Coverage for biobb_pdb_tools/pdb_tools/biobb_pdb_splitmodel.py: 74%
62 statements
« prev ^ index » next coverage.py v7.9.1, created at 2025-06-20 08:28 +0000
1#!/usr/bin/env python3
3"""Module containing the Pdbsplitmodel class and the command line interface."""
5import argparse
6import glob
7import os
8import zipfile
9from pathlib import Path
10from typing import Optional
12from biobb_common.configuration import settings
13from biobb_common.generic.biobb_object import BiobbObject
14from biobb_common.tools import file_utils as fu
15from biobb_common.tools.file_utils import launchlogger
18class Pdbsplitmodel(BiobbObject):
19 """
20 | biobb_pdb_tools Pdbsplitmodel
21 | Splits a PDB file into several, each containing one MODEL.
22 | This tool splits a PDB file into several, each containing one MODEL. It can be used to split a PDB file into several, each containing one MODEL.
24 Args:
25 input_file_path (str): PDB file. File type: input. `Sample file <https://raw.githubusercontent.com/bioexcel/biobb_pdb_tools/master/biobb_pdb_tools/test/data/pdb_tools/input_pdb_splitmodel.pdb>`_. Accepted formats: pdb (edam:format_1476).
26 output_file_path (str): ZIP file containing all PDB files splited by protein model. File type: output. `Sample file <https://github.com/bioexcel/biobb_pdb_tools/blob/master/biobb_pdb_tools/test/reference/pdb_tools/ref_pdb_splitmodel.zip>`_. Accepted formats: zip (edam:format_3987).
27 properties (dic):
28 * **binary_path** (*str*) - ("pdb_splitmodel") Path to the pdb_splitmodel executable binary.
29 * **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files.
30 * **restart** (*bool*) - (False) [WF property] Do not execute if output files exist.
32 Examples:
33 This is a use example of how to use the building block from Python::
35 from biobb_pdb_tools.pdb_tools.biobb_pdb_splitmodel import biobb_pdb_splitmodel
37 biobb_pdb_splitmodel(input_file_path='/path/to/input.pdb',
38 output_file_path='/path/to/output.zip)
40 Info:
41 * wrapped_software:
42 * name: pdb_tools
43 * version: >=2.5.0
44 * license: Apache-2.0
45 * ontology:
46 * name: EDAM
47 * schema: http://edamontology.org/EDAM.owl
49 """
51 def __init__(
52 self, input_file_path, output_file_path, properties=None, **kwargs
53 ) -> None:
54 properties = properties or {}
56 super().__init__(properties)
57 self.locals_var_dict = locals().copy()
58 self.io_dict = {
59 "in": {"input_file_path": input_file_path},
60 "out": {"output_file_path": output_file_path},
61 }
63 self.binary_path = properties.get("binary_path", "pdb_splitmodel")
64 self.properties = properties
66 self.check_properties(properties)
67 self.check_arguments()
69 @launchlogger
70 def launch(self) -> int:
71 """Execute the :class:`Pdbsplitmodel <biobb_pdb_tools.pdb_tools.pdb_splitmodel>` object."""
73 if self.check_restart():
74 return 0
75 self.stage_files()
77 self.cmd = [
78 "cd",
79 self.stage_io_dict.get("unique_dir", ""),
80 ";",
81 self.binary_path,
82 self.stage_io_dict["in"]["input_file_path"],
83 ]
85 fu.log(" ".join(self.cmd), self.out_log, self.global_log)
87 fu.log(
88 "Creating command line with instructions and required arguments",
89 self.out_log,
90 self.global_log,
91 )
92 self.run_biobb()
94 stem = Path(self.stage_io_dict["in"]["input_file_path"]).stem
95 pdb_files = glob.glob(
96 os.path.join(self.stage_io_dict.get(
97 "unique_dir", ""), stem + "_*.pdb")
98 )
100 if len(pdb_files) > 1:
101 output_zip_path = os.path.join(
102 self.stage_io_dict.get("unique_dir", ""),
103 self.stage_io_dict["out"]["output_file_path"],
104 )
105 fu.log(
106 "Saving %d pdb model files in a zip" % len(pdb_files),
107 self.out_log,
108 self.global_log,
109 )
110 with zipfile.ZipFile(output_zip_path, "w") as zipf:
111 for pdb_file in pdb_files:
112 zipf.write(pdb_file, os.path.basename(pdb_file))
113 else:
114 fu.log("The given input file has no models.",
115 self.out_log, self.global_log)
116 output_zip_path = os.path.join(
117 self.stage_io_dict.get("unique_dir", ""),
118 self.stage_io_dict["out"]["output_file_path"],
119 )
120 with zipfile.ZipFile(output_zip_path, "w") as zipf:
121 zipf.write(
122 self.stage_io_dict["in"]["input_file_path"],
123 os.path.basename(
124 self.stage_io_dict["in"]["input_file_path"]),
125 )
126 pass
128 self.copy_to_host()
129 self.tmp_files.extend([self.stage_io_dict.get("unique_dir", "")])
130 self.remove_tmp_files()
131 self.check_arguments(output_files_created=True, raise_exception=False)
133 return self.return_code
136def biobb_pdb_splitmodel(
137 input_file_path: str,
138 output_file_path: str,
139 properties: Optional[dict] = None,
140 **kwargs,
141) -> int:
142 """Create :class:`Pdbsplitmodel <biobb_pdb_tools.pdb_tools.pdb_splitmodel>` class and
143 execute the :meth:`launch() <biobb_pdb_tools.pdb_tools.pdb_splitmodel.launch>` method."""
145 return Pdbsplitmodel(
146 input_file_path=input_file_path,
147 output_file_path=output_file_path,
148 properties=properties,
149 **kwargs,
150 ).launch()
153biobb_pdb_splitmodel.__doc__ = Pdbsplitmodel.__doc__
156def main():
157 """Command line execution of this building block. Please check the command line documentation."""
158 parser = argparse.ArgumentParser(
159 description="Splits a PDB file into several, each containing one MODEL.",
160 formatter_class=lambda prog: argparse.RawTextHelpFormatter(
161 prog, width=99999),
162 )
163 parser.add_argument("--config", required=True, help="Configuration file")
165 required_args = parser.add_argument_group("required arguments")
166 required_args.add_argument(
167 "--input_file_path",
168 required=True,
169 help="Description for the first input file path. Accepted formats: pdb.",
170 )
171 required_args.add_argument(
172 "--output_file_path",
173 required=True,
174 help="Description for the output file path. Accepted formats: zip.",
175 )
177 args = parser.parse_args()
178 args.config = args.config or "{}"
179 properties = settings.ConfReader(config=args.config).get_prop_dic()
181 biobb_pdb_splitmodel(
182 input_file_path=args.input_file_path,
183 output_file_path=args.output_file_path,
184 properties=properties,
185 )
188if __name__ == "__main__":
189 main()