity_id"),
-    ("pdbx_entity_branch_descriptor", "entity_id"),
-    ("pdbx_entity_branch_list", "entity_id"),
-    ("pdbx_entity_func_bind_mode", "entity_id"),
-    ("pdbx_entity_name", "entity_id"),
-    ("pdbx_entity_nonpoly", "entity_id"),
-    ("pdbx_entity_poly_domain", "entity_id"),
-    ("pdbx_entity_poly_na_nonstandard", "entity_id"),
-    ("pdbx_entity_poly_na_type", "entity_id"),
-    ("pdbx_entity_poly_protein_class", "entity_id"),
-    ("pdbx_entity_prod_protocol", "entity_id"),
-    ("pdbx_entity_remapping", "entity_id"),
-    ("pdbx_entity_src_gen_character", "entity_id"),
-    ("pdbx_entity_src_gen_chrom", "entity_id"),
-    ("pdbx_entity_src_gen_clone", "entity_id"),
-    ("pdbx_entity_src_gen_express", "entity_id"),
-    ("pdbx_entity_src_gen_fract", "entity_id"),
-    ("pdbx_entity_src_gen_lysis", "entity_id"),
-    ("pdbx_entity_src_gen_prod_digest", "entity_id"),
-    ("pdbx_entity_src_gen_prod_other", "entity_id"),
-    ("pdbx_entity_src_gen_prod_pcr", "entity_id"),
-    ("pdbx_entity_src_gen_proteolysis", "entity_id"),
-    ("pdbx_entity_src_gen_pure", "entity_id"),
-    ("pdbx_entity_src_gen_refold", "entity_id"),
-    ("pdbx_entity_src_syn", "entity_id"),
-    ("pdbx_linked_entity_list", "entity_id"),
-    ("pdbx_prerelease_seq", "entity_id"),
-    ("pdbx_sifts_xref_db", "entity_id"),
-    ("pdbx_sifts_xref_db_segments", "entity_id"),
-    ("pdbx_struct_entity_inst", "entity_id"),
-    ("struct_asym", "entity_id"),
-    ("struct_ref", "entity_id"),
-]
-
-CATEGORIES_WITH_ASYM_ID = [
-    ("pdbx_coordinate_model", "asym_id"),
-    ("pdbx_distant_solvent_atoms", "label_asym_id"),
-    ("pdbx_linked_entity_instance_list", "asym_id"),
-    ("pdbx_poly_seq_scheme", "asym_id"),
-    ("pdbx_sifts_unp_segments", "asym_id"),
-    ("pdbx_struct_asym_gen", "asym_id"),
-    ("pdbx_struct_ncs_virus_gen", "asym_id"),
-    ("pdbx_struct_special_symmetry", "label_asym_id"),
-    ("pdbx_unobs_or_zero_occ_atoms", "label_asym_id"),
-    ("pdbx_unobs_or_zero_occ_residues", "label_asym_id"),
-    ("refine_ls_restr_ncs", "pdbx_asym_id"),
-    ("struct_biol_gen", "asym_id"),
-]
-
-CATEGORIES_WITH_AUTH_ASYM_ID = [
-    ("atom_site_anisotrop", "pdbx_auth_asym_id"),
-    ("pdbx_atom_site_aniso_tls", "auth_asym_id"),
-    ("pdbx_entity_instance_feature", "auth_asym_id"),
-    ("pdbx_feature_monomer", "auth_asym_id"),
-    ("pdbx_missing_atom_nonpoly", "auth_asym_id"),
-    ("pdbx_missing_atom_poly", "auth_asym_id"),
-    ("pdbx_modification_feature", "auth_asym_id"),
-    ("pdbx_refine_component", "auth_asym_id"),
-    ("pdbx_remediation_atom_site_mapping", "auth_asym_id"),
-    ("pdbx_rmch_outlier", "auth_asym_id"),
-    ("pdbx_rms_devs_cov_by_monomer", "auth_asym_id"),
-    ("pdbx_sequence_pattern", "auth_asym_id"),
-    ("pdbx_solvent_atom_site_mapping", "auth_asym_id"),
-    ("pdbx_stereochemistry", "auth_asym_id"),
-    ("pdbx_struct_chem_comp_diagnostics", "pdb_strand_id"),
-    ("pdbx_struct_chem_comp_feature", "pdb_strand_id"),
-    ("pdbx_struct_group_components", "auth_asym_id"),
-    ("pdbx_struct_mod_residue", "auth_asym_id"),
-    ("pdbx_sugar_phosphate_geometry", "auth_asym_id"),
-    ("pdbx_validate_chiral", "auth_asym_id"),
-    ("pdbx_validate_main_chain_plane", "auth_asym_id"),
-    ("pdbx_validate_planes", "auth_asym_id"),
-    ("pdbx_validate_planes_atom", "auth_asym_id"),
-    ("pdbx_validate_torsion", "auth_asym_id"),
-    ("struct_mon_nucl", "auth_asym_id"),
-    ("struct_mon_prot", "auth_asym_id"),
-    ("struct_site_gen", "auth_asym_id"),
-]
-
-
-def select_ids(
-    data: List[DataContainer],
-    obj_name: str,
-    tested_field_name: str,
-    extracted_field_name: str,
-    accepted_values: Set[str],
-) -> Set[str]:
-    obj = data[0].getObj(obj_name)
-    ids = set()
-
-    if obj:
-        for row in obj.getRowList():
-            row_dict = dict(zip(obj.getAttributeList(), row))
-
-            if row_dict.get(tested_field_name, None) in accepted_values:
-                ids.add(row_dict[extracted_field_name])
-
-    return ids
-
-
-def select_category_by_id(
-    data: List[DataContainer],
-    category: str,
-    field_name: str,
-    ids: List[str],
-) -> Tuple[List[str], List[List[str]]]:
-    obj = data[0].getObj(category)
-    attributes = []
-    rows = []
-
-    if obj:
-        attributes = obj.getAttributeList()
-
-        for row in obj.getRowList():
-            row_dict = dict(zip(obj.getAttributeList(), row))
-
-            if row_dict.get(field_name, None) in ids:
-                rows.append(row)
-
-    return attributes, rows
-
-
-def filter_by_poly_types(
-    file_content: str,
-    entity_poly_types: Iterable[str] = ["polyribonucleotide"],
-    retain_categories: Iterable[str] = [],
-) -> 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)
-    )
-    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
-    )
-
-    output = DataContainer("rnapolis")
-
-    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)
-
-    for category in retain_categories:
-        obj = data[0].getObj(category)
-        if obj:
-            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], retain_categories: 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
-    )
-
-    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)
-
-    for category in retain_categories:
-        obj = data[0].getObj(category)
-        if obj:
-            output.append(obj)
-
-    with tempfile.NamedTemporaryFile("rt+") as tmp:
-        adapter.writeFile(tmp.name, [output])
-        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__":
-    main()