biobb_pdb_tools/pdb_tools/biobb_pdb_mkensemble.py source
1 #!/usr/bin/env python3
2
3 """Module containing the Mkensemble class and the command line interface."""
4
5 import argparse
6 import os
7 import zipfile
8 from pathlib import Path
9 from typing import Optional
10
11 from biobb_common.configuration import settings
12 from biobb_common.generic.biobb_object import BiobbObject
13 from biobb_common.tools import file_utils as fu
14 from biobb_common.tools.file_utils import launchlogger
15
16
17 class 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.
22
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.
30
31 Examples:
32 This is a use example of how to use the building block from Python::
33
34 from biobb_pdb_tools.pdb_tools.biobb_pdb_mkensemble import biobb_pdb_mkensemble
35
36 biobb_pdb_mkensemble(input_file_path='/path/to/input1.zip',
37 output_file_path='/path/to/output.pdb')
38
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
47
48 """
49
50 def __init__(
51 self, input_file_path, output_file_path, properties=None, **kwargs
52 ) -> None:
53 properties = properties or {}
54
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 }
61
62 self.binary_path = properties.get("binary_path", "pdb_mkensemble")
63 self.properties = properties
64
65 self.check_properties(properties)
66 self.check_arguments()
67
68 @launchlogger
69 def launch(self) -> int:
70 """Execute the :class:`Mkensemble <biobb_pdb_tools.pdb_tools.pdb_mkensemble>` object."""
71
72 if self.check_restart():
73 return 0
74 self.stage_files()
75
76 input_file_path = self.stage_io_dict["in"]["input_file_path"]
77 folder_path = os.path.dirname(input_file_path)
78
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)
82
83 pdb_files = [
84 file
85 for file in os.listdir(folder_path)
86 if file.lower().endswith(".pdb")
87 ]
88
89 input_file_list = [os.path.join(folder_path, file) for file in pdb_files]
90
91 input_file_list = [Path(i) for i in input_file_list]
92 input_file_list = sorted(input_file_list, key=lambda i: i.stem.upper())
93 input_file_list = [str(i) for i in input_file_list]
94
95 self.cmd = [
96 self.binary_path,
97 *input_file_list,
98 ">",
99 self.io_dict["out"]["output_file_path"],
100 ]
101
102 else:
103 fu.log(
104 f"The archive {input_file_path} is not a ZIP!",
105 self.out_log,
106 self.global_log,
107 )
108
109 fu.log(" ".join(self.cmd), self.out_log, self.global_log)
110
111 fu.log(
112 "Creating command line with instructions and required arguments",
113 self.out_log,
114 self.global_log,
115 )
116
117 self.run_biobb()
118 self.copy_to_host()
119
120 self.tmp_files.extend([self.stage_io_dict.get("unique_dir", "")])
121 self.remove_tmp_files()
122 self.check_arguments(output_files_created=True, raise_exception=False)
123
124 return self.return_code
125
126
127 def biobb_pdb_mkensemble(
128 input_file_path: str,
129 output_file_path: str,
130 properties: Optional[dict] = None,
131 **kwargs,
132 ) -> int:
133 """Create :class:`Mkensemble <biobb_pdb_tools.pdb_tools.pdb_mkensemble>` class and
134 execute the :meth:`launch() <biobb_pdb_tools.pdb_tools.pdb_mkensemble.launch>` method."""
135 return Mkensemble(
136 input_file_path=input_file_path,
137 output_file_path=output_file_path,
138 properties=properties,
139 **kwargs,
140 ).launch()
141
- E305 Expected 2 blank lines after class or function definition, found 1
143
144
145 def main():
146 """Command line execution of this building block. Please check the command line documentation."""
147 parser = argparse.ArgumentParser(
148 description="Merges several PDB files into one multi-model (ensemble) file.",
149 formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999),
150 )
151 parser.add_argument("--config", required=True, help="Configuration file")
152 required_args = parser.add_argument_group("required arguments")
153 required_args.add_argument(
154 "--input_file_path",
155 required=True,
156 help="Description for the first input file path. Accepted formats: pdb.",
157 )
158 required_args.add_argument(
159 "--output_file_path",
160 required=True,
161 help="Description for the output file path. Accepted formats: zip.",
162 )
163
164 args = parser.parse_args()
165 args.config = args.config or "{}"
166 properties = settings.ConfReader(config=args.config).get_prop_dic()
167
168 biobb_pdb_mkensemble(
169 input_file_path=args.input_file_path,
170 output_file_path=args.output_file_path,
171 properties=properties,
172 )
173
174
175 if __name__ == "__main__":
176 main()