Coverage for biobb_pdb_tools/pdb_tools/biobb_pdb_merge.py: 80%
59 statements
« prev ^ index » next coverage.py v7.9.1, created at 2025-06-20 08:28 +0000
« 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 Pdbmerge 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 Pdbmerge(BiobbObject):
18 """
19 | biobb_pdb_tools Pdbmerge
20 | Merges several PDB files into one.
21 | This tool merges several PDB files into one. It can be used to merge several PDB files into one.
23 Args:
24 input_file_path (str): ZIP file of selected protein. File type: input. `Sample file <https://raw.githubusercontent.com/bioexcel/biobb_pdb_tools/master/biobb_pdb_tools/test/data/pdb_tools/input_pdb_merge.pdb>`_. Accepted formats: zip (edam:format_3987).
25 output_file_path (str): 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_merge.pdb>`_. Accepted formats: pdb (edam:format_1476).
26 properties (dic):
27 * **binary_path** (*str*) - ("pdb_merge") Path to the pdb_merge 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_merge import biobb_pdb_merge
36 biobb_pdb_merge(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()
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_merge")
64 self.properties = properties
66 self.check_properties(properties)
67 self.check_arguments()
69 @launchlogger
70 def launch(self) -> int:
71 """Execute the :class:`Pdbmerge <biobb_pdb_tools.pdb_tools.pdb_merge>` object."""
73 if self.check_restart():
74 return 0
75 self.stage_files()
77 input_file_path = self.stage_io_dict["in"]["input_file_path"]
78 folder_path = os.path.dirname(input_file_path)
80 if zipfile.is_zipfile(input_file_path):
81 with zipfile.ZipFile(input_file_path, "r") as zip_ref:
82 zip_ref.extractall(folder_path)
84 pdb_files = [
85 file
86 for file in os.listdir(folder_path)
87 if file.lower().endswith(".pdb")
88 ]
90 input_file_list = [os.path.join(
91 folder_path, file) for file in pdb_files]
93 input_file_list = [Path(i) for i in input_file_list]
94 input_file_list = sorted(
95 input_file_list, key=lambda i: i.stem.upper())
96 input_file_list = [str(i) for i in input_file_list]
98 self.cmd = [
99 self.binary_path,
100 *input_file_list,
101 ">",
102 self.io_dict["out"]["output_file_path"],
103 ]
105 else:
106 fu.log(
107 f"The archive {input_file_path} is not a ZIP!",
108 self.out_log,
109 self.global_log,
110 )
112 fu.log(" ".join(self.cmd), self.out_log, self.global_log)
114 fu.log(
115 "Creating command line with instructions and required arguments",
116 self.out_log,
117 self.global_log,
118 )
120 self.run_biobb()
121 self.copy_to_host()
123 self.tmp_files.extend([self.stage_io_dict.get("unique_dir", "")])
124 self.remove_tmp_files()
125 self.check_arguments(output_files_created=True, raise_exception=False)
127 return self.return_code
130def biobb_pdb_merge(
131 input_file_path: str,
132 output_file_path: str,
133 properties: Optional[dict] = None,
134 **kwargs,
135) -> int:
136 """Create :class:`Pdbmerge <biobb_pdb_tools.pdb_tools.pdb_merge>` class and
137 execute the :meth:`launch() <biobb_pdb_tools.pdb_tools.pdb_merge.launch>` method."""
138 return Pdbmerge(
139 input_file_path=input_file_path,
140 output_file_path=output_file_path,
141 properties=properties,
142 **kwargs,
143 ).launch()
146biobb_pdb_merge.__doc__ = Pdbmerge.__doc__
149def main():
150 """Command line execution of this building block. Please check the command line documentation."""
151 parser = argparse.ArgumentParser(
152 description="Merges several PDB files into one.",
153 formatter_class=lambda prog: argparse.RawTextHelpFormatter(
154 prog, width=99999),
155 )
156 parser.add_argument("--config", required=True, help="Configuration file")
158 required_args = parser.add_argument_group("required arguments")
159 required_args.add_argument(
160 "--input_file_path",
161 required=True,
162 help="Description for the first input file path. Accepted formats: pdb.",
163 )
164 required_args.add_argument(
165 "--output_file_path",
166 required=True,
167 help="Description for the output file path. Accepted formats: zip.",
168 )
170 args = parser.parse_args()
171 args.config = args.config or "{}"
172 properties = settings.ConfReader(config=args.config).get_prop_dic()
173 biobb_pdb_merge(
174 input_file_path=args.input_file_path,
175 output_file_path=args.output_file_path,
176 properties=properties,
177 )
180if __name__ == "__main__":
181 main()