RNApolis 0.7.0__py3-none-any.whl → 0.8.1__py3-none-any.whl

rnapolis/splitter.py

@@ -0,0 +1,128 @@
+#!/usr/bin/env python3
+import argparse
+import os
+import sys
+
+from rnapolis.parser import is_cif
+from rnapolis.parser_v2 import (
+    fit_to_pdb,
+    parse_cif_atoms,
+    parse_pdb_atoms,
+    write_cif,
+    write_pdb,
+)
+
+
+def main():
+    """Main function to run the splitter tool."""
+    parser = argparse.ArgumentParser(
+        description="Split a multi-model PDB or mmCIF file into separate files per model."
+    )
+    parser.add_argument("--output", "-o", help="Output directory", required=True)
+    parser.add_argument(
+        "--format",
+        "-f",
+        help="Output format (possible values: PDB, mmCIF, keep. Default: keep)",
+        default="keep",
+    )
+    parser.add_argument("file", help="Input PDB or mmCIF file to split")
+    args = parser.parse_args()
+
+    # Check if input file exists
+    if not os.path.exists(args.file):
+        print(f"Error: Input file not found: {args.file}", file=sys.stderr)
+        sys.exit(1)
+
+    # Read and parse the input file
+    input_format = "mmCIF"
+    try:
+        with open(args.file) as f:
+            if is_cif(f):
+                atoms_df = parse_cif_atoms(f)
+                model_column = "pdbx_PDB_model_num"
+            else:
+                atoms_df = parse_pdb_atoms(f)
+                input_format = "PDB"
+                model_column = "model"
+    except Exception as e:
+        print(f"Error parsing file {args.file}: {e}", file=sys.stderr)
+        sys.exit(1)
+
+    if atoms_df.empty:
+        print(f"Warning: No atoms found in {args.file}", file=sys.stderr)
+        sys.exit(0)
+
+    # Check if model column exists
+    if model_column not in atoms_df.columns:
+        print(
+            f"Error: Model column '{model_column}' not found in the parsed data from {args.file}.",
+            file=sys.stderr,
+        )
+        print(
+            "This might indicate an issue with the input file or the parser.",
+            file=sys.stderr,
+        )
+        sys.exit(1)
+
+    # Determine output format
+    output_format = args.format.upper()
+    if output_format == "KEEP":
+        output_format = input_format
+    elif output_format not in ["PDB", "MMCIF"]:
+        print(
+            f"Error: Invalid output format '{args.format}'. Choose PDB, mmCIF, or keep.",
+            file=sys.stderr,
+        )
+        sys.exit(1)
+
+    # Ensure output directory exists
+    os.makedirs(args.output, exist_ok=True)
+
+    # Group by model number
+    grouped_by_model = atoms_df.groupby(model_column)
+
+    # Get base name for output files
+    base_name = os.path.splitext(os.path.basename(args.file))[0]
+
+    # Write each model to a separate file
+    for model_num, model_df in grouped_by_model:
+        # Ensure model_df is a DataFrame copy to avoid SettingWithCopyWarning
+        model_df = model_df.copy()
+
+        # Set the correct format attribute for the writer function
+        model_df.attrs["format"] = input_format
+
+        # Construct output filename
+        ext = ".pdb" if output_format == "PDB" else ".cif"
+        output_filename = f"{base_name}_model_{model_num}{ext}"
+        output_path = os.path.join(args.output, output_filename)
+
+        print(f"Writing model {model_num} to {output_path}...")
+
+        try:
+            if output_format == "PDB":
+                df_to_write = fit_to_pdb(model_df)
+                write_pdb(df_to_write, output_path)
+            else:  # mmCIF
+                write_cif(model_df, output_path)
+        except ValueError as e:
+            # Handle errors specifically from fit_to_pdb
+            print(
+                f"Error fitting model {model_num} from {args.file} to PDB: {e}. Skipping model.",
+                file=sys.stderr,
+            )
+            continue
+        except Exception as e:
+            # Handle general writing errors
+            print(
+                f"Error writing file {output_path} for model {model_num}: {e}",
+                file=sys.stderr,
+            )
+            # Optionally continue to next model or exit
+            # sys.exit(1)
+
+    print("Splitting complete.")
+
+
+if __name__ == "__main__":
+    main()

rnapolis/unifier.py

@@ -7,7 +7,13 @@ from collections import Counter
 import pandas as pd
 
 from rnapolis.parser import is_cif
-from rnapolis.parser_v2 import parse_cif_atoms, parse_pdb_atoms, write_cif, write_pdb
+from rnapolis.parser_v2 import (
+    fit_to_pdb,
+    parse_cif_atoms,
+    parse_pdb_atoms,
+    write_cif,
+    write_pdb,
+)
 from rnapolis.tertiary_v2 import Structure
 
 
@@ -140,13 +146,22 @@ def main():
 
         ext = ".pdb" if format == "PDB" else ".cif"
 
-        with open(f"{args.output}/{base}{ext}", "w") as f:
-            df = pd.concat([residue.atoms for residue in residues])
+        df = pd.concat([residue.atoms for residue in residues])
 
+        try:
             if format == "PDB":
-                write_pdb(df, f)
+                df_to_write = fit_to_pdb(df)
+                with open(f"{args.output}/{base}{ext}", "w") as f:
+                    write_pdb(df_to_write, f)
             else:
-                write_cif(df, f)
+                with open(f"{args.output}/{base}{ext}", "w") as f:
+                    write_cif(df, f)
+        except ValueError as e:
+            print(
+                f"Error processing {path} for PDB output: {e}. Skipping file.",
+                file=sys.stderr,
+            )
+            continue
 
 
 if __name__ == "__main__":

{rnapolis-0.7.0.dist-info → rnapolis-0.8.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: RNApolis
-Version: 0.7.0
+Version: 0.8.1
 Summary: A Python library containing RNA-related bioinformatics functions and classes
 Home-page: https://github.com/tzok/rnapolis-py
 Author: Tomasz Zok

{rnapolis-0.7.0.dist-info → rnapolis-0.8.1.dist-info}/RECORD

@@ -12,16 +12,17 @@ rnapolis/mmcif_pdbx_v50.dic,sha256=5QFx1ssDaehR4_DQ-tS9VQux262SiLXaqcwmwwejF5c,5
 rnapolis/molecule_filter.py,sha256=jgcpJxx_oXEBX0d30v4k_FdwRouRUPUsEtCYWgLGpD4,7310
 rnapolis/motif_extractor.py,sha256=Lfn1iEkhkP9eZD3GPEWNAfy00QO7QPCc8wM_XS1ory8,1147
 rnapolis/parser.py,sha256=3g4mtFvpiEENFcSBBtx_E_x1vJPF9BujWnts0kb9XjE,16340
-rnapolis/parser_v2.py,sha256=ltesVKBiIKk9JlM02ttTJzLm1g5MHdPzDgQTcl40GP8,16257
+rnapolis/parser_v2.py,sha256=qG6CO3or7zmuJu368g9Nzokiqdeip4yjD14F163uH6w,40618
 rnapolis/rfam_folder.py,sha256=SjiiyML_T1__saruFwSMJEoQ7Y55GIU8ktS8ZUn5-fw,11111
+rnapolis/splitter.py,sha256=x-Zn21mkiMgvYPptUFD9BbdNIvoaM6b8GzGf6uYXEwE,4052
 rnapolis/tertiary.py,sha256=6t9ZB4w33-5n_M3sns1RoFXCOTgVAgGH4WDNG5OG9Kg,23426
 rnapolis/tertiary_v2.py,sha256=I1uyHWIUePNGO5m-suoL4ibtz02qAJUMvYm0BUKUygY,22480
 rnapolis/transformer.py,sha256=aC0nBmHHJf5TyLvBIV57Jj3tlwpvHbPo347opfAOlQA,3844
-rnapolis/unifier.py,sha256=DR1_IllgaAYT9_FUE6XC9B-2wgqbBHs2D1MjyZT2j2g,5438
+rnapolis/unifier.py,sha256=2ge7IB9FdRgzSAiVD39U_ciwtdDJ2fGzf8mUIudbrqY,5820
 rnapolis/util.py,sha256=IdquFO3PV1_KDqodjupzm0Rqvgy0CeSzxGHaGEHYXVU,543
-rnapolis-0.7.0.dist-info/licenses/LICENSE,sha256=ZGRu12MzCgbYA-Lt8MyBlmjvPZh7xfiD5u5wBx0enq4,1066
-rnapolis-0.7.0.dist-info/METADATA,sha256=Rrnbq7pKHvcPKcHPp9nWjAZZ6x8PflF2WaJCTxaRgbo,54537
-rnapolis-0.7.0.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-rnapolis-0.7.0.dist-info/entry_points.txt,sha256=D630mec6slaw_QMmzDNeBIy7p0pTtuOGnu8xTjmx8VA,404
-rnapolis-0.7.0.dist-info/top_level.txt,sha256=LcO18koxZcWoJ21KDRRRo_tyIbmXL5z61dPitZpy8yc,9
-rnapolis-0.7.0.dist-info/RECORD,,
+rnapolis-0.8.1.dist-info/licenses/LICENSE,sha256=ZGRu12MzCgbYA-Lt8MyBlmjvPZh7xfiD5u5wBx0enq4,1066
+rnapolis-0.8.1.dist-info/METADATA,sha256=NOg9-s2n313HElku8z06JiBvEhPf6oV9RR7ur20hwys,54537
+rnapolis-0.8.1.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+rnapolis-0.8.1.dist-info/entry_points.txt,sha256=H00KoN54wU3dFOofAu3H_3PADmZOBTB1hXf5TUU2uzo,438
+rnapolis-0.8.1.dist-info/top_level.txt,sha256=LcO18koxZcWoJ21KDRRRo_tyIbmXL5z61dPitZpy8yc,9
+rnapolis-0.8.1.dist-info/RECORD,,

{rnapolis-0.7.0.dist-info → rnapolis-0.8.1.dist-info}/entry_points.txt

@@ -7,5 +7,6 @@ metareader = rnapolis.metareader:main
 molecule-filter = rnapolis.molecule_filter:main
 motif-extractor = rnapolis.motif_extractor:main
 rfam-folder = rnapolis.rfam_folder:main
+splitter = rnapolis.splitter:main
 transformer = rnapolis.transformer:main
 unifier = rnapolis.unifier:main