Coverage for biobb_pdb_tools/pdb_tools/biobb_pdb_splitseg.py: 74%
62 statements
« prev ^ index » next coverage.py v7.8.0, created at 2025-05-06 12:37 +0000
1#!/usr/bin/env python3
3"""Module containing the Pdbsplitseg 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 Pdbsplitseg(BiobbObject):
19 """
20 | biobb_pdb_tools Pdbsplitseg
21 | Splits a PDB file into several, each containing one segment.
22 | This tool splits a PDB file into several, each containing one segment. It can be used to split a PDB file into several, each containing one segment.
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_splitseg.pdb>`_. Accepted formats: pdb (edam:format_1476).
26 output_file_path (str): ZIP file containing all PDB files splited by protein segment. File type: output. `Sample file <https://github.com/bioexcel/biobb_pdb_tools/blob/master/biobb_pdb_tools/test/reference/pdb_tools/ref_pdb_splitseg.zip>`_. Accepted formats: zip (edam:format_3987).
27 properties (dic):
28 * **binary_path** (*str*) - ("pdb_splitseg") Path to the pdb_splitseg 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_splitseg import biobb_pdb_splitseg
37 biobb_pdb_splitseg(input_file_path='/path/to/input.pdb',
38 output_file_path='/path/to/output.pdb')
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()
59 self.io_dict = {
60 "in": {"input_file_path": input_file_path},
61 "out": {"output_file_path": output_file_path},
62 }
64 self.binary_path = properties.get("binary_path", "pdb_splitseg")
65 self.properties = properties
67 self.check_properties(properties)
68 self.check_arguments()
70 @launchlogger
71 def launch(self) -> int:
72 """Execute the :class:`Pdbsplitseg <biobb_pdb_tools.pdb_tools.pdb_splitseg>` object."""
74 if self.check_restart():
75 return 0
76 self.stage_files()
78 self.cmd = [
79 "cd",
80 self.stage_io_dict.get("unique_dir", ""),
81 ";",
82 self.binary_path,
83 self.stage_io_dict["in"]["input_file_path"],
84 ]
86 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("unique_dir", ""), stem + "_*.pdb")
97 )
99 if len(pdb_files) > 1:
100 output_zip_path = os.path.join(
101 self.stage_io_dict.get("unique_dir", ""),
102 self.stage_io_dict["out"]["output_file_path"],
103 )
104 fu.log(
105 "Saving %d pdb segment files in a zip" % len(pdb_files),
106 self.out_log,
107 self.global_log,
108 )
109 with zipfile.ZipFile(output_zip_path, "w") as zipf:
110 for pdb_file in pdb_files:
111 zipf.write(pdb_file, os.path.basename(pdb_file))
112 else:
113 fu.log(
114 "The given input file has no segments. Saving the input file into a zip.",
115 self.out_log,
116 self.global_log,
117 )
118 output_zip_path = os.path.join(
119 self.stage_io_dict.get("unique_dir", ""),
120 self.stage_io_dict["out"]["output_file_path"],
121 )
122 with zipfile.ZipFile(output_zip_path, "w") as zipf:
123 zipf.write(
124 self.stage_io_dict["in"]["input_file_path"],
125 os.path.basename(self.stage_io_dict["in"]["input_file_path"]),
126 )
127 pass
129 self.copy_to_host()
130 self.tmp_files.extend([self.stage_io_dict.get("unique_dir", "")])
131 self.remove_tmp_files()
132 self.check_arguments(output_files_created=True, raise_exception=False)
134 return self.return_code
137def biobb_pdb_splitseg(
138 input_file_path: str,
139 output_file_path: str,
140 properties: Optional[dict] = None,
141 **kwargs,
142) -> int:
143 """Create :class:`Pdbsplitseg <biobb_pdb_tools.pdb_tools.pdb_splitseg>` class and
144 execute the :meth:`launch() <biobb_pdb_tools.pdb_tools.pdb_splitseg.launch>` method."""
146 return Pdbsplitseg(
147 input_file_path=input_file_path,
148 output_file_path=output_file_path,
149 properties=properties,
150 **kwargs,
151 ).launch()
153biobb_pdb_splitseg.__doc__ = Pdbsplitseg.__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 segment.",
160 formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999),
161 )
162 parser.add_argument("--config", required=True, help="Configuration file")
164 required_args = parser.add_argument_group("required arguments")
165 required_args.add_argument(
166 "--input_file_path",
167 required=True,
168 help="Description for the input file path. Accepted formats: pdb.",
169 )
170 required_args.add_argument(
171 "--output_file_path",
172 required=True,
173 help="Description for the output file path. Accepted formats: zip.",
174 )
176 args = parser.parse_args()
177 args.config = args.config or "{}"
178 properties = settings.ConfReader(config=args.config).get_prop_dic()
180 biobb_pdb_splitseg(
181 input_file_path=args.input_file_path,
182 output_file_path=args.output_file_path,
183 properties=properties,
184 )
187if __name__ == "__main__":
188 main()