RNApolis 0.3.15__tar.gz → 0.3.17__tar.gz

{rnapolis-0.3.15/src/RNApolis.egg-info → rnapolis-0.3.17}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: RNApolis
-Version: 0.3.15
+Version: 0.3.17
 Summary: A Python library containing RNA-related bioinformatics functions and classes
 Home-page: https://github.com/tzok/rnapolis-py
 Author: Tomasz Zok

{rnapolis-0.3.15 → rnapolis-0.3.17}/setup.py

@@ -5,7 +5,7 @@ with open("README.md") as f:
 
 setup(
     name="RNApolis",
-    version="0.3.15",
+    version="0.3.17",
     packages=["rnapolis"],
     package_dir={"": "src"},
     author="Tomasz Zok",

{rnapolis-0.3.15 → rnapolis-0.3.17/src/RNApolis.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: RNApolis
-Version: 0.3.15
+Version: 0.3.17
 Summary: A Python library containing RNA-related bioinformatics functions and classes
 Home-page: https://github.com/tzok/rnapolis-py
 Author: Tomasz Zok

{rnapolis-0.3.15 → rnapolis-0.3.17}/src/rnapolis/metareader.py

@@ -3,6 +3,7 @@ import argparse
 from typing import IO, Dict, List
 
 import orjson
+import pandas as pd
 from mmcif.io.IoAdapterPy import IoAdapterPy
 from mmcif.io.PdbxReader import DataContainer
 
@@ -46,6 +47,10 @@ def main():
         help="read the mmCIF file and list categories available inside",
         action="store_true",
     )
+    parser.add_argument(
+        "--csv-directory",
+        help="directory where to output CSV per each category",
+    )
     args = parser.parse_args()
 
     file = handle_input_file(args.path)
@@ -57,6 +62,12 @@ def main():
         result = read_metadata(file, args.category)
         print(orjson.dumps(result).decode("utf-8"))
 
+        if args.csv_directory:
+            for category in result:
+                with open(f"{args.csv_directory}/{category}.csv", "w") as f:
+                    df = pd.DataFrame(result[category])
+                    df.to_csv(f, index=False)
+
 
 if __name__ == "__main__":
     main()

{rnapolis-0.3.15 → rnapolis-0.3.17}/src/rnapolis/parser.py

@@ -1,3 +1,4 @@
+import logging
 from typing import IO, Dict, List, Optional, Tuple, Union
 
 from mmcif.io.IoAdapterPy import IoAdapterPy
@@ -5,6 +6,9 @@ from mmcif.io.IoAdapterPy import IoAdapterPy
 from rnapolis.common import ResidueAuth, ResidueLabel
 from rnapolis.tertiary import BASE_ATOMS, Atom, Residue3D, Structure3D
 
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
 
 def read_3d_structure(
     cif_or_pdb: IO[str], model: Optional[int] = None, nucleic_acid_only: bool = False
@@ -104,6 +108,14 @@ def parse_cif(
                         auth_residue_name,
                     )
 
+                if label is None and auth is None:
+                    # this should not happen in a valid mmCIF file
+                    # skipping the line
+                    logger.debug(
+                        f"Cannot parse an atom line without chain name, residue number, and residue name: {row}"
+                    )
+                    continue
+
                 model = int(row_dict.get("pdbx_PDB_model_num", "1"))
                 atom_name = row_dict["label_atom_id"]
                 x = float(row_dict["Cartn_x"])
@@ -200,7 +212,7 @@ def parse_pdb(
             if alternate_location != " ":
                 continue
             atom_name = line[12:16].strip()
-            residue_name = line[18:20].strip()
+            residue_name = line[17:20].strip()
             chain_identifier = line[21]
             residue_number = int(line[22:26].strip())
             insertion_code = line[26] if line[26] != " " else None

{rnapolis-0.3.15 → rnapolis-0.3.17}/tests/test_annotator.py

@@ -1,6 +1,6 @@
 from collections import Counter
 
-from rnapolis.annotator import extract_base_interactions
+from rnapolis.annotator import extract_base_interactions, extract_secondary_structure
 from rnapolis.parser import read_3d_structure
 
 
@@ -39,3 +39,9 @@ def test_1ehz():
                 assert (
                     False
                 ), f"Interaction {element} occurs {count} times among {labels[i]} type: {duplicates}"
+
+
+def test_8btk():
+    with open("tests/8btk_B7.cif") as f:
+        structure3d = read_3d_structure(f, 1)
+    assert extract_secondary_structure(structure3d, 1) is not None

{rnapolis-0.3.15 → rnapolis-0.3.17}/tests/test_parser.py

@@ -9,3 +9,10 @@ def test_nucleic_acid_only():
     with open("tests/184D.cif") as f:
         structure3d = read_3d_structure(f, 1, nucleic_acid_only=True)
     assert len(structure3d.residues) == 14
+
+
+def test_1ato():
+    with open("tests/1ATO.pdb") as f:
+        structure3d = read_3d_structure(f)
+    sequence = "".join([residue.one_letter_name for residue in structure3d.residues])
+    assert sequence == "GGCACCUCCUCGCGGUGCC"