Coverage for biobb_pdb_tools/pdb_tools/biobb_pdb_mkensemble.py: 80%
59 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 Mkensemble class and the command line interface."""
5import argparse
6import os
7import zipfile
8from pathlib import Path
9from typing import Optional
11from biobb_common.configuration import settings
12from biobb_common.generic.biobb_object import BiobbObject
13from biobb_common.tools import file_utils as fu
14from biobb_common.tools.file_utils import launchlogger
17class Mkensemble(BiobbObject):
18 """
19 | biobb_pdb_tools Mkensemble
20 | Merges several PDB files into one multi-model (ensemble) file.
21 | This tool merges several PDB files into one multi-model (ensemble) file. It can be used to merge several PDB files into one multi-model (ensemble) file.
23 Args:
24 input_file_path (str): ZIP file of selected proteins. File type: input. `Sample file <https://raw.githubusercontent.com/bioexcel/biobb_pdb_tools/master/biobb_pdb_tools/test/data/pdb_tools/input_pdb_mkensemble.pdb>`_. Accepted formats: zip (edam:format_3987).
25 output_file_path (str): Multi-model (ensemble) PDB file with input PDBs merged. File type: output. `Sample file <https://raw.githubusercontent.com/bioexcel/biobb_pdb_tools/master/biobb_pdb_tools/test/reference/pdb_tools/ref_pdb_mkensemble.pdb>`_. Accepted formats: pdb (edam:format_3987).
26 properties (dic):
27 * **binary_path** (*str*) - ("pdb_mkensemble") Path to the pdb_mkensemble executable binary.
28 * **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files.
29 * **restart** (*bool*) - (False) [WF property] Do not execute if output files exist.
31 Examples:
32 This is a use example of how to use the building block from Python::
34 from biobb_pdb_tools.pdb_tools.biobb_pdb_mkensemble import biobb_pdb_mkensemble
36 biobb_pdb_mkensemble(input_file_path='/path/to/input1.zip',
37 output_file_path='/path/to/output.pdb')
39 Info:
40 * wrapped_software:
41 * name: pdb_tools
42 * version: >=2.5.0
43 * license: Apache-2.0
44 * ontology:
45 * name: EDAM
46 * schema: http://edamontology.org/EDAM.owl
48 """
50 def __init__(
51 self, input_file_path, output_file_path, properties=None, **kwargs
52 ) -> None:
53 properties = properties or {}
55 super().__init__(properties)
56 self.locals_var_dict = locals().copy()
57 self.io_dict = {
58 "in": {"input_file_path": input_file_path},
59 "out": {"output_file_path": output_file_path},
60 }
62 self.binary_path = properties.get("binary_path", "pdb_mkensemble")
63 self.properties = properties
65 self.check_properties(properties)
66 self.check_arguments()
68 @launchlogger
69 def launch(self) -> int:
70 """Execute the :class:`Mkensemble <biobb_pdb_tools.pdb_tools.pdb_mkensemble>` object."""
72 if self.check_restart():
73 return 0
74 self.stage_files()
76 input_file_path = self.stage_io_dict["in"]["input_file_path"]
77 folder_path = os.path.dirname(input_file_path)
79 if zipfile.is_zipfile(input_file_path):
80 with zipfile.ZipFile(input_file_path, "r") as zip_ref:
81 zip_ref.extractall(folder_path)
83 pdb_files = [
84 file
85 for file in os.listdir(folder_path)
86 if file.lower().endswith(".pdb")
87 ]
89 input_file_list = [os.path.join(
90 folder_path, file) for file in pdb_files]
92 input_file_list = [Path(i) for i in input_file_list]
93 input_file_list = sorted(
94 input_file_list, key=lambda i: i.stem.upper())
95 input_file_list = [str(i) for i in input_file_list]
97 self.cmd = [
98 self.binary_path,
99 *input_file_list,
100 ">",
101 self.io_dict["out"]["output_file_path"],
102 ]
104 else:
105 fu.log(
106 f"The archive {input_file_path} is not a ZIP!",
107 self.out_log,
108 self.global_log,
109 )
111 fu.log(" ".join(self.cmd), self.out_log, self.global_log)
113 fu.log(
114 "Creating command line with instructions and required arguments",
115 self.out_log,
116 self.global_log,
117 )
119 self.run_biobb()
120 self.copy_to_host()
122 self.tmp_files.extend([self.stage_io_dict.get("unique_dir", "")])
123 self.remove_tmp_files()
124 self.check_arguments(output_files_created=True, raise_exception=False)
126 return self.return_code
129def biobb_pdb_mkensemble(
130 input_file_path: str,
131 output_file_path: str,
132 properties: Optional[dict] = None,
133 **kwargs,
134) -> int:
135 """Create :class:`Mkensemble <biobb_pdb_tools.pdb_tools.pdb_mkensemble>` class and
136 execute the :meth:`launch() <biobb_pdb_tools.pdb_tools.pdb_mkensemble.launch>` method."""
137 return Mkensemble(
138 input_file_path=input_file_path,
139 output_file_path=output_file_path,
140 properties=properties,
141 **kwargs,
142 ).launch()
145biobb_pdb_mkensemble.__doc__ = Mkensemble.__doc__
148def main():
149 """Command line execution of this building block. Please check the command line documentation."""
150 parser = argparse.ArgumentParser(
151 description="Merges several PDB files into one multi-model (ensemble) file.",
152 formatter_class=lambda prog: argparse.RawTextHelpFormatter(
153 prog, width=99999),
154 )
155 parser.add_argument("--config", required=True, help="Configuration file")
156 required_args = parser.add_argument_group("required arguments")
157 required_args.add_argument(
158 "--input_file_path",
159 required=True,
160 help="Description for the first input file path. Accepted formats: pdb.",
161 )
162 required_args.add_argument(
163 "--output_file_path",
164 required=True,
165 help="Description for the output file path. Accepted formats: zip.",
166 )
168 args = parser.parse_args()
169 args.config = args.config or "{}"
170 properties = settings.ConfReader(config=args.config).get_prop_dic()
172 biobb_pdb_mkensemble(
173 input_file_path=args.input_file_path,
174 output_file_path=args.output_file_path,
175 properties=properties,
176 )
179if __name__ == "__main__":
180 main()